From 96bc451a153297bf1f99ef2d633d512ea349ae7a Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:42 +0200
Subject: KVM: PPC: Introduce shared page

For transparent variable sharing between the hypervisor and guest, I introduce
a shared page. This shared page will contain all the registers the guest can
read and write safely without exiting guest context.

This patch only implements the stubs required for the basic structure of the
shared page. The actual register moving follows.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h | 2 ++
 arch/powerpc/include/asm/kvm_para.h | 5 +++++
 arch/powerpc/kernel/asm-offsets.c   | 1 +
 arch/powerpc/kvm/44x.c              | 7 +++++++
 arch/powerpc/kvm/book3s.c           | 9 ++++++++-
 arch/powerpc/kvm/e500.c             | 7 +++++++
 6 files changed, 30 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index b0b23c007d6e..53edacdf6940 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -25,6 +25,7 @@
 #include <linux/interrupt.h>
 #include <linux/types.h>
 #include <linux/kvm_types.h>
+#include <linux/kvm_para.h>
 #include <asm/kvm_asm.h>
 
 #define KVM_MAX_VCPUS 1
@@ -290,6 +291,7 @@ struct kvm_vcpu_arch {
 	struct tasklet_struct tasklet;
 	u64 dec_jiffies;
 	unsigned long pending_exceptions;
+	struct kvm_vcpu_arch_shared *shared;
 
 #ifdef CONFIG_PPC_BOOK3S
 	struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 2d48f6a63d0b..1485ba87a52a 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -20,6 +20,11 @@
 #ifndef __POWERPC_KVM_PARA_H__
 #define __POWERPC_KVM_PARA_H__
 
+#include <linux/types.h>
+
+struct kvm_vcpu_arch_shared {
+};
+
 #ifdef __KERNEL__
 
 static inline int kvm_para_available(void)
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 1c0607ddccc0..60e7db4c13af 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -400,6 +400,7 @@ int main(void)
 	DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
 	DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
 	DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
+	DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared));
 
 	/* book3s */
 #ifdef CONFIG_PPC_BOOK3S
diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index 73c0a3f64ed1..e7b1f3fca5dc 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -123,8 +123,14 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vcpu;
 
+	vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
+	if (!vcpu->arch.shared)
+		goto uninit_vcpu;
+
 	return vcpu;
 
+uninit_vcpu:
+	kvm_vcpu_uninit(vcpu);
 free_vcpu:
 	kmem_cache_free(kvm_vcpu_cache, vcpu_44x);
 out:
@@ -135,6 +141,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
 
+	free_page((unsigned long)vcpu->arch.shared);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu_44x);
 }
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index a3cef30d1d42..b3385dd6f28d 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -1242,6 +1242,10 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_shadow_vcpu;
 
+	vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
+	if (!vcpu->arch.shared)
+		goto uninit_vcpu;
+
 	vcpu->arch.host_retip = kvm_return_point;
 	vcpu->arch.host_msr = mfmsr();
 #ifdef CONFIG_PPC_BOOK3S_64
@@ -1268,10 +1272,12 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 
 	err = kvmppc_mmu_init(vcpu);
 	if (err < 0)
-		goto free_shadow_vcpu;
+		goto uninit_vcpu;
 
 	return vcpu;
 
+uninit_vcpu:
+	kvm_vcpu_uninit(vcpu);
 free_shadow_vcpu:
 	kfree(vcpu_book3s->shadow_vcpu);
 free_vcpu:
@@ -1284,6 +1290,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 
+	free_page((unsigned long)vcpu->arch.shared);
 	kvm_vcpu_uninit(vcpu);
 	kfree(vcpu_book3s->shadow_vcpu);
 	vfree(vcpu_book3s);
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index e8a00b0c4449..71750f2dd5d3 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -117,8 +117,14 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto uninit_vcpu;
 
+	vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
+	if (!vcpu->arch.shared)
+		goto uninit_tlb;
+
 	return vcpu;
 
+uninit_tlb:
+	kvmppc_e500_tlb_uninit(vcpu_e500);
 uninit_vcpu:
 	kvm_vcpu_uninit(vcpu);
 free_vcpu:
@@ -131,6 +137,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
 
+	free_page((unsigned long)vcpu->arch.shared);
 	kvmppc_e500_tlb_uninit(vcpu_e500);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
-- 
cgit v1.2.1


From 666e7252a15b7fc4a116e65deaf6da5e4ce660e3 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:43 +0200
Subject: KVM: PPC: Convert MSR to shared page

One of the most obvious registers to share with the guest directly is the
MSR. The MSR contains the "interrupts enabled" flag which the guest has to
toggle in critical sections.

So in order to bring the overhead of interrupt en- and disabling down, let's
put msr into the shared page. Keep in mind that even though you can fully read
its contents, writing to it doesn't always update all state. There are a few
safe fields that don't require hypervisor interaction. See the documentation
for a list of MSR bits that are safe to be set from inside the guest.

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/include/asm/kvm_para.h      |  1 +
 arch/powerpc/kernel/asm-offsets.c        |  2 +-
 arch/powerpc/kvm/44x_tlb.c               |  8 ++--
 arch/powerpc/kvm/book3s.c                | 65 +++++++++++++++++---------------
 arch/powerpc/kvm/book3s_32_mmu.c         | 12 +++---
 arch/powerpc/kvm/book3s_32_mmu_host.c    |  4 +-
 arch/powerpc/kvm/book3s_64_mmu.c         | 12 +++---
 arch/powerpc/kvm/book3s_64_mmu_host.c    |  4 +-
 arch/powerpc/kvm/book3s_emulate.c        |  9 +++--
 arch/powerpc/kvm/book3s_paired_singles.c |  7 ++--
 arch/powerpc/kvm/booke.c                 | 20 +++++-----
 arch/powerpc/kvm/booke.h                 |  6 +--
 arch/powerpc/kvm/booke_emulate.c         |  6 +--
 arch/powerpc/kvm/booke_interrupts.S      |  3 +-
 arch/powerpc/kvm/e500_tlb.c              | 12 +++---
 arch/powerpc/kvm/e500_tlb.h              |  2 +-
 arch/powerpc/kvm/powerpc.c               |  3 +-
 18 files changed, 93 insertions(+), 84 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 53edacdf6940..ba20f90655f3 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -211,7 +211,6 @@ struct kvm_vcpu_arch {
 	u32 cr;
 #endif
 
-	ulong msr;
 #ifdef CONFIG_PPC_BOOK3S
 	ulong shadow_msr;
 	ulong hflags;
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 1485ba87a52a..a17dc5229d99 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 
 struct kvm_vcpu_arch_shared {
+	__u64 msr;
 };
 
 #ifdef __KERNEL__
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 60e7db4c13af..1221bcdff52f 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -394,13 +394,13 @@ int main(void)
 	DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
 	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
 	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
-	DEFINE(VCPU_MSR, offsetof(struct kvm_vcpu, arch.msr));
 	DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
 	DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
 	DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));
 	DEFINE(VCPU_SPRG7, offsetof(struct kvm_vcpu, arch.sprg7));
 	DEFINE(VCPU_SHADOW_PID, offsetof(struct kvm_vcpu, arch.shadow_pid));
 	DEFINE(VCPU_SHARED, offsetof(struct kvm_vcpu, arch.shared));
+	DEFINE(VCPU_SHARED_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
 
 	/* book3s */
 #ifdef CONFIG_PPC_BOOK3S
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 9b9b5cdea840..9f71b8d6eb0d 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -221,14 +221,14 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index,
 
 int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
-	unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+	unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);
 
 	return kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
 }
 
 int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
-	unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+	unsigned int as = !!(vcpu->arch.shared->msr & MSR_DS);
 
 	return kvmppc_44x_tlb_index(vcpu, eaddr, vcpu->arch.pid, as);
 }
@@ -354,7 +354,7 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
 
 	stlbe.word1 = (hpaddr & 0xfffffc00) | ((hpaddr >> 32) & 0xf);
 	stlbe.word2 = kvmppc_44x_tlb_shadow_attrib(flags,
-	                                            vcpu->arch.msr & MSR_PR);
+	                                            vcpu->arch.shared->msr & MSR_PR);
 	stlbe.tid = !(asid & 0xff);
 
 	/* Keep track of the reference so we can properly release it later. */
@@ -423,7 +423,7 @@ static int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
 
 	/* Does it match current guest AS? */
 	/* XXX what about IS != DS? */
-	if (get_tlb_ts(tlbe) != !!(vcpu->arch.msr & MSR_IS))
+	if (get_tlb_ts(tlbe) != !!(vcpu->arch.shared->msr & MSR_IS))
 		return 0;
 
 	gpa = get_tlb_raddr(tlbe);
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index b3385dd6f28d..2efe69240e1b 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -115,31 +115,31 @@ static u32 kvmppc_get_dec(struct kvm_vcpu *vcpu)
 
 static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.shadow_msr = vcpu->arch.msr;
+	ulong smsr = vcpu->arch.shared->msr;
+
 	/* Guest MSR values */
-	vcpu->arch.shadow_msr &= MSR_FE0 | MSR_FE1 | MSR_SF | MSR_SE |
-				 MSR_BE | MSR_DE;
+	smsr &= 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;
+	smsr |= 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);
+	smsr |= (vcpu->arch.shared->msr & vcpu->arch.guest_owned_ext);
 	/* 64-bit Process MSR values */
 #ifdef CONFIG_PPC_BOOK3S_64
-	vcpu->arch.shadow_msr |= MSR_ISF | MSR_HV;
+	smsr |= MSR_ISF | MSR_HV;
 #endif
+	vcpu->arch.shadow_msr = smsr;
 }
 
 void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 {
-	ulong old_msr = vcpu->arch.msr;
+	ulong old_msr = vcpu->arch.shared->msr;
 
 #ifdef EXIT_DEBUG
 	printk(KERN_INFO "KVM: Set MSR to 0x%llx\n", msr);
 #endif
 
 	msr &= to_book3s(vcpu)->msr_mask;
-	vcpu->arch.msr = msr;
+	vcpu->arch.shared->msr = msr;
 	kvmppc_recalc_shadow_msr(vcpu);
 
 	if (msr & (MSR_WE|MSR_POW)) {
@@ -149,21 +149,21 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 		}
 	}
 
-	if ((vcpu->arch.msr & (MSR_PR|MSR_IR|MSR_DR)) !=
+	if ((vcpu->arch.shared->msr & (MSR_PR|MSR_IR|MSR_DR)) !=
 		   (old_msr & (MSR_PR|MSR_IR|MSR_DR))) {
 		kvmppc_mmu_flush_segments(vcpu);
 		kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
 	}
 
 	/* Preload FPU if it's enabled */
-	if (vcpu->arch.msr & MSR_FP)
+	if (vcpu->arch.shared->msr & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 }
 
 void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
 {
 	vcpu->arch.srr0 = kvmppc_get_pc(vcpu);
-	vcpu->arch.srr1 = vcpu->arch.msr | flags;
+	vcpu->arch.srr1 = vcpu->arch.shared->msr | flags;
 	kvmppc_set_pc(vcpu, to_book3s(vcpu)->hior + vec);
 	vcpu->arch.mmu.reset_msr(vcpu);
 }
@@ -254,11 +254,11 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 
 	switch (priority) {
 	case BOOK3S_IRQPRIO_DECREMENTER:
-		deliver = vcpu->arch.msr & MSR_EE;
+		deliver = vcpu->arch.shared->msr & MSR_EE;
 		vec = BOOK3S_INTERRUPT_DECREMENTER;
 		break;
 	case BOOK3S_IRQPRIO_EXTERNAL:
-		deliver = vcpu->arch.msr & MSR_EE;
+		deliver = vcpu->arch.shared->msr & MSR_EE;
 		vec = BOOK3S_INTERRUPT_EXTERNAL;
 		break;
 	case BOOK3S_IRQPRIO_SYSTEM_RESET:
@@ -437,7 +437,7 @@ static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
 static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
 			 struct kvmppc_pte *pte)
 {
-	int relocated = (vcpu->arch.msr & (data ? MSR_DR : MSR_IR));
+	int relocated = (vcpu->arch.shared->msr & (data ? MSR_DR : MSR_IR));
 	int r;
 
 	if (relocated) {
@@ -545,8 +545,8 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	int page_found = 0;
 	struct kvmppc_pte pte;
 	bool is_mmio = false;
-	bool dr = (vcpu->arch.msr & MSR_DR) ? true : false;
-	bool ir = (vcpu->arch.msr & MSR_IR) ? true : false;
+	bool dr = (vcpu->arch.shared->msr & MSR_DR) ? true : false;
+	bool ir = (vcpu->arch.shared->msr & MSR_IR) ? true : false;
 	u64 vsid;
 
 	relocated = data ? dr : ir;
@@ -563,7 +563,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		pte.vpage = eaddr >> 12;
 	}
 
-	switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 	case 0:
 		pte.vpage |= ((u64)VSID_REAL << (SID_SHIFT - 12));
 		break;
@@ -571,7 +571,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case MSR_IR:
 		vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);
 
-		if ((vcpu->arch.msr & (MSR_DR|MSR_IR)) == MSR_DR)
+		if ((vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) == MSR_DR)
 			pte.vpage |= ((u64)VSID_REAL_DR << (SID_SHIFT - 12));
 		else
 			pte.vpage |= ((u64)VSID_REAL_IR << (SID_SHIFT - 12));
@@ -596,14 +596,16 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		/* Page not found in guest PTE entries */
 		vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
 		to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr;
-		vcpu->arch.msr |= (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+		vcpu->arch.shared->msr |=
+			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EPERM) {
 		/* Storage protection */
 		vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
 		to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
 		to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT;
-		vcpu->arch.msr |= (to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
+		vcpu->arch.shared->msr |=
+			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EINVAL) {
 		/* Page not found in guest SLB */
@@ -695,9 +697,11 @@ static int kvmppc_read_inst(struct kvm_vcpu *vcpu)
 
 	ret = kvmppc_ld(vcpu, &srr0, sizeof(u32), &last_inst, false);
 	if (ret == -ENOENT) {
-		vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 33, 33, 1);
-		vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 34, 36, 0);
-		vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 42, 47, 0);
+		ulong msr = vcpu->arch.shared->msr;
+
+		msr = kvmppc_set_field(msr, 33, 33, 1);
+		msr = kvmppc_set_field(msr, 34, 36, 0);
+		vcpu->arch.shared->msr = kvmppc_set_field(msr, 42, 47, 0);
 		kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_INST_STORAGE);
 		return EMULATE_AGAIN;
 	}
@@ -736,7 +740,7 @@ static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
 	if (vcpu->arch.hflags & BOOK3S_HFLAG_PAIRED_SINGLE)
 		return RESUME_GUEST;
 
-	if (!(vcpu->arch.msr & msr)) {
+	if (!(vcpu->arch.shared->msr & msr)) {
 		kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 		return RESUME_GUEST;
 	}
@@ -804,7 +808,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	if ((exit_nr != 0x900) && (exit_nr != 0x500))
 		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | msr=0x%lx\n",
 			exit_nr, kvmppc_get_pc(vcpu), kvmppc_get_fault_dar(vcpu),
-			vcpu->arch.msr);
+			vcpu->arch.shared->msr);
 #endif
 	kvm_resched(vcpu);
 	switch (exit_nr) {
@@ -836,7 +840,8 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
 			r = RESUME_GUEST;
 		} else {
-			vcpu->arch.msr |= to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
+			vcpu->arch.shared->msr |=
+				to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
 			r = RESUME_GUEST;
@@ -904,7 +909,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 program_interrupt:
 		flags = to_svcpu(vcpu)->shadow_srr1 & 0x1f0000ull;
 
-		if (vcpu->arch.msr & MSR_PR) {
+		if (vcpu->arch.shared->msr & MSR_PR) {
 #ifdef EXIT_DEBUG
 			printk(KERN_INFO "Userspace triggered 0x700 exception at 0x%lx (0x%x)\n", kvmppc_get_pc(vcpu), kvmppc_get_last_inst(vcpu));
 #endif
@@ -1052,7 +1057,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->ctr = kvmppc_get_ctr(vcpu);
 	regs->lr = kvmppc_get_lr(vcpu);
 	regs->xer = kvmppc_get_xer(vcpu);
-	regs->msr = vcpu->arch.msr;
+	regs->msr = vcpu->arch.shared->msr;
 	regs->srr0 = vcpu->arch.srr0;
 	regs->srr1 = vcpu->arch.srr1;
 	regs->pid = vcpu->arch.pid;
@@ -1353,7 +1358,7 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	local_irq_enable();
 
 	/* Preload FPU if it's enabled */
-	if (vcpu->arch.msr & MSR_FP)
+	if (vcpu->arch.shared->msr & MSR_FP)
 		kvmppc_handle_ext(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL, MSR_FP);
 
 	ret = __kvmppc_vcpu_entry(kvm_run, vcpu);
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index 3292d76101d2..449bce5f021a 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -133,7 +133,7 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
 		else
 			bat = &vcpu_book3s->ibat[i];
 
-		if (vcpu->arch.msr & MSR_PR) {
+		if (vcpu->arch.shared->msr & MSR_PR) {
 			if (!bat->vp)
 				continue;
 		} else {
@@ -214,8 +214,8 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 			pte->raddr = (pteg[i+1] & ~(0xFFFULL)) | (eaddr & 0xFFF);
 			pp = pteg[i+1] & 3;
 
-			if ((sre->Kp &&  (vcpu->arch.msr & MSR_PR)) ||
-			    (sre->Ks && !(vcpu->arch.msr & MSR_PR)))
+			if ((sre->Kp &&  (vcpu->arch.shared->msr & MSR_PR)) ||
+			    (sre->Ks && !(vcpu->arch.shared->msr & MSR_PR)))
 				pp |= 4;
 
 			pte->may_write = false;
@@ -334,7 +334,7 @@ static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 	struct kvmppc_sr *sr;
 	u64 gvsid = esid;
 
-	if (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+	if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 		sr = find_sr(to_book3s(vcpu), ea);
 		if (sr->valid)
 			gvsid = sr->vsid;
@@ -343,7 +343,7 @@ static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 	/* In case we only have one of MSR_IR or MSR_DR set, let's put
 	   that in the real-mode context (and hope RM doesn't access
 	   high memory) */
-	switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 	case 0:
 		*vsid = VSID_REAL | esid;
 		break;
@@ -363,7 +363,7 @@ static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 		BUG();
 	}
 
-	if (vcpu->arch.msr & MSR_PR)
+	if (vcpu->arch.shared->msr & MSR_PR)
 		*vsid |= VSID_PR;
 
 	return 0;
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 0b51ef872c1e..67b8c38d932f 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -86,7 +86,7 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
 	struct kvmppc_sid_map *map;
 	u16 sid_map_mask;
 
-	if (vcpu->arch.msr & MSR_PR)
+	if (vcpu->arch.shared->msr & MSR_PR)
 		gvsid |= VSID_PR;
 
 	sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
@@ -253,7 +253,7 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 	u16 sid_map_mask;
 	static int backwards_map = 0;
 
-	if (vcpu->arch.msr & MSR_PR)
+	if (vcpu->arch.shared->msr & MSR_PR)
 		gvsid |= VSID_PR;
 
 	/* We might get collisions that trap in preceding order, so let's
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 4025ea26b3c1..58aa8409dae0 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -180,9 +180,9 @@ do_second:
 		goto no_page_found;
 	}
 
-	if ((vcpu->arch.msr & MSR_PR) && slbe->Kp)
+	if ((vcpu->arch.shared->msr & MSR_PR) && slbe->Kp)
 		key = 4;
-	else if (!(vcpu->arch.msr & MSR_PR) && slbe->Ks)
+	else if (!(vcpu->arch.shared->msr & MSR_PR) && slbe->Ks)
 		key = 4;
 
 	for (i=0; i<16; i+=2) {
@@ -381,7 +381,7 @@ static void kvmppc_mmu_book3s_64_slbia(struct kvm_vcpu *vcpu)
 	for (i = 1; i < vcpu_book3s->slb_nr; i++)
 		vcpu_book3s->slb[i].valid = false;
 
-	if (vcpu->arch.msr & MSR_IR) {
+	if (vcpu->arch.shared->msr & MSR_IR) {
 		kvmppc_mmu_flush_segments(vcpu);
 		kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
 	}
@@ -446,13 +446,13 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 	struct kvmppc_slb *slb;
 	u64 gvsid = esid;
 
-	if (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+	if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 		slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea);
 		if (slb)
 			gvsid = slb->vsid;
 	}
 
-	switch (vcpu->arch.msr & (MSR_DR|MSR_IR)) {
+	switch (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 	case 0:
 		*vsid = VSID_REAL | esid;
 		break;
@@ -473,7 +473,7 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 		break;
 	}
 
-	if (vcpu->arch.msr & MSR_PR)
+	if (vcpu->arch.shared->msr & MSR_PR)
 		*vsid |= VSID_PR;
 
 	return 0;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 384179a5002b..71c1f9027abb 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -66,7 +66,7 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
 	struct kvmppc_sid_map *map;
 	u16 sid_map_mask;
 
-	if (vcpu->arch.msr & MSR_PR)
+	if (vcpu->arch.shared->msr & MSR_PR)
 		gvsid |= VSID_PR;
 
 	sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
@@ -191,7 +191,7 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 	u16 sid_map_mask;
 	static int backwards_map = 0;
 
-	if (vcpu->arch.msr & MSR_PR)
+	if (vcpu->arch.shared->msr & MSR_PR)
 		gvsid |= VSID_PR;
 
 	/* We might get collisions that trap in preceding order, so let's
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index c85f906038ce..35d3c16b2938 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -86,14 +86,15 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	case 31:
 		switch (get_xop(inst)) {
 		case OP_31_XOP_MFMSR:
-			kvmppc_set_gpr(vcpu, get_rt(inst), vcpu->arch.msr);
+			kvmppc_set_gpr(vcpu, get_rt(inst),
+				       vcpu->arch.shared->msr);
 			break;
 		case OP_31_XOP_MTMSRD:
 		{
 			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);
+				vcpu->arch.shared->msr &= ~(MSR_RI | MSR_EE);
+				vcpu->arch.shared->msr |= rs & (MSR_RI | MSR_EE);
 			} else
 				kvmppc_set_msr(vcpu, rs);
 			break;
@@ -204,7 +205,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				ra = kvmppc_get_gpr(vcpu, get_ra(inst));
 
 			addr = (ra + rb) & ~31ULL;
-			if (!(vcpu->arch.msr & MSR_SF))
+			if (!(vcpu->arch.shared->msr & MSR_SF))
 				addr &= 0xffffffff;
 			vaddr = addr;
 
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c
index 474f2e24050a..626e6efaa79f 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -165,9 +165,10 @@ static inline void kvmppc_sync_qpr(struct kvm_vcpu *vcpu, int rt)
 static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store)
 {
 	u64 dsisr;
+	struct kvm_vcpu_arch_shared *shared = vcpu->arch.shared;
 
-	vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 33, 36, 0);
-	vcpu->arch.msr = kvmppc_set_field(vcpu->arch.msr, 42, 47, 0);
+	shared->msr = kvmppc_set_field(shared->msr, 33, 36, 0);
+	shared->msr = kvmppc_set_field(shared->msr, 42, 47, 0);
 	vcpu->arch.dear = eaddr;
 	/* Page Fault */
 	dsisr = kvmppc_set_field(0, 33, 33, 1);
@@ -658,7 +659,7 @@ int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	if (!kvmppc_inst_is_paired_single(vcpu, inst))
 		return EMULATE_FAIL;
 
-	if (!(vcpu->arch.msr & MSR_FP)) {
+	if (!(vcpu->arch.shared->msr & MSR_FP)) {
 		kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_FP_UNAVAIL);
 		return EMULATE_AGAIN;
 	}
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 8d4e35f5372c..4ec9d49a1cb9 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -62,7 +62,7 @@ void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu)
 {
 	int i;
 
-	printk("pc:   %08lx msr:  %08lx\n", vcpu->arch.pc, vcpu->arch.msr);
+	printk("pc:   %08lx msr:  %08llx\n", vcpu->arch.pc, vcpu->arch.shared->msr);
 	printk("lr:   %08lx ctr:  %08lx\n", vcpu->arch.lr, vcpu->arch.ctr);
 	printk("srr0: %08lx srr1: %08lx\n", vcpu->arch.srr0, vcpu->arch.srr1);
 
@@ -169,34 +169,34 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		break;
 	case BOOKE_IRQPRIO_CRITICAL:
 	case BOOKE_IRQPRIO_WATCHDOG:
-		allowed = vcpu->arch.msr & MSR_CE;
+		allowed = vcpu->arch.shared->msr & MSR_CE;
 		msr_mask = MSR_ME;
 		break;
 	case BOOKE_IRQPRIO_MACHINE_CHECK:
-		allowed = vcpu->arch.msr & MSR_ME;
+		allowed = vcpu->arch.shared->msr & MSR_ME;
 		msr_mask = 0;
 		break;
 	case BOOKE_IRQPRIO_EXTERNAL:
 	case BOOKE_IRQPRIO_DECREMENTER:
 	case BOOKE_IRQPRIO_FIT:
-		allowed = vcpu->arch.msr & MSR_EE;
+		allowed = vcpu->arch.shared->msr & MSR_EE;
 		msr_mask = MSR_CE|MSR_ME|MSR_DE;
 		break;
 	case BOOKE_IRQPRIO_DEBUG:
-		allowed = vcpu->arch.msr & MSR_DE;
+		allowed = vcpu->arch.shared->msr & MSR_DE;
 		msr_mask = MSR_ME;
 		break;
 	}
 
 	if (allowed) {
 		vcpu->arch.srr0 = vcpu->arch.pc;
-		vcpu->arch.srr1 = vcpu->arch.msr;
+		vcpu->arch.srr1 = vcpu->arch.shared->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);
+		kvmppc_set_msr(vcpu, vcpu->arch.shared->msr & msr_mask);
 
 		clear_bit(priority, &vcpu->arch.pending_exceptions);
 	}
@@ -265,7 +265,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 
 	case BOOKE_INTERRUPT_PROGRAM:
-		if (vcpu->arch.msr & MSR_PR) {
+		if (vcpu->arch.shared->msr & MSR_PR) {
 			/* Program traps generated by user-level software must be handled
 			 * by the guest kernel. */
 			kvmppc_core_queue_program(vcpu, vcpu->arch.fault_esr);
@@ -467,7 +467,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pc = 0;
-	vcpu->arch.msr = 0;
+	vcpu->arch.shared->msr = 0;
 	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
 
 	vcpu->arch.shadow_pid = 1;
@@ -490,7 +490,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->ctr = vcpu->arch.ctr;
 	regs->lr = vcpu->arch.lr;
 	regs->xer = kvmppc_get_xer(vcpu);
-	regs->msr = vcpu->arch.msr;
+	regs->msr = vcpu->arch.shared->msr;
 	regs->srr0 = vcpu->arch.srr0;
 	regs->srr1 = vcpu->arch.srr1;
 	regs->pid = vcpu->arch.pid;
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index d59bcca1f9d8..88258acc98fa 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -54,12 +54,12 @@ extern unsigned long kvmppc_booke_handlers;
  * changing. */
 static inline void kvmppc_set_msr(struct kvm_vcpu *vcpu, u32 new_msr)
 {
-	if ((new_msr & MSR_PR) != (vcpu->arch.msr & MSR_PR))
+	if ((new_msr & MSR_PR) != (vcpu->arch.shared->msr & MSR_PR))
 		kvmppc_mmu_priv_switch(vcpu, new_msr & MSR_PR);
 
-	vcpu->arch.msr = new_msr;
+	vcpu->arch.shared->msr = new_msr;
 
-	if (vcpu->arch.msr & MSR_WE) {
+	if (vcpu->arch.shared->msr & MSR_WE) {
 		kvm_vcpu_block(vcpu);
 		kvmppc_set_exit_type(vcpu, EMULATED_MTMSRWE_EXITS);
 	};
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index cbc790ee1928..b115203ac118 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -62,7 +62,7 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 		case OP_31_XOP_MFMSR:
 			rt = get_rt(inst);
-			kvmppc_set_gpr(vcpu, rt, vcpu->arch.msr);
+			kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->msr);
 			kvmppc_set_exit_type(vcpu, EMULATED_MFMSR_EXITS);
 			break;
 
@@ -74,13 +74,13 @@ int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 		case OP_31_XOP_WRTEE:
 			rs = get_rs(inst);
-			vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
+			vcpu->arch.shared->msr = (vcpu->arch.shared->msr & ~MSR_EE)
 					| (kvmppc_get_gpr(vcpu, rs) & MSR_EE);
 			kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
 			break;
 
 		case OP_31_XOP_WRTEEI:
-			vcpu->arch.msr = (vcpu->arch.msr & ~MSR_EE)
+			vcpu->arch.shared->msr = (vcpu->arch.shared->msr & ~MSR_EE)
 							 | (inst & MSR_EE);
 			kvmppc_set_exit_type(vcpu, EMULATED_WRTEE_EXITS);
 			break;
diff --git a/arch/powerpc/kvm/booke_interrupts.S b/arch/powerpc/kvm/booke_interrupts.S
index 380a78cf484d..049846911ce4 100644
--- a/arch/powerpc/kvm/booke_interrupts.S
+++ b/arch/powerpc/kvm/booke_interrupts.S
@@ -415,7 +415,8 @@ lightweight_exit:
 	lwz	r8, VCPU_GPR(r8)(r4)
 	lwz	r3, VCPU_PC(r4)
 	mtsrr0	r3
-	lwz	r3, VCPU_MSR(r4)
+	lwz	r3, VCPU_SHARED(r4)
+	lwz	r3, VCPU_SHARED_MSR(r3)
 	oris	r3, r3, KVMPPC_MSR_MASK@h
 	ori	r3, r3, KVMPPC_MSR_MASK@l
 	mtsrr1	r3
diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index 21011e12caeb..092a390876f3 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -314,10 +314,10 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 		| MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID;
 	stlbe->mas2 = (gvaddr & MAS2_EPN)
 		| e500_shadow_mas2_attrib(gtlbe->mas2,
-				vcpu_e500->vcpu.arch.msr & MSR_PR);
+				vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
 	stlbe->mas3 = (hpaddr & MAS3_RPN)
 		| e500_shadow_mas3_attrib(gtlbe->mas3,
-				vcpu_e500->vcpu.arch.msr & MSR_PR);
+				vcpu_e500->vcpu.arch.shared->msr & MSR_PR);
 	stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN;
 
 	trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
@@ -576,28 +576,28 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 
 int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
-	unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+	unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);
 
 	return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
 }
 
 int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
-	unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+	unsigned int as = !!(vcpu->arch.shared->msr & MSR_DS);
 
 	return kvmppc_e500_tlb_search(vcpu, eaddr, get_cur_pid(vcpu), as);
 }
 
 void kvmppc_mmu_itlb_miss(struct kvm_vcpu *vcpu)
 {
-	unsigned int as = !!(vcpu->arch.msr & MSR_IS);
+	unsigned int as = !!(vcpu->arch.shared->msr & MSR_IS);
 
 	kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.pc, as);
 }
 
 void kvmppc_mmu_dtlb_miss(struct kvm_vcpu *vcpu)
 {
-	unsigned int as = !!(vcpu->arch.msr & MSR_DS);
+	unsigned int as = !!(vcpu->arch.shared->msr & MSR_DS);
 
 	kvmppc_e500_deliver_tlb_miss(vcpu, vcpu->arch.fault_dear, as);
 }
diff --git a/arch/powerpc/kvm/e500_tlb.h b/arch/powerpc/kvm/e500_tlb.h
index d28e3010a5e2..458946b4775d 100644
--- a/arch/powerpc/kvm/e500_tlb.h
+++ b/arch/powerpc/kvm/e500_tlb.h
@@ -171,7 +171,7 @@ static inline int tlbe_is_host_safe(const struct kvm_vcpu *vcpu,
 
 	/* Does it match current guest AS? */
 	/* XXX what about IS != DS? */
-	if (get_tlb_ts(tlbe) != !!(vcpu->arch.msr & MSR_IS))
+	if (get_tlb_ts(tlbe) != !!(vcpu->arch.shared->msr & MSR_IS))
 		return 0;
 
 	gpa = get_tlb_raddr(tlbe);
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 72a4ad86ee91..22f6fa2982f2 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -38,7 +38,8 @@
 
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 {
-	return !(v->arch.msr & MSR_WE) || !!(v->arch.pending_exceptions);
+	return !(v->arch.shared->msr & MSR_WE) ||
+	       !!(v->arch.pending_exceptions);
 }
 
 
-- 
cgit v1.2.1


From d562de48de68b60b3d2522e7d8273d7112034ee6 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:44 +0200
Subject: KVM: PPC: Convert DSISR to shared page

The DSISR register contains information about a data page fault. It is fully
read/write from inside the guest context and we don't need to worry about
interacting based on writes of this register.

This patch converts all users of the current field to the shared page.

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_para.h      |  1 +
 arch/powerpc/kvm/book3s.c                | 11 ++++++-----
 arch/powerpc/kvm/book3s_emulate.c        |  6 +++---
 arch/powerpc/kvm/book3s_paired_singles.c |  2 +-
 5 files changed, 11 insertions(+), 10 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 8274a2d43925..b5b196166455 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -85,7 +85,6 @@ struct kvmppc_vcpu_book3s {
 	u64 hid[6];
 	u64 gqr[8];
 	int slb_nr;
-	u32 dsisr;
 	u64 sdr1;
 	u64 hior;
 	u64 msr_mask;
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index a17dc5229d99..9f7565b1de65 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -24,6 +24,7 @@
 
 struct kvm_vcpu_arch_shared {
 	__u64 msr;
+	__u32 dsisr;
 };
 
 #ifdef __KERNEL__
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 2efe69240e1b..eb401b6d4d8c 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -595,15 +595,16 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	if (page_found == -ENOENT) {
 		/* Page not found in guest PTE entries */
 		vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
-		to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr;
+		vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
 		vcpu->arch.shared->msr |=
 			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EPERM) {
 		/* Storage protection */
 		vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
-		to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
-		to_book3s(vcpu)->dsisr |= DSISR_PROTFAULT;
+		vcpu->arch.shared->dsisr =
+			to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
+		vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
 		vcpu->arch.shared->msr |=
 			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
@@ -867,7 +868,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
 		} else {
 			vcpu->arch.dear = dar;
-			to_book3s(vcpu)->dsisr = to_svcpu(vcpu)->fault_dsisr;
+			vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFUL);
 			r = RESUME_GUEST;
@@ -994,7 +995,7 @@ program_interrupt:
 	}
 	case BOOK3S_INTERRUPT_ALIGNMENT:
 		if (kvmppc_read_inst(vcpu) == EMULATE_DONE) {
-			to_book3s(vcpu)->dsisr = kvmppc_alignment_dsisr(vcpu,
+			vcpu->arch.shared->dsisr = kvmppc_alignment_dsisr(vcpu,
 				kvmppc_get_last_inst(vcpu));
 			vcpu->arch.dear = kvmppc_alignment_dar(vcpu,
 				kvmppc_get_last_inst(vcpu));
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 35d3c16b2938..9982ff163af0 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -221,7 +221,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				else if (r == -EPERM)
 					dsisr |= DSISR_PROTFAULT;
 
-				to_book3s(vcpu)->dsisr = dsisr;
+				vcpu->arch.shared->dsisr = dsisr;
 				to_svcpu(vcpu)->fault_dsisr = dsisr;
 
 				kvmppc_book3s_queue_irqprio(vcpu,
@@ -327,7 +327,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		to_book3s(vcpu)->sdr1 = spr_val;
 		break;
 	case SPRN_DSISR:
-		to_book3s(vcpu)->dsisr = spr_val;
+		vcpu->arch.shared->dsisr = spr_val;
 		break;
 	case SPRN_DAR:
 		vcpu->arch.dear = spr_val;
@@ -440,7 +440,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1);
 		break;
 	case SPRN_DSISR:
-		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->dsisr);
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dsisr);
 		break;
 	case SPRN_DAR:
 		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dear);
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c
index 626e6efaa79f..749dfbd04738 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -173,7 +173,7 @@ static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store)
 	/* Page Fault */
 	dsisr = kvmppc_set_field(0, 33, 33, 1);
 	if (is_store)
-		to_book3s(vcpu)->dsisr = kvmppc_set_field(dsisr, 38, 38, 1);
+		shared->dsisr = kvmppc_set_field(dsisr, 38, 38, 1);
 	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE);
 }
 
-- 
cgit v1.2.1


From 5e030186dfc4e4e47c84d2557b17e4aa06c76f96 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:45 +0200
Subject: KVM: PPC: Convert DAR to shared page.

The DAR register contains the address a data page fault occured at. This
register behaves pretty much like a simple data storage register that gets
written to on data faults. There is no hypervisor interaction required on
read or write.

This patch converts all users of the current field to the shared page.

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/include/asm/kvm_para.h      |  1 +
 arch/powerpc/kvm/book3s.c                | 14 +++++++-------
 arch/powerpc/kvm/book3s_emulate.c        |  6 +++---
 arch/powerpc/kvm/book3s_paired_singles.c |  2 +-
 arch/powerpc/kvm/booke.c                 |  2 +-
 arch/powerpc/kvm/booke_emulate.c         |  4 ++--
 7 files changed, 15 insertions(+), 15 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index ba20f90655f3..c852408eac38 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -231,7 +231,6 @@ struct kvm_vcpu_arch {
 	ulong csrr1;
 	ulong dsrr0;
 	ulong dsrr1;
-	ulong dear;
 	ulong esr;
 	u32 dec;
 	u32 decar;
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 9f7565b1de65..ec72a1c8c045 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -23,6 +23,7 @@
 #include <linux/types.h>
 
 struct kvm_vcpu_arch_shared {
+	__u64 dar;
 	__u64 msr;
 	__u32 dsisr;
 };
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index eb401b6d4d8c..4d46f8b13cc6 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -594,14 +594,14 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	if (page_found == -ENOENT) {
 		/* Page not found in guest PTE entries */
-		vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
+		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
 		vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
 		vcpu->arch.shared->msr |=
 			(to_svcpu(vcpu)->shadow_srr1 & 0x00000000f8000000ULL);
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EPERM) {
 		/* Storage protection */
-		vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
+		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
 		vcpu->arch.shared->dsisr =
 			to_svcpu(vcpu)->fault_dsisr & ~DSISR_NOHPTE;
 		vcpu->arch.shared->dsisr |= DSISR_PROTFAULT;
@@ -610,7 +610,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		kvmppc_book3s_queue_irqprio(vcpu, vec);
 	} else if (page_found == -EINVAL) {
 		/* Page not found in guest SLB */
-		vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
+		vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
 		kvmppc_book3s_queue_irqprio(vcpu, vec + 0x80);
 	} else if (!is_mmio &&
 		   kvmppc_visible_gfn(vcpu, pte.raddr >> PAGE_SHIFT)) {
@@ -867,17 +867,17 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		if (to_svcpu(vcpu)->fault_dsisr & DSISR_NOHPTE) {
 			r = kvmppc_handle_pagefault(run, vcpu, dar, exit_nr);
 		} else {
-			vcpu->arch.dear = dar;
+			vcpu->arch.shared->dar = dar;
 			vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-			kvmppc_mmu_pte_flush(vcpu, vcpu->arch.dear, ~0xFFFUL);
+			kvmppc_mmu_pte_flush(vcpu, dar, ~0xFFFUL);
 			r = RESUME_GUEST;
 		}
 		break;
 	}
 	case BOOK3S_INTERRUPT_DATA_SEGMENT:
 		if (kvmppc_mmu_map_segment(vcpu, kvmppc_get_fault_dar(vcpu)) < 0) {
-			vcpu->arch.dear = kvmppc_get_fault_dar(vcpu);
+			vcpu->arch.shared->dar = kvmppc_get_fault_dar(vcpu);
 			kvmppc_book3s_queue_irqprio(vcpu,
 				BOOK3S_INTERRUPT_DATA_SEGMENT);
 		}
@@ -997,7 +997,7 @@ program_interrupt:
 		if (kvmppc_read_inst(vcpu) == EMULATE_DONE) {
 			vcpu->arch.shared->dsisr = kvmppc_alignment_dsisr(vcpu,
 				kvmppc_get_last_inst(vcpu));
-			vcpu->arch.dear = kvmppc_alignment_dar(vcpu,
+			vcpu->arch.shared->dar = kvmppc_alignment_dar(vcpu,
 				kvmppc_get_last_inst(vcpu));
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 		}
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index 9982ff163af0..c1478642f856 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -212,7 +212,7 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			r = kvmppc_st(vcpu, &addr, 32, zeros, true);
 			if ((r == -ENOENT) || (r == -EPERM)) {
 				*advance = 0;
-				vcpu->arch.dear = vaddr;
+				vcpu->arch.shared->dar = vaddr;
 				to_svcpu(vcpu)->fault_dar = vaddr;
 
 				dsisr = DSISR_ISSTORE;
@@ -330,7 +330,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		vcpu->arch.shared->dsisr = spr_val;
 		break;
 	case SPRN_DAR:
-		vcpu->arch.dear = spr_val;
+		vcpu->arch.shared->dar = spr_val;
 		break;
 	case SPRN_HIOR:
 		to_book3s(vcpu)->hior = spr_val;
@@ -443,7 +443,7 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dsisr);
 		break;
 	case SPRN_DAR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dear);
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dar);
 		break;
 	case SPRN_HIOR:
 		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->hior);
diff --git a/arch/powerpc/kvm/book3s_paired_singles.c b/arch/powerpc/kvm/book3s_paired_singles.c
index 749dfbd04738..807576f148ce 100644
--- a/arch/powerpc/kvm/book3s_paired_singles.c
+++ b/arch/powerpc/kvm/book3s_paired_singles.c
@@ -169,7 +169,7 @@ static void kvmppc_inject_pf(struct kvm_vcpu *vcpu, ulong eaddr, bool is_store)
 
 	shared->msr = kvmppc_set_field(shared->msr, 33, 36, 0);
 	shared->msr = kvmppc_set_field(shared->msr, 42, 47, 0);
-	vcpu->arch.dear = eaddr;
+	shared->dar = eaddr;
 	/* Page Fault */
 	dsisr = kvmppc_set_field(0, 33, 33, 1);
 	if (is_store)
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 4ec9d49a1cb9..4aab6d2ce133 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -195,7 +195,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 		if (update_esr == true)
 			vcpu->arch.esr = vcpu->arch.queued_esr;
 		if (update_dear == true)
-			vcpu->arch.dear = vcpu->arch.queued_dear;
+			vcpu->arch.shared->dar = vcpu->arch.queued_dear;
 		kvmppc_set_msr(vcpu, vcpu->arch.shared->msr & msr_mask);
 
 		clear_bit(priority, &vcpu->arch.pending_exceptions);
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index b115203ac118..51ef4539ed51 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -105,7 +105,7 @@ int kvmppc_booke_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 
 	switch (sprn) {
 	case SPRN_DEAR:
-		vcpu->arch.dear = spr_val; break;
+		vcpu->arch.shared->dar = spr_val; break;
 	case SPRN_ESR:
 		vcpu->arch.esr = spr_val; break;
 	case SPRN_DBCR0:
@@ -200,7 +200,7 @@ int kvmppc_booke_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_IVPR:
 		kvmppc_set_gpr(vcpu, rt, vcpu->arch.ivpr); break;
 	case SPRN_DEAR:
-		kvmppc_set_gpr(vcpu, rt, vcpu->arch.dear); break;
+		kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->dar); break;
 	case SPRN_ESR:
 		kvmppc_set_gpr(vcpu, rt, vcpu->arch.esr); break;
 	case SPRN_DBCR0:
-- 
cgit v1.2.1


From de7906c36ca1e22a3e3600e95c6a4e2c1e4e2e9c Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:46 +0200
Subject: KVM: PPC: Convert SRR0 and SRR1 to shared page

The SRR0 and SRR1 registers contain cached values of the PC and MSR
respectively. They get written to by the hypervisor when an interrupt
occurs or directly by the kernel. They are also used to tell the rfi(d)
instruction where to jump to.

Because it only gets touched on defined events that, it's very simple to
share with the guest. Hypervisor and guest both have full r/w access.

This patch converts all users of the current field to the shared page.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h |  2 --
 arch/powerpc/include/asm/kvm_para.h |  2 ++
 arch/powerpc/kvm/book3s.c           | 12 ++++++------
 arch/powerpc/kvm/book3s_emulate.c   |  4 ++--
 arch/powerpc/kvm/booke.c            | 15 ++++++++-------
 arch/powerpc/kvm/booke_emulate.c    |  4 ++--
 arch/powerpc/kvm/emulate.c          | 12 ++++++++----
 7 files changed, 28 insertions(+), 23 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index c852408eac38..5255d754f9a9 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -225,8 +225,6 @@ struct kvm_vcpu_arch {
 	ulong sprg5;
 	ulong sprg6;
 	ulong sprg7;
-	ulong srr0;
-	ulong srr1;
 	ulong csrr0;
 	ulong csrr1;
 	ulong dsrr0;
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index ec72a1c8c045..d7fc6c2c9730 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -23,6 +23,8 @@
 #include <linux/types.h>
 
 struct kvm_vcpu_arch_shared {
+	__u64 srr0;
+	__u64 srr1;
 	__u64 dar;
 	__u64 msr;
 	__u32 dsisr;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 4d46f8b13cc6..afa0dd4a27f4 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -162,8 +162,8 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 
 void kvmppc_inject_interrupt(struct kvm_vcpu *vcpu, int vec, u64 flags)
 {
-	vcpu->arch.srr0 = kvmppc_get_pc(vcpu);
-	vcpu->arch.srr1 = vcpu->arch.shared->msr | flags;
+	vcpu->arch.shared->srr0 = kvmppc_get_pc(vcpu);
+	vcpu->arch.shared->srr1 = vcpu->arch.shared->msr | flags;
 	kvmppc_set_pc(vcpu, to_book3s(vcpu)->hior + vec);
 	vcpu->arch.mmu.reset_msr(vcpu);
 }
@@ -1059,8 +1059,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->lr = kvmppc_get_lr(vcpu);
 	regs->xer = kvmppc_get_xer(vcpu);
 	regs->msr = vcpu->arch.shared->msr;
-	regs->srr0 = vcpu->arch.srr0;
-	regs->srr1 = vcpu->arch.srr1;
+	regs->srr0 = vcpu->arch.shared->srr0;
+	regs->srr1 = vcpu->arch.shared->srr1;
 	regs->pid = vcpu->arch.pid;
 	regs->sprg0 = vcpu->arch.sprg0;
 	regs->sprg1 = vcpu->arch.sprg1;
@@ -1086,8 +1086,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	kvmppc_set_lr(vcpu, regs->lr);
 	kvmppc_set_xer(vcpu, regs->xer);
 	kvmppc_set_msr(vcpu, regs->msr);
-	vcpu->arch.srr0 = regs->srr0;
-	vcpu->arch.srr1 = regs->srr1;
+	vcpu->arch.shared->srr0 = regs->srr0;
+	vcpu->arch.shared->srr1 = regs->srr1;
 	vcpu->arch.sprg0 = regs->sprg0;
 	vcpu->arch.sprg1 = regs->sprg1;
 	vcpu->arch.sprg2 = regs->sprg2;
diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index c1478642f856..f333cb445349 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -73,8 +73,8 @@ int kvmppc_core_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		switch (get_xop(inst)) {
 		case OP_19_XOP_RFID:
 		case OP_19_XOP_RFI:
-			kvmppc_set_pc(vcpu, vcpu->arch.srr0);
-			kvmppc_set_msr(vcpu, vcpu->arch.srr1);
+			kvmppc_set_pc(vcpu, vcpu->arch.shared->srr0);
+			kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1);
 			*advance = 0;
 			break;
 
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 4aab6d2ce133..793df28b628d 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -64,7 +64,8 @@ void kvmppc_dump_vcpu(struct kvm_vcpu *vcpu)
 
 	printk("pc:   %08lx msr:  %08llx\n", vcpu->arch.pc, vcpu->arch.shared->msr);
 	printk("lr:   %08lx ctr:  %08lx\n", vcpu->arch.lr, vcpu->arch.ctr);
-	printk("srr0: %08lx srr1: %08lx\n", vcpu->arch.srr0, vcpu->arch.srr1);
+	printk("srr0: %08llx srr1: %08llx\n", vcpu->arch.shared->srr0,
+					    vcpu->arch.shared->srr1);
 
 	printk("exceptions: %08lx\n", vcpu->arch.pending_exceptions);
 
@@ -189,8 +190,8 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	}
 
 	if (allowed) {
-		vcpu->arch.srr0 = vcpu->arch.pc;
-		vcpu->arch.srr1 = vcpu->arch.shared->msr;
+		vcpu->arch.shared->srr0 = vcpu->arch.pc;
+		vcpu->arch.shared->srr1 = vcpu->arch.shared->msr;
 		vcpu->arch.pc = vcpu->arch.ivpr | vcpu->arch.ivor[priority];
 		if (update_esr == true)
 			vcpu->arch.esr = vcpu->arch.queued_esr;
@@ -491,8 +492,8 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->lr = vcpu->arch.lr;
 	regs->xer = kvmppc_get_xer(vcpu);
 	regs->msr = vcpu->arch.shared->msr;
-	regs->srr0 = vcpu->arch.srr0;
-	regs->srr1 = vcpu->arch.srr1;
+	regs->srr0 = vcpu->arch.shared->srr0;
+	regs->srr1 = vcpu->arch.shared->srr1;
 	regs->pid = vcpu->arch.pid;
 	regs->sprg0 = vcpu->arch.sprg0;
 	regs->sprg1 = vcpu->arch.sprg1;
@@ -518,8 +519,8 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	vcpu->arch.lr = regs->lr;
 	kvmppc_set_xer(vcpu, regs->xer);
 	kvmppc_set_msr(vcpu, regs->msr);
-	vcpu->arch.srr0 = regs->srr0;
-	vcpu->arch.srr1 = regs->srr1;
+	vcpu->arch.shared->srr0 = regs->srr0;
+	vcpu->arch.shared->srr1 = regs->srr1;
 	vcpu->arch.sprg0 = regs->sprg0;
 	vcpu->arch.sprg1 = regs->sprg1;
 	vcpu->arch.sprg2 = regs->sprg2;
diff --git a/arch/powerpc/kvm/booke_emulate.c b/arch/powerpc/kvm/booke_emulate.c
index 51ef4539ed51..1260f5f24c0c 100644
--- a/arch/powerpc/kvm/booke_emulate.c
+++ b/arch/powerpc/kvm/booke_emulate.c
@@ -31,8 +31,8 @@
 
 static void kvmppc_emul_rfi(struct kvm_vcpu *vcpu)
 {
-	vcpu->arch.pc = vcpu->arch.srr0;
-	kvmppc_set_msr(vcpu, vcpu->arch.srr1);
+	vcpu->arch.pc = vcpu->arch.shared->srr0;
+	kvmppc_set_msr(vcpu, vcpu->arch.shared->srr1);
 }
 
 int kvmppc_booke_emulate_op(struct kvm_run *run, struct kvm_vcpu *vcpu,
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index 4568ec386c2a..ad0fa4ff4ea0 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -242,9 +242,11 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 			switch (sprn) {
 			case SPRN_SRR0:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.srr0); break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->srr0);
+				break;
 			case SPRN_SRR1:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.srr1); break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->srr1);
+				break;
 			case SPRN_PVR:
 				kvmppc_set_gpr(vcpu, rt, vcpu->arch.pvr); break;
 			case SPRN_PIR:
@@ -320,9 +322,11 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			rs = get_rs(inst);
 			switch (sprn) {
 			case SPRN_SRR0:
-				vcpu->arch.srr0 = kvmppc_get_gpr(vcpu, rs); break;
+				vcpu->arch.shared->srr0 = kvmppc_get_gpr(vcpu, rs);
+				break;
 			case SPRN_SRR1:
-				vcpu->arch.srr1 = kvmppc_get_gpr(vcpu, rs); break;
+				vcpu->arch.shared->srr1 = kvmppc_get_gpr(vcpu, rs);
+				break;
 
 			/* XXX We need to context-switch the timebase for
 			 * watchdog and FIT. */
-- 
cgit v1.2.1


From a73a9599e03eef1324d5aeecaebc1b339d2e1664 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:47 +0200
Subject: KVM: PPC: Convert SPRG[0-4] to shared page

When in kernel mode there are 4 additional registers available that are
simple data storage. Instead of exiting to the hypervisor to read and
write those, we can just share them with the guest using the page.

This patch converts all users of the current field to the shared page.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h |  4 ----
 arch/powerpc/include/asm/kvm_para.h |  4 ++++
 arch/powerpc/kvm/book3s.c           | 16 ++++++++--------
 arch/powerpc/kvm/booke.c            | 16 ++++++++--------
 arch/powerpc/kvm/emulate.c          | 24 ++++++++++++++++--------
 5 files changed, 36 insertions(+), 28 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 5255d754f9a9..221cf85e9a6e 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -217,10 +217,6 @@ struct kvm_vcpu_arch {
 	ulong guest_owned_ext;
 #endif
 	u32 mmucr;
-	ulong sprg0;
-	ulong sprg1;
-	ulong sprg2;
-	ulong sprg3;
 	ulong sprg4;
 	ulong sprg5;
 	ulong sprg6;
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index d7fc6c2c9730..e402999ba193 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -23,6 +23,10 @@
 #include <linux/types.h>
 
 struct kvm_vcpu_arch_shared {
+	__u64 sprg0;
+	__u64 sprg1;
+	__u64 sprg2;
+	__u64 sprg3;
 	__u64 srr0;
 	__u64 srr1;
 	__u64 dar;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index afa0dd4a27f4..cfd7fe5c3a62 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -1062,10 +1062,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->srr0 = vcpu->arch.shared->srr0;
 	regs->srr1 = vcpu->arch.shared->srr1;
 	regs->pid = vcpu->arch.pid;
-	regs->sprg0 = vcpu->arch.sprg0;
-	regs->sprg1 = vcpu->arch.sprg1;
-	regs->sprg2 = vcpu->arch.sprg2;
-	regs->sprg3 = vcpu->arch.sprg3;
+	regs->sprg0 = vcpu->arch.shared->sprg0;
+	regs->sprg1 = vcpu->arch.shared->sprg1;
+	regs->sprg2 = vcpu->arch.shared->sprg2;
+	regs->sprg3 = vcpu->arch.shared->sprg3;
 	regs->sprg5 = vcpu->arch.sprg4;
 	regs->sprg6 = vcpu->arch.sprg5;
 	regs->sprg7 = vcpu->arch.sprg6;
@@ -1088,10 +1088,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	kvmppc_set_msr(vcpu, regs->msr);
 	vcpu->arch.shared->srr0 = regs->srr0;
 	vcpu->arch.shared->srr1 = regs->srr1;
-	vcpu->arch.sprg0 = regs->sprg0;
-	vcpu->arch.sprg1 = regs->sprg1;
-	vcpu->arch.sprg2 = regs->sprg2;
-	vcpu->arch.sprg3 = regs->sprg3;
+	vcpu->arch.shared->sprg0 = regs->sprg0;
+	vcpu->arch.shared->sprg1 = regs->sprg1;
+	vcpu->arch.shared->sprg2 = regs->sprg2;
+	vcpu->arch.shared->sprg3 = regs->sprg3;
 	vcpu->arch.sprg5 = regs->sprg4;
 	vcpu->arch.sprg6 = regs->sprg5;
 	vcpu->arch.sprg7 = regs->sprg6;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 793df28b628d..b2c8c423c4d5 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -495,10 +495,10 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	regs->srr0 = vcpu->arch.shared->srr0;
 	regs->srr1 = vcpu->arch.shared->srr1;
 	regs->pid = vcpu->arch.pid;
-	regs->sprg0 = vcpu->arch.sprg0;
-	regs->sprg1 = vcpu->arch.sprg1;
-	regs->sprg2 = vcpu->arch.sprg2;
-	regs->sprg3 = vcpu->arch.sprg3;
+	regs->sprg0 = vcpu->arch.shared->sprg0;
+	regs->sprg1 = vcpu->arch.shared->sprg1;
+	regs->sprg2 = vcpu->arch.shared->sprg2;
+	regs->sprg3 = vcpu->arch.shared->sprg3;
 	regs->sprg5 = vcpu->arch.sprg4;
 	regs->sprg6 = vcpu->arch.sprg5;
 	regs->sprg7 = vcpu->arch.sprg6;
@@ -521,10 +521,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	kvmppc_set_msr(vcpu, regs->msr);
 	vcpu->arch.shared->srr0 = regs->srr0;
 	vcpu->arch.shared->srr1 = regs->srr1;
-	vcpu->arch.sprg0 = regs->sprg0;
-	vcpu->arch.sprg1 = regs->sprg1;
-	vcpu->arch.sprg2 = regs->sprg2;
-	vcpu->arch.sprg3 = regs->sprg3;
+	vcpu->arch.shared->sprg0 = regs->sprg0;
+	vcpu->arch.shared->sprg1 = regs->sprg1;
+	vcpu->arch.shared->sprg2 = regs->sprg2;
+	vcpu->arch.shared->sprg3 = regs->sprg3;
 	vcpu->arch.sprg5 = regs->sprg4;
 	vcpu->arch.sprg6 = regs->sprg5;
 	vcpu->arch.sprg7 = regs->sprg6;
diff --git a/arch/powerpc/kvm/emulate.c b/arch/powerpc/kvm/emulate.c
index ad0fa4ff4ea0..454869b5e91e 100644
--- a/arch/powerpc/kvm/emulate.c
+++ b/arch/powerpc/kvm/emulate.c
@@ -263,13 +263,17 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 				kvmppc_set_gpr(vcpu, rt, get_tb()); break;
 
 			case SPRN_SPRG0:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg0); break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg0);
+				break;
 			case SPRN_SPRG1:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg1); break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg1);
+				break;
 			case SPRN_SPRG2:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg2); break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg2);
+				break;
 			case SPRN_SPRG3:
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.sprg3); break;
+				kvmppc_set_gpr(vcpu, rt, vcpu->arch.shared->sprg3);
+				break;
 			/* Note: SPRG4-7 are user-readable, so we don't get
 			 * a trap. */
 
@@ -341,13 +345,17 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 				break;
 
 			case SPRN_SPRG0:
-				vcpu->arch.sprg0 = kvmppc_get_gpr(vcpu, rs); break;
+				vcpu->arch.shared->sprg0 = kvmppc_get_gpr(vcpu, rs);
+				break;
 			case SPRN_SPRG1:
-				vcpu->arch.sprg1 = kvmppc_get_gpr(vcpu, rs); break;
+				vcpu->arch.shared->sprg1 = kvmppc_get_gpr(vcpu, rs);
+				break;
 			case SPRN_SPRG2:
-				vcpu->arch.sprg2 = kvmppc_get_gpr(vcpu, rs); break;
+				vcpu->arch.shared->sprg2 = kvmppc_get_gpr(vcpu, rs);
+				break;
 			case SPRN_SPRG3:
-				vcpu->arch.sprg3 = kvmppc_get_gpr(vcpu, rs); break;
+				vcpu->arch.shared->sprg3 = kvmppc_get_gpr(vcpu, rs);
+				break;
 
 			default:
 				emulated = kvmppc_core_emulate_mtspr(vcpu, sprn, rs);
-- 
cgit v1.2.1


From 2a342ed57756ad5d8af5456959433884367e5ab2 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:48 +0200
Subject: KVM: PPC: Implement hypervisor interface

To communicate with KVM directly we need to plumb some sort of interface
between the guest and KVM. Usually those interfaces use hypercalls.

This hypercall implementation is described in the last patch of the series
in a special documentation file. Please read that for further information.

This patch implements stubs to handle KVM PPC hypercalls on the host and
guest side alike.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_para.h | 114 +++++++++++++++++++++++++++++++++++-
 arch/powerpc/include/asm/kvm_ppc.h  |   1 +
 arch/powerpc/kernel/Makefile        |   2 +
 arch/powerpc/kernel/kvm.c           |  68 +++++++++++++++++++++
 arch/powerpc/kvm/book3s.c           |   9 ++-
 arch/powerpc/kvm/booke.c            |  10 +++-
 arch/powerpc/kvm/powerpc.c          |  32 ++++++++++
 7 files changed, 232 insertions(+), 4 deletions(-)
 create mode 100644 arch/powerpc/kernel/kvm.c

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index e402999ba193..556fd59ee0f1 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -21,6 +21,7 @@
 #define __POWERPC_KVM_PARA_H__
 
 #include <linux/types.h>
+#include <linux/of.h>
 
 struct kvm_vcpu_arch_shared {
 	__u64 sprg0;
@@ -34,16 +35,127 @@ struct kvm_vcpu_arch_shared {
 	__u32 dsisr;
 };
 
+#define KVM_SC_MAGIC_R0		0x4b564d21 /* "KVM!" */
+#define HC_VENDOR_KVM		(42 << 16)
+#define HC_EV_SUCCESS		0
+#define HC_EV_UNIMPLEMENTED	12
+
 #ifdef __KERNEL__
 
+#ifdef CONFIG_KVM_GUEST
+
+static inline int kvm_para_available(void)
+{
+	struct device_node *hyper_node;
+
+	hyper_node = of_find_node_by_path("/hypervisor");
+	if (!hyper_node)
+		return 0;
+
+	if (!of_device_is_compatible(hyper_node, "linux,kvm"))
+		return 0;
+
+	return 1;
+}
+
+extern unsigned long kvm_hypercall(unsigned long *in,
+				   unsigned long *out,
+				   unsigned long nr);
+
+#else
+
 static inline int kvm_para_available(void)
 {
 	return 0;
 }
 
+static unsigned long kvm_hypercall(unsigned long *in,
+				   unsigned long *out,
+				   unsigned long nr)
+{
+	return HC_EV_UNIMPLEMENTED;
+}
+
+#endif
+
+static inline long kvm_hypercall0_1(unsigned int nr, unsigned long *r2)
+{
+	unsigned long in[8];
+	unsigned long out[8];
+	unsigned long r;
+
+	r = kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+	*r2 = out[0];
+
+	return r;
+}
+
+static inline long kvm_hypercall0(unsigned int nr)
+{
+	unsigned long in[8];
+	unsigned long out[8];
+
+	return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+}
+
+static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
+{
+	unsigned long in[8];
+	unsigned long out[8];
+
+	in[0] = p1;
+	return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+}
+
+static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
+				  unsigned long p2)
+{
+	unsigned long in[8];
+	unsigned long out[8];
+
+	in[0] = p1;
+	in[1] = p2;
+	return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+}
+
+static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
+				  unsigned long p2, unsigned long p3)
+{
+	unsigned long in[8];
+	unsigned long out[8];
+
+	in[0] = p1;
+	in[1] = p2;
+	in[2] = p3;
+	return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+}
+
+static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
+				  unsigned long p2, unsigned long p3,
+				  unsigned long p4)
+{
+	unsigned long in[8];
+	unsigned long out[8];
+
+	in[0] = p1;
+	in[1] = p2;
+	in[2] = p3;
+	in[3] = p4;
+	return kvm_hypercall(in, out, nr | HC_VENDOR_KVM);
+}
+
+
 static inline unsigned int kvm_arch_para_features(void)
 {
-	return 0;
+	unsigned long r;
+
+	if (!kvm_para_available())
+		return 0;
+
+	if(kvm_hypercall0_1(KVM_HC_FEATURES, &r))
+		return 0;
+
+	return r;
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 18d139ec2d22..ecb3bc74c344 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -107,6 +107,7 @@ extern int kvmppc_booke_init(void);
 extern void kvmppc_booke_exit(void);
 
 extern void kvmppc_core_destroy_mmu(struct kvm_vcpu *vcpu);
+extern int kvmppc_kvm_pv(struct kvm_vcpu *vcpu);
 
 /*
  * Cuts out inst bits with ordering according to spec.
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 1dda70129141..3a6955dc7191 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -127,6 +127,8 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
 obj-y				+= ppc_save_regs.o
 endif
 
+obj-$(CONFIG_KVM_GUEST)		+= kvm.o
+
 # Disable GCOV in odd or sensitive code
 GCOV_PROFILE_prom_init.o := n
 GCOV_PROFILE_ftrace.o := n
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
new file mode 100644
index 000000000000..4f85505e4653
--- /dev/null
+++ b/arch/powerpc/kernel/kvm.c
@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 2010 SUSE Linux Products GmbH. All rights reserved.
+ *
+ * Authors:
+ *     Alexander Graf <agraf@suse.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/init.h>
+#include <linux/kvm_para.h>
+#include <linux/slab.h>
+#include <linux/of.h>
+
+#include <asm/reg.h>
+#include <asm/kvm_ppc.h>
+#include <asm/sections.h>
+#include <asm/cacheflush.h>
+#include <asm/disassemble.h>
+
+unsigned long kvm_hypercall(unsigned long *in,
+			    unsigned long *out,
+			    unsigned long nr)
+{
+	unsigned long register r0 asm("r0");
+	unsigned long register r3 asm("r3") = in[0];
+	unsigned long register r4 asm("r4") = in[1];
+	unsigned long register r5 asm("r5") = in[2];
+	unsigned long register r6 asm("r6") = in[3];
+	unsigned long register r7 asm("r7") = in[4];
+	unsigned long register r8 asm("r8") = in[5];
+	unsigned long register r9 asm("r9") = in[6];
+	unsigned long register r10 asm("r10") = in[7];
+	unsigned long register r11 asm("r11") = nr;
+	unsigned long register r12 asm("r12");
+
+	asm volatile("bl	kvm_hypercall_start"
+		     : "=r"(r0), "=r"(r3), "=r"(r4), "=r"(r5), "=r"(r6),
+		       "=r"(r7), "=r"(r8), "=r"(r9), "=r"(r10), "=r"(r11),
+		       "=r"(r12)
+		     : "r"(r3), "r"(r4), "r"(r5), "r"(r6), "r"(r7), "r"(r8),
+		       "r"(r9), "r"(r10), "r"(r11)
+		     : "memory", "cc", "xer", "ctr", "lr");
+
+	out[0] = r4;
+	out[1] = r5;
+	out[2] = r6;
+	out[3] = r7;
+	out[4] = r8;
+	out[5] = r9;
+	out[6] = r10;
+	out[7] = r11;
+
+	return r3;
+}
+EXPORT_SYMBOL_GPL(kvm_hypercall);
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index cfd7fe5c3a62..5cb5f0d9381f 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -947,10 +947,10 @@ program_interrupt:
 		break;
 	}
 	case BOOK3S_INTERRUPT_SYSCALL:
-		// XXX make user settable
 		if (vcpu->arch.osi_enabled &&
 		    (((u32)kvmppc_get_gpr(vcpu, 3)) == OSI_SC_MAGIC_R3) &&
 		    (((u32)kvmppc_get_gpr(vcpu, 4)) == OSI_SC_MAGIC_R4)) {
+			/* MOL hypercalls */
 			u64 *gprs = run->osi.gprs;
 			int i;
 
@@ -959,8 +959,13 @@ program_interrupt:
 				gprs[i] = kvmppc_get_gpr(vcpu, i);
 			vcpu->arch.osi_needed = 1;
 			r = RESUME_HOST_NV;
-
+		} else if (!(vcpu->arch.shared->msr & MSR_PR) &&
+		    (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
+			/* KVM PV hypercalls */
+			kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
+			r = RESUME_GUEST;
 		} else {
+			/* Guest syscalls */
 			vcpu->stat.syscall_exits++;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
 			r = RESUME_GUEST;
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index b2c8c423c4d5..13e0747178e3 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -338,7 +338,15 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		break;
 
 	case BOOKE_INTERRUPT_SYSCALL:
-		kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SYSCALL);
+		if (!(vcpu->arch.shared->msr & MSR_PR) &&
+		    (((u32)kvmppc_get_gpr(vcpu, 0)) == KVM_SC_MAGIC_R0)) {
+			/* KVM PV hypercalls */
+			kvmppc_set_gpr(vcpu, 3, kvmppc_kvm_pv(vcpu));
+			r = RESUME_GUEST;
+		} else {
+			/* Guest syscalls */
+			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_SYSCALL);
+		}
 		kvmppc_account_exit(vcpu, SYSCALL_EXITS);
 		r = RESUME_GUEST;
 		break;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 22f6fa2982f2..a4cf4b47e232 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -42,6 +42,38 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
 	       !!(v->arch.pending_exceptions);
 }
 
+int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
+{
+	int nr = kvmppc_get_gpr(vcpu, 11);
+	int r;
+	unsigned long __maybe_unused param1 = kvmppc_get_gpr(vcpu, 3);
+	unsigned long __maybe_unused param2 = kvmppc_get_gpr(vcpu, 4);
+	unsigned long __maybe_unused param3 = kvmppc_get_gpr(vcpu, 5);
+	unsigned long __maybe_unused param4 = kvmppc_get_gpr(vcpu, 6);
+	unsigned long r2 = 0;
+
+	if (!(vcpu->arch.shared->msr & MSR_SF)) {
+		/* 32 bit mode */
+		param1 &= 0xffffffff;
+		param2 &= 0xffffffff;
+		param3 &= 0xffffffff;
+		param4 &= 0xffffffff;
+	}
+
+	switch (nr) {
+	case HC_VENDOR_KVM | KVM_HC_FEATURES:
+		r = HC_EV_SUCCESS;
+
+		/* Second return value is in r4 */
+		kvmppc_set_gpr(vcpu, 4, r2);
+		break;
+	default:
+		r = HC_EV_UNIMPLEMENTED;
+		break;
+	}
+
+	return r;
+}
 
 int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
-- 
cgit v1.2.1


From 5c6cedf488a1144ac4f683f3ea1a642533d1dcd2 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:49 +0200
Subject: KVM: PPC: Add PV guest critical sections

When running in hooked code we need a way to disable interrupts without
clobbering any interrupts or exiting out to the hypervisor.

To achieve this, we have an additional critical field in the shared page. If
that field is equal to the r1 register of the guest, it tells the hypervisor
that we're in such a critical section and thus may not receive any interrupts.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_para.h |  1 +
 arch/powerpc/kvm/book3s.c           | 18 ++++++++++++++++--
 arch/powerpc/kvm/booke.c            | 15 +++++++++++++++
 3 files changed, 32 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 556fd59ee0f1..4577e7b6dff1 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -24,6 +24,7 @@
 #include <linux/of.h>
 
 struct kvm_vcpu_arch_shared {
+	__u64 critical;		/* Guest may not get interrupts if == r1 */
 	__u64 sprg0;
 	__u64 sprg1;
 	__u64 sprg2;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 5cb5f0d9381f..d6227ff0ceae 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -251,14 +251,28 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 	int deliver = 1;
 	int vec = 0;
 	ulong flags = 0ULL;
+	ulong crit_raw = vcpu->arch.shared->critical;
+	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
+	bool crit;
+
+	/* Truncate crit indicators in 32 bit mode */
+	if (!(vcpu->arch.shared->msr & MSR_SF)) {
+		crit_raw &= 0xffffffff;
+		crit_r1 &= 0xffffffff;
+	}
+
+	/* Critical section when crit == r1 */
+	crit = (crit_raw == crit_r1);
+	/* ... and we're in supervisor mode */
+	crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
 
 	switch (priority) {
 	case BOOK3S_IRQPRIO_DECREMENTER:
-		deliver = vcpu->arch.shared->msr & MSR_EE;
+		deliver = (vcpu->arch.shared->msr & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_DECREMENTER;
 		break;
 	case BOOK3S_IRQPRIO_EXTERNAL:
-		deliver = vcpu->arch.shared->msr & MSR_EE;
+		deliver = (vcpu->arch.shared->msr & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_EXTERNAL;
 		break;
 	case BOOK3S_IRQPRIO_SYSTEM_RESET:
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 13e0747178e3..104d0ee8c8aa 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -147,6 +147,20 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	int allowed = 0;
 	ulong uninitialized_var(msr_mask);
 	bool update_esr = false, update_dear = false;
+	ulong crit_raw = vcpu->arch.shared->critical;
+	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
+	bool crit;
+
+	/* Truncate crit indicators in 32 bit mode */
+	if (!(vcpu->arch.shared->msr & MSR_SF)) {
+		crit_raw &= 0xffffffff;
+		crit_r1 &= 0xffffffff;
+	}
+
+	/* Critical section when crit == r1 */
+	crit = (crit_raw == crit_r1);
+	/* ... and we're in supervisor mode */
+	crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
 
 	switch (priority) {
 	case BOOKE_IRQPRIO_DTLB_MISS:
@@ -181,6 +195,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	case BOOKE_IRQPRIO_DECREMENTER:
 	case BOOKE_IRQPRIO_FIT:
 		allowed = vcpu->arch.shared->msr & MSR_EE;
+		allowed = allowed && !crit;
 		msr_mask = MSR_CE|MSR_ME|MSR_DE;
 		break;
 	case BOOKE_IRQPRIO_DEBUG:
-- 
cgit v1.2.1


From fad93fe1d452960eb838109222cc949eb77f2859 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:50 +0200
Subject: KVM: PPC: Add PV guest scratch registers

While running in hooked code we need to store register contents out because
we must not clobber any registers.

So let's add some fields to the shared page we can just happily write to.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_para.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 4577e7b6dff1..5be00c9533d2 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -24,6 +24,9 @@
 #include <linux/of.h>
 
 struct kvm_vcpu_arch_shared {
+	__u64 scratch1;
+	__u64 scratch2;
+	__u64 scratch3;
 	__u64 critical;		/* Guest may not get interrupts if == r1 */
 	__u64 sprg0;
 	__u64 sprg1;
-- 
cgit v1.2.1


From 90bba358873dc96a6746f0df453a0a8ca3d6b86e Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:51 +0200
Subject: KVM: PPC: Tell guest about pending interrupts

When the guest turns on interrupts again, it needs to know if we have an
interrupt pending for it. Because if so, it should rather get out of guest
context and get the interrupt.

So we introduce a new field in the shared page that we use to tell the guest
that there's a pending interrupt lying around.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_para.h | 1 +
 arch/powerpc/kvm/book3s.c           | 7 +++++++
 arch/powerpc/kvm/booke.c            | 7 +++++++
 3 files changed, 15 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 5be00c9533d2..0653b0d238b4 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -37,6 +37,7 @@ struct kvm_vcpu_arch_shared {
 	__u64 dar;
 	__u64 msr;
 	__u32 dsisr;
+	__u32 int_pending;	/* Tells the guest if we have an interrupt */
 };
 
 #define KVM_SC_MAGIC_R0		0x4b564d21 /* "KVM!" */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index d6227ff0ceae..06229fec5c9f 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -337,6 +337,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 {
 	unsigned long *pending = &vcpu->arch.pending_exceptions;
+	unsigned long old_pending = vcpu->arch.pending_exceptions;
 	unsigned int priority;
 
 #ifdef EXIT_DEBUG
@@ -356,6 +357,12 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 					 BITS_PER_BYTE * sizeof(*pending),
 					 priority + 1);
 	}
+
+	/* Tell the guest about our interrupt status */
+	if (*pending)
+		vcpu->arch.shared->int_pending = 1;
+	else if (old_pending)
+		vcpu->arch.shared->int_pending = 0;
 }
 
 void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 104d0ee8c8aa..c604277011a6 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -224,6 +224,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 {
 	unsigned long *pending = &vcpu->arch.pending_exceptions;
+	unsigned long old_pending = vcpu->arch.pending_exceptions;
 	unsigned int priority;
 
 	priority = __ffs(*pending);
@@ -235,6 +236,12 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 		                         BITS_PER_BYTE * sizeof(*pending),
 		                         priority + 1);
 	}
+
+	/* Tell the guest about our interrupt status */
+	if (*pending)
+		vcpu->arch.shared->int_pending = 1;
+	else if (old_pending)
+		vcpu->arch.shared->int_pending = 0;
 }
 
 /**
-- 
cgit v1.2.1


From 28e83b4fa7f8bd114940fa933ac8cbe80969eba2 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:52 +0200
Subject: KVM: PPC: Make PAM a define

On PowerPC it's very normal to not support all of the physical RAM in real mode.
To check if we're matching on the shared page or not, we need to know the limits
so we can restrain ourselves to that range.

So let's make it a define instead of open-coding it. And while at it, let's also
increase it.

Signed-off-by: Alexander Graf <agraf@suse.de>

v2 -> v3:

  - RMO -> PAM (non-magic page)
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h | 3 +++
 arch/powerpc/kvm/book3s.c           | 4 ++--
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 221cf85e9a6e..1674da8134cb 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -48,6 +48,9 @@
 #define HPTEG_HASH_NUM_VPTE		(1 << HPTEG_HASH_BITS_VPTE)
 #define HPTEG_HASH_NUM_VPTE_LONG	(1 << HPTEG_HASH_BITS_VPTE_LONG)
 
+/* Physical Address Mask - allowed range of real mode RAM access */
+#define KVM_PAM			0x0fffffffffffffffULL
+
 struct kvm;
 struct kvm_run;
 struct kvm_vcpu;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 06229fec5c9f..0ed5376df82c 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -465,7 +465,7 @@ static int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr, bool data,
 		r = vcpu->arch.mmu.xlate(vcpu, eaddr, pte, data);
 	} else {
 		pte->eaddr = eaddr;
-		pte->raddr = eaddr & 0xffffffff;
+		pte->raddr = eaddr & KVM_PAM;
 		pte->vpage = VSID_REAL | eaddr >> 12;
 		pte->may_read = true;
 		pte->may_write = true;
@@ -579,7 +579,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		pte.may_execute = true;
 		pte.may_read = true;
 		pte.may_write = true;
-		pte.raddr = eaddr & 0xffffffff;
+		pte.raddr = eaddr & KVM_PAM;
 		pte.eaddr = eaddr;
 		pte.vpage = eaddr >> 12;
 	}
-- 
cgit v1.2.1


From beb03f14da9ceff76ff08cbb8af064b52dc21f7e Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:53 +0200
Subject: KVM: PPC: First magic page steps

We will be introducing a method to project the shared page in guest context.
As soon as we're talking about this coupling, the shared page is colled magic
page.

This patch introduces simple defines, so the follow-up patches are easier to
read.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 1674da8134cb..e1da77579e65 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -287,6 +287,8 @@ struct kvm_vcpu_arch {
 	u64 dec_jiffies;
 	unsigned long pending_exceptions;
 	struct kvm_vcpu_arch_shared *shared;
+	unsigned long magic_page_pa; /* phys addr to map the magic page to */
+	unsigned long magic_page_ea; /* effect. addr to map the magic page to */
 
 #ifdef CONFIG_PPC_BOOK3S
 	struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
-- 
cgit v1.2.1


From e8508940a88691ad3d1c46608cd968eb4be9cbc5 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:54 +0200
Subject: KVM: PPC: Magic Page Book3s support

We need to override EA as well as PA lookups for the magic page. When the guest
tells us to project it, the magic page overrides any guest mappings.

In order to reflect that, we need to hook into all the MMU layers of KVM to
force map the magic page if necessary.

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/kvm/book3s.c             | 35 ++++++++++++++++++++++++++++++++---
 arch/powerpc/kvm/book3s_32_mmu.c      | 16 ++++++++++++++++
 arch/powerpc/kvm/book3s_32_mmu_host.c |  2 +-
 arch/powerpc/kvm/book3s_64_mmu.c      | 30 +++++++++++++++++++++++++++++-
 arch/powerpc/kvm/book3s_64_mmu_host.c |  9 ++-------
 6 files changed, 81 insertions(+), 12 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index b5b196166455..00cf8b07e502 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -130,6 +130,7 @@ extern void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat,
 			   bool upper, u32 val);
 extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
 extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu);
+extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 extern u32 kvmppc_trampoline_lowmem;
 extern u32 kvmppc_trampoline_enter;
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 0ed5376df82c..eee97b5a7400 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -419,6 +419,25 @@ void kvmppc_set_pvr(struct kvm_vcpu *vcpu, u32 pvr)
 	}
 }
 
+pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	ulong mp_pa = vcpu->arch.magic_page_pa;
+
+	/* Magic page override */
+	if (unlikely(mp_pa) &&
+	    unlikely(((gfn << PAGE_SHIFT) & KVM_PAM) ==
+		     ((mp_pa & PAGE_MASK) & KVM_PAM))) {
+		ulong shared_page = ((ulong)vcpu->arch.shared) & PAGE_MASK;
+		pfn_t pfn;
+
+		pfn = (pfn_t)virt_to_phys((void*)shared_page) >> PAGE_SHIFT;
+		get_page(pfn_to_page(pfn));
+		return pfn;
+	}
+
+	return gfn_to_pfn(vcpu->kvm, gfn);
+}
+
 /* Book3s_32 CPUs always have 32 bytes cache line size, which Linux assumes. To
  * make Book3s_32 Linux work on Book3s_64, we have to make sure we trap dcbz to
  * emulate 32 bytes dcbz length.
@@ -554,6 +573,13 @@ mmio:
 
 static int kvmppc_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
 {
+	ulong mp_pa = vcpu->arch.magic_page_pa;
+
+	if (unlikely(mp_pa) &&
+	    unlikely((mp_pa & KVM_PAM) >> PAGE_SHIFT == gfn)) {
+		return 1;
+	}
+
 	return kvm_is_visible_gfn(vcpu->kvm, gfn);
 }
 
@@ -1257,6 +1283,7 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	struct kvmppc_vcpu_book3s *vcpu_book3s;
 	struct kvm_vcpu *vcpu;
 	int err = -ENOMEM;
+	unsigned long p;
 
 	vcpu_book3s = vmalloc(sizeof(struct kvmppc_vcpu_book3s));
 	if (!vcpu_book3s)
@@ -1274,8 +1301,10 @@ struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_shadow_vcpu;
 
-	vcpu->arch.shared = (void*)__get_free_page(GFP_KERNEL|__GFP_ZERO);
-	if (!vcpu->arch.shared)
+	p = __get_free_page(GFP_KERNEL|__GFP_ZERO);
+	/* the real shared page fills the last 4k of our page */
+	vcpu->arch.shared = (void*)(p + PAGE_SIZE - 4096);
+	if (!p)
 		goto uninit_vcpu;
 
 	vcpu->arch.host_retip = kvm_return_point;
@@ -1322,7 +1351,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 
-	free_page((unsigned long)vcpu->arch.shared);
+	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
 	kvm_vcpu_uninit(vcpu);
 	kfree(vcpu_book3s->shadow_vcpu);
 	vfree(vcpu_book3s);
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index 449bce5f021a..a7d121adc842 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -281,8 +281,24 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 				      struct kvmppc_pte *pte, bool data)
 {
 	int r;
+	ulong mp_ea = vcpu->arch.magic_page_ea;
 
 	pte->eaddr = eaddr;
+
+	/* Magic page override */
+	if (unlikely(mp_ea) &&
+	    unlikely((eaddr & ~0xfffULL) == (mp_ea & ~0xfffULL)) &&
+	    !(vcpu->arch.shared->msr & MSR_PR)) {
+		pte->vpage = kvmppc_mmu_book3s_32_ea_to_vp(vcpu, eaddr, data);
+		pte->raddr = vcpu->arch.magic_page_pa | (pte->raddr & 0xfff);
+		pte->raddr &= KVM_PAM;
+		pte->may_execute = true;
+		pte->may_read = true;
+		pte->may_write = true;
+
+		return 0;
+	}
+
 	r = kvmppc_mmu_book3s_32_xlate_bat(vcpu, eaddr, pte, data);
 	if (r < 0)
 	       r = kvmppc_mmu_book3s_32_xlate_pte(vcpu, eaddr, pte, data, true);
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 67b8c38d932f..05e8c9eb0e16 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -147,7 +147,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	struct hpte_cache *pte;
 
 	/* Get host physical address for gpa */
-	hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
+	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
 	if (kvm_is_error_hva(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n",
 				 orig_pte->eaddr);
diff --git a/arch/powerpc/kvm/book3s_64_mmu.c b/arch/powerpc/kvm/book3s_64_mmu.c
index 58aa8409dae0..d7889ef3211e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu.c
+++ b/arch/powerpc/kvm/book3s_64_mmu.c
@@ -163,6 +163,22 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	bool found = false;
 	bool perm_err = false;
 	int second = 0;
+	ulong mp_ea = vcpu->arch.magic_page_ea;
+
+	/* Magic page override */
+	if (unlikely(mp_ea) &&
+	    unlikely((eaddr & ~0xfffULL) == (mp_ea & ~0xfffULL)) &&
+	    !(vcpu->arch.shared->msr & MSR_PR)) {
+		gpte->eaddr = eaddr;
+		gpte->vpage = kvmppc_mmu_book3s_64_ea_to_vp(vcpu, eaddr, data);
+		gpte->raddr = vcpu->arch.magic_page_pa | (gpte->raddr & 0xfff);
+		gpte->raddr &= KVM_PAM;
+		gpte->may_execute = true;
+		gpte->may_read = true;
+		gpte->may_write = true;
+
+		return 0;
+	}
 
 	slbe = kvmppc_mmu_book3s_64_find_slbe(vcpu_book3s, eaddr);
 	if (!slbe)
@@ -445,6 +461,7 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 	ulong ea = esid << SID_SHIFT;
 	struct kvmppc_slb *slb;
 	u64 gvsid = esid;
+	ulong mp_ea = vcpu->arch.magic_page_ea;
 
 	if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 		slb = kvmppc_mmu_book3s_64_find_slbe(to_book3s(vcpu), ea);
@@ -464,7 +481,7 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 		break;
 	case MSR_DR|MSR_IR:
 		if (!slb)
-			return -ENOENT;
+			goto no_slb;
 
 		*vsid = gvsid;
 		break;
@@ -477,6 +494,17 @@ static int kvmppc_mmu_book3s_64_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 		*vsid |= VSID_PR;
 
 	return 0;
+
+no_slb:
+	/* Catch magic page case */
+	if (unlikely(mp_ea) &&
+	    unlikely(esid == (mp_ea >> SID_SHIFT)) &&
+	    !(vcpu->arch.shared->msr & MSR_PR)) {
+		*vsid = VSID_REAL | esid;
+		return 0;
+	}
+
+	return -EINVAL;
 }
 
 static bool kvmppc_mmu_book3s_64_is_dcbz32(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 71c1f9027abb..6cdd19a82bda 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -101,18 +101,13 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 	struct kvmppc_sid_map *map;
 
 	/* Get host physical address for gpa */
-	hpaddr = gfn_to_pfn(vcpu->kvm, orig_pte->raddr >> PAGE_SHIFT);
+	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
 	if (kvm_is_error_hva(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
 		return -EINVAL;
 	}
 	hpaddr <<= PAGE_SHIFT;
-#if PAGE_SHIFT == 12
-#elif PAGE_SHIFT == 16
-	hpaddr |= orig_pte->raddr & 0xf000;
-#else
-#error Unknown page size
-#endif
+	hpaddr |= orig_pte->raddr & (~0xfffULL & ~PAGE_MASK);
 
 	/* and write the mapping ea -> hpa into the pt */
 	vcpu->arch.mmu.esid_to_vsid(vcpu, orig_pte->eaddr >> SID_SHIFT, &vsid);
-- 
cgit v1.2.1


From 5fc87407b55f5799418f4dc5931232c2bc06d077 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:55 +0200
Subject: KVM: PPC: Expose magic page support to guest

Now that we have the shared page in place and the MMU code knows about
the magic page, we can expose that capability to the guest!

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_para.h |  2 ++
 arch/powerpc/kvm/powerpc.c          | 11 +++++++++++
 2 files changed, 13 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 0653b0d238b4..7438ab360120 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -45,6 +45,8 @@ struct kvm_vcpu_arch_shared {
 #define HC_EV_SUCCESS		0
 #define HC_EV_UNIMPLEMENTED	12
 
+#define KVM_FEATURE_MAGIC_PAGE	1
+
 #ifdef __KERNEL__
 
 #ifdef CONFIG_KVM_GUEST
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index a4cf4b47e232..fecfe043458d 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -61,8 +61,19 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 	}
 
 	switch (nr) {
+	case HC_VENDOR_KVM | KVM_HC_PPC_MAP_MAGIC_PAGE:
+	{
+		vcpu->arch.magic_page_pa = param1;
+		vcpu->arch.magic_page_ea = param2;
+
+		r = HC_EV_SUCCESS;
+		break;
+	}
 	case HC_VENDOR_KVM | KVM_HC_FEATURES:
 		r = HC_EV_SUCCESS;
+#if defined(CONFIG_PPC_BOOK3S) /* XXX Missing magic page on BookE */
+		r2 |= (1 << KVM_FEATURE_MAGIC_PAGE);
+#endif
 
 		/* Second return value is in r4 */
 		kvmppc_set_gpr(vcpu, 4, r2);
-- 
cgit v1.2.1


From d17051cb8d223dffd6bb847b0565ef1654f8e0e1 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:57 +0200
Subject: KVM: PPC: Generic KVM PV guest support

We have all the hypervisor pieces in place now, but the guest parts are still
missing.

This patch implements basic awareness of KVM when running Linux as guest. It
doesn't do anything with it yet though.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/Makefile      |  2 +-
 arch/powerpc/kernel/asm-offsets.c | 15 +++++++++++++++
 arch/powerpc/kernel/kvm.c         |  3 +++
 arch/powerpc/kernel/kvm_emul.S    | 36 ++++++++++++++++++++++++++++++++++++
 arch/powerpc/platforms/Kconfig    | 10 ++++++++++
 5 files changed, 65 insertions(+), 1 deletion(-)
 create mode 100644 arch/powerpc/kernel/kvm_emul.S

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 3a6955dc7191..be257b0aae36 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -127,7 +127,7 @@ ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
 obj-y				+= ppc_save_regs.o
 endif
 
-obj-$(CONFIG_KVM_GUEST)		+= kvm.o
+obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvm_emul.o
 
 # Disable GCOV in odd or sensitive code
 GCOV_PROFILE_prom_init.o := n
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 1221bcdff52f..37486cafb69d 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -465,6 +465,21 @@ int main(void)
 	DEFINE(VCPU_FAULT_ESR, offsetof(struct kvm_vcpu, arch.fault_esr));
 #endif /* CONFIG_PPC_BOOK3S */
 #endif
+
+#ifdef CONFIG_KVM_GUEST
+	DEFINE(KVM_MAGIC_SCRATCH1, offsetof(struct kvm_vcpu_arch_shared,
+					    scratch1));
+	DEFINE(KVM_MAGIC_SCRATCH2, offsetof(struct kvm_vcpu_arch_shared,
+					    scratch2));
+	DEFINE(KVM_MAGIC_SCRATCH3, offsetof(struct kvm_vcpu_arch_shared,
+					    scratch3));
+	DEFINE(KVM_MAGIC_INT, offsetof(struct kvm_vcpu_arch_shared,
+				       int_pending));
+	DEFINE(KVM_MAGIC_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
+	DEFINE(KVM_MAGIC_CRITICAL, offsetof(struct kvm_vcpu_arch_shared,
+					    critical));
+#endif
+
 #ifdef CONFIG_44x
 	DEFINE(PGD_T_LOG2, PGD_T_LOG2);
 	DEFINE(PTE_T_LOG2, PTE_T_LOG2);
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 4f85505e4653..a5ece71ecdd2 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -30,6 +30,9 @@
 #include <asm/cacheflush.h>
 #include <asm/disassemble.h>
 
+#define KVM_MAGIC_PAGE		(-4096L)
+#define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
+
 unsigned long kvm_hypercall(unsigned long *in,
 			    unsigned long *out,
 			    unsigned long nr)
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
new file mode 100644
index 000000000000..5cfa2aeeecb0
--- /dev/null
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -0,0 +1,36 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License, version 2, as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
+ *
+ * Copyright SUSE Linux Products GmbH 2010
+ *
+ * Authors: Alexander Graf <agraf@suse.de>
+ */
+
+#include <asm/ppc_asm.h>
+#include <asm/kvm_asm.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/asm-offsets.h>
+
+/* Hypercall entry point. Will be patched with device tree instructions. */
+
+.global kvm_hypercall_start
+kvm_hypercall_start:
+	li	r3, -1
+	nop
+	nop
+	nop
+	blr
+
+#define KVM_MAGIC_PAGE		(-4096)
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 81c9208025fa..956154f32cfe 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -21,6 +21,16 @@ source "arch/powerpc/platforms/44x/Kconfig"
 source "arch/powerpc/platforms/40x/Kconfig"
 source "arch/powerpc/platforms/amigaone/Kconfig"
 
+config KVM_GUEST
+	bool "KVM Guest support"
+	default y
+	---help---
+	  This option enables various optimizations for running under the KVM
+	  hypervisor. Overhead for the kernel when not running inside KVM should
+	  be minimal.
+
+	  In case of doubt, say Y
+
 config PPC_NATIVE
 	bool
 	depends on 6xx || PPC64
-- 
cgit v1.2.1


From 73a18109829e7696226a9fd4062d339e7c6ee130 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:58 +0200
Subject: KVM: PPC: KVM PV guest stubs

We will soon start and replace instructions from the text section with
other, paravirtualized versions. To ease the readability of those patches
I split out the generic looping and magic page mapping code out.

This patch still only contains stubs. But at least it loops through the
text section :).

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c | 95 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 95 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index a5ece71ecdd2..e93366fbbd21 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -33,6 +33,62 @@
 #define KVM_MAGIC_PAGE		(-4096L)
 #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
 
+#define KVM_MASK_RT		0x03e00000
+
+static bool kvm_patching_worked = true;
+
+static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
+{
+	*inst = new_inst;
+	flush_icache_range((ulong)inst, (ulong)inst + 4);
+}
+
+static void kvm_map_magic_page(void *data)
+{
+	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
+		       KVM_MAGIC_PAGE,  /* Physical Address */
+		       KVM_MAGIC_PAGE); /* Effective Address */
+}
+
+static void kvm_check_ins(u32 *inst)
+{
+	u32 _inst = *inst;
+	u32 inst_no_rt = _inst & ~KVM_MASK_RT;
+	u32 inst_rt = _inst & KVM_MASK_RT;
+
+	switch (inst_no_rt) {
+	}
+
+	switch (_inst) {
+	}
+}
+
+static void kvm_use_magic_page(void)
+{
+	u32 *p;
+	u32 *start, *end;
+	u32 tmp;
+
+	/* Tell the host to map the magic page to -4096 on all CPUs */
+	on_each_cpu(kvm_map_magic_page, NULL, 1);
+
+	/* Quick self-test to see if the mapping works */
+	if (__get_user(tmp, (u32*)KVM_MAGIC_PAGE)) {
+		kvm_patching_worked = false;
+		return;
+	}
+
+	/* Now loop through all code and find instructions */
+	start = (void*)_stext;
+	end = (void*)_etext;
+
+	for (p = start; p < end; p++)
+		kvm_check_ins(p);
+
+	printk(KERN_INFO "KVM: Live patching for a fast VM %s\n",
+			 kvm_patching_worked ? "worked" : "failed");
+}
+
 unsigned long kvm_hypercall(unsigned long *in,
 			    unsigned long *out,
 			    unsigned long nr)
@@ -69,3 +125,42 @@ unsigned long kvm_hypercall(unsigned long *in,
 	return r3;
 }
 EXPORT_SYMBOL_GPL(kvm_hypercall);
+
+static int kvm_para_setup(void)
+{
+	extern u32 kvm_hypercall_start;
+	struct device_node *hyper_node;
+	u32 *insts;
+	int len, i;
+
+	hyper_node = of_find_node_by_path("/hypervisor");
+	if (!hyper_node)
+		return -1;
+
+	insts = (u32*)of_get_property(hyper_node, "hcall-instructions", &len);
+	if (len % 4)
+		return -1;
+	if (len > (4 * 4))
+		return -1;
+
+	for (i = 0; i < (len / 4); i++)
+		kvm_patch_ins(&(&kvm_hypercall_start)[i], insts[i]);
+
+	return 0;
+}
+
+static int __init kvm_guest_init(void)
+{
+	if (!kvm_para_available())
+		return 0;
+
+	if (kvm_para_setup())
+		return 0;
+
+	if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
+		kvm_use_magic_page();
+
+	return 0;
+}
+
+postcore_initcall(kvm_guest_init);
-- 
cgit v1.2.1


From d1293c927568f5b5b8dd3fa263a98683cf8556dc Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:47:59 +0200
Subject: KVM: PPC: PV instructions to loads and stores

Some instructions can simply be replaced by load and store instructions to
or from the magic page.

This patch replaces often called instructions that fall into the above category.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c | 109 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 109 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index e93366fbbd21..9ec572c4d2a5 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -33,7 +33,34 @@
 #define KVM_MAGIC_PAGE		(-4096L)
 #define magic_var(x) KVM_MAGIC_PAGE + offsetof(struct kvm_vcpu_arch_shared, x)
 
+#define KVM_INST_LWZ		0x80000000
+#define KVM_INST_STW		0x90000000
+#define KVM_INST_LD		0xe8000000
+#define KVM_INST_STD		0xf8000000
+#define KVM_INST_NOP		0x60000000
+#define KVM_INST_B		0x48000000
+#define KVM_INST_B_MASK		0x03ffffff
+#define KVM_INST_B_MAX		0x01ffffff
+
 #define KVM_MASK_RT		0x03e00000
+#define KVM_INST_MFMSR		0x7c0000a6
+#define KVM_INST_MFSPR_SPRG0	0x7c1042a6
+#define KVM_INST_MFSPR_SPRG1	0x7c1142a6
+#define KVM_INST_MFSPR_SPRG2	0x7c1242a6
+#define KVM_INST_MFSPR_SPRG3	0x7c1342a6
+#define KVM_INST_MFSPR_SRR0	0x7c1a02a6
+#define KVM_INST_MFSPR_SRR1	0x7c1b02a6
+#define KVM_INST_MFSPR_DAR	0x7c1302a6
+#define KVM_INST_MFSPR_DSISR	0x7c1202a6
+
+#define KVM_INST_MTSPR_SPRG0	0x7c1043a6
+#define KVM_INST_MTSPR_SPRG1	0x7c1143a6
+#define KVM_INST_MTSPR_SPRG2	0x7c1243a6
+#define KVM_INST_MTSPR_SPRG3	0x7c1343a6
+#define KVM_INST_MTSPR_SRR0	0x7c1a03a6
+#define KVM_INST_MTSPR_SRR1	0x7c1b03a6
+#define KVM_INST_MTSPR_DAR	0x7c1303a6
+#define KVM_INST_MTSPR_DSISR	0x7c1203a6
 
 static bool kvm_patching_worked = true;
 
@@ -43,6 +70,34 @@ static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
 	flush_icache_range((ulong)inst, (ulong)inst + 4);
 }
 
+static void kvm_patch_ins_ld(u32 *inst, long addr, u32 rt)
+{
+#ifdef CONFIG_64BIT
+	kvm_patch_ins(inst, KVM_INST_LD | rt | (addr & 0x0000fffc));
+#else
+	kvm_patch_ins(inst, KVM_INST_LWZ | rt | ((addr + 4) & 0x0000fffc));
+#endif
+}
+
+static void kvm_patch_ins_lwz(u32 *inst, long addr, u32 rt)
+{
+	kvm_patch_ins(inst, KVM_INST_LWZ | rt | (addr & 0x0000ffff));
+}
+
+static void kvm_patch_ins_std(u32 *inst, long addr, u32 rt)
+{
+#ifdef CONFIG_64BIT
+	kvm_patch_ins(inst, KVM_INST_STD | rt | (addr & 0x0000fffc));
+#else
+	kvm_patch_ins(inst, KVM_INST_STW | rt | ((addr + 4) & 0x0000fffc));
+#endif
+}
+
+static void kvm_patch_ins_stw(u32 *inst, long addr, u32 rt)
+{
+	kvm_patch_ins(inst, KVM_INST_STW | rt | (addr & 0x0000fffc));
+}
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -57,6 +112,60 @@ static void kvm_check_ins(u32 *inst)
 	u32 inst_rt = _inst & KVM_MASK_RT;
 
 	switch (inst_no_rt) {
+	/* Loads */
+	case KVM_INST_MFMSR:
+		kvm_patch_ins_ld(inst, magic_var(msr), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SPRG0:
+		kvm_patch_ins_ld(inst, magic_var(sprg0), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SPRG1:
+		kvm_patch_ins_ld(inst, magic_var(sprg1), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SPRG2:
+		kvm_patch_ins_ld(inst, magic_var(sprg2), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SPRG3:
+		kvm_patch_ins_ld(inst, magic_var(sprg3), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SRR0:
+		kvm_patch_ins_ld(inst, magic_var(srr0), inst_rt);
+		break;
+	case KVM_INST_MFSPR_SRR1:
+		kvm_patch_ins_ld(inst, magic_var(srr1), inst_rt);
+		break;
+	case KVM_INST_MFSPR_DAR:
+		kvm_patch_ins_ld(inst, magic_var(dar), inst_rt);
+		break;
+	case KVM_INST_MFSPR_DSISR:
+		kvm_patch_ins_lwz(inst, magic_var(dsisr), inst_rt);
+		break;
+
+	/* Stores */
+	case KVM_INST_MTSPR_SPRG0:
+		kvm_patch_ins_std(inst, magic_var(sprg0), inst_rt);
+		break;
+	case KVM_INST_MTSPR_SPRG1:
+		kvm_patch_ins_std(inst, magic_var(sprg1), inst_rt);
+		break;
+	case KVM_INST_MTSPR_SPRG2:
+		kvm_patch_ins_std(inst, magic_var(sprg2), inst_rt);
+		break;
+	case KVM_INST_MTSPR_SPRG3:
+		kvm_patch_ins_std(inst, magic_var(sprg3), inst_rt);
+		break;
+	case KVM_INST_MTSPR_SRR0:
+		kvm_patch_ins_std(inst, magic_var(srr0), inst_rt);
+		break;
+	case KVM_INST_MTSPR_SRR1:
+		kvm_patch_ins_std(inst, magic_var(srr1), inst_rt);
+		break;
+	case KVM_INST_MTSPR_DAR:
+		kvm_patch_ins_std(inst, magic_var(dar), inst_rt);
+		break;
+	case KVM_INST_MTSPR_DSISR:
+		kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt);
+		break;
 	}
 
 	switch (_inst) {
-- 
cgit v1.2.1


From d1290b15e7f139e24150cc6e6d8e904214359e8a Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:00 +0200
Subject: KVM: PPC: PV tlbsync to nop

With our current MMU scheme we don't need to know about the tlbsync instruction.
So we can just nop it out.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 9ec572c4d2a5..3258922cc22c 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -62,6 +62,8 @@
 #define KVM_INST_MTSPR_DAR	0x7c1303a6
 #define KVM_INST_MTSPR_DSISR	0x7c1203a6
 
+#define KVM_INST_TLBSYNC	0x7c00046c
+
 static bool kvm_patching_worked = true;
 
 static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
@@ -98,6 +100,11 @@ static void kvm_patch_ins_stw(u32 *inst, long addr, u32 rt)
 	kvm_patch_ins(inst, KVM_INST_STW | rt | (addr & 0x0000fffc));
 }
 
+static void kvm_patch_ins_nop(u32 *inst)
+{
+	kvm_patch_ins(inst, KVM_INST_NOP);
+}
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -166,6 +173,11 @@ static void kvm_check_ins(u32 *inst)
 	case KVM_INST_MTSPR_DSISR:
 		kvm_patch_ins_stw(inst, magic_var(dsisr), inst_rt);
 		break;
+
+	/* Nops */
+	case KVM_INST_TLBSYNC:
+		kvm_patch_ins_nop(inst);
+		break;
 	}
 
 	switch (_inst) {
-- 
cgit v1.2.1


From 2d4f567103ff5a931e773f2e356b4eb303115deb Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:01 +0200
Subject: KVM: PPC: Introduce kvm_tmp framework

We will soon require more sophisticated methods to replace single instructions
with multiple instructions. We do that by branching to a memory region where we
write replacement code for the instruction to.

This region needs to be within 32 MB of the patched instruction though, because
that's the furthest we can jump with immediate branches.

So we keep 1MB of free space around in bss. After we're done initing we can just
tell the mm system that the unused pages are free, but until then we have enough
space to fit all our code in.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c | 42 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 3258922cc22c..926f93fd722d 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -65,6 +65,8 @@
 #define KVM_INST_TLBSYNC	0x7c00046c
 
 static bool kvm_patching_worked = true;
+static char kvm_tmp[1024 * 1024];
+static int kvm_tmp_index;
 
 static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
 {
@@ -105,6 +107,23 @@ static void kvm_patch_ins_nop(u32 *inst)
 	kvm_patch_ins(inst, KVM_INST_NOP);
 }
 
+static u32 *kvm_alloc(int len)
+{
+	u32 *p;
+
+	if ((kvm_tmp_index + len) > ARRAY_SIZE(kvm_tmp)) {
+		printk(KERN_ERR "KVM: No more space (%d + %d)\n",
+				kvm_tmp_index, len);
+		kvm_patching_worked = false;
+		return NULL;
+	}
+
+	p = (void*)&kvm_tmp[kvm_tmp_index];
+	kvm_tmp_index += len;
+
+	return p;
+}
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -270,17 +289,36 @@ static int kvm_para_setup(void)
 	return 0;
 }
 
+static __init void kvm_free_tmp(void)
+{
+	unsigned long start, end;
+
+	start = (ulong)&kvm_tmp[kvm_tmp_index + (PAGE_SIZE - 1)] & PAGE_MASK;
+	end = (ulong)&kvm_tmp[ARRAY_SIZE(kvm_tmp)] & PAGE_MASK;
+
+	/* Free the tmp space we don't need */
+	for (; start < end; start += PAGE_SIZE) {
+		ClearPageReserved(virt_to_page(start));
+		init_page_count(virt_to_page(start));
+		free_page(start);
+		totalram_pages++;
+	}
+}
+
 static int __init kvm_guest_init(void)
 {
 	if (!kvm_para_available())
-		return 0;
+		goto free_tmp;
 
 	if (kvm_para_setup())
-		return 0;
+		goto free_tmp;
 
 	if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
 		kvm_use_magic_page();
 
+free_tmp:
+	kvm_free_tmp();
+
 	return 0;
 }
 
-- 
cgit v1.2.1


From 71ee8e34fe26252b11668a95708783ec9c58cbda Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:02 +0200
Subject: KVM: PPC: Introduce branch patching helper

We will need to patch several instruction streams over to a different
code path, so we need a way to patch a single instruction with a branch
somewhere else.

This patch adds a helper to facilitate this patching.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 926f93fd722d..239a70d750a2 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -107,6 +107,20 @@ static void kvm_patch_ins_nop(u32 *inst)
 	kvm_patch_ins(inst, KVM_INST_NOP);
 }
 
+static void kvm_patch_ins_b(u32 *inst, int addr)
+{
+#ifdef CONFIG_RELOCATABLE
+	/* On relocatable kernels interrupts handlers and our code
+	   can be in different regions, so we don't patch them */
+
+	extern u32 __end_interrupts;
+	if ((ulong)inst < (ulong)&__end_interrupts)
+		return;
+#endif
+
+	kvm_patch_ins(inst, KVM_INST_B | (addr & KVM_INST_B_MASK));
+}
+
 static u32 *kvm_alloc(int len)
 {
 	u32 *p;
-- 
cgit v1.2.1


From 92234722ed631f472f1c4d79d35d8e5cf6910002 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:03 +0200
Subject: KVM: PPC: PV assembler helpers

When we hook an instruction we need to make sure we don't clobber any of
the registers at that point. So we write them out to scratch space in the
magic page. To make sure we don't fall into a race with another piece of
hooked code, we need to disable interrupts.

To make the later patches and code in general easier readable, let's introduce
a set of defines that save and restore r30, r31 and cr. Let's also define some
helpers to read the lower 32 bits of a 64 bit field on 32 bit systems.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm_emul.S | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 5cfa2aeeecb0..1dac72dd6f6e 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -34,3 +34,33 @@ kvm_hypercall_start:
 	blr
 
 #define KVM_MAGIC_PAGE		(-4096)
+
+#ifdef CONFIG_64BIT
+#define LL64(reg, offs, reg2)	ld	reg, (offs)(reg2)
+#define STL64(reg, offs, reg2)	std	reg, (offs)(reg2)
+#else
+#define LL64(reg, offs, reg2)	lwz	reg, (offs + 4)(reg2)
+#define STL64(reg, offs, reg2)	stw	reg, (offs + 4)(reg2)
+#endif
+
+#define SCRATCH_SAVE							\
+	/* Enable critical section. We are critical if			\
+	   shared->critical == r1 */					\
+	STL64(r1, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0);		\
+									\
+	/* Save state */						\
+	PPC_STL	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH1)(0);		\
+	PPC_STL	r30, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH2)(0);		\
+	mfcr	r31;							\
+	stw	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH3)(0);
+
+#define SCRATCH_RESTORE							\
+	/* Restore state */						\
+	PPC_LL	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH1)(0);		\
+	lwz	r30, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH3)(0);		\
+	mtcr	r30;							\
+	PPC_LL	r30, (KVM_MAGIC_PAGE + KVM_MAGIC_SCRATCH2)(0);		\
+									\
+	/* Disable critical section. We are critical if			\
+	   shared->critical == r1 and r2 is always != r1 */		\
+	STL64(r2, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0);
-- 
cgit v1.2.1


From 819a63dc792b0888edd3eda306a9e1e049dcbb1c Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:04 +0200
Subject: KVM: PPC: PV mtmsrd L=1

The PowerPC ISA has a special instruction for mtmsr that only changes the EE
and RI bits, namely the L=1 form.

Since that one is reasonably often occuring and simple to implement, let's
go with this first. Writing EE=0 is always just a store. Doing EE=1 also
requires us to check for pending interrupts and if necessary exit back to the
hypervisor.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c      | 45 +++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/kvm_emul.S | 56 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 101 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 239a70d750a2..717ab0dded25 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -63,6 +63,7 @@
 #define KVM_INST_MTSPR_DSISR	0x7c1203a6
 
 #define KVM_INST_TLBSYNC	0x7c00046c
+#define KVM_INST_MTMSRD_L1	0x7c010164
 
 static bool kvm_patching_worked = true;
 static char kvm_tmp[1024 * 1024];
@@ -138,6 +139,43 @@ static u32 *kvm_alloc(int len)
 	return p;
 }
 
+extern u32 kvm_emulate_mtmsrd_branch_offs;
+extern u32 kvm_emulate_mtmsrd_reg_offs;
+extern u32 kvm_emulate_mtmsrd_len;
+extern u32 kvm_emulate_mtmsrd[];
+
+static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
+{
+	u32 *p;
+	int distance_start;
+	int distance_end;
+	ulong next_inst;
+
+	p = kvm_alloc(kvm_emulate_mtmsrd_len * 4);
+	if (!p)
+		return;
+
+	/* Find out where we are and put everything there */
+	distance_start = (ulong)p - (ulong)inst;
+	next_inst = ((ulong)inst + 4);
+	distance_end = next_inst - (ulong)&p[kvm_emulate_mtmsrd_branch_offs];
+
+	/* Make sure we only write valid b instructions */
+	if (distance_start > KVM_INST_B_MAX) {
+		kvm_patching_worked = false;
+		return;
+	}
+
+	/* Modify the chunk to fit the invocation */
+	memcpy(p, kvm_emulate_mtmsrd, kvm_emulate_mtmsrd_len * 4);
+	p[kvm_emulate_mtmsrd_branch_offs] |= distance_end & KVM_INST_B_MASK;
+	p[kvm_emulate_mtmsrd_reg_offs] |= rt;
+	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsrd_len * 4);
+
+	/* Patch the invocation */
+	kvm_patch_ins_b(inst, distance_start);
+}
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -211,6 +249,13 @@ static void kvm_check_ins(u32 *inst)
 	case KVM_INST_TLBSYNC:
 		kvm_patch_ins_nop(inst);
 		break;
+
+	/* Rewrites */
+	case KVM_INST_MTMSRD_L1:
+		/* We use r30 and r31 during the hook */
+		if (get_rt(inst_rt) < 30)
+			kvm_patch_ins_mtmsrd(inst, inst_rt);
+		break;
 	}
 
 	switch (_inst) {
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 1dac72dd6f6e..10dc4a6632fd 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -64,3 +64,59 @@ kvm_hypercall_start:
 	/* Disable critical section. We are critical if			\
 	   shared->critical == r1 and r2 is always != r1 */		\
 	STL64(r2, KVM_MAGIC_PAGE + KVM_MAGIC_CRITICAL, 0);
+
+.global kvm_emulate_mtmsrd
+kvm_emulate_mtmsrd:
+
+	SCRATCH_SAVE
+
+	/* Put MSR & ~(MSR_EE|MSR_RI) in r31 */
+	LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+	lis	r30, (~(MSR_EE | MSR_RI))@h
+	ori	r30, r30, (~(MSR_EE | MSR_RI))@l
+	and	r31, r31, r30
+
+	/* OR the register's (MSR_EE|MSR_RI) on MSR */
+kvm_emulate_mtmsrd_reg:
+	andi.	r30, r0, (MSR_EE|MSR_RI)
+	or	r31, r31, r30
+
+	/* Put MSR back into magic page */
+	STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	/* Check if we have to fetch an interrupt */
+	lwz	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
+	cmpwi	r31, 0
+	beq+	no_check
+
+	/* Check if we may trigger an interrupt */
+	andi.	r30, r30, MSR_EE
+	beq	no_check
+
+	SCRATCH_RESTORE
+
+	/* Nag hypervisor */
+	tlbsync
+
+	b	kvm_emulate_mtmsrd_branch
+
+no_check:
+
+	SCRATCH_RESTORE
+
+	/* Go back to caller */
+kvm_emulate_mtmsrd_branch:
+	b	.
+kvm_emulate_mtmsrd_end:
+
+.global kvm_emulate_mtmsrd_branch_offs
+kvm_emulate_mtmsrd_branch_offs:
+	.long (kvm_emulate_mtmsrd_branch - kvm_emulate_mtmsrd) / 4
+
+.global kvm_emulate_mtmsrd_reg_offs
+kvm_emulate_mtmsrd_reg_offs:
+	.long (kvm_emulate_mtmsrd_reg - kvm_emulate_mtmsrd) / 4
+
+.global kvm_emulate_mtmsrd_len
+kvm_emulate_mtmsrd_len:
+	.long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
-- 
cgit v1.2.1


From 7810927760a0d16d7a41be4dab895fbbf9445bc0 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:05 +0200
Subject: KVM: PPC: PV mtmsrd L=0 and mtmsr

There is also a form of mtmsr where all bits need to be addressed. While the
PPC64 Linux kernel behaves resonably well here, on PPC32 we do not have an
L=1 form. It does mtmsr even for simple things like only changing EE.

So we need to hook into that one as well and check for a mask of bits that we
deem safe to change from within guest context.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c      | 51 +++++++++++++++++++++++++
 arch/powerpc/kernel/kvm_emul.S | 84 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 135 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 717ab0dded25..8ac57e2c52fa 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -63,7 +63,9 @@
 #define KVM_INST_MTSPR_DSISR	0x7c1203a6
 
 #define KVM_INST_TLBSYNC	0x7c00046c
+#define KVM_INST_MTMSRD_L0	0x7c000164
 #define KVM_INST_MTMSRD_L1	0x7c010164
+#define KVM_INST_MTMSR		0x7c000124
 
 static bool kvm_patching_worked = true;
 static char kvm_tmp[1024 * 1024];
@@ -176,6 +178,49 @@ static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
 	kvm_patch_ins_b(inst, distance_start);
 }
 
+extern u32 kvm_emulate_mtmsr_branch_offs;
+extern u32 kvm_emulate_mtmsr_reg1_offs;
+extern u32 kvm_emulate_mtmsr_reg2_offs;
+extern u32 kvm_emulate_mtmsr_reg3_offs;
+extern u32 kvm_emulate_mtmsr_orig_ins_offs;
+extern u32 kvm_emulate_mtmsr_len;
+extern u32 kvm_emulate_mtmsr[];
+
+static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
+{
+	u32 *p;
+	int distance_start;
+	int distance_end;
+	ulong next_inst;
+
+	p = kvm_alloc(kvm_emulate_mtmsr_len * 4);
+	if (!p)
+		return;
+
+	/* Find out where we are and put everything there */
+	distance_start = (ulong)p - (ulong)inst;
+	next_inst = ((ulong)inst + 4);
+	distance_end = next_inst - (ulong)&p[kvm_emulate_mtmsr_branch_offs];
+
+	/* Make sure we only write valid b instructions */
+	if (distance_start > KVM_INST_B_MAX) {
+		kvm_patching_worked = false;
+		return;
+	}
+
+	/* Modify the chunk to fit the invocation */
+	memcpy(p, kvm_emulate_mtmsr, kvm_emulate_mtmsr_len * 4);
+	p[kvm_emulate_mtmsr_branch_offs] |= distance_end & KVM_INST_B_MASK;
+	p[kvm_emulate_mtmsr_reg1_offs] |= rt;
+	p[kvm_emulate_mtmsr_reg2_offs] |= rt;
+	p[kvm_emulate_mtmsr_reg3_offs] |= rt;
+	p[kvm_emulate_mtmsr_orig_ins_offs] = *inst;
+	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsr_len * 4);
+
+	/* Patch the invocation */
+	kvm_patch_ins_b(inst, distance_start);
+}
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -256,6 +301,12 @@ static void kvm_check_ins(u32 *inst)
 		if (get_rt(inst_rt) < 30)
 			kvm_patch_ins_mtmsrd(inst, inst_rt);
 		break;
+	case KVM_INST_MTMSR:
+	case KVM_INST_MTMSRD_L0:
+		/* We use r30 and r31 during the hook */
+		if (get_rt(inst_rt) < 30)
+			kvm_patch_ins_mtmsr(inst, inst_rt);
+		break;
 	}
 
 	switch (_inst) {
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 10dc4a6632fd..8cd22f47dd01 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -120,3 +120,87 @@ kvm_emulate_mtmsrd_reg_offs:
 .global kvm_emulate_mtmsrd_len
 kvm_emulate_mtmsrd_len:
 	.long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
+
+
+#define MSR_SAFE_BITS (MSR_EE | MSR_CE | MSR_ME | MSR_RI)
+#define MSR_CRITICAL_BITS ~MSR_SAFE_BITS
+
+.global kvm_emulate_mtmsr
+kvm_emulate_mtmsr:
+
+	SCRATCH_SAVE
+
+	/* Fetch old MSR in r31 */
+	LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	/* Find the changed bits between old and new MSR */
+kvm_emulate_mtmsr_reg1:
+	xor	r31, r0, r31
+
+	/* Check if we need to really do mtmsr */
+	LOAD_REG_IMMEDIATE(r30, MSR_CRITICAL_BITS)
+	and.	r31, r31, r30
+
+	/* No critical bits changed? Maybe we can stay in the guest. */
+	beq	maybe_stay_in_guest
+
+do_mtmsr:
+
+	SCRATCH_RESTORE
+
+	/* Just fire off the mtmsr if it's critical */
+kvm_emulate_mtmsr_orig_ins:
+	mtmsr	r0
+
+	b	kvm_emulate_mtmsr_branch
+
+maybe_stay_in_guest:
+
+	/* Check if we have to fetch an interrupt */
+	lwz	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
+	cmpwi	r31, 0
+	beq+	no_mtmsr
+
+	/* Check if we may trigger an interrupt */
+kvm_emulate_mtmsr_reg2:
+	andi.	r31, r0, MSR_EE
+	beq	no_mtmsr
+
+	b	do_mtmsr
+
+no_mtmsr:
+
+	/* Put MSR into magic page because we don't call mtmsr */
+kvm_emulate_mtmsr_reg3:
+	STL64(r0, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	SCRATCH_RESTORE
+
+	/* Go back to caller */
+kvm_emulate_mtmsr_branch:
+	b	.
+kvm_emulate_mtmsr_end:
+
+.global kvm_emulate_mtmsr_branch_offs
+kvm_emulate_mtmsr_branch_offs:
+	.long (kvm_emulate_mtmsr_branch - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_reg1_offs
+kvm_emulate_mtmsr_reg1_offs:
+	.long (kvm_emulate_mtmsr_reg1 - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_reg2_offs
+kvm_emulate_mtmsr_reg2_offs:
+	.long (kvm_emulate_mtmsr_reg2 - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_reg3_offs
+kvm_emulate_mtmsr_reg3_offs:
+	.long (kvm_emulate_mtmsr_reg3 - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_orig_ins_offs
+kvm_emulate_mtmsr_orig_ins_offs:
+	.long (kvm_emulate_mtmsr_orig_ins - kvm_emulate_mtmsr) / 4
+
+.global kvm_emulate_mtmsr_len
+kvm_emulate_mtmsr_len:
+	.long (kvm_emulate_mtmsr_end - kvm_emulate_mtmsr) / 4
-- 
cgit v1.2.1


From 644bfa013fd589b0df2470a66bcd104318ef24cd Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:06 +0200
Subject: KVM: PPC: PV wrteei

On BookE the preferred way to write the EE bit is the wrteei instruction. It
already encodes the EE bit in the instruction.

So in order to get BookE some speedups as well, let's also PV'nize thati
instruction.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/kvm.c      | 50 ++++++++++++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/kvm_emul.S | 41 ++++++++++++++++++++++++++++++++++
 2 files changed, 91 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 8ac57e2c52fa..e93681753deb 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -67,6 +67,9 @@
 #define KVM_INST_MTMSRD_L1	0x7c010164
 #define KVM_INST_MTMSR		0x7c000124
 
+#define KVM_INST_WRTEEI_0	0x7c000146
+#define KVM_INST_WRTEEI_1	0x7c008146
+
 static bool kvm_patching_worked = true;
 static char kvm_tmp[1024 * 1024];
 static int kvm_tmp_index;
@@ -221,6 +224,47 @@ static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
 	kvm_patch_ins_b(inst, distance_start);
 }
 
+#ifdef CONFIG_BOOKE
+
+extern u32 kvm_emulate_wrteei_branch_offs;
+extern u32 kvm_emulate_wrteei_ee_offs;
+extern u32 kvm_emulate_wrteei_len;
+extern u32 kvm_emulate_wrteei[];
+
+static void kvm_patch_ins_wrteei(u32 *inst)
+{
+	u32 *p;
+	int distance_start;
+	int distance_end;
+	ulong next_inst;
+
+	p = kvm_alloc(kvm_emulate_wrteei_len * 4);
+	if (!p)
+		return;
+
+	/* Find out where we are and put everything there */
+	distance_start = (ulong)p - (ulong)inst;
+	next_inst = ((ulong)inst + 4);
+	distance_end = next_inst - (ulong)&p[kvm_emulate_wrteei_branch_offs];
+
+	/* Make sure we only write valid b instructions */
+	if (distance_start > KVM_INST_B_MAX) {
+		kvm_patching_worked = false;
+		return;
+	}
+
+	/* Modify the chunk to fit the invocation */
+	memcpy(p, kvm_emulate_wrteei, kvm_emulate_wrteei_len * 4);
+	p[kvm_emulate_wrteei_branch_offs] |= distance_end & KVM_INST_B_MASK;
+	p[kvm_emulate_wrteei_ee_offs] |= (*inst & MSR_EE);
+	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_wrteei_len * 4);
+
+	/* Patch the invocation */
+	kvm_patch_ins_b(inst, distance_start);
+}
+
+#endif
+
 static void kvm_map_magic_page(void *data)
 {
 	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
@@ -310,6 +354,12 @@ static void kvm_check_ins(u32 *inst)
 	}
 
 	switch (_inst) {
+#ifdef CONFIG_BOOKE
+	case KVM_INST_WRTEEI_0:
+	case KVM_INST_WRTEEI_1:
+		kvm_patch_ins_wrteei(inst);
+		break;
+#endif
 	}
 }
 
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 8cd22f47dd01..3199f65ede2c 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -204,3 +204,44 @@ kvm_emulate_mtmsr_orig_ins_offs:
 .global kvm_emulate_mtmsr_len
 kvm_emulate_mtmsr_len:
 	.long (kvm_emulate_mtmsr_end - kvm_emulate_mtmsr) / 4
+
+
+
+.global kvm_emulate_wrteei
+kvm_emulate_wrteei:
+
+	SCRATCH_SAVE
+
+	/* Fetch old MSR in r31 */
+	LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	/* Remove MSR_EE from old MSR */
+	li	r30, 0
+	ori	r30, r30, MSR_EE
+	andc	r31, r31, r30
+
+	/* OR new MSR_EE onto the old MSR */
+kvm_emulate_wrteei_ee:
+	ori	r31, r31, 0
+
+	/* Write new MSR value back */
+	STL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+
+	SCRATCH_RESTORE
+
+	/* Go back to caller */
+kvm_emulate_wrteei_branch:
+	b	.
+kvm_emulate_wrteei_end:
+
+.global kvm_emulate_wrteei_branch_offs
+kvm_emulate_wrteei_branch_offs:
+	.long (kvm_emulate_wrteei_branch - kvm_emulate_wrteei) / 4
+
+.global kvm_emulate_wrteei_ee_offs
+kvm_emulate_wrteei_ee_offs:
+	.long (kvm_emulate_wrteei_ee - kvm_emulate_wrteei) / 4
+
+.global kvm_emulate_wrteei_len
+kvm_emulate_wrteei_len:
+	.long (kvm_emulate_wrteei_end - kvm_emulate_wrteei) / 4
-- 
cgit v1.2.1


From 15711e9c927bfc08e66791cbf0ca7887c0880768 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 14:48:08 +0200
Subject: KVM: PPC: Add get_pvinfo interface to query hypercall instructions

We need to tell the guest the opcodes that make up a hypercall through
interfaces that are controlled by userspace. So we need to add a call
for userspace to allow it to query those opcodes so it can pass them
on.

This is required because the hypercall opcodes can change based on
the hypervisor conditions. If we're running in hardware accelerated
hypervisor mode, a hypercall looks different from when we're running
without hardware acceleration.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/powerpc.c | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index fecfe043458d..6a53a3f86dae 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -191,6 +191,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PPC_UNSET_IRQ:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_PPC_OSI:
+	case KVM_CAP_PPC_GET_PVINFO:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -578,16 +579,53 @@ out:
 	return r;
 }
 
+static int kvm_vm_ioctl_get_pvinfo(struct kvm_ppc_pvinfo *pvinfo)
+{
+	u32 inst_lis = 0x3c000000;
+	u32 inst_ori = 0x60000000;
+	u32 inst_nop = 0x60000000;
+	u32 inst_sc = 0x44000002;
+	u32 inst_imm_mask = 0xffff;
+
+	/*
+	 * The hypercall to get into KVM from within guest context is as
+	 * follows:
+	 *
+	 *    lis r0, r0, KVM_SC_MAGIC_R0@h
+	 *    ori r0, KVM_SC_MAGIC_R0@l
+	 *    sc
+	 *    nop
+	 */
+	pvinfo->hcall[0] = inst_lis | ((KVM_SC_MAGIC_R0 >> 16) & inst_imm_mask);
+	pvinfo->hcall[1] = inst_ori | (KVM_SC_MAGIC_R0 & inst_imm_mask);
+	pvinfo->hcall[2] = inst_sc;
+	pvinfo->hcall[3] = inst_nop;
+
+	return 0;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
                        unsigned int ioctl, unsigned long arg)
 {
+	void __user *argp = (void __user *)arg;
 	long r;
 
 	switch (ioctl) {
+	case KVM_PPC_GET_PVINFO: {
+		struct kvm_ppc_pvinfo pvinfo;
+		r = kvm_vm_ioctl_get_pvinfo(&pvinfo);
+		if (copy_to_user(argp, &pvinfo, sizeof(pvinfo))) {
+			r = -EFAULT;
+			goto out;
+		}
+
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
 
+out:
 	return r;
 }
 
-- 
cgit v1.2.1


From 5302104235f0e9f05781b92a4ab25d20e4537f56 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 15:04:16 +0200
Subject: KVM: PPC: Book3S_32 MMU debug compile fixes

Due to previous changes, the Book3S_32 guest MMU code didn't compile properly
when enabling debugging.

This patch repairs the broken code paths, making it possible to define DEBUG_MMU
and friends again.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/book3s_32_mmu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index a7d121adc842..5bf4bf8c9e65 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -104,7 +104,7 @@ static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3
 	pteg = (vcpu_book3s->sdr1 & 0xffff0000) | hash;
 
 	dprintk("MMU: pc=0x%lx eaddr=0x%lx sdr1=0x%llx pteg=0x%x vsid=0x%x\n",
-		vcpu_book3s->vcpu.arch.pc, eaddr, vcpu_book3s->sdr1, pteg,
+		kvmppc_get_pc(&vcpu_book3s->vcpu), eaddr, vcpu_book3s->sdr1, pteg,
 		sre->vsid);
 
 	r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT);
@@ -269,7 +269,7 @@ no_page_found:
 		dprintk_pte("KVM MMU: No PTE found (sdr1=0x%llx ptegp=0x%lx)\n",
 			    to_book3s(vcpu)->sdr1, ptegp);
 		for (i=0; i<16; i+=2) {
-			dprintk_pte("   %02d: 0x%x - 0x%x (0x%llx)\n",
+			dprintk_pte("   %02d: 0x%x - 0x%x (0x%x)\n",
 				    i, pteg[i], pteg[i+1], ptem);
 		}
 	}
-- 
cgit v1.2.1


From 2e0908afaf03675d22e40ce45a66b8d2070214ac Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 15:04:17 +0200
Subject: KVM: PPC: RCU'ify the Book3s MMU

So far we've been running all code without locking of any sort. This wasn't
really an issue because I didn't see any parallel access to the shadow MMU
code coming.

But then I started to implement dirty bitmapping to MOL which has the video
code in its own thread, so suddenly we had the dirty bitmap code run in
parallel to the shadow mmu code. And with that came trouble.

So I went ahead and made the MMU modifying functions as parallelizable as
I could think of. I hope I didn't screw up too much RCU logic :-). If you
know your way around RCU and locking and what needs to be done when, please
take a look at this patch.

Signed-off-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/book3s_mmu_hpte.c  | 78 ++++++++++++++++++++++++++++---------
 2 files changed, 61 insertions(+), 19 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index e1da77579e65..fafc71aa3343 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -165,6 +165,7 @@ struct hpte_cache {
 	struct hlist_node list_pte;
 	struct hlist_node list_vpte;
 	struct hlist_node list_vpte_long;
+	struct rcu_head rcu_head;
 	u64 host_va;
 	u64 pfn;
 	ulong slot;
@@ -295,6 +296,7 @@ struct kvm_vcpu_arch {
 	struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
 	struct hlist_head hpte_hash_vpte_long[HPTEG_HASH_NUM_VPTE_LONG];
 	int hpte_cache_count;
+	spinlock_t mmu_lock;
 #endif
 };
 
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index 4868d4a7ebc5..b64389362446 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -60,68 +60,94 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	u64 index;
 
+	spin_lock(&vcpu->arch.mmu_lock);
+
 	/* Add to ePTE list */
 	index = kvmppc_mmu_hash_pte(pte->pte.eaddr);
-	hlist_add_head(&pte->list_pte, &vcpu->arch.hpte_hash_pte[index]);
+	hlist_add_head_rcu(&pte->list_pte, &vcpu->arch.hpte_hash_pte[index]);
 
 	/* Add to vPTE list */
 	index = kvmppc_mmu_hash_vpte(pte->pte.vpage);
-	hlist_add_head(&pte->list_vpte, &vcpu->arch.hpte_hash_vpte[index]);
+	hlist_add_head_rcu(&pte->list_vpte, &vcpu->arch.hpte_hash_vpte[index]);
 
 	/* Add to vPTE_long list */
 	index = kvmppc_mmu_hash_vpte_long(pte->pte.vpage);
-	hlist_add_head(&pte->list_vpte_long,
-		       &vcpu->arch.hpte_hash_vpte_long[index]);
+	hlist_add_head_rcu(&pte->list_vpte_long,
+			   &vcpu->arch.hpte_hash_vpte_long[index]);
+
+	spin_unlock(&vcpu->arch.mmu_lock);
+}
+
+static void free_pte_rcu(struct rcu_head *head)
+{
+	struct hpte_cache *pte = container_of(head, struct hpte_cache, rcu_head);
+	kmem_cache_free(hpte_cache, pte);
 }
 
 static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
+	/* pte already invalidated? */
+	if (hlist_unhashed(&pte->list_pte))
+		return;
+
 	dprintk_mmu("KVM: Flushing SPT: 0x%lx (0x%llx) -> 0x%llx\n",
 		    pte->pte.eaddr, pte->pte.vpage, pte->host_va);
 
 	/* Different for 32 and 64 bit */
 	kvmppc_mmu_invalidate_pte(vcpu, pte);
 
+	spin_lock(&vcpu->arch.mmu_lock);
+
+	hlist_del_init_rcu(&pte->list_pte);
+	hlist_del_init_rcu(&pte->list_vpte);
+	hlist_del_init_rcu(&pte->list_vpte_long);
+
+	spin_unlock(&vcpu->arch.mmu_lock);
+
 	if (pte->pte.may_write)
 		kvm_release_pfn_dirty(pte->pfn);
 	else
 		kvm_release_pfn_clean(pte->pfn);
 
-	hlist_del(&pte->list_pte);
-	hlist_del(&pte->list_vpte);
-	hlist_del(&pte->list_vpte_long);
-
 	vcpu->arch.hpte_cache_count--;
-	kmem_cache_free(hpte_cache, pte);
+	call_rcu(&pte->rcu_head, free_pte_rcu);
 }
 
 static void kvmppc_mmu_pte_flush_all(struct kvm_vcpu *vcpu)
 {
 	struct hpte_cache *pte;
-	struct hlist_node *node, *tmp;
+	struct hlist_node *node;
 	int i;
 
+	rcu_read_lock();
+
 	for (i = 0; i < HPTEG_HASH_NUM_VPTE_LONG; i++) {
 		struct hlist_head *list = &vcpu->arch.hpte_hash_vpte_long[i];
 
-		hlist_for_each_entry_safe(pte, node, tmp, list, list_vpte_long)
+		hlist_for_each_entry_rcu(pte, node, list, list_vpte_long)
 			invalidate_pte(vcpu, pte);
 	}
+
+	rcu_read_unlock();
 }
 
 static void kvmppc_mmu_pte_flush_page(struct kvm_vcpu *vcpu, ulong guest_ea)
 {
 	struct hlist_head *list;
-	struct hlist_node *node, *tmp;
+	struct hlist_node *node;
 	struct hpte_cache *pte;
 
 	/* Find the list of entries in the map */
 	list = &vcpu->arch.hpte_hash_pte[kvmppc_mmu_hash_pte(guest_ea)];
 
+	rcu_read_lock();
+
 	/* Check the list for matching entries and invalidate */
-	hlist_for_each_entry_safe(pte, node, tmp, list, list_pte)
+	hlist_for_each_entry_rcu(pte, node, list, list_pte)
 		if ((pte->pte.eaddr & ~0xfffUL) == guest_ea)
 			invalidate_pte(vcpu, pte);
+
+	rcu_read_unlock();
 }
 
 void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
@@ -156,33 +182,41 @@ void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
 static void kvmppc_mmu_pte_vflush_short(struct kvm_vcpu *vcpu, u64 guest_vp)
 {
 	struct hlist_head *list;
-	struct hlist_node *node, *tmp;
+	struct hlist_node *node;
 	struct hpte_cache *pte;
 	u64 vp_mask = 0xfffffffffULL;
 
 	list = &vcpu->arch.hpte_hash_vpte[kvmppc_mmu_hash_vpte(guest_vp)];
 
+	rcu_read_lock();
+
 	/* Check the list for matching entries and invalidate */
-	hlist_for_each_entry_safe(pte, node, tmp, list, list_vpte)
+	hlist_for_each_entry_rcu(pte, node, list, list_vpte)
 		if ((pte->pte.vpage & vp_mask) == guest_vp)
 			invalidate_pte(vcpu, pte);
+
+	rcu_read_unlock();
 }
 
 /* Flush with mask 0xffffff000 */
 static void kvmppc_mmu_pte_vflush_long(struct kvm_vcpu *vcpu, u64 guest_vp)
 {
 	struct hlist_head *list;
-	struct hlist_node *node, *tmp;
+	struct hlist_node *node;
 	struct hpte_cache *pte;
 	u64 vp_mask = 0xffffff000ULL;
 
 	list = &vcpu->arch.hpte_hash_vpte_long[
 		kvmppc_mmu_hash_vpte_long(guest_vp)];
 
+	rcu_read_lock();
+
 	/* Check the list for matching entries and invalidate */
-	hlist_for_each_entry_safe(pte, node, tmp, list, list_vpte_long)
+	hlist_for_each_entry_rcu(pte, node, list, list_vpte_long)
 		if ((pte->pte.vpage & vp_mask) == guest_vp)
 			invalidate_pte(vcpu, pte);
+
+	rcu_read_unlock();
 }
 
 void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
@@ -206,21 +240,25 @@ void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
 
 void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
 {
-	struct hlist_node *node, *tmp;
+	struct hlist_node *node;
 	struct hpte_cache *pte;
 	int i;
 
 	dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%lx - 0x%lx\n",
 		    vcpu->arch.hpte_cache_count, pa_start, pa_end);
 
+	rcu_read_lock();
+
 	for (i = 0; i < HPTEG_HASH_NUM_VPTE_LONG; i++) {
 		struct hlist_head *list = &vcpu->arch.hpte_hash_vpte_long[i];
 
-		hlist_for_each_entry_safe(pte, node, tmp, list, list_vpte_long)
+		hlist_for_each_entry_rcu(pte, node, list, list_vpte_long)
 			if ((pte->pte.raddr >= pa_start) &&
 			    (pte->pte.raddr < pa_end))
 				invalidate_pte(vcpu, pte);
 	}
+
+	rcu_read_unlock();
 }
 
 struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu)
@@ -259,6 +297,8 @@ int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu)
 	kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_vpte_long,
 				  ARRAY_SIZE(vcpu->arch.hpte_hash_vpte_long));
 
+	spin_lock_init(&vcpu->arch.mmu_lock);
+
 	return 0;
 }
 
-- 
cgit v1.2.1


From 49451389ecc2b4336c305678c210b25fadd18994 Mon Sep 17 00:00:00 2001
From: Gleb Natapov <gleb@redhat.com>
Date: Thu, 29 Jul 2010 15:04:18 +0200
Subject: KVM: PPC: correctly check gfn_to_pfn() return value

On failure gfn_to_pfn returns bad_page so use correct function to check
for that.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/book3s_32_mmu_host.c | 2 +-
 arch/powerpc/kvm/book3s_64_mmu_host.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 05e8c9eb0e16..343452cff9b2 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -148,7 +148,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 
 	/* Get host physical address for gpa */
 	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
-	if (kvm_is_error_hva(hpaddr)) {
+	if (is_error_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n",
 				 orig_pte->eaddr);
 		return -EINVAL;
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 6cdd19a82bda..672b1495f265 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -102,7 +102,7 @@ int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *orig_pte)
 
 	/* Get host physical address for gpa */
 	hpaddr = kvmppc_gfn_to_pfn(vcpu, orig_pte->raddr >> PAGE_SHIFT);
-	if (kvm_is_error_hva(hpaddr)) {
+	if (is_error_pfn(hpaddr)) {
 		printk(KERN_INFO "Couldn't get guest page for gfn %lx!\n", orig_pte->eaddr);
 		return -EINVAL;
 	}
-- 
cgit v1.2.1


From 2d27fc5eac0205588cb59ae138062e5e96695276 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 15:04:19 +0200
Subject: KVM: PPC: Add book3s_32 tlbie flush acceleration

On Book3s_32 the tlbie instruction flushed effective addresses by the mask
0x0ffff000. This is pretty hard to reflect with a hash that hashes ~0xfff, so
to speed up that target we should also keep a special hash around for it.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_host.h |  4 ++++
 arch/powerpc/kvm/book3s_mmu_hpte.c  | 40 ++++++++++++++++++++++++++++++++-----
 2 files changed, 39 insertions(+), 5 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index fafc71aa3343..bba3b9b72a39 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -42,9 +42,11 @@
 
 #define HPTEG_CACHE_NUM			(1 << 15)
 #define HPTEG_HASH_BITS_PTE		13
+#define HPTEG_HASH_BITS_PTE_LONG	12
 #define HPTEG_HASH_BITS_VPTE		13
 #define HPTEG_HASH_BITS_VPTE_LONG	5
 #define HPTEG_HASH_NUM_PTE		(1 << HPTEG_HASH_BITS_PTE)
+#define HPTEG_HASH_NUM_PTE_LONG		(1 << HPTEG_HASH_BITS_PTE_LONG)
 #define HPTEG_HASH_NUM_VPTE		(1 << HPTEG_HASH_BITS_VPTE)
 #define HPTEG_HASH_NUM_VPTE_LONG	(1 << HPTEG_HASH_BITS_VPTE_LONG)
 
@@ -163,6 +165,7 @@ struct kvmppc_mmu {
 
 struct hpte_cache {
 	struct hlist_node list_pte;
+	struct hlist_node list_pte_long;
 	struct hlist_node list_vpte;
 	struct hlist_node list_vpte_long;
 	struct rcu_head rcu_head;
@@ -293,6 +296,7 @@ struct kvm_vcpu_arch {
 
 #ifdef CONFIG_PPC_BOOK3S
 	struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
+	struct hlist_head hpte_hash_pte_long[HPTEG_HASH_NUM_PTE_LONG];
 	struct hlist_head hpte_hash_vpte[HPTEG_HASH_NUM_VPTE];
 	struct hlist_head hpte_hash_vpte_long[HPTEG_HASH_NUM_VPTE_LONG];
 	int hpte_cache_count;
diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index b64389362446..02c64ab99c97 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -45,6 +45,12 @@ static inline u64 kvmppc_mmu_hash_pte(u64 eaddr)
 	return hash_64(eaddr >> PTE_SIZE, HPTEG_HASH_BITS_PTE);
 }
 
+static inline u64 kvmppc_mmu_hash_pte_long(u64 eaddr)
+{
+	return hash_64((eaddr & 0x0ffff000) >> PTE_SIZE,
+		       HPTEG_HASH_BITS_PTE_LONG);
+}
+
 static inline u64 kvmppc_mmu_hash_vpte(u64 vpage)
 {
 	return hash_64(vpage & 0xfffffffffULL, HPTEG_HASH_BITS_VPTE);
@@ -66,6 +72,11 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	index = kvmppc_mmu_hash_pte(pte->pte.eaddr);
 	hlist_add_head_rcu(&pte->list_pte, &vcpu->arch.hpte_hash_pte[index]);
 
+	/* Add to ePTE_long list */
+	index = kvmppc_mmu_hash_pte_long(pte->pte.eaddr);
+	hlist_add_head_rcu(&pte->list_pte_long,
+			   &vcpu->arch.hpte_hash_pte_long[index]);
+
 	/* Add to vPTE list */
 	index = kvmppc_mmu_hash_vpte(pte->pte.vpage);
 	hlist_add_head_rcu(&pte->list_vpte, &vcpu->arch.hpte_hash_vpte[index]);
@@ -99,6 +110,7 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	spin_lock(&vcpu->arch.mmu_lock);
 
 	hlist_del_init_rcu(&pte->list_pte);
+	hlist_del_init_rcu(&pte->list_pte_long);
 	hlist_del_init_rcu(&pte->list_vpte);
 	hlist_del_init_rcu(&pte->list_vpte_long);
 
@@ -150,10 +162,28 @@ static void kvmppc_mmu_pte_flush_page(struct kvm_vcpu *vcpu, ulong guest_ea)
 	rcu_read_unlock();
 }
 
-void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
+static void kvmppc_mmu_pte_flush_long(struct kvm_vcpu *vcpu, ulong guest_ea)
 {
-	u64 i;
+	struct hlist_head *list;
+	struct hlist_node *node;
+	struct hpte_cache *pte;
+
+	/* Find the list of entries in the map */
+	list = &vcpu->arch.hpte_hash_pte_long[
+			kvmppc_mmu_hash_pte_long(guest_ea)];
 
+	rcu_read_lock();
+
+	/* Check the list for matching entries and invalidate */
+	hlist_for_each_entry_rcu(pte, node, list, list_pte_long)
+		if ((pte->pte.eaddr & 0x0ffff000UL) == guest_ea)
+			invalidate_pte(vcpu, pte);
+
+	rcu_read_unlock();
+}
+
+void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
+{
 	dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%lx & 0x%lx\n",
 		    vcpu->arch.hpte_cache_count, guest_ea, ea_mask);
 
@@ -164,9 +194,7 @@ void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
 		kvmppc_mmu_pte_flush_page(vcpu, guest_ea);
 		break;
 	case 0x0ffff000:
-		/* 32-bit flush w/o segment, go through all possible segments */
-		for (i = 0; i < 0x100000000ULL; i += 0x10000000ULL)
-			kvmppc_mmu_pte_flush(vcpu, guest_ea | i, ~0xfffUL);
+		kvmppc_mmu_pte_flush_long(vcpu, guest_ea);
 		break;
 	case 0:
 		/* Doing a complete flush -> start from scratch */
@@ -292,6 +320,8 @@ int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu)
 	/* init hpte lookup hashes */
 	kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_pte,
 				  ARRAY_SIZE(vcpu->arch.hpte_hash_pte));
+	kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_pte_long,
+				  ARRAY_SIZE(vcpu->arch.hpte_hash_pte_long));
 	kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_vpte,
 				  ARRAY_SIZE(vcpu->arch.hpte_hash_vpte));
 	kvmppc_mmu_hpte_init_hash(vcpu->arch.hpte_hash_vpte_long,
-- 
cgit v1.2.1


From 0e677903878ef90e09a45507255c0b1e36166064 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 15:04:20 +0200
Subject: KVM: PPC: Use MSR_DR for external load_up

Book3S_32 requires MSR_DR to be disabled during load_up_xxx while on Book3S_64
it's supposed to be enabled. I misread the code and disabled it in both cases,
potentially breaking the PS3 which has a really small RMA.

This patch makes KVM work on the PS3 again.

Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/book3s_rmhandlers.S | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 506d5c316c96..229d3d662af9 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -202,8 +202,25 @@ _GLOBAL(kvmppc_rmcall)
 
 #if defined(CONFIG_PPC_BOOK3S_32)
 #define STACK_LR	INT_FRAME_SIZE+4
+
+/* load_up_xxx have to run with MSR_DR=0 on Book3S_32 */
+#define MSR_EXT_START						\
+	PPC_STL	r20, _NIP(r1);					\
+	mfmsr	r20;						\
+	LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE);			\
+	andc	r3,r20,r3;		/* Disable DR,EE */	\
+	mtmsr	r3;						\
+	sync
+
+#define MSR_EXT_END						\
+	mtmsr	r20;			/* Enable DR,EE */	\
+	sync;							\
+	PPC_LL	r20, _NIP(r1)
+
 #elif defined(CONFIG_PPC_BOOK3S_64)
 #define STACK_LR	_LINK
+#define MSR_EXT_START
+#define MSR_EXT_END
 #endif
 
 /*
@@ -215,19 +232,12 @@ _GLOBAL(kvmppc_load_up_ ## what);				\
 	PPC_STLU r1, -INT_FRAME_SIZE(r1);			\
 	mflr	r3;						\
 	PPC_STL	r3, STACK_LR(r1);				\
-	PPC_STL	r20, _NIP(r1);					\
-	mfmsr	r20;						\
-	LOAD_REG_IMMEDIATE(r3, MSR_DR|MSR_EE);			\
-	andc	r3,r20,r3;		/* Disable DR,EE */	\
-	mtmsr	r3;						\
-	sync;							\
+	MSR_EXT_START;						\
 								\
 	bl	FUNC(load_up_ ## what);				\
 								\
-	mtmsr	r20;			/* Enable DR,EE */	\
-	sync;							\
+	MSR_EXT_END;						\
 	PPC_LL	r3, STACK_LR(r1);				\
-	PPC_LL	r20, _NIP(r1);					\
 	mtlr	r3;						\
 	addi	r1, r1, INT_FRAME_SIZE;				\
 	blr
-- 
cgit v1.2.1


From 2b05d71fefc3b83e686bead355c6d35e440c4261 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 15:04:21 +0200
Subject: KVM: PPC: Make long relocations be ulong

On Book3S KVM we directly expose some asm pointers to C code as
variables. These need to be relocated and thus break on relocatable
kernels.

To make sure we can at least build, let's mark them as long instead
of u32 where 64bit relocations don't work.

This fixes the following build error:

WARNING: 2 bad relocations^M
> c000000000008590 R_PPC64_ADDR32    .text+0x4000000000008460^M
> c000000000008594 R_PPC64_ADDR32    .text+0x4000000000008598^M

Please keep in mind that actually using KVM on a relocated kernel
might still break. This only fixes the compile problem.

Reported-by: Subrata Modak <subrata@linux.vnet.ibm.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/include/asm/kvm_book3s.h | 4 ++--
 arch/powerpc/kvm/book3s_rmhandlers.S  | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 00cf8b07e502..f04f516c97da 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -132,8 +132,8 @@ extern void kvmppc_giveup_ext(struct kvm_vcpu *vcpu, ulong msr);
 extern int kvmppc_emulate_paired_single(struct kvm_run *run, struct kvm_vcpu *vcpu);
 extern pfn_t kvmppc_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 
-extern u32 kvmppc_trampoline_lowmem;
-extern u32 kvmppc_trampoline_enter;
+extern ulong kvmppc_trampoline_lowmem;
+extern ulong 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);
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index 229d3d662af9..2b9c9088d00e 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -252,10 +252,10 @@ define_load_up(vsx)
 
 .global kvmppc_trampoline_lowmem
 kvmppc_trampoline_lowmem:
-	.long kvmppc_handler_lowmem_trampoline - CONFIG_KERNEL_START
+	PPC_LONG kvmppc_handler_lowmem_trampoline - CONFIG_KERNEL_START
 
 .global kvmppc_trampoline_enter
 kvmppc_trampoline_enter:
-	.long kvmppc_handler_trampoline_enter - CONFIG_KERNEL_START
+	PPC_LONG kvmppc_handler_trampoline_enter - CONFIG_KERNEL_START
 
 #include "book3s_segment.S"
-- 
cgit v1.2.1


From a58ddea556f8877ccf7caa046b6d6b32982f5b1d Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 29 Jul 2010 15:04:22 +0200
Subject: KVM: PPC: Move KVM trampolines before __end_interrupts

When using a relocatable kernel we need to make sure that the trampline code
and the interrupt handlers are both copied to low memory. The only way to do
this reliably is to put them in the copied section.

This patch should make relocated kernels work with KVM.

KVM-Stable-Tag
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/exceptions-64s.S | 6 ++++++
 arch/powerpc/kernel/head_64.S        | 6 ------
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index f53029a01554..1667a078b3e6 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -299,6 +299,12 @@ slb_miss_user_pseries:
 	b	.				/* prevent spec. execution */
 #endif /* __DISABLED__ */
 
+/* KVM's trampoline code needs to be close to the interrupt handlers */
+
+#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
+#include "../kvm/book3s_rmhandlers.S"
+#endif
+
 	.align	7
 	.globl	__end_interrupts
 __end_interrupts:
diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
index c571cd3c1453..f0dd577e4a5b 100644
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@@ -166,12 +166,6 @@ exception_marker:
 #include "exceptions-64s.S"
 #endif
 
-/* KVM trampoline code needs to be close to the interrupt handlers */
-
-#ifdef CONFIG_KVM_BOOK3S_64_HANDLER
-#include "../kvm/book3s_rmhandlers.S"
-#endif
-
 _GLOBAL(generic_secondary_thread_init)
 	mr	r24,r3
 
-- 
cgit v1.2.1


From 646bab55a278ceb1cf43b1f80d3dd468be62a421 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <yjwei@cn.fujitsu.com>
Date: Tue, 17 Aug 2010 10:08:52 +0800
Subject: KVM: PPC: fix leakage of error page in kvmppc_patch_dcbz()

Add kvm_release_page_clean() after is_error_page() to avoid
leakage of error page.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kvm/book3s.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index eee97b5a7400..7656b6df0d8b 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -455,8 +455,10 @@ static void kvmppc_patch_dcbz(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte)
 	int i;
 
 	hpage = gfn_to_page(vcpu->kvm, pte->raddr >> PAGE_SHIFT);
-	if (is_error_page(hpage))
+	if (is_error_page(hpage)) {
+		kvm_release_page_clean(hpage);
 		return;
+	}
 
 	hpage_offset = pte->raddr & ~PAGE_MASK;
 	hpage_offset &= ~0xFFFULL;
-- 
cgit v1.2.1


From 989044ee0fdc6c22a11ea1d22e2a3d17463cb564 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 30 Aug 2010 12:01:56 +0200
Subject: KVM: PPC: Fix CONFIG_KVM_GUEST && !CONFIG_KVM case

When CONFIG_KVM_GUEST is selected, but CONFIG_KVM is not, we were missing
some defines in asm-offsets.c and included too many headers at other places.

This patch makes above configuration work.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Avi Kivity <avi@redhat.com>
---
 arch/powerpc/kernel/asm-offsets.c | 6 +++---
 arch/powerpc/kernel/kvm.c         | 1 -
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 37486cafb69d..6d92b4e13ebf 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -48,11 +48,11 @@
 #ifdef CONFIG_PPC_ISERIES
 #include <asm/iseries/alpaca.h>
 #endif
-#ifdef CONFIG_KVM
+#if defined(CONFIG_KVM) || defined(CONFIG_KVM_GUEST)
 #include <linux/kvm_host.h>
-#ifndef CONFIG_BOOKE
-#include <asm/kvm_book3s.h>
 #endif
+#if defined(CONFIG_KVM) && defined(CONFIG_PPC_BOOK3S)
+#include <asm/kvm_book3s.h>
 #endif
 
 #ifdef CONFIG_PPC32
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index e93681753deb..d3a2cc50d611 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -25,7 +25,6 @@
 #include <linux/of.h>
 
 #include <asm/reg.h>
-#include <asm/kvm_ppc.h>
 #include <asm/sections.h>
 #include <asm/cacheflush.h>
 #include <asm/disassemble.h>
-- 
cgit v1.2.1


From bed1ed9860d3744cc6488831fa5672d5c7aff4be Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 11:06:26 +0200
Subject: KVM: PPC: Move EXIT_DEBUG partially to tracepoints

We have a debug printk on every exit that is usually #ifdef'ed out. Using
tracepoints makes a lot more sense here though, as they can be dynamically
enabled.

This patch converts the most commonly used debug printks of EXIT_DEBUG to
tracepoints.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s.c | 26 ++++--------------------
 arch/powerpc/kvm/trace.h  | 51 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 55 insertions(+), 22 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 7656b6df0d8b..37db61d37041 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -17,6 +17,7 @@
 #include <linux/kvm_host.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include "trace.h"
 
 #include <asm/reg.h>
 #include <asm/cputable.h>
@@ -35,7 +36,6 @@
 #define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
 
 /* #define EXIT_DEBUG */
-/* #define EXIT_DEBUG_SIMPLE */
 /* #define DEBUG_EXT */
 
 static int kvmppc_handle_ext(struct kvm_vcpu *vcpu, unsigned int exit_nr,
@@ -105,14 +105,6 @@ void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu)
 	kvmppc_giveup_ext(vcpu, MSR_VSX);
 }
 
-#if defined(EXIT_DEBUG)
-static u32 kvmppc_get_dec(struct kvm_vcpu *vcpu)
-{
-	u64 jd = mftb() - vcpu->arch.dec_jiffies;
-	return vcpu->arch.dec - jd;
-}
-#endif
-
 static void kvmppc_recalc_shadow_msr(struct kvm_vcpu *vcpu)
 {
 	ulong smsr = vcpu->arch.shared->msr;
@@ -850,16 +842,8 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	run->ready_for_interrupt_injection = 1;
-#ifdef EXIT_DEBUG
-	printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | dec=0x%x | msr=0x%lx\n",
-		exit_nr, kvmppc_get_pc(vcpu), kvmppc_get_fault_dar(vcpu),
-		kvmppc_get_dec(vcpu), to_svcpu(vcpu)->shadow_srr1);
-#elif defined (EXIT_DEBUG_SIMPLE)
-	if ((exit_nr != 0x900) && (exit_nr != 0x500))
-		printk(KERN_EMERG "exit_nr=0x%x | pc=0x%lx | dar=0x%lx | msr=0x%lx\n",
-			exit_nr, kvmppc_get_pc(vcpu), kvmppc_get_fault_dar(vcpu),
-			vcpu->arch.shared->msr);
-#endif
+
+	trace_kvm_book3s_exit(exit_nr, vcpu);
 	kvm_resched(vcpu);
 	switch (exit_nr) {
 	case BOOK3S_INTERRUPT_INST_STORAGE:
@@ -1091,9 +1075,7 @@ program_interrupt:
 		}
 	}
 
-#ifdef EXIT_DEBUG
-	printk(KERN_EMERG "KVM exit: vcpu=0x%p pc=0x%lx r=0x%x\n", vcpu, kvmppc_get_pc(vcpu), r);
-#endif
+	trace_kvm_book3s_reenter(r, vcpu);
 
 	return r;
 }
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index a8e840018052..b5e9d81a1ea2 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -98,6 +98,57 @@ TRACE_EVENT(kvm_gtlb_write,
 		__entry->word1, __entry->word2)
 );
 
+
+/*************************************************************************
+ *                         Book3S trace points                           *
+ *************************************************************************/
+
+#ifdef CONFIG_PPC_BOOK3S
+
+TRACE_EVENT(kvm_book3s_exit,
+	TP_PROTO(unsigned int exit_nr, struct kvm_vcpu *vcpu),
+	TP_ARGS(exit_nr, vcpu),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	exit_nr		)
+		__field(	unsigned long,	pc		)
+		__field(	unsigned long,	msr		)
+		__field(	unsigned long,	dar		)
+		__field(	unsigned long,	srr1		)
+	),
+
+	TP_fast_assign(
+		__entry->exit_nr	= exit_nr;
+		__entry->pc		= kvmppc_get_pc(vcpu);
+		__entry->dar		= kvmppc_get_fault_dar(vcpu);
+		__entry->msr		= vcpu->arch.shared->msr;
+		__entry->srr1		= to_svcpu(vcpu)->shadow_srr1;
+	),
+
+	TP_printk("exit=0x%x | pc=0x%lx | msr=0x%lx | dar=0x%lx | srr1=0x%lx",
+		  __entry->exit_nr, __entry->pc, __entry->msr, __entry->dar,
+		  __entry->srr1)
+);
+
+TRACE_EVENT(kvm_book3s_reenter,
+	TP_PROTO(int r, struct kvm_vcpu *vcpu),
+	TP_ARGS(r, vcpu),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	r		)
+		__field(	unsigned long,	pc		)
+	),
+
+	TP_fast_assign(
+		__entry->r		= r;
+		__entry->pc		= kvmppc_get_pc(vcpu);
+	),
+
+	TP_printk("reentry r=%d | pc=0x%lx", __entry->r, __entry->pc)
+);
+
+#endif /* CONFIG_PPC_BOOK3S */
+
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.1


From 82fdee7bce546c3ce38dcf0db6096eea73dbe7bd Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 11:38:54 +0200
Subject: KVM: PPC: Move book3s_64 mmu map debug print to trace point

This patch moves Book3s MMU debugging over to tracepoints.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_64_mmu_host.c | 13 ++-----------
 arch/powerpc/kvm/trace.h              | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 11 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 672b1495f265..aa516ad81de7 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -28,19 +28,13 @@
 #include <asm/machdep.h>
 #include <asm/mmu_context.h>
 #include <asm/hw_irq.h>
+#include "trace.h"
 
 #define PTE_SIZE 12
 #define VSID_ALL 0
 
-/* #define DEBUG_MMU */
 /* #define DEBUG_SLB */
 
-#ifdef DEBUG_MMU
-#define dprintk_mmu(a, ...) printk(KERN_INFO a, __VA_ARGS__)
-#else
-#define dprintk_mmu(a, ...) do { } while(0)
-#endif
-
 #ifdef DEBUG_SLB
 #define dprintk_slb(a, ...) printk(KERN_INFO a, __VA_ARGS__)
 #else
@@ -156,10 +150,7 @@ map_again:
 	} else {
 		struct hpte_cache *pte = kvmppc_mmu_hpte_cache_next(vcpu);
 
-		dprintk_mmu("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx\n",
-			    ((rflags & HPTE_R_PP) == 3) ? '-' : 'w',
-			    (rflags & HPTE_R_N) ? '-' : 'x',
-			    orig_pte->eaddr, hpteg, va, orig_pte->vpage, hpaddr);
+		trace_kvm_book3s_64_mmu_map(rflags, hpteg, va, hpaddr, orig_pte);
 
 		/* The ppc_md code may give us a secondary entry even though we
 		   asked for a primary. Fix up. */
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index b5e9d81a1ea2..8ed6f1c7c86e 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -147,6 +147,40 @@ TRACE_EVENT(kvm_book3s_reenter,
 	TP_printk("reentry r=%d | pc=0x%lx", __entry->r, __entry->pc)
 );
 
+#ifdef CONFIG_PPC_BOOK3S_64
+
+TRACE_EVENT(kvm_book3s_64_mmu_map,
+	TP_PROTO(int rflags, ulong hpteg, ulong va, pfn_t hpaddr,
+		 struct kvmppc_pte *orig_pte),
+	TP_ARGS(rflags, hpteg, va, hpaddr, orig_pte),
+
+	TP_STRUCT__entry(
+		__field(	unsigned char,		flag_w		)
+		__field(	unsigned char,		flag_x		)
+		__field(	unsigned long,		eaddr		)
+		__field(	unsigned long,		hpteg		)
+		__field(	unsigned long,		va		)
+		__field(	unsigned long long,	vpage		)
+		__field(	unsigned long,		hpaddr		)
+	),
+
+	TP_fast_assign(
+		__entry->flag_w	= ((rflags & HPTE_R_PP) == 3) ? '-' : 'w';
+		__entry->flag_x	= (rflags & HPTE_R_N) ? '-' : 'x';
+		__entry->eaddr	= orig_pte->eaddr;
+		__entry->hpteg	= hpteg;
+		__entry->va	= va;
+		__entry->vpage	= orig_pte->vpage;
+		__entry->hpaddr	= hpaddr;
+	),
+
+	TP_printk("KVM: %c%c Map 0x%lx: [%lx] 0x%lx (0x%llx) -> %lx",
+		  __entry->flag_w, __entry->flag_x, __entry->eaddr,
+		  __entry->hpteg, __entry->va, __entry->vpage, __entry->hpaddr)
+);
+
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
 #endif /* CONFIG_PPC_BOOK3S */
 
 #endif /* _TRACE_KVM_H */
-- 
cgit v1.2.1


From 4c4eea7769d0099ea09f9bdb7aed1cc61d57c9d6 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 12:51:07 +0200
Subject: KVM: PPC: Add tracepoint for generic mmu map

This patch moves the generic mmu map debugging over to tracepoints.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_mmu_hpte.c |  3 +++
 arch/powerpc/kvm/trace.h           | 29 +++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index 02c64ab99c97..ac94bd992564 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -21,6 +21,7 @@
 #include <linux/kvm_host.h>
 #include <linux/hash.h>
 #include <linux/slab.h>
+#include "trace.h"
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -66,6 +67,8 @@ void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	u64 index;
 
+	trace_kvm_book3s_mmu_map(pte);
+
 	spin_lock(&vcpu->arch.mmu_lock);
 
 	/* Add to ePTE list */
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index 8ed6f1c7c86e..68a84442d799 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -181,6 +181,35 @@ TRACE_EVENT(kvm_book3s_64_mmu_map,
 
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
+TRACE_EVENT(kvm_book3s_mmu_map,
+	TP_PROTO(struct hpte_cache *pte),
+	TP_ARGS(pte),
+
+	TP_STRUCT__entry(
+		__field(	u64,		host_va		)
+		__field(	u64,		pfn		)
+		__field(	ulong,		eaddr		)
+		__field(	u64,		vpage		)
+		__field(	ulong,		raddr		)
+		__field(	int,		flags		)
+	),
+
+	TP_fast_assign(
+		__entry->host_va	= pte->host_va;
+		__entry->pfn		= pte->pfn;
+		__entry->eaddr		= pte->pte.eaddr;
+		__entry->vpage		= pte->pte.vpage;
+		__entry->raddr		= pte->pte.raddr;
+		__entry->flags		= (pte->pte.may_read ? 0x4 : 0) |
+					  (pte->pte.may_write ? 0x2 : 0) |
+					  (pte->pte.may_execute ? 0x1 : 0);
+	),
+
+	TP_printk("Map: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
+		  __entry->host_va, __entry->pfn, __entry->eaddr,
+		  __entry->vpage, __entry->raddr, __entry->flags)
+);
+
 #endif /* CONFIG_PPC_BOOK3S */
 
 #endif /* _TRACE_KVM_H */
-- 
cgit v1.2.1


From 8696ee431233171b3c1cc82bae0193efc4fef2ac Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 12:55:19 +0200
Subject: KVM: PPC: Move pte invalidate debug code to tracepoint

This patch moves the SPTE flush debug printk over to tracepoints.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_mmu_hpte.c |  3 +--
 arch/powerpc/kvm/trace.h           | 29 +++++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index ac94bd992564..3397152a2b26 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -104,8 +104,7 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 	if (hlist_unhashed(&pte->list_pte))
 		return;
 
-	dprintk_mmu("KVM: Flushing SPT: 0x%lx (0x%llx) -> 0x%llx\n",
-		    pte->pte.eaddr, pte->pte.vpage, pte->host_va);
+	trace_kvm_book3s_mmu_invalidate(pte);
 
 	/* Different for 32 and 64 bit */
 	kvmppc_mmu_invalidate_pte(vcpu, pte);
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index 68a84442d799..06ad93e40648 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -210,6 +210,35 @@ TRACE_EVENT(kvm_book3s_mmu_map,
 		  __entry->vpage, __entry->raddr, __entry->flags)
 );
 
+TRACE_EVENT(kvm_book3s_mmu_invalidate,
+	TP_PROTO(struct hpte_cache *pte),
+	TP_ARGS(pte),
+
+	TP_STRUCT__entry(
+		__field(	u64,		host_va		)
+		__field(	u64,		pfn		)
+		__field(	ulong,		eaddr		)
+		__field(	u64,		vpage		)
+		__field(	ulong,		raddr		)
+		__field(	int,		flags		)
+	),
+
+	TP_fast_assign(
+		__entry->host_va	= pte->host_va;
+		__entry->pfn		= pte->pfn;
+		__entry->eaddr		= pte->pte.eaddr;
+		__entry->vpage		= pte->pte.vpage;
+		__entry->raddr		= pte->pte.raddr;
+		__entry->flags		= (pte->pte.may_read ? 0x4 : 0) |
+					  (pte->pte.may_write ? 0x2 : 0) |
+					  (pte->pte.may_execute ? 0x1 : 0);
+	),
+
+	TP_printk("Flush: hva=%llx pfn=%llx ea=%lx vp=%llx ra=%lx [%x]",
+		  __entry->host_va, __entry->pfn, __entry->eaddr,
+		  __entry->vpage, __entry->raddr, __entry->flags)
+);
+
 #endif /* CONFIG_PPC_BOOK3S */
 
 #endif /* _TRACE_KVM_H */
-- 
cgit v1.2.1


From c22c31963b4b0c23250e8f520a76427b3986b73b Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 13:38:18 +0200
Subject: KVM: PPC: Fix sid map search after flush

After a flush the sid map contained lots of entries with 0 for their gvsid and
hvsid value. Unfortunately, 0 can be a real value the guest searches for when
looking up a vsid so it would incorrectly find the host's 0 hvsid mapping which
doesn't belong to our sid space.

So let's also check for the valid bit that indicated that the sid we're
looking at actually contains useful data.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_64_mmu_host.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index aa516ad81de7..ebb1b5ddabfb 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -65,14 +65,14 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
 
 	sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
 	map = &to_book3s(vcpu)->sid_map[sid_map_mask];
-	if (map->guest_vsid == gvsid) {
+	if (map->valid && (map->guest_vsid == gvsid)) {
 		dprintk_slb("SLB: Searching: 0x%llx -> 0x%llx\n",
 			    gvsid, map->host_vsid);
 		return map;
 	}
 
 	map = &to_book3s(vcpu)->sid_map[SID_MAP_MASK - sid_map_mask];
-	if (map->guest_vsid == gvsid) {
+	if (map->valid && (map->guest_vsid == gvsid)) {
 		dprintk_slb("SLB: Searching 0x%llx -> 0x%llx\n",
 			    gvsid, map->host_vsid);
 		return map;
-- 
cgit v1.2.1


From c60b4cf70127941e2f944a7971a7f6b3ecb367ac Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 13:40:30 +0200
Subject: KVM: PPC: Add tracepoints for generic spte flushes

The different ways of flusing shadow ptes have their own debug prints which use
stupid old printk.

Let's move them to tracepoints, making them easier available, faster and
possible to activate on demand

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_mmu_hpte.c | 18 +++---------------
 arch/powerpc/kvm/trace.h           | 23 +++++++++++++++++++++++
 2 files changed, 26 insertions(+), 15 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index 3397152a2b26..bd6a7676d0c8 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -31,14 +31,6 @@
 
 #define PTE_SIZE	12
 
-/* #define DEBUG_MMU */
-
-#ifdef DEBUG_MMU
-#define dprintk_mmu(a, ...) printk(KERN_INFO a, __VA_ARGS__)
-#else
-#define dprintk_mmu(a, ...) do { } while(0)
-#endif
-
 static struct kmem_cache *hpte_cache;
 
 static inline u64 kvmppc_mmu_hash_pte(u64 eaddr)
@@ -186,9 +178,7 @@ static void kvmppc_mmu_pte_flush_long(struct kvm_vcpu *vcpu, ulong guest_ea)
 
 void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
 {
-	dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%lx & 0x%lx\n",
-		    vcpu->arch.hpte_cache_count, guest_ea, ea_mask);
-
+	trace_kvm_book3s_mmu_flush("", vcpu, guest_ea, ea_mask);
 	guest_ea &= ea_mask;
 
 	switch (ea_mask) {
@@ -251,8 +241,7 @@ static void kvmppc_mmu_pte_vflush_long(struct kvm_vcpu *vcpu, u64 guest_vp)
 
 void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
 {
-	dprintk_mmu("KVM: Flushing %d Shadow vPTEs: 0x%llx & 0x%llx\n",
-		    vcpu->arch.hpte_cache_count, guest_vp, vp_mask);
+	trace_kvm_book3s_mmu_flush("v", vcpu, guest_vp, vp_mask);
 	guest_vp &= vp_mask;
 
 	switch(vp_mask) {
@@ -274,8 +263,7 @@ void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
 	struct hpte_cache *pte;
 	int i;
 
-	dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%lx - 0x%lx\n",
-		    vcpu->arch.hpte_cache_count, pa_start, pa_end);
+	trace_kvm_book3s_mmu_flush("p", vcpu, pa_start, pa_end);
 
 	rcu_read_lock();
 
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index 06ad93e40648..23f757a69163 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -239,6 +239,29 @@ TRACE_EVENT(kvm_book3s_mmu_invalidate,
 		  __entry->vpage, __entry->raddr, __entry->flags)
 );
 
+TRACE_EVENT(kvm_book3s_mmu_flush,
+	TP_PROTO(const char *type, struct kvm_vcpu *vcpu, unsigned long long p1,
+		 unsigned long long p2),
+	TP_ARGS(type, vcpu, p1, p2),
+
+	TP_STRUCT__entry(
+		__field(	int,			count		)
+		__field(	unsigned long long,	p1		)
+		__field(	unsigned long long,	p2		)
+		__field(	const char *,		type		)
+	),
+
+	TP_fast_assign(
+		__entry->count		= vcpu->arch.hpte_cache_count;
+		__entry->p1		= p1;
+		__entry->p2		= p2;
+		__entry->type		= type;
+	),
+
+	TP_printk("Flush %d %sPTEs: %llx - %llx",
+		  __entry->count, __entry->type, __entry->p1, __entry->p2)
+);
+
 #endif /* CONFIG_PPC_BOOK3S */
 
 #endif /* _TRACE_KVM_H */
-- 
cgit v1.2.1


From 4cb6b7ea0cd085e6613153ad69608cad6421abcc Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 16:08:22 +0200
Subject: KVM: PPC: Preload magic page when in kernel mode

When the guest jumps into kernel mode and has the magic page mapped, theres a
very high chance that it will also use it. So let's detect that scenario and
map the segment accordingly.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 37db61d37041..54ca578239db 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -145,6 +145,16 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 		   (old_msr & (MSR_PR|MSR_IR|MSR_DR))) {
 		kvmppc_mmu_flush_segments(vcpu);
 		kvmppc_mmu_map_segment(vcpu, kvmppc_get_pc(vcpu));
+
+		/* Preload magic page segment when in kernel mode */
+		if (!(msr & MSR_PR) && vcpu->arch.magic_page_pa) {
+			struct kvm_vcpu_arch *a = &vcpu->arch;
+
+			if (msr & MSR_DR)
+				kvmppc_mmu_map_segment(vcpu, a->magic_page_ea);
+			else
+				kvmppc_mmu_map_segment(vcpu, a->magic_page_pa);
+		}
 	}
 
 	/* Preload FPU if it's enabled */
-- 
cgit v1.2.1


From 2e602847d9c2d6b487bda62bbbe550db40ca912f Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 20:11:39 +0200
Subject: KVM: PPC: Don't flush PTEs on NX/RO hit

When hitting a no-execute or read-only data/inst storage interrupt we were
flushing the respective PTE so we're sure it gets properly overwritten next.

According to the spec, this is unnecessary though. The guest issues a tlbie
anyways, so we're safe to just keep the PTE around and have it manually removed
from the guest, saving us a flush.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s.c | 2 --
 1 file changed, 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 54ca578239db..2fb528f417ff 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -887,7 +887,6 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			vcpu->arch.shared->msr |=
 				to_svcpu(vcpu)->shadow_srr1 & 0x58000000;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-			kvmppc_mmu_pte_flush(vcpu, kvmppc_get_pc(vcpu), ~0xFFFUL);
 			r = RESUME_GUEST;
 		}
 		break;
@@ -913,7 +912,6 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			vcpu->arch.shared->dar = dar;
 			vcpu->arch.shared->dsisr = to_svcpu(vcpu)->fault_dsisr;
 			kvmppc_book3s_queue_irqprio(vcpu, exit_nr);
-			kvmppc_mmu_pte_flush(vcpu, dar, ~0xFFFUL);
 			r = RESUME_GUEST;
 		}
 		break;
-- 
cgit v1.2.1


From e7c1d14e3bf40b87e6a3f68964b36dbb2c875c0f Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 21:24:48 +0200
Subject: KVM: PPC: Make invalidation code more reliable

There is a race condition in the pte invalidation code path where we can't
be sure if a pte was invalidated already. So let's move the spin lock around
to get rid of the race.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_mmu_hpte.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_mmu_hpte.c b/arch/powerpc/kvm/book3s_mmu_hpte.c
index bd6a7676d0c8..79751d8dd131 100644
--- a/arch/powerpc/kvm/book3s_mmu_hpte.c
+++ b/arch/powerpc/kvm/book3s_mmu_hpte.c
@@ -92,10 +92,6 @@ static void free_pte_rcu(struct rcu_head *head)
 
 static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
-	/* pte already invalidated? */
-	if (hlist_unhashed(&pte->list_pte))
-		return;
-
 	trace_kvm_book3s_mmu_invalidate(pte);
 
 	/* Different for 32 and 64 bit */
@@ -103,18 +99,24 @@ static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 
 	spin_lock(&vcpu->arch.mmu_lock);
 
+	/* pte already invalidated in between? */
+	if (hlist_unhashed(&pte->list_pte)) {
+		spin_unlock(&vcpu->arch.mmu_lock);
+		return;
+	}
+
 	hlist_del_init_rcu(&pte->list_pte);
 	hlist_del_init_rcu(&pte->list_pte_long);
 	hlist_del_init_rcu(&pte->list_vpte);
 	hlist_del_init_rcu(&pte->list_vpte_long);
 
-	spin_unlock(&vcpu->arch.mmu_lock);
-
 	if (pte->pte.may_write)
 		kvm_release_pfn_dirty(pte->pfn);
 	else
 		kvm_release_pfn_clean(pte->pfn);
 
+	spin_unlock(&vcpu->arch.mmu_lock);
+
 	vcpu->arch.hpte_cache_count--;
 	call_rcu(&pte->rcu_head, free_pte_rcu);
 }
-- 
cgit v1.2.1


From 928d78be54014e65498e289fdc3f82acc4b804a9 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 21:25:33 +0200
Subject: KVM: PPC: Move slb debugging to tracepoints

This patch moves debugging printks for shadow SLB debugging over to tracepoints.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_64_mmu_host.c | 22 +++--------
 arch/powerpc/kvm/trace.h              | 73 +++++++++++++++++++++++++++++++++++
 2 files changed, 78 insertions(+), 17 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index ebb1b5ddabfb..321c931f691c 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -33,14 +33,6 @@
 #define PTE_SIZE 12
 #define VSID_ALL 0
 
-/* #define DEBUG_SLB */
-
-#ifdef DEBUG_SLB
-#define dprintk_slb(a, ...) printk(KERN_INFO a, __VA_ARGS__)
-#else
-#define dprintk_slb(a, ...) do { } while(0)
-#endif
-
 void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	ppc_md.hpte_invalidate(pte->slot, pte->host_va,
@@ -66,20 +58,17 @@ static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
 	sid_map_mask = kvmppc_sid_hash(vcpu, gvsid);
 	map = &to_book3s(vcpu)->sid_map[sid_map_mask];
 	if (map->valid && (map->guest_vsid == gvsid)) {
-		dprintk_slb("SLB: Searching: 0x%llx -> 0x%llx\n",
-			    gvsid, map->host_vsid);
+		trace_kvm_book3s_slb_found(gvsid, map->host_vsid);
 		return map;
 	}
 
 	map = &to_book3s(vcpu)->sid_map[SID_MAP_MASK - sid_map_mask];
 	if (map->valid && (map->guest_vsid == gvsid)) {
-		dprintk_slb("SLB: Searching 0x%llx -> 0x%llx\n",
-			    gvsid, map->host_vsid);
+		trace_kvm_book3s_slb_found(gvsid, map->host_vsid);
 		return map;
 	}
 
-	dprintk_slb("SLB: Searching %d/%d: 0x%llx -> not found\n",
-		    sid_map_mask, SID_MAP_MASK - sid_map_mask, gvsid);
+	trace_kvm_book3s_slb_fail(sid_map_mask, gvsid);
 	return NULL;
 }
 
@@ -205,8 +194,7 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 	map->guest_vsid = gvsid;
 	map->valid = true;
 
-	dprintk_slb("SLB: New mapping at %d: 0x%llx -> 0x%llx\n",
-		    sid_map_mask, gvsid, map->host_vsid);
+	trace_kvm_book3s_slb_map(sid_map_mask, gvsid, map->host_vsid);
 
 	return map;
 }
@@ -278,7 +266,7 @@ int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr)
 	to_svcpu(vcpu)->slb[slb_index].esid = slb_esid;
 	to_svcpu(vcpu)->slb[slb_index].vsid = slb_vsid;
 
-	dprintk_slb("slbmte %#llx, %#llx\n", slb_vsid, slb_esid);
+	trace_kvm_book3s_slbmte(slb_vsid, slb_esid);
 
 	return 0;
 }
diff --git a/arch/powerpc/kvm/trace.h b/arch/powerpc/kvm/trace.h
index 23f757a69163..3aca1b042b8c 100644
--- a/arch/powerpc/kvm/trace.h
+++ b/arch/powerpc/kvm/trace.h
@@ -262,6 +262,79 @@ TRACE_EVENT(kvm_book3s_mmu_flush,
 		  __entry->count, __entry->type, __entry->p1, __entry->p2)
 );
 
+TRACE_EVENT(kvm_book3s_slb_found,
+	TP_PROTO(unsigned long long gvsid, unsigned long long hvsid),
+	TP_ARGS(gvsid, hvsid),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long long,	gvsid		)
+		__field(	unsigned long long,	hvsid		)
+	),
+
+	TP_fast_assign(
+		__entry->gvsid		= gvsid;
+		__entry->hvsid		= hvsid;
+	),
+
+	TP_printk("%llx -> %llx", __entry->gvsid, __entry->hvsid)
+);
+
+TRACE_EVENT(kvm_book3s_slb_fail,
+	TP_PROTO(u16 sid_map_mask, unsigned long long gvsid),
+	TP_ARGS(sid_map_mask, gvsid),
+
+	TP_STRUCT__entry(
+		__field(	unsigned short,		sid_map_mask	)
+		__field(	unsigned long long,	gvsid		)
+	),
+
+	TP_fast_assign(
+		__entry->sid_map_mask	= sid_map_mask;
+		__entry->gvsid		= gvsid;
+	),
+
+	TP_printk("%x/%x: %llx", __entry->sid_map_mask,
+		  SID_MAP_MASK - __entry->sid_map_mask, __entry->gvsid)
+);
+
+TRACE_EVENT(kvm_book3s_slb_map,
+	TP_PROTO(u16 sid_map_mask, unsigned long long gvsid,
+		 unsigned long long hvsid),
+	TP_ARGS(sid_map_mask, gvsid, hvsid),
+
+	TP_STRUCT__entry(
+		__field(	unsigned short,		sid_map_mask	)
+		__field(	unsigned long long,	guest_vsid	)
+		__field(	unsigned long long,	host_vsid	)
+	),
+
+	TP_fast_assign(
+		__entry->sid_map_mask	= sid_map_mask;
+		__entry->guest_vsid	= gvsid;
+		__entry->host_vsid	= hvsid;
+	),
+
+	TP_printk("%x: %llx -> %llx", __entry->sid_map_mask,
+		  __entry->guest_vsid, __entry->host_vsid)
+);
+
+TRACE_EVENT(kvm_book3s_slbmte,
+	TP_PROTO(u64 slb_vsid, u64 slb_esid),
+	TP_ARGS(slb_vsid, slb_esid),
+
+	TP_STRUCT__entry(
+		__field(	u64,	slb_vsid	)
+		__field(	u64,	slb_esid	)
+	),
+
+	TP_fast_assign(
+		__entry->slb_vsid	= slb_vsid;
+		__entry->slb_esid	= slb_esid;
+	),
+
+	TP_printk("%llx, %llx", __entry->slb_vsid, __entry->slb_esid)
+);
+
 #endif /* CONFIG_PPC_BOOK3S */
 
 #endif /* _TRACE_KVM_H */
-- 
cgit v1.2.1


From b9877ce2994cc812f00dbb2adb88c1749b6dac86 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 21:48:53 +0200
Subject: KVM: PPC: Revert "KVM: PPC: Use kernel hash function"

It turns out the in-kernel hash function is sub-optimal for our subtle
hash inputs where every bit is significant. So let's revert to the original
hash functions.

This reverts commit 05340ab4f9a6626f7a2e8f9fe5397c61d494f445.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_32_mmu_host.c | 10 ++++++++--
 arch/powerpc/kvm/book3s_64_mmu_host.c | 11 +++++++++--
 2 files changed, 17 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 343452cff9b2..57dddeb23b9b 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -19,7 +19,6 @@
  */
 
 #include <linux/kvm_host.h>
-#include <linux/hash.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -77,7 +76,14 @@ void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
  * a hash, so we don't waste cycles on looping */
 static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid)
 {
-	return hash_64(gvsid, SID_MAP_BITS);
+	return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 5)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 4)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 3)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 2)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 1)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 0)) & SID_MAP_MASK));
 }
 
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 321c931f691c..e7c4d00b99cf 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -20,7 +20,6 @@
  */
 
 #include <linux/kvm_host.h>
-#include <linux/hash.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -44,9 +43,17 @@ void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
  * a hash, so we don't waste cycles on looping */
 static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid)
 {
-	return hash_64(gvsid, SID_MAP_BITS);
+	return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 5)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 4)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 3)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 2)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 1)) & SID_MAP_MASK) ^
+		     ((gvsid >> (SID_MAP_BITS * 0)) & SID_MAP_MASK));
 }
 
+
 static struct kvmppc_sid_map *find_sid_vsid(struct kvm_vcpu *vcpu, u64 gvsid)
 {
 	struct kvmppc_sid_map *map;
-- 
cgit v1.2.1


From cb24c50826e0722bffb0674f088954cd4980818b Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 22:05:00 +0200
Subject: KVM: PPC: Remove unused define

The define VSID_ALL is unused. Let's remove it.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_64_mmu_host.c | 1 -
 1 file changed, 1 deletion(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index e7c4d00b99cf..4040c8d16ad5 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -30,7 +30,6 @@
 #include "trace.h"
 
 #define PTE_SIZE 12
-#define VSID_ALL 0
 
 void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
-- 
cgit v1.2.1


From 7508e16c9f2a20f7721d7bc47c33a7b34c873a2c Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 3 Aug 2010 11:32:56 +0200
Subject: KVM: PPC: Add feature bitmap for magic page

We will soon add SR PV support to the shared page, so we need some
infrastructure that allows the guest to query for features KVM exports.

This patch adds a second return value to the magic mapping that
indicated to the guest which features are available.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_para.h |  2 ++
 arch/powerpc/kernel/kvm.c           | 21 +++++++++++++++------
 arch/powerpc/kvm/powerpc.c          |  5 ++++-
 3 files changed, 21 insertions(+), 7 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 7438ab360120..43c1b2260af8 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -47,6 +47,8 @@ struct kvm_vcpu_arch_shared {
 
 #define KVM_FEATURE_MAGIC_PAGE	1
 
+#define KVM_MAGIC_FEAT_SR	(1 << 0)
+
 #ifdef __KERNEL__
 
 #ifdef CONFIG_KVM_GUEST
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index d3a2cc50d611..226882fe85a6 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -266,12 +266,20 @@ static void kvm_patch_ins_wrteei(u32 *inst)
 
 static void kvm_map_magic_page(void *data)
 {
-	kvm_hypercall2(KVM_HC_PPC_MAP_MAGIC_PAGE,
-		       KVM_MAGIC_PAGE,  /* Physical Address */
-		       KVM_MAGIC_PAGE); /* Effective Address */
+	u32 *features = data;
+
+	ulong in[8];
+	ulong out[8];
+
+	in[0] = KVM_MAGIC_PAGE;
+	in[1] = KVM_MAGIC_PAGE;
+
+	kvm_hypercall(in, out, HC_VENDOR_KVM | KVM_HC_PPC_MAP_MAGIC_PAGE);
+
+	*features = out[0];
 }
 
-static void kvm_check_ins(u32 *inst)
+static void kvm_check_ins(u32 *inst, u32 features)
 {
 	u32 _inst = *inst;
 	u32 inst_no_rt = _inst & ~KVM_MASK_RT;
@@ -367,9 +375,10 @@ static void kvm_use_magic_page(void)
 	u32 *p;
 	u32 *start, *end;
 	u32 tmp;
+	u32 features;
 
 	/* Tell the host to map the magic page to -4096 on all CPUs */
-	on_each_cpu(kvm_map_magic_page, NULL, 1);
+	on_each_cpu(kvm_map_magic_page, &features, 1);
 
 	/* Quick self-test to see if the mapping works */
 	if (__get_user(tmp, (u32*)KVM_MAGIC_PAGE)) {
@@ -382,7 +391,7 @@ static void kvm_use_magic_page(void)
 	end = (void*)_etext;
 
 	for (p = start; p < end; p++)
-		kvm_check_ins(p);
+		kvm_check_ins(p, features);
 
 	printk(KERN_INFO "KVM: Live patching for a fast VM %s\n",
 			 kvm_patching_worked ? "worked" : "failed");
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 6a53a3f86dae..496d7a5200dc 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -66,6 +66,8 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 		vcpu->arch.magic_page_pa = param1;
 		vcpu->arch.magic_page_ea = param2;
 
+		r2 = 0;
+
 		r = HC_EV_SUCCESS;
 		break;
 	}
@@ -76,13 +78,14 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 #endif
 
 		/* Second return value is in r4 */
-		kvmppc_set_gpr(vcpu, 4, r2);
 		break;
 	default:
 		r = HC_EV_UNIMPLEMENTED;
 		break;
 	}
 
+	kvmppc_set_gpr(vcpu, 4, r2);
+
 	return r;
 }
 
-- 
cgit v1.2.1


From c1c88e2fa16f979ba3e99018a53962abe852b30f Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 2 Aug 2010 23:23:04 +0200
Subject: KVM: PPC: Move BAT handling code into spr handler

The current approach duplicates the spr->bat finding logic and makes it harder
to reuse the actually used variables. So let's move everything down to the spr
handler.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s_emulate.c | 48 +++++++++++++--------------------------
 1 file changed, 16 insertions(+), 32 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s_emulate.c b/arch/powerpc/kvm/book3s_emulate.c
index f333cb445349..466846557089 100644
--- a/arch/powerpc/kvm/book3s_emulate.c
+++ b/arch/powerpc/kvm/book3s_emulate.c
@@ -264,7 +264,7 @@ void kvmppc_set_bat(struct kvm_vcpu *vcpu, struct kvmppc_bat *bat, bool upper,
 	}
 }
 
-static u32 kvmppc_read_bat(struct kvm_vcpu *vcpu, int sprn)
+static struct kvmppc_bat *kvmppc_find_bat(struct kvm_vcpu *vcpu, int sprn)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 	struct kvmppc_bat *bat;
@@ -286,35 +286,7 @@ static u32 kvmppc_read_bat(struct kvm_vcpu *vcpu, int sprn)
 		BUG();
 	}
 
-	if (sprn % 2)
-		return bat->raw >> 32;
-	else
-		return bat->raw;
-}
-
-static void kvmppc_write_bat(struct kvm_vcpu *vcpu, int sprn, u32 val)
-{
-	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
-	struct kvmppc_bat *bat;
-
-	switch (sprn) {
-	case SPRN_IBAT0U ... SPRN_IBAT3L:
-		bat = &vcpu_book3s->ibat[(sprn - SPRN_IBAT0U) / 2];
-		break;
-	case SPRN_IBAT4U ... SPRN_IBAT7L:
-		bat = &vcpu_book3s->ibat[4 + ((sprn - SPRN_IBAT4U) / 2)];
-		break;
-	case SPRN_DBAT0U ... SPRN_DBAT3L:
-		bat = &vcpu_book3s->dbat[(sprn - SPRN_DBAT0U) / 2];
-		break;
-	case SPRN_DBAT4U ... SPRN_DBAT7L:
-		bat = &vcpu_book3s->dbat[4 + ((sprn - SPRN_DBAT4U) / 2)];
-		break;
-	default:
-		BUG();
-	}
-
-	kvmppc_set_bat(vcpu, bat, !(sprn % 2), val);
+	return bat;
 }
 
 int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
@@ -339,12 +311,16 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 	case SPRN_IBAT4U ... SPRN_IBAT7L:
 	case SPRN_DBAT0U ... SPRN_DBAT3L:
 	case SPRN_DBAT4U ... SPRN_DBAT7L:
-		kvmppc_write_bat(vcpu, sprn, (u32)spr_val);
+	{
+		struct kvmppc_bat *bat = kvmppc_find_bat(vcpu, sprn);
+
+		kvmppc_set_bat(vcpu, bat, !(sprn % 2), (u32)spr_val);
 		/* BAT writes happen so rarely that we're ok to flush
 		 * everything here */
 		kvmppc_mmu_pte_flush(vcpu, 0, 0);
 		kvmppc_mmu_flush_segments(vcpu);
 		break;
+	}
 	case SPRN_HID0:
 		to_book3s(vcpu)->hid[0] = spr_val;
 		break;
@@ -434,8 +410,16 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_IBAT4U ... SPRN_IBAT7L:
 	case SPRN_DBAT0U ... SPRN_DBAT3L:
 	case SPRN_DBAT4U ... SPRN_DBAT7L:
-		kvmppc_set_gpr(vcpu, rt, kvmppc_read_bat(vcpu, sprn));
+	{
+		struct kvmppc_bat *bat = kvmppc_find_bat(vcpu, sprn);
+
+		if (sprn % 2)
+			kvmppc_set_gpr(vcpu, rt, bat->raw >> 32);
+		else
+			kvmppc_set_gpr(vcpu, rt, bat->raw);
+
 		break;
+	}
 	case SPRN_SDR1:
 		kvmppc_set_gpr(vcpu, rt, to_book3s(vcpu)->sdr1);
 		break;
-- 
cgit v1.2.1


From 8e8651783ff2458f31098be7c2abacf2fcab054a Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 3 Aug 2010 01:06:11 +0200
Subject: KVM: PPC: Interpret SR registers on demand

Right now we're examining the contents of Book3s_32's segment registers when
the register is written and put the interpreted contents into a struct.

There are two reasons this is bad. For starters, the struct has worse real-time
performance, as it occupies more ram. But the more important part is that with
segment registers being interpreted from their raw values, we can put them in
the shared page, allowing guests to mess with them directly.

This patch makes the internal representation of SRs be u32s.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h | 11 +----
 arch/powerpc/kvm/book3s.c             |  4 +-
 arch/powerpc/kvm/book3s_32_mmu.c      | 79 +++++++++++++++++++----------------
 3 files changed, 46 insertions(+), 48 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index f04f516c97da..08846520220c 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -38,15 +38,6 @@ struct kvmppc_slb {
 	bool class	: 1;
 };
 
-struct kvmppc_sr {
-	u32 raw;
-	u32 vsid;
-	bool Ks		: 1;
-	bool Kp		: 1;
-	bool nx		: 1;
-	bool valid	: 1;
-};
-
 struct kvmppc_bat {
 	u64 raw;
 	u32 bepi;
@@ -79,7 +70,7 @@ struct kvmppc_vcpu_book3s {
 		u64 vsid;
 	} slb_shadow[64];
 	u8 slb_shadow_max;
-	struct kvmppc_sr sr[16];
+	u32 sr[16];
 	struct kvmppc_bat ibat[8];
 	struct kvmppc_bat dbat[8];
 	u64 hid[6];
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 2fb528f417ff..34472afbb3ec 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -1162,8 +1162,8 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 		}
 	} else {
 		for (i = 0; i < 16; i++) {
-			sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw;
-			sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i].raw;
+			sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i];
+			sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i];
 		}
 		for (i = 0; i < 8; i++) {
 			sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw;
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index 5bf4bf8c9e65..d4ff76fd1ff9 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -58,14 +58,39 @@ static inline bool check_debug_ip(struct kvm_vcpu *vcpu)
 #endif
 }
 
+static inline u32 sr_vsid(u32 sr_raw)
+{
+	return sr_raw & 0x0fffffff;
+}
+
+static inline bool sr_valid(u32 sr_raw)
+{
+	return (sr_raw & 0x80000000) ? false : true;
+}
+
+static inline bool sr_ks(u32 sr_raw)
+{
+	return (sr_raw & 0x40000000) ? true: false;
+}
+
+static inline bool sr_kp(u32 sr_raw)
+{
+	return (sr_raw & 0x20000000) ? true: false;
+}
+
+static inline bool sr_nx(u32 sr_raw)
+{
+	return (sr_raw & 0x10000000) ? true: false;
+}
+
 static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
 					  struct kvmppc_pte *pte, bool data);
 static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 					     u64 *vsid);
 
-static struct kvmppc_sr *find_sr(struct kvmppc_vcpu_book3s *vcpu_book3s, gva_t eaddr)
+static u32 find_sr(struct kvmppc_vcpu_book3s *vcpu_book3s, gva_t eaddr)
 {
-	return &vcpu_book3s->sr[(eaddr >> 28) & 0xf];
+	return vcpu_book3s->sr[(eaddr >> 28) & 0xf];
 }
 
 static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
@@ -87,7 +112,7 @@ static void kvmppc_mmu_book3s_32_reset_msr(struct kvm_vcpu *vcpu)
 }
 
 static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3s,
-				      struct kvmppc_sr *sre, gva_t eaddr,
+				      u32 sre, gva_t eaddr,
 				      bool primary)
 {
 	u32 page, hash, pteg, htabmask;
@@ -96,7 +121,7 @@ static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3
 	page = (eaddr & 0x0FFFFFFF) >> 12;
 	htabmask = ((vcpu_book3s->sdr1 & 0x1FF) << 16) | 0xFFC0;
 
-	hash = ((sre->vsid ^ page) << 6);
+	hash = ((sr_vsid(sre) ^ page) << 6);
 	if (!primary)
 		hash = ~hash;
 	hash &= htabmask;
@@ -105,7 +130,7 @@ static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3
 
 	dprintk("MMU: pc=0x%lx eaddr=0x%lx sdr1=0x%llx pteg=0x%x vsid=0x%x\n",
 		kvmppc_get_pc(&vcpu_book3s->vcpu), eaddr, vcpu_book3s->sdr1, pteg,
-		sre->vsid);
+		sr_vsid(sre));
 
 	r = gfn_to_hva(vcpu_book3s->vcpu.kvm, pteg >> PAGE_SHIFT);
 	if (kvm_is_error_hva(r))
@@ -113,10 +138,9 @@ static hva_t kvmppc_mmu_book3s_32_get_pteg(struct kvmppc_vcpu_book3s *vcpu_book3
 	return r | (pteg & ~PAGE_MASK);
 }
 
-static u32 kvmppc_mmu_book3s_32_get_ptem(struct kvmppc_sr *sre, gva_t eaddr,
-				    bool primary)
+static u32 kvmppc_mmu_book3s_32_get_ptem(u32 sre, gva_t eaddr, bool primary)
 {
-	return ((eaddr & 0x0fffffff) >> 22) | (sre->vsid << 7) |
+	return ((eaddr & 0x0fffffff) >> 22) | (sr_vsid(sre) << 7) |
 	       (primary ? 0 : 0x40) | 0x80000000;
 }
 
@@ -180,7 +204,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 				     bool primary)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
-	struct kvmppc_sr *sre;
+	u32 sre;
 	hva_t ptegp;
 	u32 pteg[16];
 	u32 ptem = 0;
@@ -190,7 +214,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 	sre = find_sr(vcpu_book3s, eaddr);
 
 	dprintk_pte("SR 0x%lx: vsid=0x%x, raw=0x%x\n", eaddr >> 28,
-		    sre->vsid, sre->raw);
+		    sr_vsid(sre), sre);
 
 	pte->vpage = kvmppc_mmu_book3s_32_ea_to_vp(vcpu, eaddr, data);
 
@@ -214,8 +238,8 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 			pte->raddr = (pteg[i+1] & ~(0xFFFULL)) | (eaddr & 0xFFF);
 			pp = pteg[i+1] & 3;
 
-			if ((sre->Kp &&  (vcpu->arch.shared->msr & MSR_PR)) ||
-			    (sre->Ks && !(vcpu->arch.shared->msr & MSR_PR)))
+			if ((sr_kp(sre) &&  (vcpu->arch.shared->msr & MSR_PR)) ||
+			    (sr_ks(sre) && !(vcpu->arch.shared->msr & MSR_PR)))
 				pp |= 4;
 
 			pte->may_write = false;
@@ -311,30 +335,13 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 static u32 kvmppc_mmu_book3s_32_mfsrin(struct kvm_vcpu *vcpu, u32 srnum)
 {
-	return to_book3s(vcpu)->sr[srnum].raw;
+	return to_book3s(vcpu)->sr[srnum];
 }
 
 static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum,
 					ulong value)
 {
-	struct kvmppc_sr *sre;
-
-	sre = &to_book3s(vcpu)->sr[srnum];
-
-	/* Flush any left-over shadows from the previous SR */
-
-	/* XXX Not necessary? */
-	/* kvmppc_mmu_pte_flush(vcpu, ((u64)sre->vsid) << 28, 0xf0000000ULL); */
-
-	/* And then put in the new SR */
-	sre->raw = value;
-	sre->vsid = (value & 0x0fffffff);
-	sre->valid = (value & 0x80000000) ? false : true;
-	sre->Ks = (value & 0x40000000) ? true : false;
-	sre->Kp = (value & 0x20000000) ? true : false;
-	sre->nx = (value & 0x10000000) ? true : false;
-
-	/* Map the new segment */
+	to_book3s(vcpu)->sr[srnum] = value;
 	kvmppc_mmu_map_segment(vcpu, srnum << SID_SHIFT);
 }
 
@@ -347,13 +354,13 @@ static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 					     u64 *vsid)
 {
 	ulong ea = esid << SID_SHIFT;
-	struct kvmppc_sr *sr;
+	u32 sr;
 	u64 gvsid = esid;
 
 	if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
 		sr = find_sr(to_book3s(vcpu), ea);
-		if (sr->valid)
-			gvsid = sr->vsid;
+		if (sr_valid(sr))
+			gvsid = sr_vsid(sr);
 	}
 
 	/* In case we only have one of MSR_IR or MSR_DR set, let's put
@@ -370,8 +377,8 @@ static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 		*vsid = VSID_REAL_DR | gvsid;
 		break;
 	case MSR_DR|MSR_IR:
-		if (sr->valid)
-			*vsid = sr->vsid;
+		if (sr_valid(sr))
+			*vsid = sr_vsid(sr);
 		else
 			*vsid = VSID_BAT | gvsid;
 		break;
-- 
cgit v1.2.1


From df1bfa25d81f9451715ccbbb67551e0f792ceec8 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 3 Aug 2010 02:29:27 +0200
Subject: KVM: PPC: Put segment registers in shared page

Now that the actual mtsr doesn't do anything anymore, we can move the sr
contents over to the shared page, so a guest can directly read and write
its sr contents from guest context.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h |  1 -
 arch/powerpc/include/asm/kvm_para.h   |  1 +
 arch/powerpc/kvm/book3s.c             |  7 +++----
 arch/powerpc/kvm/book3s_32_mmu.c      | 12 ++++++------
 arch/powerpc/kvm/powerpc.c            |  2 +-
 5 files changed, 11 insertions(+), 12 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 08846520220c..be8aac24ba83 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -70,7 +70,6 @@ struct kvmppc_vcpu_book3s {
 		u64 vsid;
 	} slb_shadow[64];
 	u8 slb_shadow_max;
-	u32 sr[16];
 	struct kvmppc_bat ibat[8];
 	struct kvmppc_bat dbat[8];
 	u64 hid[6];
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 43c1b2260af8..d79fd0910964 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -38,6 +38,7 @@ struct kvm_vcpu_arch_shared {
 	__u64 msr;
 	__u32 dsisr;
 	__u32 int_pending;	/* Tells the guest if we have an interrupt */
+	__u32 sr[16];
 };
 
 #define KVM_SC_MAGIC_R0		0x4b564d21 /* "KVM!" */
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 34472afbb3ec..02a9cb165d53 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -1161,10 +1161,9 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 			sregs->u.s.ppc64.slb[i].slbv = vcpu3s->slb[i].origv;
 		}
 	} else {
-		for (i = 0; i < 16; i++) {
-			sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i];
-			sregs->u.s.ppc32.sr[i] = vcpu3s->sr[i];
-		}
+		for (i = 0; i < 16; i++)
+			sregs->u.s.ppc32.sr[i] = vcpu->arch.shared->sr[i];
+
 		for (i = 0; i < 8; i++) {
 			sregs->u.s.ppc32.ibat[i] = vcpu3s->ibat[i].raw;
 			sregs->u.s.ppc32.dbat[i] = vcpu3s->dbat[i].raw;
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index d4ff76fd1ff9..c8cefdd15fd8 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -88,9 +88,9 @@ static int kvmppc_mmu_book3s_32_xlate_bat(struct kvm_vcpu *vcpu, gva_t eaddr,
 static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 					     u64 *vsid);
 
-static u32 find_sr(struct kvmppc_vcpu_book3s *vcpu_book3s, gva_t eaddr)
+static u32 find_sr(struct kvm_vcpu *vcpu, gva_t eaddr)
 {
-	return vcpu_book3s->sr[(eaddr >> 28) & 0xf];
+	return vcpu->arch.shared->sr[(eaddr >> 28) & 0xf];
 }
 
 static u64 kvmppc_mmu_book3s_32_ea_to_vp(struct kvm_vcpu *vcpu, gva_t eaddr,
@@ -211,7 +211,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 	int i;
 	int found = 0;
 
-	sre = find_sr(vcpu_book3s, eaddr);
+	sre = find_sr(vcpu, eaddr);
 
 	dprintk_pte("SR 0x%lx: vsid=0x%x, raw=0x%x\n", eaddr >> 28,
 		    sr_vsid(sre), sre);
@@ -335,13 +335,13 @@ static int kvmppc_mmu_book3s_32_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 
 static u32 kvmppc_mmu_book3s_32_mfsrin(struct kvm_vcpu *vcpu, u32 srnum)
 {
-	return to_book3s(vcpu)->sr[srnum];
+	return vcpu->arch.shared->sr[srnum];
 }
 
 static void kvmppc_mmu_book3s_32_mtsrin(struct kvm_vcpu *vcpu, u32 srnum,
 					ulong value)
 {
-	to_book3s(vcpu)->sr[srnum] = value;
+	vcpu->arch.shared->sr[srnum] = value;
 	kvmppc_mmu_map_segment(vcpu, srnum << SID_SHIFT);
 }
 
@@ -358,7 +358,7 @@ static int kvmppc_mmu_book3s_32_esid_to_vsid(struct kvm_vcpu *vcpu, ulong esid,
 	u64 gvsid = esid;
 
 	if (vcpu->arch.shared->msr & (MSR_DR|MSR_IR)) {
-		sr = find_sr(to_book3s(vcpu), ea);
+		sr = find_sr(vcpu, ea);
 		if (sr_valid(sr))
 			gvsid = sr_vsid(sr);
 	}
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 496d7a5200dc..028891c0baff 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -66,7 +66,7 @@ int kvmppc_kvm_pv(struct kvm_vcpu *vcpu)
 		vcpu->arch.magic_page_pa = param1;
 		vcpu->arch.magic_page_ea = param2;
 
-		r2 = 0;
+		r2 = KVM_MAGIC_FEAT_SR;
 
 		r = HC_EV_SUCCESS;
 		break;
-- 
cgit v1.2.1


From cbe487fac7fc016dbabbcbe83f11384e1803a56d Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 3 Aug 2010 10:39:35 +0200
Subject: KVM: PPC: Add mtsrin PV code

This is the guest side of the mtsr acceleration. Using this a guest can now
call mtsrin with almost no overhead as long as it ensures that it only uses
it with (MSR_IR|MSR_DR) == 0. Linux does that, so we're good.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/asm-offsets.c |  1 +
 arch/powerpc/kernel/kvm.c         | 60 +++++++++++++++++++++++++++++++++++++++
 arch/powerpc/kernel/kvm_emul.S    | 50 ++++++++++++++++++++++++++++++++
 3 files changed, 111 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6d92b4e13ebf..7f0d6fcc28a3 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -478,6 +478,7 @@ int main(void)
 	DEFINE(KVM_MAGIC_MSR, offsetof(struct kvm_vcpu_arch_shared, msr));
 	DEFINE(KVM_MAGIC_CRITICAL, offsetof(struct kvm_vcpu_arch_shared,
 					    critical));
+	DEFINE(KVM_MAGIC_SR, offsetof(struct kvm_vcpu_arch_shared, sr));
 #endif
 
 #ifdef CONFIG_44x
diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 226882fe85a6..c8bab24ff8ac 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -42,6 +42,7 @@
 #define KVM_INST_B_MAX		0x01ffffff
 
 #define KVM_MASK_RT		0x03e00000
+#define KVM_MASK_RB		0x0000f800
 #define KVM_INST_MFMSR		0x7c0000a6
 #define KVM_INST_MFSPR_SPRG0	0x7c1042a6
 #define KVM_INST_MFSPR_SPRG1	0x7c1142a6
@@ -69,6 +70,8 @@
 #define KVM_INST_WRTEEI_0	0x7c000146
 #define KVM_INST_WRTEEI_1	0x7c008146
 
+#define KVM_INST_MTSRIN		0x7c0001e4
+
 static bool kvm_patching_worked = true;
 static char kvm_tmp[1024 * 1024];
 static int kvm_tmp_index;
@@ -264,6 +267,51 @@ static void kvm_patch_ins_wrteei(u32 *inst)
 
 #endif
 
+#ifdef CONFIG_PPC_BOOK3S_32
+
+extern u32 kvm_emulate_mtsrin_branch_offs;
+extern u32 kvm_emulate_mtsrin_reg1_offs;
+extern u32 kvm_emulate_mtsrin_reg2_offs;
+extern u32 kvm_emulate_mtsrin_orig_ins_offs;
+extern u32 kvm_emulate_mtsrin_len;
+extern u32 kvm_emulate_mtsrin[];
+
+static void kvm_patch_ins_mtsrin(u32 *inst, u32 rt, u32 rb)
+{
+	u32 *p;
+	int distance_start;
+	int distance_end;
+	ulong next_inst;
+
+	p = kvm_alloc(kvm_emulate_mtsrin_len * 4);
+	if (!p)
+		return;
+
+	/* Find out where we are and put everything there */
+	distance_start = (ulong)p - (ulong)inst;
+	next_inst = ((ulong)inst + 4);
+	distance_end = next_inst - (ulong)&p[kvm_emulate_mtsrin_branch_offs];
+
+	/* Make sure we only write valid b instructions */
+	if (distance_start > KVM_INST_B_MAX) {
+		kvm_patching_worked = false;
+		return;
+	}
+
+	/* Modify the chunk to fit the invocation */
+	memcpy(p, kvm_emulate_mtsrin, kvm_emulate_mtsrin_len * 4);
+	p[kvm_emulate_mtsrin_branch_offs] |= distance_end & KVM_INST_B_MASK;
+	p[kvm_emulate_mtsrin_reg1_offs] |= (rb << 10);
+	p[kvm_emulate_mtsrin_reg2_offs] |= rt;
+	p[kvm_emulate_mtsrin_orig_ins_offs] = *inst;
+	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtsrin_len * 4);
+
+	/* Patch the invocation */
+	kvm_patch_ins_b(inst, distance_start);
+}
+
+#endif
+
 static void kvm_map_magic_page(void *data)
 {
 	u32 *features = data;
@@ -360,6 +408,18 @@ static void kvm_check_ins(u32 *inst, u32 features)
 		break;
 	}
 
+	switch (inst_no_rt & ~KVM_MASK_RB) {
+#ifdef CONFIG_PPC_BOOK3S_32
+	case KVM_INST_MTSRIN:
+		if (features & KVM_MAGIC_FEAT_SR) {
+			u32 inst_rb = _inst & KVM_MASK_RB;
+			kvm_patch_ins_mtsrin(inst, inst_rt, inst_rb);
+		}
+		break;
+		break;
+#endif
+	}
+
 	switch (_inst) {
 #ifdef CONFIG_BOOKE
 	case KVM_INST_WRTEEI_0:
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 3199f65ede2c..a6e97e7a55e0 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -245,3 +245,53 @@ kvm_emulate_wrteei_ee_offs:
 .global kvm_emulate_wrteei_len
 kvm_emulate_wrteei_len:
 	.long (kvm_emulate_wrteei_end - kvm_emulate_wrteei) / 4
+
+
+.global kvm_emulate_mtsrin
+kvm_emulate_mtsrin:
+
+	SCRATCH_SAVE
+
+	LL64(r31, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+	andi.	r31, r31, MSR_DR | MSR_IR
+	beq	kvm_emulate_mtsrin_reg1
+
+	SCRATCH_RESTORE
+
+kvm_emulate_mtsrin_orig_ins:
+	nop
+	b	kvm_emulate_mtsrin_branch
+
+kvm_emulate_mtsrin_reg1:
+	/* rX >> 26 */
+	rlwinm  r30,r0,6,26,29
+
+kvm_emulate_mtsrin_reg2:
+	stw	r0, (KVM_MAGIC_PAGE + KVM_MAGIC_SR)(r30)
+
+	SCRATCH_RESTORE
+
+	/* Go back to caller */
+kvm_emulate_mtsrin_branch:
+	b	.
+kvm_emulate_mtsrin_end:
+
+.global kvm_emulate_mtsrin_branch_offs
+kvm_emulate_mtsrin_branch_offs:
+	.long (kvm_emulate_mtsrin_branch - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_reg1_offs
+kvm_emulate_mtsrin_reg1_offs:
+	.long (kvm_emulate_mtsrin_reg1 - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_reg2_offs
+kvm_emulate_mtsrin_reg2_offs:
+	.long (kvm_emulate_mtsrin_reg2 - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_orig_ins_offs
+kvm_emulate_mtsrin_orig_ins_offs:
+	.long (kvm_emulate_mtsrin_orig_ins - kvm_emulate_mtsrin) / 4
+
+.global kvm_emulate_mtsrin_len
+kvm_emulate_mtsrin_len:
+	.long (kvm_emulate_mtsrin_end - kvm_emulate_mtsrin) / 4
-- 
cgit v1.2.1


From 512ba59ed9c580b5e5575beda0041bb19a641127 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 5 Aug 2010 11:26:04 +0200
Subject: KVM: PPC: Make PV mtmsr work with r30 and r31

So far we've been restricting ourselves to r0-r29 as registers an mtmsr
instruction could use. This was bad, as there are some code paths in
Linux actually using r30.

So let's instead handle all registers gracefully and get rid of that
stupid limitation

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/kvm.c      | 39 ++++++++++++++++++++++++++++++++-------
 arch/powerpc/kernel/kvm_emul.S | 17 ++++++++---------
 2 files changed, 40 insertions(+), 16 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index c8bab24ff8ac..10b681c092ed 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -42,6 +42,7 @@
 #define KVM_INST_B_MAX		0x01ffffff
 
 #define KVM_MASK_RT		0x03e00000
+#define KVM_RT_30		0x03c00000
 #define KVM_MASK_RB		0x0000f800
 #define KVM_INST_MFMSR		0x7c0000a6
 #define KVM_INST_MFSPR_SPRG0	0x7c1042a6
@@ -82,6 +83,15 @@ static inline void kvm_patch_ins(u32 *inst, u32 new_inst)
 	flush_icache_range((ulong)inst, (ulong)inst + 4);
 }
 
+static void kvm_patch_ins_ll(u32 *inst, long addr, u32 rt)
+{
+#ifdef CONFIG_64BIT
+	kvm_patch_ins(inst, KVM_INST_LD | rt | (addr & 0x0000fffc));
+#else
+	kvm_patch_ins(inst, KVM_INST_LWZ | rt | (addr & 0x0000fffc));
+#endif
+}
+
 static void kvm_patch_ins_ld(u32 *inst, long addr, u32 rt)
 {
 #ifdef CONFIG_64BIT
@@ -186,7 +196,6 @@ static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
 extern u32 kvm_emulate_mtmsr_branch_offs;
 extern u32 kvm_emulate_mtmsr_reg1_offs;
 extern u32 kvm_emulate_mtmsr_reg2_offs;
-extern u32 kvm_emulate_mtmsr_reg3_offs;
 extern u32 kvm_emulate_mtmsr_orig_ins_offs;
 extern u32 kvm_emulate_mtmsr_len;
 extern u32 kvm_emulate_mtmsr[];
@@ -216,9 +225,27 @@ static void kvm_patch_ins_mtmsr(u32 *inst, u32 rt)
 	/* Modify the chunk to fit the invocation */
 	memcpy(p, kvm_emulate_mtmsr, kvm_emulate_mtmsr_len * 4);
 	p[kvm_emulate_mtmsr_branch_offs] |= distance_end & KVM_INST_B_MASK;
-	p[kvm_emulate_mtmsr_reg1_offs] |= rt;
-	p[kvm_emulate_mtmsr_reg2_offs] |= rt;
-	p[kvm_emulate_mtmsr_reg3_offs] |= rt;
+
+	/* Make clobbered registers work too */
+	switch (get_rt(rt)) {
+	case 30:
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg1_offs],
+				 magic_var(scratch2), KVM_RT_30);
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg2_offs],
+				 magic_var(scratch2), KVM_RT_30);
+		break;
+	case 31:
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg1_offs],
+				 magic_var(scratch1), KVM_RT_30);
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsr_reg2_offs],
+				 magic_var(scratch1), KVM_RT_30);
+		break;
+	default:
+		p[kvm_emulate_mtmsr_reg1_offs] |= rt;
+		p[kvm_emulate_mtmsr_reg2_offs] |= rt;
+		break;
+	}
+
 	p[kvm_emulate_mtmsr_orig_ins_offs] = *inst;
 	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsr_len * 4);
 
@@ -402,9 +429,7 @@ static void kvm_check_ins(u32 *inst, u32 features)
 		break;
 	case KVM_INST_MTMSR:
 	case KVM_INST_MTMSRD_L0:
-		/* We use r30 and r31 during the hook */
-		if (get_rt(inst_rt) < 30)
-			kvm_patch_ins_mtmsr(inst, inst_rt);
+		kvm_patch_ins_mtmsr(inst, inst_rt);
 		break;
 	}
 
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index a6e97e7a55e0..65305325250b 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -135,7 +135,8 @@ kvm_emulate_mtmsr:
 
 	/* Find the changed bits between old and new MSR */
 kvm_emulate_mtmsr_reg1:
-	xor	r31, r0, r31
+	ori	r30, r0, 0
+	xor	r31, r30, r31
 
 	/* Check if we need to really do mtmsr */
 	LOAD_REG_IMMEDIATE(r30, MSR_CRITICAL_BITS)
@@ -156,14 +157,17 @@ kvm_emulate_mtmsr_orig_ins:
 
 maybe_stay_in_guest:
 
+	/* Get the target register in r30 */
+kvm_emulate_mtmsr_reg2:
+	ori	r30, r0, 0
+
 	/* Check if we have to fetch an interrupt */
 	lwz	r31, (KVM_MAGIC_PAGE + KVM_MAGIC_INT)(0)
 	cmpwi	r31, 0
 	beq+	no_mtmsr
 
 	/* Check if we may trigger an interrupt */
-kvm_emulate_mtmsr_reg2:
-	andi.	r31, r0, MSR_EE
+	andi.	r31, r30, MSR_EE
 	beq	no_mtmsr
 
 	b	do_mtmsr
@@ -171,8 +175,7 @@ kvm_emulate_mtmsr_reg2:
 no_mtmsr:
 
 	/* Put MSR into magic page because we don't call mtmsr */
-kvm_emulate_mtmsr_reg3:
-	STL64(r0, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
+	STL64(r30, KVM_MAGIC_PAGE + KVM_MAGIC_MSR, 0)
 
 	SCRATCH_RESTORE
 
@@ -193,10 +196,6 @@ kvm_emulate_mtmsr_reg1_offs:
 kvm_emulate_mtmsr_reg2_offs:
 	.long (kvm_emulate_mtmsr_reg2 - kvm_emulate_mtmsr) / 4
 
-.global kvm_emulate_mtmsr_reg3_offs
-kvm_emulate_mtmsr_reg3_offs:
-	.long (kvm_emulate_mtmsr_reg3 - kvm_emulate_mtmsr) / 4
-
 .global kvm_emulate_mtmsr_orig_ins_offs
 kvm_emulate_mtmsr_orig_ins_offs:
 	.long (kvm_emulate_mtmsr_orig_ins - kvm_emulate_mtmsr) / 4
-- 
cgit v1.2.1


From 9ee18b1e08e6a5648aeaaf998eabc72b5304cc17 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 5 Aug 2010 12:24:40 +0200
Subject: KVM: PPC: Update int_pending also on dequeue

When having a decrementor interrupt pending, the dequeuing happens manually
through an mtdec instruction. This instruction simply calls dequeue on that
interrupt, so the int_pending hint doesn't get updated.

This patch enables updating the int_pending hint also on dequeue, thus
correctly enabling guests to stay in guest contexts more often.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 02a9cb165d53..7adea6320654 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -201,6 +201,9 @@ static void kvmppc_book3s_dequeue_irqprio(struct kvm_vcpu *vcpu,
 {
 	clear_bit(kvmppc_book3s_vec2irqprio(vec),
 		  &vcpu->arch.pending_exceptions);
+
+	if (!vcpu->arch.pending_exceptions)
+		vcpu->arch.shared->int_pending = 0;
 }
 
 void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
-- 
cgit v1.2.1


From df08bd10266ce6132278f6b4ddc4bb0a12330b56 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Thu, 5 Aug 2010 15:44:41 +0200
Subject: KVM: PPC: Make PV mtmsrd L=1 work with r30 and r31

We had an arbitrary limitation in mtmsrd L=1 that kept us from using r30 and
r31 as input registers. Let's get rid of that and get more potential speedups!

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/kvm.c      | 21 +++++++++++++++++----
 arch/powerpc/kernel/kvm_emul.S |  8 +++++++-
 2 files changed, 24 insertions(+), 5 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 10b681c092ed..48a033865410 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -158,6 +158,7 @@ static u32 *kvm_alloc(int len)
 
 extern u32 kvm_emulate_mtmsrd_branch_offs;
 extern u32 kvm_emulate_mtmsrd_reg_offs;
+extern u32 kvm_emulate_mtmsrd_orig_ins_offs;
 extern u32 kvm_emulate_mtmsrd_len;
 extern u32 kvm_emulate_mtmsrd[];
 
@@ -186,7 +187,21 @@ static void kvm_patch_ins_mtmsrd(u32 *inst, u32 rt)
 	/* Modify the chunk to fit the invocation */
 	memcpy(p, kvm_emulate_mtmsrd, kvm_emulate_mtmsrd_len * 4);
 	p[kvm_emulate_mtmsrd_branch_offs] |= distance_end & KVM_INST_B_MASK;
-	p[kvm_emulate_mtmsrd_reg_offs] |= rt;
+	switch (get_rt(rt)) {
+	case 30:
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsrd_reg_offs],
+				 magic_var(scratch2), KVM_RT_30);
+		break;
+	case 31:
+		kvm_patch_ins_ll(&p[kvm_emulate_mtmsrd_reg_offs],
+				 magic_var(scratch1), KVM_RT_30);
+		break;
+	default:
+		p[kvm_emulate_mtmsrd_reg_offs] |= rt;
+		break;
+	}
+
+	p[kvm_emulate_mtmsrd_orig_ins_offs] = *inst;
 	flush_icache_range((ulong)p, (ulong)p + kvm_emulate_mtmsrd_len * 4);
 
 	/* Patch the invocation */
@@ -423,9 +438,7 @@ static void kvm_check_ins(u32 *inst, u32 features)
 
 	/* Rewrites */
 	case KVM_INST_MTMSRD_L1:
-		/* We use r30 and r31 during the hook */
-		if (get_rt(inst_rt) < 30)
-			kvm_patch_ins_mtmsrd(inst, inst_rt);
+		kvm_patch_ins_mtmsrd(inst, inst_rt);
 		break;
 	case KVM_INST_MTMSR:
 	case KVM_INST_MTMSRD_L0:
diff --git a/arch/powerpc/kernel/kvm_emul.S b/arch/powerpc/kernel/kvm_emul.S
index 65305325250b..f2b1b2523e61 100644
--- a/arch/powerpc/kernel/kvm_emul.S
+++ b/arch/powerpc/kernel/kvm_emul.S
@@ -78,7 +78,8 @@ kvm_emulate_mtmsrd:
 
 	/* OR the register's (MSR_EE|MSR_RI) on MSR */
 kvm_emulate_mtmsrd_reg:
-	andi.	r30, r0, (MSR_EE|MSR_RI)
+	ori	r30, r0, 0
+	andi.	r30, r30, (MSR_EE|MSR_RI)
 	or	r31, r31, r30
 
 	/* Put MSR back into magic page */
@@ -96,6 +97,7 @@ kvm_emulate_mtmsrd_reg:
 	SCRATCH_RESTORE
 
 	/* Nag hypervisor */
+kvm_emulate_mtmsrd_orig_ins:
 	tlbsync
 
 	b	kvm_emulate_mtmsrd_branch
@@ -117,6 +119,10 @@ kvm_emulate_mtmsrd_branch_offs:
 kvm_emulate_mtmsrd_reg_offs:
 	.long (kvm_emulate_mtmsrd_reg - kvm_emulate_mtmsrd) / 4
 
+.global kvm_emulate_mtmsrd_orig_ins_offs
+kvm_emulate_mtmsrd_orig_ins_offs:
+	.long (kvm_emulate_mtmsrd_orig_ins - kvm_emulate_mtmsrd) / 4
+
 .global kvm_emulate_mtmsrd_len
 kvm_emulate_mtmsrd_len:
 	.long (kvm_emulate_mtmsrd_end - kvm_emulate_mtmsrd) / 4
-- 
cgit v1.2.1


From ad0873763a83e7b31ba87a85ec2027dd6a9d7b55 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 17 Aug 2010 11:41:44 +0200
Subject: KVM: PPC: Force enable nap on KVM

There are some heuristics in the PPC power management code that try to find
out if the particular hardware we're running on supports proper power management
or just hangs the machine when going into nap mode.

Since we know that KVM is safe with nap, let's force enable it in the PV code
once we're certain that we are on a KVM VM.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/kvm.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 48a033865410..669d989be1d6 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -582,6 +582,9 @@ static int __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
 		kvm_use_magic_page();
 
+	/* Enable napping */
+	powersave_nap = 1;
+
 free_tmp:
 	kvm_free_tmp();
 
-- 
cgit v1.2.1


From 8b6db3bc965c204db6868d4005808b4fdc9c46d7 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Sun, 15 Aug 2010 08:04:24 +0200
Subject: KVM: PPC: Implement correct SID mapping on Book3s_32

Up until now we were doing segment mappings wrong on Book3s_32. For Book3s_64
we were using a trick where we know that a single mmu_context gives us 16 bits
of context ids.

The mm system on Book3s_32 instead uses a clever algorithm to distribute VSIDs
across the available range, so a context id really only gives us 16 available
VSIDs.

To keep at least a few guest processes in the SID shadow, let's map a number of
contexts that we can use as VSID pool. This makes the code be actually correct
and shouldn't hurt performance too much.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_book3s.h | 15 +++++++--
 arch/powerpc/kvm/book3s_32_mmu_host.c | 57 +++++++++++++++++++----------------
 arch/powerpc/kvm/book3s_64_mmu_host.c |  8 ++---
 3 files changed, 48 insertions(+), 32 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index be8aac24ba83..d62e703f1214 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -60,6 +60,13 @@ struct kvmppc_sid_map {
 #define SID_MAP_NUM     (1 << SID_MAP_BITS)
 #define SID_MAP_MASK    (SID_MAP_NUM - 1)
 
+#ifdef CONFIG_PPC_BOOK3S_64
+#define SID_CONTEXTS	1
+#else
+#define SID_CONTEXTS	128
+#define VSID_POOL_SIZE	(SID_CONTEXTS * 16)
+#endif
+
 struct kvmppc_vcpu_book3s {
 	struct kvm_vcpu vcpu;
 	struct kvmppc_book3s_shadow_vcpu *shadow_vcpu;
@@ -78,10 +85,14 @@ struct kvmppc_vcpu_book3s {
 	u64 sdr1;
 	u64 hior;
 	u64 msr_mask;
-	u64 vsid_first;
 	u64 vsid_next;
+#ifdef CONFIG_PPC_BOOK3S_32
+	u32 vsid_pool[VSID_POOL_SIZE];
+#else
+	u64 vsid_first;
 	u64 vsid_max;
-	int context_id;
+#endif
+	int context_id[SID_CONTEXTS];
 	ulong prog_flags; /* flags to inject when giving a 700 trap */
 };
 
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 57dddeb23b9b..9fecbfbce773 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -275,18 +275,15 @@ static struct kvmppc_sid_map *create_sid_map(struct kvm_vcpu *vcpu, u64 gvsid)
 	backwards_map = !backwards_map;
 
 	/* Uh-oh ... out of mappings. Let's flush! */
-	if (vcpu_book3s->vsid_next >= vcpu_book3s->vsid_max) {
-		vcpu_book3s->vsid_next = vcpu_book3s->vsid_first;
+	if (vcpu_book3s->vsid_next >= VSID_POOL_SIZE) {
+		vcpu_book3s->vsid_next = 0;
 		memset(vcpu_book3s->sid_map, 0,
 		       sizeof(struct kvmppc_sid_map) * SID_MAP_NUM);
 		kvmppc_mmu_pte_flush(vcpu, 0, 0);
 		kvmppc_mmu_flush_segments(vcpu);
 	}
-	map->host_vsid = vcpu_book3s->vsid_next;
-
-	/* Would have to be 111 to be completely aligned with the rest of
-	   Linux, but that is just way too little space! */
-	vcpu_book3s->vsid_next+=1;
+	map->host_vsid = vcpu_book3s->vsid_pool[vcpu_book3s->vsid_next];
+	vcpu_book3s->vsid_next++;
 
 	map->guest_vsid = gvsid;
 	map->valid = true;
@@ -333,40 +330,38 @@ void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
 {
+	int i;
+
 	kvmppc_mmu_hpte_destroy(vcpu);
 	preempt_disable();
-	__destroy_context(to_book3s(vcpu)->context_id);
+	for (i = 0; i < SID_CONTEXTS; i++)
+		__destroy_context(to_book3s(vcpu)->context_id[i]);
 	preempt_enable();
 }
 
 /* From mm/mmu_context_hash32.c */
-#define CTX_TO_VSID(ctx) (((ctx) * (897 * 16)) & 0xffffff)
+#define CTX_TO_VSID(c, id)	((((c) * (897 * 16)) + (id * 0x111)) & 0xffffff)
 
 int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	int err;
 	ulong sdr1;
+	int i;
+	int j;
 
-	err = __init_new_context();
-	if (err < 0)
-		return -1;
-	vcpu3s->context_id = err;
-
-	vcpu3s->vsid_max = CTX_TO_VSID(vcpu3s->context_id + 1) - 1;
-	vcpu3s->vsid_first = CTX_TO_VSID(vcpu3s->context_id);
-
-#if 0 /* XXX still doesn't guarantee uniqueness */
-	/* We could collide with the Linux vsid space because the vsid
-	 * wraps around at 24 bits. We're safe if we do our own space
-	 * though, so let's always set the highest bit. */
+	for (i = 0; i < SID_CONTEXTS; i++) {
+		err = __init_new_context();
+		if (err < 0)
+			goto init_fail;
+		vcpu3s->context_id[i] = err;
 
-	vcpu3s->vsid_max |= 0x00800000;
-	vcpu3s->vsid_first |= 0x00800000;
-#endif
-	BUG_ON(vcpu3s->vsid_max < vcpu3s->vsid_first);
+		/* Remember context id for this combination */
+		for (j = 0; j < 16; j++)
+			vcpu3s->vsid_pool[(i * 16) + j] = CTX_TO_VSID(err, j);
+	}
 
-	vcpu3s->vsid_next = vcpu3s->vsid_first;
+	vcpu3s->vsid_next = 0;
 
 	/* Remember where the HTAB is */
 	asm ( "mfsdr1 %0" : "=r"(sdr1) );
@@ -376,4 +371,14 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
 	kvmppc_mmu_hpte_init(vcpu);
 
 	return 0;
+
+init_fail:
+	for (j = 0; j < i; j++) {
+		if (!vcpu3s->context_id[j])
+			continue;
+
+		__destroy_context(to_book3s(vcpu)->context_id[j]);
+	}
+
+	return -1;
 }
diff --git a/arch/powerpc/kvm/book3s_64_mmu_host.c b/arch/powerpc/kvm/book3s_64_mmu_host.c
index 4040c8d16ad5..fa2f08434ba5 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_host.c
@@ -286,7 +286,7 @@ void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu)
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvmppc_mmu_hpte_destroy(vcpu);
-	__destroy_context(to_book3s(vcpu)->context_id);
+	__destroy_context(to_book3s(vcpu)->context_id[0]);
 }
 
 int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
@@ -297,10 +297,10 @@ int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
 	err = __init_new_context();
 	if (err < 0)
 		return -1;
-	vcpu3s->context_id = err;
+	vcpu3s->context_id[0] = err;
 
-	vcpu3s->vsid_max = ((vcpu3s->context_id + 1) << USER_ESID_BITS) - 1;
-	vcpu3s->vsid_first = vcpu3s->context_id << USER_ESID_BITS;
+	vcpu3s->vsid_max = ((vcpu3s->context_id[0] + 1) << USER_ESID_BITS) - 1;
+	vcpu3s->vsid_first = vcpu3s->context_id[0] << USER_ESID_BITS;
 	vcpu3s->vsid_next = vcpu3s->vsid_first;
 
 	kvmppc_mmu_hpte_init(vcpu);
-- 
cgit v1.2.1


From 296c19d0b4072dd9594daeec532563e56bddd119 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Sun, 15 Aug 2010 08:39:19 +0200
Subject: KVM: PPC: Don't put MSR_POW in MSR

On Book3S a mtmsr with the MSR_POW bit set indicates that the OS is in
idle and only needs to be waked up on the next interrupt.

Now, unfortunately we let that bit slip into the stored MSR value which
is not what the real CPU does, so that we ended up executing code like
this:

	r = mfmsr();
	/* r containts MSR_POW */
	mtmsr(r | MSR_EE);

This obviously breaks, as we're going into idle mode in code sections that
don't expect to be idling.

This patch masks MSR_POW out of the stored MSR value on wakeup, making
guests happy again.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/book3s.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 7adea6320654..5833df7e8ccc 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -134,10 +134,14 @@ void kvmppc_set_msr(struct kvm_vcpu *vcpu, u64 msr)
 	vcpu->arch.shared->msr = msr;
 	kvmppc_recalc_shadow_msr(vcpu);
 
-	if (msr & (MSR_WE|MSR_POW)) {
+	if (msr & MSR_POW) {
 		if (!vcpu->arch.pending_exceptions) {
 			kvm_vcpu_block(vcpu);
 			vcpu->stat.halt_wakeup++;
+
+			/* Unset POW bit after we woke up */
+			msr &= ~MSR_POW;
+			vcpu->arch.shared->msr = msr;
 		}
 	}
 
-- 
cgit v1.2.1


From 082decf29a9fe5bd5dcbfb26223e44edd9deabed Mon Sep 17 00:00:00 2001
From: Hollis Blanchard <hollis_blanchard@mentor.com>
Date: Sat, 7 Aug 2010 10:33:56 -0700
Subject: KVM: PPC: initialize IVORs in addition to IVPR

Developers can now tell at a glace the exact type of the premature interrupt,
instead of just knowing that there was some premature interrupt.

Signed-off-by: Hollis Blanchard <hollis_blanchard@mentor.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/booke.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index c604277011a6..835f6d0e4f20 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -497,15 +497,19 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 /* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
+	int i;
+
 	vcpu->arch.pc = 0;
 	vcpu->arch.shared->msr = 0;
 	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
 
 	vcpu->arch.shadow_pid = 1;
 
-	/* Eye-catching number so we know if the guest takes an interrupt
-	 * before it's programmed its own IVPR. */
+	/* Eye-catching numbers so we know if the guest takes an interrupt
+	 * before it's programmed its own IVPR/IVORs. */
 	vcpu->arch.ivpr = 0x55550000;
+	for (i = 0; i < BOOKE_IRQPRIO_MAX; i++)
+		vcpu->arch.ivor[i] = 0x7700 | i * 4;
 
 	kvmppc_init_timing_stats(vcpu);
 
-- 
cgit v1.2.1


From 0b3bafc8e5867039e265869749abbb7ea6dd2c8b Mon Sep 17 00:00:00 2001
From: Hollis Blanchard <hollis_blanchard@mentor.com>
Date: Sat, 7 Aug 2010 10:33:57 -0700
Subject: KVM: PPC: fix compilation of "dump tlbs" debug function

Missing local variable.

Signed-off-by: Hollis Blanchard <hollis_blanchard@mentor.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/44x_tlb.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 9f71b8d6eb0d..5f3cff83e089 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -47,6 +47,7 @@
 #ifdef DEBUG
 void kvmppc_dump_tlbs(struct kvm_vcpu *vcpu)
 {
+	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
 	struct kvmppc_44x_tlbe *tlbe;
 	int i;
 
-- 
cgit v1.2.1


From ebc65874e9e8f3b8bbbc69aa49acd7489cd41c52 Mon Sep 17 00:00:00 2001
From: Hollis Blanchard <hollis_blanchard@mentor.com>
Date: Sat, 7 Aug 2010 10:33:58 -0700
Subject: KVM: PPC: allow ppc440gp to pass the compatibility check

Match only the first part of cur_cpu_spec->platform.

440GP (the first 440 processor) is identified by the string "ppc440gp", while
all later 440 processors use simply "ppc440".

Signed-off-by: Hollis Blanchard <hollis_blanchard@mentor.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/44x.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/44x.c b/arch/powerpc/kvm/44x.c
index e7b1f3fca5dc..74d0e7421143 100644
--- a/arch/powerpc/kvm/44x.c
+++ b/arch/powerpc/kvm/44x.c
@@ -43,7 +43,7 @@ int kvmppc_core_check_processor_compat(void)
 {
 	int r;
 
-	if (strcmp(cur_cpu_spec->platform, "ppc440") == 0)
+	if (strncmp(cur_cpu_spec->platform, "ppc440", 6) == 0)
 		r = 0;
 	else
 		r = -ENOTSUPP;
@@ -72,6 +72,7 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 	/* Since the guest can directly access the timebase, it must know the
 	 * real timebase frequency. Accordingly, it must see the state of
 	 * CCR1[TCS]. */
+	/* XXX CCR1 doesn't exist on all 440 SoCs. */
 	vcpu->arch.ccr1 = mfspr(SPRN_CCR1);
 
 	for (i = 0; i < ARRAY_SIZE(vcpu_44x->shadow_refs); i++)
-- 
cgit v1.2.1


From 591bd8e7b4c8b9246d7a1c81ffbd28e35dc5de4e Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 17 Aug 2010 22:08:39 +0200
Subject: KVM: PPC: Enable napping only for Book3s_64

Before I incorrectly enabled napping also for BookE, which would result in
needless dcache flushes. Since we only need to force enable napping on
Book3s_64 because it doesn't go into MSR_POW otherwise, we can just #ifdef
that code to this particular platform.

Reported-by: Scott Wood <scottwood@freescale.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kernel/kvm.c | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kernel/kvm.c b/arch/powerpc/kernel/kvm.c
index 669d989be1d6..428d0e538aec 100644
--- a/arch/powerpc/kernel/kvm.c
+++ b/arch/powerpc/kernel/kvm.c
@@ -582,8 +582,10 @@ static int __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_MAGIC_PAGE))
 		kvm_use_magic_page();
 
+#ifdef CONFIG_PPC_BOOK3S_64
 	/* Enable napping */
 	powersave_nap = 1;
+#endif
 
 free_tmp:
 	kvm_free_tmp();
-- 
cgit v1.2.1


From 17bd158006a33615270f9dba15c62f49bd447435 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 30 Aug 2010 10:44:15 +0200
Subject: KVM: PPC: Implement Level interrupts on Book3S

The current interrupt logic is just completely broken. We get a notification
from user space, telling us that an interrupt is there. But then user space
expects us that we just acknowledge an interrupt once we deliver it to the
guest.

This is not how real hardware works though. On real hardware, the interrupt
controller pulls the external interrupt line until it gets notified that the
interrupt was received.

So in reality we have two events: pulling and letting go of the interrupt line.

To maintain backwards compatibility, I added a new request for the pulling
part. The letting go part was implemented earlier already.

With this in place, we can now finally start guests that do not randomly stall
and stop to work at random times.

This patch implements above logic for Book3S.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm.h     |  1 +
 arch/powerpc/include/asm/kvm_asm.h |  4 +++-
 arch/powerpc/kvm/book3s.c          | 30 +++++++++++++++++++++++++++---
 3 files changed, 31 insertions(+), 4 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm.h b/arch/powerpc/include/asm/kvm.h
index 6c5547d82bbe..18ea6963ad77 100644
--- a/arch/powerpc/include/asm/kvm.h
+++ b/arch/powerpc/include/asm/kvm.h
@@ -86,5 +86,6 @@ struct kvm_guest_debug_arch {
 
 #define KVM_INTERRUPT_SET	-1U
 #define KVM_INTERRUPT_UNSET	-2U
+#define KVM_INTERRUPT_SET_LEVEL	-3U
 
 #endif /* __LINUX_KVM_POWERPC_H */
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index c5ea4cda34b3..5b7504674397 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -58,6 +58,7 @@
 #define BOOK3S_INTERRUPT_INST_STORAGE	0x400
 #define BOOK3S_INTERRUPT_INST_SEGMENT	0x480
 #define BOOK3S_INTERRUPT_EXTERNAL	0x500
+#define BOOK3S_INTERRUPT_EXTERNAL_LEVEL	0x501
 #define BOOK3S_INTERRUPT_ALIGNMENT	0x600
 #define BOOK3S_INTERRUPT_PROGRAM	0x700
 #define BOOK3S_INTERRUPT_FP_UNAVAIL	0x800
@@ -84,7 +85,8 @@
 #define BOOK3S_IRQPRIO_EXTERNAL			13
 #define BOOK3S_IRQPRIO_DECREMENTER		14
 #define BOOK3S_IRQPRIO_PERFORMANCE_MONITOR	15
-#define BOOK3S_IRQPRIO_MAX			16
+#define BOOK3S_IRQPRIO_EXTERNAL_LEVEL		16
+#define BOOK3S_IRQPRIO_MAX			17
 
 #define BOOK3S_HFLAG_DCBZ32			0x1
 #define BOOK3S_HFLAG_SLB			0x2
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 5833df7e8ccc..e316847c08c0 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -186,6 +186,7 @@ static int kvmppc_book3s_vec2irqprio(unsigned int vec)
 	case 0x400: prio = BOOK3S_IRQPRIO_INST_STORAGE;		break;
 	case 0x480: prio = BOOK3S_IRQPRIO_INST_SEGMENT;		break;
 	case 0x500: prio = BOOK3S_IRQPRIO_EXTERNAL;		break;
+	case 0x501: prio = BOOK3S_IRQPRIO_EXTERNAL_LEVEL;	break;
 	case 0x600: prio = BOOK3S_IRQPRIO_ALIGNMENT;		break;
 	case 0x700: prio = BOOK3S_IRQPRIO_PROGRAM;		break;
 	case 0x800: prio = BOOK3S_IRQPRIO_FP_UNAVAIL;		break;
@@ -246,13 +247,19 @@ void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
 void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                 struct kvm_interrupt *irq)
 {
-	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
+	unsigned int vec = BOOK3S_INTERRUPT_EXTERNAL;
+
+	if (irq->irq == KVM_INTERRUPT_SET_LEVEL)
+		vec = BOOK3S_INTERRUPT_EXTERNAL_LEVEL;
+
+	kvmppc_book3s_queue_irqprio(vcpu, vec);
 }
 
 void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
                                   struct kvm_interrupt *irq)
 {
 	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL);
+	kvmppc_book3s_dequeue_irqprio(vcpu, BOOK3S_INTERRUPT_EXTERNAL_LEVEL);
 }
 
 int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
@@ -281,6 +288,7 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 		vec = BOOK3S_INTERRUPT_DECREMENTER;
 		break;
 	case BOOK3S_IRQPRIO_EXTERNAL:
+	case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
 		deliver = (vcpu->arch.shared->msr & MSR_EE) && !crit;
 		vec = BOOK3S_INTERRUPT_EXTERNAL;
 		break;
@@ -343,6 +351,23 @@ int kvmppc_book3s_irqprio_deliver(struct kvm_vcpu *vcpu, unsigned int priority)
 	return deliver;
 }
 
+/*
+ * This function determines if an irqprio should be cleared once issued.
+ */
+static bool clear_irqprio(struct kvm_vcpu *vcpu, unsigned int priority)
+{
+	switch (priority) {
+		case BOOK3S_IRQPRIO_DECREMENTER:
+			/* DEC interrupts get cleared by mtdec */
+			return false;
+		case BOOK3S_IRQPRIO_EXTERNAL_LEVEL:
+			/* External interrupts get cleared by userspace */
+			return false;
+	}
+
+	return true;
+}
+
 void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 {
 	unsigned long *pending = &vcpu->arch.pending_exceptions;
@@ -356,8 +381,7 @@ void kvmppc_core_deliver_interrupts(struct kvm_vcpu *vcpu)
 	priority = __ffs(*pending);
 	while (priority < BOOK3S_IRQPRIO_MAX) {
 		if (kvmppc_book3s_irqprio_deliver(vcpu, priority) &&
-		    (priority != BOOK3S_IRQPRIO_DECREMENTER)) {
-			/* DEC interrupts get cleared by mtdec */
+		    clear_irqprio(vcpu, priority)) {
 			clear_bit(priority, &vcpu->arch.pending_exceptions);
 			break;
 		}
-- 
cgit v1.2.1


From 7b4203e8cb5c5d9bc49da62b7a6fa4ba876a1b3f Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 30 Aug 2010 13:50:45 +0200
Subject: KVM: PPC: Expose level based interrupt cap

Now that we have all the level interrupt magic in place, let's
expose the capability to user space, so it can make use of it!

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

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 028891c0baff..2f87a1627f6c 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -192,6 +192,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PPC_SEGSTATE:
 	case KVM_CAP_PPC_PAIRED_SINGLES:
 	case KVM_CAP_PPC_UNSET_IRQ:
+	case KVM_CAP_PPC_IRQ_LEVEL:
 	case KVM_CAP_ENABLE_CAP:
 	case KVM_CAP_PPC_OSI:
 	case KVM_CAP_PPC_GET_PVINFO:
-- 
cgit v1.2.1


From c5335f17651de5075313524ccc3881527268966f Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Mon, 30 Aug 2010 14:03:24 +0200
Subject: KVM: PPC: Implement level interrupts for BookE

BookE also wants to support level based interrupts, so let's implement
all the necessary logic there. We need to trick a bit here because the
irqprios are 1:1 assigned to architecture defined values. But since there
is some space left there, we can just pick a random one and move it later
on - it's internal anyways.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/booke.c | 17 +++++++++++++++--
 arch/powerpc/kvm/booke.h |  4 +++-
 2 files changed, 18 insertions(+), 3 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 835f6d0e4f20..77575d08c818 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -131,13 +131,19 @@ void kvmppc_core_dequeue_dec(struct kvm_vcpu *vcpu)
 void kvmppc_core_queue_external(struct kvm_vcpu *vcpu,
                                 struct kvm_interrupt *irq)
 {
-	kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_EXTERNAL);
+	unsigned int prio = BOOKE_IRQPRIO_EXTERNAL;
+
+	if (irq->irq == KVM_INTERRUPT_SET_LEVEL)
+		prio = BOOKE_IRQPRIO_EXTERNAL_LEVEL;
+
+	kvmppc_booke_queue_irqprio(vcpu, prio);
 }
 
 void kvmppc_core_dequeue_external(struct kvm_vcpu *vcpu,
                                   struct kvm_interrupt *irq)
 {
 	clear_bit(BOOKE_IRQPRIO_EXTERNAL, &vcpu->arch.pending_exceptions);
+	clear_bit(BOOKE_IRQPRIO_EXTERNAL_LEVEL, &vcpu->arch.pending_exceptions);
 }
 
 /* Deliver the interrupt of the corresponding priority, if possible. */
@@ -150,6 +156,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	ulong crit_raw = vcpu->arch.shared->critical;
 	ulong crit_r1 = kvmppc_get_gpr(vcpu, 1);
 	bool crit;
+	bool keep_irq = false;
 
 	/* Truncate crit indicators in 32 bit mode */
 	if (!(vcpu->arch.shared->msr & MSR_SF)) {
@@ -162,6 +169,11 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	/* ... and we're in supervisor mode */
 	crit = crit && !(vcpu->arch.shared->msr & MSR_PR);
 
+	if (priority == BOOKE_IRQPRIO_EXTERNAL_LEVEL) {
+		priority = BOOKE_IRQPRIO_EXTERNAL;
+		keep_irq = true;
+	}
+
 	switch (priority) {
 	case BOOKE_IRQPRIO_DTLB_MISS:
 	case BOOKE_IRQPRIO_DATA_STORAGE:
@@ -214,7 +226,8 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 			vcpu->arch.shared->dar = vcpu->arch.queued_dear;
 		kvmppc_set_msr(vcpu, vcpu->arch.shared->msr & msr_mask);
 
-		clear_bit(priority, &vcpu->arch.pending_exceptions);
+		if (!keep_irq)
+			clear_bit(priority, &vcpu->arch.pending_exceptions);
 	}
 
 	return allowed;
diff --git a/arch/powerpc/kvm/booke.h b/arch/powerpc/kvm/booke.h
index 88258acc98fa..492bb7030358 100644
--- a/arch/powerpc/kvm/booke.h
+++ b/arch/powerpc/kvm/booke.h
@@ -46,7 +46,9 @@
 #define BOOKE_IRQPRIO_FIT 17
 #define BOOKE_IRQPRIO_DECREMENTER 18
 #define BOOKE_IRQPRIO_PERFORMANCE_MONITOR 19
-#define BOOKE_IRQPRIO_MAX 19
+/* Internal pseudo-irqprio for level triggered externals */
+#define BOOKE_IRQPRIO_EXTERNAL_LEVEL 20
+#define BOOKE_IRQPRIO_MAX 20
 
 extern unsigned long kvmppc_booke_handlers;
 
-- 
cgit v1.2.1


From 21e537ba149be99c4d31a04949ca6e0770379662 Mon Sep 17 00:00:00 2001
From: Kyle Moffett <Kyle.D.Moffett@boeing.com>
Date: Mon, 30 Aug 2010 11:38:39 -0400
Subject: KVM: PPC: e500_tlb: Fix a minor copy-paste tracing bug

The kvmppc_e500_stlbe_invalidate() function was trying to pass too many
parameters to trace_kvm_stlb_inval().  This appears to be a bad
copy-paste from a call to trace_kvm_stlb_write().

Signed-off-by: Kyle Moffett <Kyle.D.Moffett@boeing.com>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/e500_tlb.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index 092a390876f3..a413883cf948 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -226,8 +226,7 @@ static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 	kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
 	stlbe->mas1 = 0;
-	trace_kvm_stlb_inval(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
-			     stlbe->mas3, stlbe->mas7);
+	trace_kvm_stlb_inval(index_of(tlbsel, esel));
 }
 
 static void kvmppc_e500_tlb1_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
-- 
cgit v1.2.1


From 344941beb9926418663e171a347d1a31d727fe45 Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Tue, 31 Aug 2010 03:45:39 +0200
Subject: KVM: PPC: Fix compile error in e500_tlb.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The e500_tlb.c file didn't compile for me due to the following error:

arch/powerpc/kvm/e500_tlb.c: In function ‘kvmppc_e500_shadow_map’:
arch/powerpc/kvm/e500_tlb.c:300: error: format ‘%lx’ expects type ‘long unsigned int’, but argument 2 has type ‘gfn_t’

So let's explicitly cast the argument to make printk happy.

Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/kvm/e500_tlb.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/kvm/e500_tlb.c b/arch/powerpc/kvm/e500_tlb.c
index a413883cf948..d6d6d47a75a9 100644
--- a/arch/powerpc/kvm/e500_tlb.c
+++ b/arch/powerpc/kvm/e500_tlb.c
@@ -297,7 +297,8 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	/* Get reference to new page. */
 	new_page = gfn_to_page(vcpu_e500->vcpu.kvm, gfn);
 	if (is_error_page(new_page)) {
-		printk(KERN_ERR "Couldn't get guest page for gfn %lx!\n", gfn);
+		printk(KERN_ERR "Couldn't get guest page for gfn %lx!\n",
+				(long)gfn);
 		kvm_release_page_clean(new_page);
 		return;
 	}
-- 
cgit v1.2.1


From 26e673c3003bc8f24bdbbdcb8bc91a78556f579a Mon Sep 17 00:00:00 2001
From: Alexander Graf <agraf@suse.de>
Date: Fri, 3 Sep 2010 10:22:19 +0200
Subject: KVM: PPC: Move of include to __KERNEL__ section

We have to protect the include for linux/of.h by __KERNEL__ so it doesn't
accidently get referenced outside.

This patch fixes this and makes the tree compile again.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Alexander Graf <agraf@suse.de>
---
 arch/powerpc/include/asm/kvm_para.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'arch/powerpc')

diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index d79fd0910964..50533f9adf40 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -21,7 +21,6 @@
 #define __POWERPC_KVM_PARA_H__
 
 #include <linux/types.h>
-#include <linux/of.h>
 
 struct kvm_vcpu_arch_shared {
 	__u64 scratch1;
@@ -54,6 +53,8 @@ struct kvm_vcpu_arch_shared {
 
 #ifdef CONFIG_KVM_GUEST
 
+#include <linux/of.h>
+
 static inline int kvm_para_available(void)
 {
 	struct device_node *hyper_node;
-- 
cgit v1.2.1