Merge branch 'kvm-updates/2.6.36' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.36' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (198 commits)
  KVM: VMX: Fix host GDT.LIMIT corruption
  KVM: MMU: using __xchg_spte more smarter
  KVM: MMU: cleanup spte set and accssed/dirty tracking
  KVM: MMU: don't atomicly set spte if it's not present
  KVM: MMU: fix page dirty tracking lost while sync page
  KVM: MMU: fix broken page accessed tracking with ept enabled
  KVM: MMU: add missing reserved bits check in speculative path
  KVM: MMU: fix mmu notifier invalidate handler for huge spte
  KVM: x86 emulator: fix xchg instruction emulation
  KVM: x86: Call mask notifiers from pic
  KVM: x86: never re-execute instruction with enabled tdp
  KVM: Document KVM_GET_SUPPORTED_CPUID2 ioctl
  KVM: x86: emulator: inc/dec can have lock prefix
  KVM: MMU: Eliminate redundant temporaries in FNAME(fetch)
  KVM: MMU: Validate all gptes during fetch, not just those used for new pages
  KVM: MMU: Simplify spte fetch() function
  KVM: MMU: Add gpte_valid() helper
  KVM: MMU: Add validate_direct_spte() helper
  KVM: MMU: Add drop_large_spte() helper
  KVM: MMU: Use __set_spte to link shadow pages
  ...

46 files changed, 2729 insertions, 1992 deletions

diff --git a/arch/ia64/include/asm/kvm_host.h b/arch/ia64/include/asm/kvm_host.h
index a362e67e0ca..2f229e5de49 100644
--- a/arch/ia64/include/asm/kvm_host.h
+++ b/arch/ia64/include/asm/kvm_host.h
@@ -235,6 +235,7 @@ struct kvm_vm_data {
 #define KVM_REQ_PTC_G		32
 #define KVM_REQ_RESUME		33
 
+#define KVM_HPAGE_GFN_SHIFT(x)	0
 #define KVM_NR_PAGE_SIZES	1
 #define KVM_PAGES_PER_HPAGE(x)	1
 
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 21b701374f7..5cb58655cd5 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -725,8 +725,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	int r;
 	sigset_t sigsaved;
 
-	vcpu_load(vcpu);
-
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
@@ -748,7 +746,6 @@ out:
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 
-	vcpu_put(vcpu);
 	return r;
 }
 
@@ -883,8 +880,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	struct vpd *vpd = to_host(vcpu->kvm, vcpu->arch.vpd);
 	int i;
 
-	vcpu_load(vcpu);
-
 	for (i = 0; i < 16; i++) {
 		vpd->vgr[i] = regs->vpd.vgr[i];
 		vpd->vbgr[i] = regs->vpd.vbgr[i];
@@ -931,8 +926,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	vcpu->arch.itc_offset = regs->saved_itc - kvm_get_itc(vcpu);
 	set_bit(KVM_REQ_RESUME, &vcpu->requests);
 
-	vcpu_put(vcpu);
-
 	return 0;
 }
 
@@ -1802,35 +1795,24 @@ void kvm_arch_exit(void)
 	kvm_vmm_info = NULL;
 }
 
-static int kvm_ia64_sync_dirty_log(struct kvm *kvm,
-		struct kvm_dirty_log *log)
+static void kvm_ia64_sync_dirty_log(struct kvm *kvm,
+				    struct kvm_memory_slot *memslot)
 {
-	struct kvm_memory_slot *memslot;
-	int r, i;
+	int i;
 	long base;
 	unsigned long n;
 	unsigned long *dirty_bitmap = (unsigned long *)(kvm->arch.vm_base +
 			offsetof(struct kvm_vm_data, kvm_mem_dirty_log));
 
-	r = -EINVAL;
-	if (log->slot >= KVM_MEMORY_SLOTS)
-		goto out;
-
-	memslot = &kvm->memslots->memslots[log->slot];
-	r = -ENOENT;
-	if (!memslot->dirty_bitmap)
-		goto out;
-
 	n = kvm_dirty_bitmap_bytes(memslot);
 	base = memslot->base_gfn / BITS_PER_LONG;
 
+	spin_lock(&kvm->arch.dirty_log_lock);
 	for (i = 0; i < n/sizeof(long); ++i) {
 		memslot->dirty_bitmap[i] = dirty_bitmap[base + i];
 		dirty_bitmap[base + i] = 0;
 	}
-	r = 0;
-out:
-	return r;
+	spin_unlock(&kvm->arch.dirty_log_lock);
 }
 
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
@@ -1842,12 +1824,17 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	int is_dirty = 0;
 
 	mutex_lock(&kvm->slots_lock);
-	spin_lock(&kvm->arch.dirty_log_lock);
 
-	r = kvm_ia64_sync_dirty_log(kvm, log);
-	if (r)
+	r = -EINVAL;
+	if (log->slot >= KVM_MEMORY_SLOTS)
+		goto out;
+
+	memslot = &kvm->memslots->memslots[log->slot];
+	r = -ENOENT;
+	if (!memslot->dirty_bitmap)
 		goto out;
 
+	kvm_ia64_sync_dirty_log(kvm, memslot);
 	r = kvm_get_dirty_log(kvm, log, &is_dirty);
 	if (r)
 		goto out;
@@ -1855,14 +1842,12 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	/* If nothing is dirty, don't bother messing with page tables. */
 	if (is_dirty) {
 		kvm_flush_remote_tlbs(kvm);
-		memslot = &kvm->memslots->memslots[log->slot];
 		n = kvm_dirty_bitmap_bytes(memslot);
 		memset(memslot->dirty_bitmap, 0, n);
 	}
 	r = 0;
 out:
 	mutex_unlock(&kvm->slots_lock);
-	spin_unlock(&kvm->arch.dirty_log_lock);
 	return r;
 }
 
@@ -1953,11 +1938,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return vcpu->arch.timer_fired;
 }
 
-gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
-{
-	return gfn;
-}
-
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
 	return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE) ||
@@ -1967,9 +1947,7 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
-	vcpu_load(vcpu);
 	mp_state->mp_state = vcpu->arch.mp_state;
-	vcpu_put(vcpu);
 	return 0;
 }
 
@@ -2000,10 +1978,8 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 {
 	int r = 0;
 
-	vcpu_load(vcpu);
 	vcpu->arch.mp_state = mp_state->mp_state;
 	if (vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)
 		r = vcpu_reset(vcpu);
-	vcpu_put(vcpu);
 	return r;
 }
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index 6f74d93725a..8274a2d4392 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -115,7 +115,15 @@ extern void kvmppc_mmu_book3s_32_init(struct kvm_vcpu *vcpu);
 extern int kvmppc_mmu_map_page(struct kvm_vcpu *vcpu, struct kvmppc_pte *pte);
 extern int kvmppc_mmu_map_segment(struct kvm_vcpu *vcpu, ulong eaddr);
 extern void kvmppc_mmu_flush_segments(struct kvm_vcpu *vcpu);
-extern struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, bool data);
+
+extern void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
+extern struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu);
+extern void kvmppc_mmu_hpte_destroy(struct kvm_vcpu *vcpu);
+extern int kvmppc_mmu_hpte_init(struct kvm_vcpu *vcpu);
+extern void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
+extern int kvmppc_mmu_hpte_sysinit(void);
+extern void kvmppc_mmu_hpte_sysexit(void);
+
 extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);
 extern int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);
 extern void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec);
diff --git a/arch/powerpc/include/asm/kvm_fpu.h b/arch/powerpc/include/asm/kvm_fpu.h
index 94f05de9ad0..c3d4f0518a6 100644
--- a/arch/powerpc/include/asm/kvm_fpu.h
+++ b/arch/powerpc/include/asm/kvm_fpu.h
@@ -22,24 +22,24 @@
 
 #include <linux/types.h>
 
-extern void fps_fres(struct thread_struct *t, u32 *dst, u32 *src1);
-extern void fps_frsqrte(struct thread_struct *t, u32 *dst, u32 *src1);
-extern void fps_fsqrts(struct thread_struct *t, u32 *dst, u32 *src1);
+extern void fps_fres(u64 *fpscr, u32 *dst, u32 *src1);
+extern void fps_frsqrte(u64 *fpscr, u32 *dst, u32 *src1);
+extern void fps_fsqrts(u64 *fpscr, u32 *dst, u32 *src1);
 
-extern void fps_fadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2);
-extern void fps_fdivs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2);
-extern void fps_fmuls(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2);
-extern void fps_fsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2);
+extern void fps_fadds(u64 *fpscr, u32 *dst, u32 *src1, u32 *src2);
+extern void fps_fdivs(u64 *fpscr, u32 *dst, u32 *src1, u32 *src2);
+extern void fps_fmuls(u64 *fpscr, u32 *dst, u32 *src1, u32 *src2);
+extern void fps_fsubs(u64 *fpscr, u32 *dst, u32 *src1, u32 *src2);
 
-extern void fps_fmadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2,
+extern void fps_fmadds(u64 *fpscr, u32 *dst, u32 *src1, u32 *src2,
 		       u32 *src3);
-extern void fps_fmsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2,
+extern void fps_fmsubs(u64 *fpscr, u32 *dst, u32 *src1, u32 *src2,
 		       u32 *src3);
-extern void fps_fnmadds(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2,
+extern void fps_fnmadds(u64 *fpscr, u32 *dst, u32 *src1, u32 *src2,
 		        u32 *src3);
-extern void fps_fnmsubs(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2,
+extern void fps_fnmsubs(u64 *fpscr, u32 *dst, u32 *src1, u32 *src2,
 		        u32 *src3);
-extern void fps_fsel(struct thread_struct *t, u32 *dst, u32 *src1, u32 *src2,
+extern void fps_fsel(u64 *fpscr, u32 *dst, u32 *src1, u32 *src2,
 		     u32 *src3);
 
 #define FPD_ONE_IN(name) extern void fpd_ ## name(u64 *fpscr, u32 *cr, \
@@ -82,4 +82,7 @@ FPD_THREE_IN(fmadd)
 FPD_THREE_IN(fnmsub)
 FPD_THREE_IN(fnmadd)
 
+extern void kvm_cvt_fd(u32 *from, u64 *to, u64 *fpscr);
+extern void kvm_cvt_df(u64 *from, u32 *to, u64 *fpscr);
+
 #endif
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 0c9ad869dec..b0b23c007d6 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -35,10 +35,17 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
 /* We don't currently support large pages. */
+#define KVM_HPAGE_GFN_SHIFT(x)	0
 #define KVM_NR_PAGE_SIZES	1
 #define KVM_PAGES_PER_HPAGE(x)	(1UL<<31)
 
-#define HPTEG_CACHE_NUM 1024
+#define HPTEG_CACHE_NUM			(1 << 15)
+#define HPTEG_HASH_BITS_PTE		13
+#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_VPTE		(1 << HPTEG_HASH_BITS_VPTE)
+#define HPTEG_HASH_NUM_VPTE_LONG	(1 << HPTEG_HASH_BITS_VPTE_LONG)
 
 struct kvm;
 struct kvm_run;
@@ -151,6 +158,9 @@ struct kvmppc_mmu {
 };
 
 struct hpte_cache {
+	struct hlist_node list_pte;
+	struct hlist_node list_vpte;
+	struct hlist_node list_vpte_long;
 	u64 host_va;
 	u64 pfn;
 	ulong slot;
@@ -282,8 +292,10 @@ struct kvm_vcpu_arch {
 	unsigned long pending_exceptions;
 
 #ifdef CONFIG_PPC_BOOK3S
-	struct hpte_cache hpte_cache[HPTEG_CACHE_NUM];
-	int hpte_cache_offset;
+	struct hlist_head hpte_hash_pte[HPTEG_HASH_NUM_PTE];
+	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;
 #endif
 };
 
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 3b4dcc82a4c..ab3e392ac63 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -101,10 +101,6 @@ EXPORT_SYMBOL(pci_dram_offset);
 EXPORT_SYMBOL(start_thread);
 EXPORT_SYMBOL(kernel_thread);
 
-#ifdef CONFIG_PPC_FPU
-EXPORT_SYMBOL_GPL(cvt_df);
-EXPORT_SYMBOL_GPL(cvt_fd);
-#endif
 EXPORT_SYMBOL(giveup_fpu);
 #ifdef CONFIG_ALTIVEC
 EXPORT_SYMBOL(giveup_altivec);
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 812312542e5..9b9b5cdea84 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -316,7 +316,8 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
 	gfn = gpaddr >> PAGE_SHIFT;
 	new_page = gfn_to_page(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 %llx!\n",
+			(unsigned long long)gfn);
 		kvm_release_page_clean(new_page);
 		return;
 	}
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index ff436066bf7..d45c818a384 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -45,6 +45,7 @@ kvm-book3s_64-objs := \
 	book3s.o \
 	book3s_emulate.o \
 	book3s_interrupts.o \
+	book3s_mmu_hpte.o \
 	book3s_64_mmu_host.o \
 	book3s_64_mmu.o \
 	book3s_32_mmu.o
@@ -57,6 +58,7 @@ kvm-book3s_32-objs := \
 	book3s.o \
 	book3s_emulate.o \
 	book3s_interrupts.o \
+	book3s_mmu_hpte.o \
 	book3s_32_mmu_host.o \
 	book3s_32_mmu.o
 kvm-objs-$(CONFIG_KVM_BOOK3S_32) := $(kvm-book3s_32-objs)
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index b998abf1a63..a3cef30d1d4 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -1047,8 +1047,6 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
 
-	vcpu_load(vcpu);
-
 	regs->pc = kvmppc_get_pc(vcpu);
 	regs->cr = kvmppc_get_cr(vcpu);
 	regs->ctr = kvmppc_get_ctr(vcpu);
@@ -1069,8 +1067,6 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		regs->gpr[i] = kvmppc_get_gpr(vcpu, i);
 
-	vcpu_put(vcpu);
-
 	return 0;
 }
 
@@ -1078,8 +1074,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 {
 	int i;
 
-	vcpu_load(vcpu);
-
 	kvmppc_set_pc(vcpu, regs->pc);
 	kvmppc_set_cr(vcpu, regs->cr);
 	kvmppc_set_ctr(vcpu, regs->ctr);
@@ -1099,8 +1093,6 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	for (i = 0; i < ARRAY_SIZE(regs->gpr); i++)
 		kvmppc_set_gpr(vcpu, i, regs->gpr[i]);
 
-	vcpu_put(vcpu);
-
 	return 0;
 }
 
@@ -1110,8 +1102,6 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	int i;
 
-	vcpu_load(vcpu);
-
 	sregs->pvr = vcpu->arch.pvr;
 
 	sregs->u.s.sdr1 = to_book3s(vcpu)->sdr1;
@@ -1131,8 +1121,6 @@ int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
 		}
 	}
 
-	vcpu_put(vcpu);
-
 	return 0;
 }
 
@@ -1142,8 +1130,6 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	int i;
 
-	vcpu_load(vcpu);
-
 	kvmppc_set_pvr(vcpu, sregs->pvr);
 
 	vcpu3s->sdr1 = sregs->u.s.sdr1;
@@ -1171,8 +1157,6 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 	/* Flush the MMU after messing with the segments */
 	kvmppc_mmu_pte_flush(vcpu, 0, 0);
 
-	vcpu_put(vcpu);
-
 	return 0;
 }
 
@@ -1309,12 +1293,17 @@ extern int __kvmppc_vcpu_entry(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu);
 int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 {
 	int ret;
-	struct thread_struct ext_bkp;
+	double fpr[32][TS_FPRWIDTH];
+	unsigned int fpscr;
+	int fpexc_mode;
 #ifdef CONFIG_ALTIVEC
-	bool save_vec = current->thread.used_vr;
+	vector128 vr[32];
+	vector128 vscr;
+	unsigned long uninitialized_var(vrsave);
+	int used_vr;
 #endif
 #ifdef CONFIG_VSX
-	bool save_vsx = current->thread.used_vsr;
+	int used_vsr;
 #endif
 	ulong ext_msr;
 
@@ -1327,27 +1316,27 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	/* Save FPU state in stack */
 	if (current->thread.regs->msr & MSR_FP)
 		giveup_fpu(current);
-	memcpy(ext_bkp.fpr, current->thread.fpr, sizeof(current->thread.fpr));
-	ext_bkp.fpscr = current->thread.fpscr;
-	ext_bkp.fpexc_mode = current->thread.fpexc_mode;
+	memcpy(fpr, current->thread.fpr, sizeof(current->thread.fpr));
+	fpscr = current->thread.fpscr.val;
+	fpexc_mode = current->thread.fpexc_mode;
 
 #ifdef CONFIG_ALTIVEC
 	/* Save Altivec state in stack */
-	if (save_vec) {
+	used_vr = current->thread.used_vr;
+	if (used_vr) {
 		if (current->thread.regs->msr & MSR_VEC)
 			giveup_altivec(current);
-		memcpy(ext_bkp.vr, current->thread.vr, sizeof(ext_bkp.vr));
-		ext_bkp.vscr = current->thread.vscr;
-		ext_bkp.vrsave = current->thread.vrsave;
+		memcpy(vr, current->thread.vr, sizeof(current->thread.vr));
+		vscr = current->thread.vscr;
+		vrsave = current->thread.vrsave;
 	}
-	ext_bkp.used_vr = current->thread.used_vr;
 #endif
 
 #ifdef CONFIG_VSX
 	/* Save VSX state in stack */
-	if (save_vsx && (current->thread.regs->msr & MSR_VSX))
+	used_vsr = current->thread.used_vsr;
+	if (used_vsr && (current->thread.regs->msr & MSR_VSX))
 			__giveup_vsx(current);
-	ext_bkp.used_vsr = current->thread.used_vsr;
 #endif
 
 	/* Remember the MSR with disabled extensions */
@@ -1372,22 +1361,22 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvmppc_giveup_ext(vcpu, MSR_VSX);
 
 	/* Restore FPU state from stack */
-	memcpy(current->thread.fpr, ext_bkp.fpr, sizeof(ext_bkp.fpr));
-	current->thread.fpscr = ext_bkp.fpscr;
-	current->thread.fpexc_mode = ext_bkp.fpexc_mode;
+	memcpy(current->thread.fpr, fpr, sizeof(current->thread.fpr));
+	current->thread.fpscr.val = fpscr;
+	current->thread.fpexc_mode = fpexc_mode;
 
 #ifdef CONFIG_ALTIVEC
 	/* Restore Altivec state from stack */
-	if (save_vec && current->thread.used_vr) {
-		memcpy(current->thread.vr, ext_bkp.vr, sizeof(ext_bkp.vr));
-		current->thread.vscr = ext_bkp.vscr;
-		current->thread.vrsave= ext_bkp.vrsave;
+	if (used_vr && current->thread.used_vr) {
+		memcpy(current->thread.vr, vr, sizeof(current->thread.vr));
+		current->thread.vscr = vscr;
+		current->thread.vrsave = vrsave;
 	}
-	current->thread.used_vr = ext_bkp.used_vr;
+	current->thread.used_vr = used_vr;
 #endif
 
 #ifdef CONFIG_VSX
-	current->thread.used_vsr = ext_bkp.used_vsr;
+	current->thread.used_vsr = used_vsr;
 #endif
 
 	return ret;
@@ -1395,12 +1384,22 @@ int __kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 static int kvmppc_book3s_init(void)
 {
-	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0,
-			THIS_MODULE);
+	int r;
+
+	r = kvm_init(NULL, sizeof(struct kvmppc_vcpu_book3s), 0,
+		     THIS_MODULE);
+
+	if (r)
+		return r;
+
+	r = kvmppc_mmu_hpte_sysinit();
+
+	return r;
 }
 
 static void kvmppc_book3s_exit(void)
 {
+	kvmppc_mmu_hpte_sysexit();
 	kvm_exit();
 }
 
diff --git a/arch/powerpc/kvm/book3s_32_mmu.c b/arch/powerpc/kvm/book3s_32_mmu.c
index 0b10503c8a4..3292d76101d 100644
--- a/arch/powerpc/kvm/book3s_32_mmu.c
+++ b/arch/powerpc/kvm/book3s_32_mmu.c
@@ -354,10 +354,10 @@ 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)
-			return -1;
-
-		*vsid = sr->vsid;
+		if (sr->valid)
+			*vsid = sr->vsid;
+		else
+			*vsid = VSID_BAT | gvsid;
 		break;
 	default:
 		BUG();
diff --git a/arch/powerpc/kvm/book3s_32_mmu_host.c b/arch/powerpc/kvm/book3s_32_mmu_host.c
index 0bb66005338..0b51ef872c1 100644
--- a/arch/powerpc/kvm/book3s_32_mmu_host.c
+++ b/arch/powerpc/kvm/book3s_32_mmu_host.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/kvm_host.h>
+#include <linux/hash.h>
 
 #include <asm/kvm_ppc.h>
 #include <asm/kvm_book3s.h>
@@ -57,139 +58,26 @@
 static ulong htab;
 static u32 htabmask;
 
-static void invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
+void kvmppc_mmu_invalidate_pte(struct kvm_vcpu *vcpu, struct hpte_cache *pte)
 {
 	volatile u32 *pteg;
 
-	dprintk_mmu("KVM: Flushing SPTE: 0x%llx (0x%llx) -> 0x%llx\n",
-		    pte->pte.eaddr, pte->pte.vpage, pte->host_va);
-
+	/* Remove from host HTAB */
 	pteg = (u32*)pte->slot;
-
 	pteg[0] = 0;
+
+	/* And make sure it's gone from the TLB too */
 	asm volatile ("sync");
 	asm volatile ("tlbie %0" : : "r" (pte->pte.eaddr) : "memory");
 	asm volatile ("sync");
 	asm volatile ("tlbsync");
-
-	pte->host_va = 0;
-
-	if (pte->pte.may_write)
-		kvm_release_pfn_dirty(pte->pfn);
-	else
-		kvm_release_pfn_clean(pte->pfn);
-}
-
-void kvmppc_mmu_pte_flush(struct kvm_vcpu *vcpu, ulong guest_ea, ulong ea_mask)
-{
-	int i;
-
-	dprintk_mmu("KVM: Flushing %d Shadow PTEs: 0x%x & 0x%x\n",
-		    vcpu->arch.hpte_cache_offset, guest_ea, ea_mask);
-	BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM);
-
-	guest_ea &= ea_mask;
-	for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) {
-		struct hpte_cache *pte;
-
-		pte = &vcpu->arch.hpte_cache[i];
-		if (!pte->host_va)
-			continue;
-
-		if ((pte->pte.eaddr & ea_mask) == guest_ea) {
-			invalidate_pte(vcpu, pte);
-		}
-	}
-
-	/* Doing a complete flush -> start from scratch */
-	if (!ea_mask)
-		vcpu->arch.hpte_cache_offset = 0;
-}
-
-void kvmppc_mmu_pte_vflush(struct kvm_vcpu *vcpu, u64 guest_vp, u64 vp_mask)
-{
-	int i;
-
-	dprintk_mmu("KVM: Flushing %d Shadow vPTEs: 0x%llx & 0x%llx\n",
-		    vcpu->arch.hpte_cache_offset, guest_vp, vp_mask);
-	BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM);
-
-	guest_vp &= vp_mask;
-	for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) {
-		struct hpte_cache *pte;
-
-		pte = &vcpu->arch.hpte_cache[i];
-		if (!pte->host_va)
-			continue;
-
-		if ((pte->pte.vpage & vp_mask) == guest_vp) {
-			invalidate_pte(vcpu, pte);
-		}
-	}
-}
-
-void kvmppc_mmu_pte_pflush(struct kvm_vcpu *vcpu, ulong pa_start, ulong pa_end)
-{
-	int i;
-
-	dprintk_mmu("KVM: Flushing %d Shadow pPTEs: 0x%llx & 0x%llx\n",
-		    vcpu->arch.hpte_cache_offset, pa_start, pa_end);
-	BUG_ON(vcpu->arch.hpte_cache_offset > HPTEG_CACHE_NUM);
-
-	for (i = 0; i < vcpu->arch.hpte_cache_offset; i++) {
-		struct hpte_cache *pte;
-
-		pte = &vcpu->arch.hpte_cache[i];
-		if (!pte->host_va)
-			continue;
-
-		if ((pte->pte.raddr >= pa_start) &&
-		    (pte->pte.raddr < pa_end)) {
-			invalidate_pte(vcpu, pte);
-		}
-	}
-}
-
-struct kvmppc_pte *kvmppc_mmu_find_pte(struct kvm_vcpu *vcpu, u64 ea, bool data)
-{
-	int i;
-	u64 guest_vp;
-
-	guest_vp = vcpu->arch.mmu.ea_to_vp(vcpu, ea, false);
-	for (i=0; i<vcpu->arch.hpte_cache_offset; i++) {
-		struct hpte_cache *pte;
-
-		pte = &vcpu->arch.hpte_cache[i];
-		if (!pte->host_va)
-			continue;
-
-		if (pte->pte.vpage == guest_vp)
-			return &pte->pte;
-	}
-
-	return NULL;
-}
-
-static int kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu)
-{
-	if (vcpu->arch.hpte_cache_offset == HPTEG_CACHE_NUM)
-		kvmppc_mmu_pte_flush(vcpu, 0, 0);
-
-	return vcpu->arch.hpte_cache_offset++;
 }
 
 /* We keep 512 gvsid->hvsid entries, mapping the guest ones to the array using
  * a hash, so we don't waste cycles on looping */
 static u16 kvmppc_sid_hash(struct kvm_vcpu *vcpu, u64 gvsid)
 {
-	return (u16)(((gvsid >> (SID_MAP_BITS * 7)) & SID_MAP_MASK) ^
-		     ((gvsid >> (SID_MAP_BITS * 6)) & SID_MAP_MASK) ^
-		     ((gvsid