Merge tag 'kvm-5.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "This is the first batch of KVM changes.

  ARM:
   - cleanups and corner case fixes.

  PPC:
   - Bugfixes

  x86:
   - Support for mapping DAX areas with large nested page table entries.

   - Cleanups and bugfixes here too. A particularly important one is a
     fix for FPU load when the thread has TIF_NEED_FPU_LOAD. There is
     also a race condition which could be used in guest userspace to
     exploit the guest kernel, for which the embargo expired today.

   - Fast path for IPI delivery vmexits, shaving about 200 clock cycles
     from IPI latency.

   - Protect against "Spectre-v1/L1TF" (bring data in the cache via
     speculative out of bound accesses, use L1TF on the sibling
     hyperthread to read it), which unfortunately is an even bigger
     whack-a-mole game than SpectreV1.

  Sean continues his mission to rewrite KVM. In addition to a sizable
  number of x86 patches, this time he contributed a pretty large
  refactoring of vCPU creation that affects all architectures but should
  not have any visible effect.

  s390 will come next week together with some more x86 patches"

* tag 'kvm-5.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (204 commits)
  x86/KVM: Clean up host's steal time structure
  x86/KVM: Make sure KVM_VCPU_FLUSH_TLB flag is not missed
  x86/kvm: Cache gfn to pfn translation
  x86/kvm: Introduce kvm_(un)map_gfn()
  x86/kvm: Be careful not to clear KVM_VCPU_FLUSH_TLB bit
  KVM: PPC: Book3S PR: Fix -Werror=return-type build failure
  KVM: PPC: Book3S HV: Release lock on page-out failure path
  KVM: arm64: Treat emulated TVAL TimerValue as a signed 32-bit integer
  KVM: arm64: pmu: Only handle supported event counters
  KVM: arm64: pmu: Fix chained SW_INCR counters
  KVM: arm64: pmu: Don't mark a counter as chained if the odd one is disabled
  KVM: arm64: pmu: Don't increment SW_INCR if PMCR.E is unset
  KVM: x86: Use a typedef for fastop functions
  KVM: X86: Add 'else' to unify fastop and execute call path
  KVM: x86: inline memslot_valid_for_gpte
  KVM: x86/mmu: Use huge pages for DAX-backed files
  KVM: x86/mmu: Remove lpage_is_disallowed() check from set_spte()
  KVM: x86/mmu: Fold max_mapping_level() into kvm_mmu_hugepage_adjust()
  KVM: x86/mmu: Zap any compound page when collapsing sptes
  KVM: x86/mmu: Remove obsolete gfn restoration in FNAME(fetch)
  ...

17 files changed, 173 insertions, 207 deletions

diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index 13bd870609c3..e90c073e437e 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -350,6 +350,7 @@
 #define H_SVM_PAGE_OUT		0xEF04
 #define H_SVM_INIT_START	0xEF08
 #define H_SVM_INIT_DONE		0xEF0C
+#define H_SVM_INIT_ABORT	0xEF14
 
 /* Values for 2nd argument to H_SET_MODE */
 #define H_SET_MODE_RESOURCE_SET_CIABR		1
diff --git a/arch/powerpc/include/asm/kvm_book3s_uvmem.h b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
index 50204e228f16..5a9834e0e2d1 100644
--- a/arch/powerpc/include/asm/kvm_book3s_uvmem.h
+++ b/arch/powerpc/include/asm/kvm_book3s_uvmem.h
@@ -19,8 +19,9 @@ unsigned long kvmppc_h_svm_page_out(struct kvm *kvm,
 unsigned long kvmppc_h_svm_init_start(struct kvm *kvm);
 unsigned long kvmppc_h_svm_init_done(struct kvm *kvm);
 int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn);
+unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm);
 void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
-			     struct kvm *kvm);
+			     struct kvm *kvm, bool skip_page_out);
 #else
 static inline int kvmppc_uvmem_init(void)
 {
@@ -62,6 +63,11 @@ static inline unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
 	return H_UNSUPPORTED;
 }
 
+static inline unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
+{
+	return H_UNSUPPORTED;
+}
+
 static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
 {
 	return -EFAULT;
@@ -69,6 +75,6 @@ static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
 
 static inline void
 kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
-			struct kvm *kvm) { }
+			struct kvm *kvm, bool skip_page_out) { }
 #endif /* CONFIG_PPC_UV */
 #endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 0a398f2321c2..6e8b8ffd06ad 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -278,6 +278,7 @@ struct kvm_resize_hpt;
 /* Flag values for kvm_arch.secure_guest */
 #define KVMPPC_SECURE_INIT_START 0x1 /* H_SVM_INIT_START has been called */
 #define KVMPPC_SECURE_INIT_DONE  0x2 /* H_SVM_INIT_DONE completed */
+#define KVMPPC_SECURE_INIT_ABORT 0x4 /* H_SVM_INIT_ABORT issued */
 
 struct kvm_arch {
 	unsigned int lpid;
diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index 3d2f871241a8..bc2494e5710a 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -119,8 +119,7 @@ extern int kvmppc_xlate(struct kvm_vcpu *vcpu, ulong eaddr,
 			enum xlate_instdata xlid, enum xlate_readwrite xlrw,
 			struct kvmppc_pte *pte);
 
-extern struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm,
-                                                unsigned int id);
+extern int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_check_processor_compat(void);
@@ -274,7 +273,7 @@ struct kvmppc_ops {
 	void (*inject_interrupt)(struct kvm_vcpu *vcpu, int vec, u64 srr1_flags);
 	void (*set_msr)(struct kvm_vcpu *vcpu, u64 msr);
 	int (*vcpu_run)(struct kvm_run *run, struct kvm_vcpu *vcpu);
-	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned int id);
+	int (*vcpu_create)(struct kvm_vcpu *vcpu);
 	void (*vcpu_free)(struct kvm_vcpu *vcpu);
 	int (*check_requests)(struct kvm_vcpu *vcpu);
 	int (*get_dirty_log)(struct kvm *kvm, struct kvm_dirty_log *log);
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 58a59ee998e2..d07a8e12fa15 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -471,11 +471,6 @@ int kvmppc_load_last_inst(struct kvm_vcpu *vcpu,
 }
 EXPORT_SYMBOL_GPL(kvmppc_load_last_inst);
 
-int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
-{
-	return 0;
-}
-
 int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	return 0;
@@ -789,9 +784,9 @@ void kvmppc_decrementer_func(struct kvm_vcpu *vcpu)
 	kvm_vcpu_kick(vcpu);
 }
 
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu)
 {
-	return kvm->arch.kvm_ops->vcpu_create(kvm, id);
+	return vcpu->kvm->arch.kvm_ops->vcpu_create(vcpu);
 }
 
 void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index d381526c5c9b..6c372f5c61b6 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -284,7 +284,7 @@ static long kvmppc_virtmode_do_h_enter(struct kvm *kvm, unsigned long flags,
 	/* Protect linux PTE lookup from page table destruction */
 	rcu_read_lock_sched();	/* this disables preemption too */
 	ret = kvmppc_do_h_enter(kvm, flags, pte_index, pteh, ptel,
-				current->mm->pgd, false, pte_idx_ret);
+				kvm->mm->pgd, false, pte_idx_ret);
 	rcu_read_unlock_sched();
 	if (ret == H_TOO_HARD) {
 		/* this can't happen */
@@ -573,7 +573,7 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	is_ci = false;
 	pfn = 0;
 	page = NULL;
-	mm = current->mm;
+	mm = kvm->mm;
 	pte_size = PAGE_SIZE;
 	writing = (dsisr & DSISR_ISSTORE) != 0;
 	/* If writing != 0, then the HPTE must allow writing, if we get here */
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index da857c8ba6e4..744dba98e5d1 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -1102,7 +1102,7 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
 	unsigned int shift;
 
 	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)
-		kvmppc_uvmem_drop_pages(memslot, kvm);
+		kvmppc_uvmem_drop_pages(memslot, kvm, true);
 
 	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
 		return;
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index 883a66e76638..ee6c103bb7d5 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -253,10 +253,11 @@ static int kvm_spapr_tce_release(struct inode *inode, struct file *filp)
 		}
 	}
 
+	account_locked_vm(kvm->mm,
+		kvmppc_stt_pages(kvmppc_tce_pages(stt->size)), false);
+
 	kvm_put_kvm(stt->kvm);
 
-	account_locked_vm(current->mm,
-		kvmppc_stt_pages(kvmppc_tce_pages(stt->size)), false);
 	call_rcu(&stt->rcu, release_spapr_tce_table);
 
 	return 0;
@@ -272,6 +273,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 {
 	struct kvmppc_spapr_tce_table *stt = NULL;
 	struct kvmppc_spapr_tce_table *siter;
+	struct mm_struct *mm = kvm->mm;
 	unsigned long npages, size = args->size;
 	int ret = -ENOMEM;
 
@@ -280,7 +282,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 		return -EINVAL;
 
 	npages = kvmppc_tce_pages(size);
-	ret = account_locked_vm(current->mm, kvmppc_stt_pages(npages), true);
+	ret = account_locked_vm(mm, kvmppc_stt_pages(npages), true);
 	if (ret)
 		return ret;
 
@@ -326,7 +328,7 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 
 	kfree(stt);
  fail_acct:
-	account_locked_vm(current->mm, kvmppc_stt_pages(npages), false);
+	account_locked_vm(mm, kvmppc_stt_pages(npages), false);
 	return ret;
 }
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 6ff3f896d908..2cefd071b848 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1091,6 +1091,9 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	case H_SVM_INIT_DONE:
 		ret = kvmppc_h_svm_init_done(vcpu->kvm);
 		break;
+	case H_SVM_INIT_ABORT:
+		ret = kvmppc_h_svm_init_abort(vcpu->kvm);
+		break;
 
 	default:
 		return RESUME_HOST;
@@ -2271,22 +2274,16 @@ static void debugfs_vcpu_init(struct kvm_vcpu *vcpu, unsigned int id)
 }
 #endif /* CONFIG_KVM_BOOK3S_HV_EXIT_TIMING */
 
-static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
-						   unsigned int id)
+static int kvmppc_core_vcpu_create_hv(struct kvm_vcpu *vcpu)
 {
-	struct kvm_vcpu *vcpu;
 	int err;
 	int core;
 	struct kvmppc_vcore *vcore;
+	struct kvm *kvm;
+	unsigned int id;
 
-	err = -ENOMEM;
-	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	if (!vcpu)
-		goto out;
-
-	err = kvm_vcpu_init(vcpu, kvm, id);
-	if (err)
-		goto free_vcpu;
+	kvm = vcpu->kvm;
+	id = vcpu->vcpu_id;
 
 	vcpu->arch.shared = &vcpu->arch.shregs;
 #ifdef CONFIG_KVM_BOOK3S_PR_POSSIBLE
@@ -2368,7 +2365,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	mutex_unlock(&kvm->lock);
 
 	if (!vcore)
-		goto free_vcpu;
+		return err;
 
 	spin_lock(&vcore->lock);
 	++vcore->num_threads;
@@ -2383,12 +2380,7 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 
 	debugfs_vcpu_init(vcpu, id);
 
-	return vcpu;
-
-free_vcpu:
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
-out:
-	return ERR_PTR(err);
+	return 0;
 }
 
 static int kvmhv_set_smt_mode(struct kvm *kvm, unsigned long smt_mode,
@@ -2442,8 +2434,6 @@ static void kvmppc_core_vcpu_free_hv(struct kvm_vcpu *vcpu)
 	unpin_vpa(vcpu->kvm, &vcpu->arch.slb_shadow);
 	unpin_vpa(vcpu->kvm, &vcpu->arch.vpa);
 	spin_unlock(&vcpu->arch.vpa_update_lock);
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
 static int kvmppc_core_check_requests_hv(struct kvm_vcpu *vcpu)
@@ -4285,7 +4275,7 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 	user_vrsave = mfspr(SPRN_VRSAVE);
 
 	vcpu->arch.wqp = &vcpu->arch.vcore->wq;
-	vcpu->arch.pgdir = current->mm->pgd;
+	vcpu->arch.pgdir = kvm->mm->pgd;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
 
 	do {
@@ -4640,14 +4630,14 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 
 	/* Look up the VMA for the start of this memory slot */
 	hva = memslot->userspace_addr;
-	down_read(&current->mm->mmap_sem);
-	vma = find_vma(current->mm, hva);
+	down_read(&kvm->mm->mmap_sem);
+	vma = find_vma(kvm->mm, hva);
 	if (!vma || vma->vm_start > hva || (vma->vm_flags & VM_IO))
 		goto up_out;
 
 	psize = vma_kernel_pagesize(vma);
 
-	up_read(&current->mm->mmap_sem);
+	up_read(&kvm->mm->mmap_sem);
 
 	/* We can handle 4k, 64k or 16M pages in the VRMA */
 	if (psize >= 0x1000000)
@@ -4680,7 +4670,7 @@ static int kvmppc_hv_setup_htab_rma(struct kvm_vcpu *vcpu)
 	return err;
 
  up_out:
-	up_read(&current->mm->mmap_sem);
+	up_read(&kvm->mm->mmap_sem);
 	goto out_srcu;
 }
 
@@ -5477,7 +5467,7 @@ static int kvmhv_svm_off(struct kvm *kvm)
 			continue;
 
 		kvm_for_each_memslot(memslot, slots) {
-			kvmppc_uvmem_drop_pages(memslot, kvm);
+			kvmppc_uvmem_drop_pages(memslot, kvm, true);
 			uv_unregister_mem_slot(kvm->arch.lpid, memslot->id);
 		}
 	}
diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 2de264fc3156..79b1202b1c62 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -258,7 +258,7 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
  * QEMU page table with normal PTEs from newly allocated pages.
  */
 void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
-			     struct kvm *kvm)
+			     struct kvm *kvm, bool skip_page_out)
 {
 	int i;
 	struct kvmppc_uvmem_page_pvt *pvt;
@@ -276,7 +276,7 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
 
 		uvmem_page = pfn_to_page(uvmem_pfn);
 		pvt = uvmem_page->zone_device_data;
-		pvt->skip_page_out = true;
+		pvt->skip_page_out = skip_page_out;
 		mutex_unlock(&kvm->arch.uvmem_lock);
 
 		pfn = gfn_to_pfn(kvm, gfn);
@@ -286,6 +286,34 @@ void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
 	}
 }
 
+unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
+{
+	int srcu_idx;
+	struct kvm_memory_slot *memslot;
+
+	/*
+	 * Expect to be called only after INIT_START and before INIT_DONE.
+	 * If INIT_DONE was completed, use normal VM termination sequence.
+	 */
+	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
+		return H_UNSUPPORTED;
+
+	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+		return H_STATE;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+
+	kvm_for_each_memslot(memslot, kvm_memslots(kvm))
+		kvmppc_uvmem_drop_pages(memslot, kvm, false);
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	kvm->arch.secure_guest = 0;
+	uv_svm_terminate(kvm->arch.lpid);
+
+	return H_PARAMETER;
+}
+
 /*
  * Get a free device PFN from the pool
  *
@@ -543,7 +571,7 @@ kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start,
 
 	ret = migrate_vma_setup(&mig);
 	if (ret)
-		return ret;
+		goto out;
 
 	spage = migrate_pfn_to_page(*mig.src);
 	if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE))
diff --git a/arch/powerpc/kvm/book3s_pr.c b/arch/powerpc/kvm/book3s_pr.c
index ce4fcf76e53e..729a0f12a752 100644
--- a/arch/powerpc/kvm/book3s_pr.c
+++ b/arch/powerpc/kvm/book3s_pr.c
@@ -1744,21 +1744,17 @@ static int kvmppc_set_one_reg_pr(struct kvm_vcpu *vcpu, u64 id,
 	return r;
 }
 
-static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
-						   unsigned int id)
+static int kvmppc_core_vcpu_create_pr(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s;
-	struct kvm_vcpu *vcpu;
-	int err = -ENOMEM;
 	unsigned long p;
+	int err;
 
-	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	if (!vcpu)
-		goto out;
+	err = -ENOMEM;
 
 	vcpu_book3s = vzalloc(sizeof(struct kvmppc_vcpu_book3s));
 	if (!vcpu_book3s)
-		goto free_vcpu;
+		goto out;
 	vcpu->arch.book3s = vcpu_book3s;
 
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
@@ -1768,14 +1764,9 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 		goto free_vcpu3s;
 #endif
 
-	err = kvm_vcpu_init(vcpu, kvm, id);
-	if (err)
-		goto free_shadow_vcpu;
-
-	err = -ENOMEM;
 	p = __get_free_page(GFP_KERNEL|__GFP_ZERO);
 	if (!p)
-		goto uninit_vcpu;
+		goto free_shadow_vcpu;
 	vcpu->arch.shared = (void *)p;
 #ifdef CONFIG_PPC_BOOK3S_64
 	/* Always start the shared struct in native endian mode */
@@ -1806,22 +1797,20 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_pr(struct kvm *kvm,
 
 	err = kvmppc_mmu_init(vcpu);
 	if (err < 0)
-		goto uninit_vcpu;
+		goto free_shared_page;
 
-	return vcpu;
+	return 0;
 
-uninit_vcpu:
-	kvm_vcpu_uninit(vcpu);
+free_shared_page:
+	free_page((unsigned long)vcpu->arch.shared);
 free_shadow_vcpu:
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kfree(vcpu->arch.shadow_vcpu);
 free_vcpu3s:
 #endif
 	vfree(vcpu_book3s);
-free_vcpu:
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
 out:
-	return ERR_PTR(err);
+	return err;
 }
 
 static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
@@ -1829,12 +1818,10 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 
 	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
-	kvm_vcpu_uninit(vcpu);
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kfree(vcpu->arch.shadow_vcpu);
 #endif
 	vfree(vcpu_book3s);
-	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
 static int kvmppc_vcpu_run_pr(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
@@ -2030,6 +2017,7 @@ static int kvm_vm_ioctl_get_smmu_info_pr(struct kvm *kvm,
 {
 	/* We should not get called */
 	BUG();
+	return 0;
 }
 #endif /* CONFIG_PPC64 */
 
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
index d83adb1e1490..6ef0151ff70a 100644
--- a/arch/powerpc/kvm/book3s_xive_native.c
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -631,7 +631,7 @@ static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	gfn = gpa_to_gfn(kvm_eq.qaddr);
 
-	page_size = kvm_host_page_size(kvm, gfn);
+	page_size = kvm_host_page_size(vcpu, gfn);
 	if (1ull << kvm_eq.qshift > page_size) {
 		srcu_read_unlock(&kvm->srcu, srcu_idx);
 		pr_warn("Incompatible host page size %lx!\n", page_size);
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index be9a45874194..7b27604adadf 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -775,7 +775,7 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	debug = current->thread.debug;
 	current->thread.debug = vcpu->arch.dbg_reg;
 
-	vcpu->arch.pgdir = current->mm->pgd;
+	vcpu->arch.pgdir = vcpu->kvm->mm->pgd;
 	kvmppc_fix_ee_before_entry();
 
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
@@ -1377,36 +1377,6 @@ static void kvmppc_set_tsr(struct kvm_vcpu *vcpu, u32 new_tsr)
 	update_timer_ints(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;
-	int r;
-
-	vcpu->arch.regs.nip = 0;
-	vcpu->arch.shared->pir = vcpu->vcpu_id;
-	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
-	kvmppc_set_msr(vcpu, 0);
-
-#ifndef CONFIG_KVM_BOOKE_HV
-	vcpu->arch.shadow_msr = MSR_USER | MSR_IS | MSR_DS;
-	vcpu->arch.shadow_pid = 1;
-	vcpu->arch.shared->msr = 0;
-#endif
-
-	/* 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);
-
-	r = kvmppc_core_vcpu_setup(vcpu);
-	kvmppc_sanity_check(vcpu);
-	return r;
-}
-
 int kvmppc_subarch_vcpu_init(struct kvm_vcpu *vcpu)
 {
 	/* setup watchdog timer once */
@@ -2114,9 +2084,40 @@ int kvmppc_core_init_vm(struct kvm *kvm)
 	return kvm->arch.kvm_ops->init_vm(kvm);
 }
 
-struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
+int kvmppc_core_vcpu_create(struct kvm_vcpu *vcpu)
 {
-	return kvm->arch.kvm_ops->vcpu_create(kvm, id);
+	int i;
+	int r;
+
+	r = vcpu->kvm->arch.kvm_ops->vcpu_create(vcpu);
+	if (r)
+		return r;
+
+	/* Initial guest state: 16MB mapping 0 -> 0, PC = 0, MSR = 0, R1 = 16MB */
+	vcpu->arch.regs.nip = 0;
+	vcpu->arch.shared->pir = vcpu->vcpu_id;
+	kvmppc_set_gpr(vcpu, 1, (16<<20) - 8); /* -8 for the callee-save LR slot */
+	kvmppc_set_msr(vcpu, 0);
+
+#ifndef CONFIG_KVM_BOOKE_HV
+	vcpu->arch.shadow_msr = MSR_USER | MSR_IS | MSR_DS;
+	vcpu->arch.shadow_pid = 1;
+	vcpu->arch.shared->msr = 0;
+#endif
+
+	/* 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);
+
+	r = kvmppc_core_vcpu_setup(vcpu);
+	if (r)
+		vcpu->kvm->arch.kvm_ops->vcpu_free(vcpu);
+	kvmppc_sanity_check(vcpu);
+	return r;
 }
 
 void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
diff --git a/arch/powerpc/kvm/e500.c b/arch/powerpc/kvm/e500.c
index 00649ca5fa9a..f2b4feaff6d2 100644
--- a/arch/powerpc/kvm/e500.c
+++ b/arch/powerpc/kvm/e500.c
@@ -433,31 +433,16 @@ static int kvmppc_set_one_reg_e500(struct kvm_vcpu *vcpu, u64 id,
 	return r;
 }
 
-static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm,
-						     unsigned int id)
+static int kvmppc_core_vcpu_create_e500(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500;
-	struct kvm_vcpu *vcpu;
 	int err;
 
-	BUILD_BUG_ON_MSG(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0,
-		"struct kvm_vcpu must be at offset 0 for arch usercopy region");
+	BUILD_BUG_ON(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0);
+	vcpu_e500 = to_e500(vcpu);
 
-	vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	if (!vcpu_e500) {
-		err = -ENOMEM;
-		goto out;
-	}
-
-	vcpu = &vcpu_e500->vcpu;
-	err = kvm_vcpu_init(vcpu, kvm, id);
-	if (err)
-		goto free_vcpu;
-
-	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL) {
-		err = -ENOMEM;
-		goto uninit_vcpu;
-	}
+	if (kvmppc_e500_id_table_alloc(vcpu_e500) == NULL)
+		return -ENOMEM;
 
 	err = kvmppc_e500_tlb_init(vcpu_e500);
 	if (err)
@@ -469,18 +454,13 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500(struct kvm *kvm,
 		goto uninit_tlb;
 	}
 
-	return vcpu;
+	return 0;
 
 uninit_tlb:
 	kvmppc_e500_tlb_uninit(vcpu_e500);
 uninit_id:
 	kvmppc_e500_id_table_free(vcpu_e500);
-uninit_vcpu:
-	kvm_vcpu_uninit(vcpu);
-free_vcpu:
-	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
-out:
-	return ERR_PTR(err);
+	return err;
 }
 
 static void kvmppc_core_vcpu_free_e500(struct kvm_vcpu *vcpu)
@@ -490,8 +470,6 @@ static void kvmppc_core_vcpu_free_e500(struct kvm_vcpu *vcpu)
 	free_page((unsigned long)vcpu->arch.shared);
 	kvmppc_e500_tlb_uninit(vcpu_e500);
 	kvmppc_e500_id_table_free(vcpu_e500);
-	kvm_vcpu_uninit(vcpu);
-	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
 static int kvmppc_core_init_vm_e500(struct kvm *kvm)
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index 318e65c65999..e6b06cb2b92c 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -301,30 +301,20 @@ static int kvmppc_set_one_reg_e500mc(struct kvm_vcpu *vcpu, u64 id,
 	return r;
 }
 
-static struct kvm_vcpu *kvmppc_core_vcpu_create_e500mc(struct kvm *kvm,
-						       unsigned int id)
+static int kvmppc_core_vcpu_create_e500mc(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500;
-	struct kvm_vcpu *vcpu;
 	int err;
 
-	vcpu_e500 = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
-	if (!vcpu_e500) {
-		err = -ENOMEM;
-		goto out;
-	}
-	vcpu = &vcpu_e500->vcpu;
+	BUILD_BUG_ON(offsetof(struct kvmppc_vcpu_e500, vcpu) != 0);
+	vcpu_e500 = to_e500(vcpu);
 
 	/* Invalid PIR value -- this LPID dosn't have valid state on any cpu */
 	vcpu->arch.oldpir = 0xffffffff;
 
-	err = kvm_vcpu_init(vcpu, kvm, id);
-	if (err)
-		goto free_vcpu;
-
 	err = kvmppc_e500_tlb_init(vcpu_e500);
 	if (err)
-		goto uninit_vcpu;
+		return err;
 
 	vcpu->arch.shared = (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
 	if (!vcpu->arch.shared) {
@@ -332,17 +322,11 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_e500mc(struct kvm *kvm,
 		goto uninit_tlb;
 	}
 
-	return vcpu;
+	return 0;
 
 uninit_tlb:
 	kvmppc_e500_tlb_uninit(vcpu_e500);
-uninit_vcpu:
-	kvm_vcpu_uninit(vcpu);
-
-free_vcpu:
-	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
-out:
-	return ERR_PTR(err);
+	return err;
 }
 
 static void kvmppc_core_vcpu_free_e500mc(struct kvm_vcpu *vcpu)
@@ -351,8 +335,6 @@ static void kvmppc_core_vcpu_free_e500mc(struct kvm_vcpu *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);
 }
 
 static int kvmppc_core_init_vm_e500mc(struct kvm *kvm)
diff --git a/arch/powerpc/kvm/emulate_loadstore.c b/arch/powerpc/kvm/emulate_loadstore.c
index 2e496eb86e94..1139bc56e004 100644
--- a/arch/powerpc/kvm/emulate_loadstore.c
+++ b/arch/powerpc/kvm/emulate_loadstore.c
@@ -73,7 +73,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 	u32 inst;
-	int ra, rs, rt;
 	enum emulation_result emulated = EMULATE_FAIL;
 	int advance = 1;
 	struct instruction_op op;
@@ -85,10 +84,6 @@ int kvmppc_emulate_loadstore(struct kvm_vcpu *vcpu)
 	if (emulated != EMULATE_DONE)
 		return emulated;
 
-	ra = get_ra(inst);
-	rs = get_rs(inst);
-	rt = get_rt(inst);
-
 	vcpu->arch.mmio_vsx_copy_nums = 0;
 	vcpu->arch.mmio_vsx_offset = 0;
 	vcpu->arch.mmio_copy_type = KVMPPC_VSX_COPY_NONE;
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 416fb3d2a1d0..1af96fb5dc6f 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -475,7 +475,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 #endif
 
 	kvm_for_each_vcpu(i, vcpu, kvm)
-		kvm_arch_vcpu_free(vcpu);
+		kvm_vcpu_destroy(vcpu);
 
 	mutex_lock(&kvm->lock);
 	for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
@@ -720,22 +720,55 @@ void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 	kvmppc_core_flush_memslot(kvm, slot);
 }
 
-struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
+int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
+{
+	return 0;
+}
+
+static enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
 {
 	struct kvm_vcpu *vcpu;
-	vcpu = kvmppc_core_vcpu_create(kvm, id);
-	if (!IS_ERR(vcpu)) {
-		vcpu->arch.wqp = &vcpu->wq;
-		kvmppc_create_vcpu_debugfs(vcpu, id);
-	}
-	return vcpu;
+
+	vcpu = container_of(timer, struct kvm_vcpu, arch.dec_timer);
+	kvmppc_decrementer_func(vcpu);
+
+	return HRTIMER_NORESTART;
+}
+
+int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
+{
+	int err;
+
+	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
+	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
+	vcpu->arch.dec_expires = get_tb();
+
+#ifdef CONFIG_KVM_EXIT_TIMING
+	mutex_init(&vcpu->arch.exit_timing_lock);
+#endif
+	err = kvmppc_subarch_vcpu_init(vcpu);
+	if (err)
+		return err;
+
+	err = kvmppc_core_vcpu_create(vcpu);
+	if (err)
+		goto out_vcpu_uninit;
+
+	vcpu->arch.wqp = &vcpu->wq;
+	kvmppc_create_vcpu_debugfs(vcpu, vcpu->vcpu_id);
+	return 0;
+
+out_vcpu_uninit:
+	kvmppc_mmu_destroy(vcpu);
+	kvmppc_subarch_vcpu_uninit(vcpu);
+	return err;
 }
 
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
 }
 
-void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
 	/* Make sure we're not using the vcpu anymore */
 	hrtimer_cancel(&vcpu->arch.dec_timer);
@@ -758,11 +791,9 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 	}
 
 	kvmppc_core_vcpu_free(vcpu);
-}
 
-void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
-{
-	kvm_arch_vcpu_free(vcpu);
+	kvmppc_mmu_destroy(vcpu);
+	kvmppc_subarch_vcpu_uninit(vcpu);
 }
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
@@ -770,37 +801,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return kvmppc_core_pending_dec(vcpu);
 }
 
-static enum hrtimer_restart kvmppc_decrementer_wakeup(struct hrtimer *timer)
-{
-	struct kvm_vcpu *vcpu;
-
-	vcpu = container_of(timer, struct kvm_vcpu, arch.dec_timer);
-	kvmppc_decrementer_func(vcpu);
-
-	return HRTIMER_NORESTART;
-}
-
-int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
-{
-	int ret;
-
-	hrtimer_init(&vcpu->arch.dec_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
-	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
-	vcpu->arch.dec_expires = get_tb();
-
-#ifdef CONFIG_KVM_EXIT_TIMING
-	mutex_init(&vcpu->arch.exit_timing_lock);
-#endif
-	ret = kvmppc_subarch_vcpu_init(vcpu);
-	return ret;
-}
-
-void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
-{
-	kvmppc_mmu_destroy(vcpu);
-	kvmppc_subarch_vcpu_uninit(vcpu);
-}
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 #ifdef CONFIG_BOOKE