Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini: "ARM: - support for SVE and Pointer Authentication in guests - PMU improvements POWER: - support for direct access to the POWER9 XIVE interrupt controller - memory and performance optimizations x86: - support for accessing memory not backed by struct page - fixes and refactoring Generic: - dirty page tracking improvements" * tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (155 commits) kvm: fix compilation on aarch64 Revert "KVM: nVMX: Expose RDPMC-exiting only when guest supports PMU" kvm: x86: Fix L1TF mitigation for shadow MMU KVM: nVMX: Disable intercept for FS/GS base MSRs in vmcs02 when possible KVM: PPC: Book3S: Remove useless checks in 'release' method of KVM device KVM: PPC: Book3S HV: XIVE: Fix spelling mistake "acessing" -> "accessing" KVM: PPC: Book3S HV: Make sure to load LPID for radix VCPUs kvm: nVMX: Set nested_run_pending in vmx_set_nested_state after checks complete tests: kvm: Add tests for KVM_SET_NESTED_STATE KVM: nVMX: KVM_SET_NESTED_STATE - Tear down old EVMCS state before setting new state tests: kvm: Add tests for KVM_CAP_MAX_VCPUS and KVM_CAP_MAX_CPU_ID tests: kvm: Add tests to .gitignore KVM: Introduce KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 KVM: Fix kvm_clear_dirty_log_protect off-by-(minus-)one KVM: Fix the bitmap range to copy during clear dirty KVM: arm64: Fix ptrauth ID register masking logic KVM: x86: use direct accessors for RIP and RSP KVM: VMX: Use accessors for GPRs outside of dedicated caching logic KVM: x86: Omit caching logic for always-available GPRs kvm, x86: Properly check whether a pfn is an MMIO or not ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2019-05-17 10:33:30 -0700
committer: Linus Torvalds <torvalds@linux-foundation.org> 2019-05-17 10:33:30 -0700
commit: 0ef0fd351550130129bbdb77362488befd7b69d2 (patch)
tree: 23186172f5f85c06e18e3ee1a9619879df03c5df /arch/powerpc/kvm
parent: 4489da7183099f569a7d3dd819c975073c04bc72 (diff)
parent: c011d23ba046826ccf8c4a4a6c1d01c9ccaa1403 (diff)
13 files changed, 2069 insertions, 269 deletions
diff --git a/arch/powerpc/kvm/Makefile b/arch/powerpc/kvm/Makefile
index 3223aec88b2c..4c67cc79de7c 100644
--- a/arch/powerpc/kvm/Makefile
+++ b/arch/powerpc/kvm/Makefile
@@ -94,7 +94,7 @@ endif
 kvm-book3s_64-objs-$(CONFIG_KVM_XICS) += \
 	book3s_xics.o
 
-kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o
+kvm-book3s_64-objs-$(CONFIG_KVM_XIVE) += book3s_xive.o book3s_xive_native.o
 kvm-book3s_64-objs-$(CONFIG_SPAPR_TCE_IOMMU) += book3s_64_vio.o
 
 kvm-book3s_64-module-objs := \
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 10c5579d20ce..61a212d0daf0 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -651,6 +651,18 @@ int kvmppc_get_one_reg(struct kvm_vcpu *vcpu, u64 id,
 				*val = get_reg_val(id, kvmppc_xics_get_icp(vcpu));
 			break;
 #endif /* CONFIG_KVM_XICS */
+#ifdef CONFIG_KVM_XIVE
+		case KVM_REG_PPC_VP_STATE:
+			if (!vcpu->arch.xive_vcpu) {
+				r = -ENXIO;
+				break;
+			}
+			if (xive_enabled())
+				r = kvmppc_xive_native_get_vp(vcpu, val);
+			else
+				r = -ENXIO;
+			break;
+#endif /* CONFIG_KVM_XIVE */
 		case KVM_REG_PPC_FSCR:
 			*val = get_reg_val(id, vcpu->arch.fscr);
 			break;
@@ -724,6 +736,18 @@ int kvmppc_set_one_reg(struct kvm_vcpu *vcpu, u64 id,
 				r = kvmppc_xics_set_icp(vcpu, set_reg_val(id, *val));
 			break;
 #endif /* CONFIG_KVM_XICS */
+#ifdef CONFIG_KVM_XIVE
+		case KVM_REG_PPC_VP_STATE:
+			if (!vcpu->arch.xive_vcpu) {
+				r = -ENXIO;
+				break;
+			}
+			if (xive_enabled())
+				r = kvmppc_xive_native_set_vp(vcpu, val);
+			else
+				r = -ENXIO;
+			break;
+#endif /* CONFIG_KVM_XIVE */
 		case KVM_REG_PPC_FSCR:
 			vcpu->arch.fscr = set_reg_val(id, *val);
 			break;
@@ -891,6 +915,17 @@ void kvmppc_core_destroy_vm(struct kvm *kvm)
 	kvmppc_rtas_tokens_free(kvm);
 	WARN_ON(!list_empty(&kvm->arch.spapr_tce_tables));
 #endif
+
+#ifdef CONFIG_KVM_XICS
+	/*
+	 * Free the XIVE devices which are not directly freed by the
+	 * device 'release' method
+	 */
+	kfree(kvm->arch.xive_devices.native);
+	kvm->arch.xive_devices.native = NULL;
+	kfree(kvm->arch.xive_devices.xics_on_xive);
+	kvm->arch.xive_devices.xics_on_xive = NULL;
+#endif /* CONFIG_KVM_XICS */
 }
 
 int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu)
@@ -1050,6 +1085,9 @@ static int kvmppc_book3s_init(void)
 	if (xics_on_xive()) {
 		kvmppc_xive_init_module();
 		kvm_register_device_ops(&kvm_xive_ops, KVM_DEV_TYPE_XICS);
+		kvmppc_xive_native_init_module();
+		kvm_register_device_ops(&kvm_xive_native_ops,
+					KVM_DEV_TYPE_XIVE);
 	} else
 #endif
 		kvm_register_device_ops(&kvm_xics_ops, KVM_DEV_TYPE_XICS);
@@ -1060,8 +1098,10 @@ static int kvmppc_book3s_init(void)
 static void kvmppc_book3s_exit(void)
 {
 #ifdef CONFIG_KVM_XICS
-	if (xics_on_xive())
+	if (xics_on_xive()) {
 		kvmppc_xive_exit_module();
+		kvmppc_xive_native_exit_module();
+	}
 #endif
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kvmppc_book3s_exit_pr();
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index f100e331e69b..66270e07449a 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -228,11 +228,33 @@ static void release_spapr_tce_table(struct rcu_head *head)
 	unsigned long i, npages = kvmppc_tce_pages(stt->size);
 
 	for (i = 0; i < npages; i++)
-		__free_page(stt->pages[i]);
+		if (stt->pages[i])
+			__free_page(stt->pages[i]);
 
 	kfree(stt);
 }
 
+static struct page *kvm_spapr_get_tce_page(struct kvmppc_spapr_tce_table *stt,
+		unsigned long sttpage)
+{
+	struct page *page = stt->pages[sttpage];
+
+	if (page)
+		return page;
+
+	mutex_lock(&stt->alloc_lock);
+	page = stt->pages[sttpage];
+	if (!page) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		WARN_ON_ONCE(!page);
+		if (page)
+			stt->pages[sttpage] = page;
+	}
+	mutex_unlock(&stt->alloc_lock);
+
+	return page;
+}
+
 static vm_fault_t kvm_spapr_tce_fault(struct vm_fault *vmf)
 {
 	struct kvmppc_spapr_tce_table *stt = vmf->vma->vm_file->private_data;
@@ -241,7 +263,10 @@ static vm_fault_t kvm_spapr_tce_fault(struct vm_fault *vmf)
 	if (vmf->pgoff >= kvmppc_tce_pages(stt->size))
 		return VM_FAULT_SIGBUS;
 
-	page = stt->pages[vmf->pgoff];
+	page = kvm_spapr_get_tce_page(stt, vmf->pgoff);
+	if (!page)
+		return VM_FAULT_OOM;
+
 	get_page(page);
 	vmf->page = page;
 	return 0;
@@ -296,7 +321,6 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	struct kvmppc_spapr_tce_table *siter;
 	unsigned long npages, size = args->size;
 	int ret = -ENOMEM;
-	int i;
 
 	if (!args->size || args->page_shift < 12 || args->page_shift > 34 ||
 		(args->offset + args->size > (ULLONG_MAX >> args->page_shift)))
@@ -318,14 +342,9 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	stt->offset = args->offset;
 	stt->size = size;
 	stt->kvm = kvm;
+	mutex_init(&stt->alloc_lock);
 	INIT_LIST_HEAD_RCU(&stt->iommu_tables);
 
-	for (i = 0; i < npages; i++) {
-		stt->pages[i] = alloc_page(GFP_KERNEL | __GFP_ZERO);
-		if (!stt->pages[i])
-			goto fail;
-	}
-
 	mutex_lock(&kvm->lock);
 
 	/* Check this LIOBN hasn't been previously allocated */
@@ -352,17 +371,28 @@ long kvm_vm_ioctl_create_spapr_tce(struct kvm *kvm,
 	if (ret >= 0)
 		return ret;
 
- fail:
-	for (i = 0; i < npages; i++)
-		if (stt->pages[i])
-			__free_page(stt->pages[i]);
-
 	kfree(stt);
  fail_acct:
 	kvmppc_account_memlimit(kvmppc_stt_pages(npages), false);
 	return ret;
 }
 
+static long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce,
+		unsigned long *ua)
+{
+	unsigned long gfn = tce >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	memslot = search_memslots(kvm_memslots(kvm), gfn);
+	if (!memslot)
+		return -EINVAL;
+
+	*ua = __gfn_to_hva_memslot(memslot, gfn) |
+		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+
+	return 0;
+}
+
 static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt,
 		unsigned long tce)
 {
@@ -378,7 +408,7 @@ static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt,
 	if (iommu_tce_check_gpa(stt->page_shift, gpa))
 		return H_TOO_HARD;
 
-	if (kvmppc_tce_to_ua(stt->kvm, tce, &ua, NULL))
+	if (kvmppc_tce_to_ua(stt->kvm, tce, &ua))
 		return H_TOO_HARD;
 
 	list_for_each_entry_rcu(stit, &stt->iommu_tables, next) {
@@ -397,6 +427,36 @@ static long kvmppc_tce_validate(struct kvmppc_spapr_tce_table *stt,
 	return H_SUCCESS;
 }
 
+/*
+ * Handles TCE requests for emulated devices.
+ * Puts guest TCE values to the table and expects user space to convert them.
+ * Cannot fail so kvmppc_tce_validate must be called before it.
+ */
+static void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
+		unsigned long idx, unsigned long tce)
+{
+	struct page *page;
+	u64 *tbl;
+	unsigned long sttpage;
+
+	idx -= stt->offset;
+	sttpage = idx / TCES_PER_PAGE;
+	page = stt->pages[sttpage];
+
+	if (!page) {
+		/* We allow any TCE, not just with read|write permissions */
+		if (!tce)
+			return;
+
+		page = kvm_spapr_get_tce_page(stt, sttpage);
+		if (!page)
+			return;
+	}
+	tbl = page_to_virt(page);
+
+	tbl[idx % TCES_PER_PAGE] = tce;
+}
+
 static void kvmppc_clear_tce(struct mm_struct *mm, struct iommu_table *tbl,
 		unsigned long entry)
 {
@@ -551,7 +611,7 @@ long kvmppc_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 
 	dir = iommu_tce_direction(tce);
 
-	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL)) {
+	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua)) {
 		ret = H_PARAMETER;
 		goto unlock_exit;
 	}
@@ -612,7 +672,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		return ret;
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua, NULL)) {
+	if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua)) {
 		ret = H_TOO_HARD;
 		goto unlock_exit;
 	}
@@ -647,7 +707,7 @@ long kvmppc_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		}
 		tce = be64_to_cpu(tce);
 
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
+		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua))
 			return H_PARAMETER;
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 2206bc729b9a..484b47fa3960 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -66,8 +66,6 @@
 
 #endif
 
-#define TCES_PER_PAGE	(PAGE_SIZE / sizeof(u64))
-
 /*
  * Finds a TCE table descriptor by LIOBN.
  *
@@ -88,6 +86,25 @@ struct kvmppc_spapr_tce_table *kvmppc_find_table(struct kvm *kvm,
 EXPORT_SYMBOL_GPL(kvmppc_find_table);
 
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+static long kvmppc_rm_tce_to_ua(struct kvm *kvm, unsigned long tce,
+		unsigned long *ua, unsigned long **prmap)
+{
+	unsigned long gfn = tce >> PAGE_SHIFT;
+	struct kvm_memory_slot *memslot;
+
+	memslot = search_memslots(kvm_memslots_raw(kvm), gfn);
+	if (!memslot)
+		return -EINVAL;
+
+	*ua = __gfn_to_hva_memslot(memslot, gfn) |
+		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+
+	if (prmap)
+		*prmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
+
+	return 0;
+}
+
 /*
  * Validates TCE address.
  * At the moment flags and page mask are validated.
@@ -111,7 +128,7 @@ static long kvmppc_rm_tce_validate(struct kvmppc_spapr_tce_table *stt,
 	if (iommu_tce_check_gpa(stt->page_shift, gpa))
 		return H_PARAMETER;
 
-	if (kvmppc_tce_to_ua(stt->kvm, tce, &ua, NULL))
+	if (kvmppc_rm_tce_to_ua(stt->kvm, tce, &ua, NULL))
 		return H_TOO_HARD;
 
 	list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
@@ -129,7 +146,6 @@ static long kvmppc_rm_tce_validate(struct kvmppc_spapr_tce_table *stt,
 
 	return H_SUCCESS;
 }
-#endif /* CONFIG_KVM_BOOK3S_HV_POSSIBLE */
 
 /* Note on the use of page_address() in real mode,
  *
@@ -161,13 +177,9 @@ static u64 *kvmppc_page_address(struct page *page)
 /*
  * Handles TCE requests for emulated devices.
  * Puts guest TCE values to the table and expects user space to convert them.
- * Called in both real and virtual modes.
- * Cannot fail so kvmppc_tce_validate must be called before it.
- *
- * WARNING: This will be called in real-mode on HV KVM and virtual
- *          mode on PR KVM
+ * Cannot fail so kvmppc_rm_tce_validate must be called before it.
  */
-void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
+static void kvmppc_rm_tce_put(struct kvmppc_spapr_tce_table *stt,
 		unsigned long idx, unsigned long tce)
 {
 	struct page *page;
@@ -175,35 +187,48 @@ void kvmppc_tce_put(struct kvmppc_spapr_tce_table *stt,
 
 	idx -= stt->offset;
 	page = stt->pages[idx / TCES_PER_PAGE];
+	/*
+	 * page must not be NULL in real mode,
+	 * kvmppc_rm_ioba_validate() must have taken care of this.
+	 */
+	WARN_ON_ONCE_RM(!page);
 	tbl = kvmppc_page_address(page);
 
 	tbl[idx % TCES_PER_PAGE] = tce;
 }
-EXPORT_SYMBOL_GPL(kvmppc_tce_put);
 
-long kvmppc_tce_to_ua(struct kvm *kvm, unsigned long tce,
-		unsigned long *ua, unsigned long **prmap)
+/*
+ * TCEs pages are allocated in kvmppc_rm_tce_put() which won't be able to do so
+ * in real mode.
+ * Check if kvmppc_rm_tce_put() can succeed in real mode, i.e. a TCEs page is
+ * allocated or not required (when clearing a tce entry).
+ */
+static long kvmppc_rm_ioba_validate(struct kvmppc_spapr_tce_table *stt,
+		unsigned long ioba, unsigned long npages, bool clearing)
 {
-	unsigned long gfn = tce >> PAGE_SHIFT;
-	struct kvm_memory_slot *memslot;
+	unsigned long i, idx, sttpage, sttpages;
+	unsigned long ret = kvmppc_ioba_validate(stt, ioba, npages);
 
-	memslot = search_memslots(kvm_memslots(kvm), gfn);
-	if (!memslot)
-		return -EINVAL;
-
-	*ua = __gfn_to_hva_memslot(memslot, gfn) |
-		(tce & ~(PAGE_MASK | TCE_PCI_READ | TCE_PCI_WRITE));
+	if (ret)
+		return ret;
+	/*
+	 * clearing==true says kvmppc_rm_tce_put won't be allocating pages
+	 * for empty tces.
+	 */
+	if (clearing)
+		return H_SUCCESS;
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
-	if (prmap)
-		*prmap = &memslot->arch.rmap[gfn - memslot->base_gfn];
-#endif
+	idx = (ioba >> stt->page_shift) - stt->offset;
+	sttpage = idx / TCES_PER_PAGE;
+	sttpages = _ALIGN_UP(idx % TCES_PER_PAGE + npages, TCES_PER_PAGE) /
+			TCES_PER_PAGE;
+	for (i = sttpage; i < sttpage + sttpages; ++i)
+		if (!stt->pages[i])
+			return H_TOO_HARD;
 
-	return 0;
+	return H_SUCCESS;
 }
-EXPORT_SYMBOL_GPL(kvmppc_tce_to_ua);
 
-#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 static long iommu_tce_xchg_rm(struct mm_struct *mm, struct iommu_table *tbl,
 		unsigned long entry, unsigned long *hpa,
 		enum dma_data_direction *direction)
@@ -381,7 +406,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 	if (!stt)
 		return H_TOO_HARD;
 
-	ret = kvmppc_ioba_validate(stt, ioba, 1);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, 1, tce == 0);
 	if (ret != H_SUCCESS)
 		return ret;
 
@@ -390,7 +415,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		return ret;
 
 	dir = iommu_tce_direction(tce);
-	if ((dir != DMA_NONE) && kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
+	if ((dir != DMA_NONE) && kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
 		return H_PARAMETER;
 
 	entry = ioba >> stt->page_shift;
@@ -409,7 +434,7 @@ long kvmppc_rm_h_put_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 		}
 	}
 
-	kvmppc_tce_put(stt, entry, tce);
+	kvmppc_rm_tce_put(stt, entry, tce);
 
 	return H_SUCCESS;
 }
@@ -480,7 +505,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 	if (tce_list & (SZ_4K - 1))
 		return H_PARAMETER;
 
-	ret = kvmppc_ioba_validate(stt, ioba, npages);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, npages, false);
 	if (ret != H_SUCCESS)
 		return ret;
 
@@ -492,7 +517,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 */
 		struct mm_iommu_table_group_mem_t *mem;
 
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua, NULL))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua, NULL))
 			return H_TOO_HARD;
 
 		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
@@ -508,7 +533,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		 * We do not require memory to be preregistered in this case
 		 * so lock rmap and do __find_linux_pte_or_hugepte().
 		 */
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce_list, &ua, &rmap))
 			return H_TOO_HARD;
 
 		rmap = (void *) vmalloc_to_phys(rmap);
@@ -542,7 +567,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 		unsigned long tce = be64_to_cpu(((u64 *)tces)[i]);
 
 		ua = 0;
-		if (kvmppc_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
+		if (kvmppc_rm_tce_to_ua(vcpu->kvm, tce, &ua, NULL))
 			return H_PARAMETER;
 
 		list_for_each_entry_lockless(stit, &stt->iommu_tables, next) {
@@ -557,7 +582,7 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 			}
 		}
 
-		kvmppc_tce_put(stt, entry + i, tce);
+		kvmppc_rm_tce_put(stt, entry + i, tce);
 	}
 
 unlock_exit:
@@ -583,7 +608,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	if (!stt)
 		return H_TOO_HARD;
 
-	ret = kvmppc_ioba_validate(stt, ioba, npages);
+	ret = kvmppc_rm_ioba_validate(stt, ioba, npages, tce_value == 0);
 	if (ret != H_SUCCESS)
 		return ret;
 
@@ -610,7 +635,7 @@ long kvmppc_rm_h_stuff_tce(struct kvm_vcpu *vcpu,
 	}
 
 	for (i = 0; i < npages; ++i, ioba += (1ULL << stt->page_shift))
-		kvmppc_tce_put(stt, ioba >> stt->page_shift, tce_value);
+		kvmppc_rm_tce_put(stt, ioba >> stt->page_shift, tce_value);
 
 	return H_SUCCESS;
 }
@@ -635,6 +660,10 @@ long kvmppc_h_get_tce(struct kvm_vcpu *vcpu, unsigned long liobn,
 
 	idx = (ioba >> stt->page_shift) - stt->offset;
 	page = stt->pages[idx / TCES_PER_PAGE];
+	if (!page) {
+		vcpu->arch.regs.gpr[4] = 0;
+		return H_SUCCESS;
+	}
 	tbl = (u64 *)page_address(page);
 
 	vcpu->arch.regs.gpr[4] = tbl[idx % TCES_PER_PAGE];
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 7bdcd4d7a9f0..d5fc624e0655 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -750,7 +750,7 @@ static bool kvmppc_doorbell_pending(struct kvm_vcpu *vcpu)
 	/*
 	 * Ensure that the read of vcore->dpdes comes after the read
 	 * of vcpu->doorbell_request.  This barrier matches the
-	 * smb_wmb() in kvmppc_guest_entry_inject().
+	 * smp_wmb() in kvmppc_guest_entry_inject().
 	 */
 	smp_rmb();
 	vc = vcpu->arch.vcore;
@@ -802,6 +802,80 @@ static int kvmppc_h_set_mode(struct kvm_vcpu *vcpu, unsigned long mflags,
 	}
 }
 
+/* Copy guest memory in place - must reside within a single memslot */
+static int kvmppc_copy_guest(struct kvm *kvm, gpa_t to, gpa_t from,
+				  unsigned long len)
+{
+	struct kvm_memory_slot *to_memslot = NULL;
+	struct kvm_memory_slot *from_memslot = NULL;
+	unsigned long to_addr, from_addr;
+	int r;
+
+	/* Get HPA for from address */
+	from_memslot = gfn_to_memslot(kvm, from >> PAGE_SHIFT);
+	if (!from_memslot)
+		return -EFAULT;
+	if ((from + len) >= ((from_memslot->base_gfn + from_memslot->npages)
+			     << PAGE_SHIFT))
+		return -EINVAL;
+	from_addr = gfn_to_hva_memslot(from_memslot, from >> PAGE_SHIFT);
+	if (kvm_is_error_hva(from_addr))
+		return -EFAULT;
+	from_addr |= (from & (PAGE_SIZE - 1));
+
+	/* Get HPA for to address */
+	to_memslot = gfn_to_memslot(kvm, to >> PAGE_SHIFT);
+	if (!to_memslot)
+		return -EFAULT;
+	if ((to + len) >= ((to_memslot->base_gfn + to_memslot->npages)
+			   << PAGE_SHIFT))
+		return -EINVAL;
+	to_addr = gfn_to_hva_memslot(to_memslot, to >> PAGE_SHIFT);
+	if (kvm_is_error_hva(to_addr))
+		return -EFAULT;
+	to_addr |= (to & (PAGE_SIZE - 1));
+
+	/* Perform copy */
+	r = raw_copy_in_user((void __user *)to_addr, (void __user *)from_addr,
+			     len);
+	if (r)
+		return -EFAULT;
+	mark_page_dirty(kvm, to >> PAGE_SHIFT);
+	return 0;
+}
+
+static long kvmppc_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
+			       unsigned long dest, unsigned long src)
+{
+	u64 pg_sz = SZ_4K;		/* 4K page size */
+	u64 pg_mask = SZ_4K - 1;
+	int ret;
+
+	/* Check for invalid flags (H_PAGE_SET_LOANED covers all CMO flags) */
+	if (flags & ~(H_ICACHE_INVALIDATE | H_ICACHE_SYNCHRONIZE |
+		      H_ZERO_PAGE | H_COPY_PAGE | H_PAGE_SET_LOANED))
+		return H_PARAMETER;
+
+	/* dest (and src if copy_page flag set) must be page aligned */
+	if ((dest & pg_mask) || ((flags & H_COPY_PAGE) && (src & pg_mask)))
+		return H_PARAMETER;
+
+	/* zero and/or copy the page as determined by the flags */
+	if (flags & H_COPY_PAGE) {
+		ret = kvmppc_copy_guest(vcpu->kvm, dest, src, pg_sz);
+		if (ret < 0)
+			return H_PARAMETER;
+	} else if (flags & H_ZERO_PAGE) {
+		ret = kvm_clear_guest(vcpu->kvm, dest, pg_sz);
+		if (ret < 0)
+			return H_PARAMETER;
+	}
+
+	/* We can ignore the remaining flags */
+
+	return H_SUCCESS;
+}
+
 static int kvm_arch_vcpu_yield_to(struct kvm_vcpu *target)
 {
 	struct kvmppc_vcore *vcore = target->arch.vcore;
@@ -1004,6 +1078,11 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (nesting_enabled(vcpu->kvm))
 			ret = kvmhv_copy_tofrom_guest_nested(vcpu);
 		break;
+	case H_PAGE_INIT:
+		ret = kvmppc_h_page_init(vcpu, kvmppc_get_gpr(vcpu, 4),
+					 kvmppc_get_gpr(vcpu, 5),
+					 kvmppc_get_gpr(vcpu, 6));
+		break;
 	default:
 		return RESUME_HOST;
 	}
@@ -1048,6 +1127,7 @@ static int kvmppc_hcall_impl_hv(unsigned long cmd)
 	case H_IPOLL:
 	case H_XIRR_X:
 #endif
+	case H_PAGE_INIT:
 		return 1;
 	}
 
@@ -2505,37 +2585,6 @@ static void kvmppc_prepare_radix_vcpu(struct kvm_vcpu *vcpu, int pcpu)
 	}
 }
 
-static void kvmppc_radix_check_need_tlb_flush(struct kvm *kvm, int pcpu,
-					      struct kvm_nested_guest *nested)
-{
-	cpumask_t *need_tlb_flush;
-	int lpid;
-
-	if (!cpu_has_feature(CPU_FTR_HVMODE))
-		return;
-
-	if (cpu_has_feature(CPU_FTR_ARCH_300))
-		pcpu &= ~0x3UL;
-
-	if (nested) {
-		lpid = nested->shadow_lpid;
-		need_tlb_flush = &nested->need_tlb_flush;
-	} else {
-		lpid = kvm->arch.lpid;
-		need_tlb_flush = &kvm->arch.need_tlb_flush;
-	}
-
-	mtspr(SPRN_LPID, lpid);
-	isync();
-	smp_mb();
-
-	if (cpumask_test_cpu(pcpu, need_tlb_flush)) {
-		radix__local_flush_tlb_lpid_guest(lpid);
-		/* Clear the bit after the TLB flush */
-		cpumask_clear_cpu(pcpu, need_tlb_flush);
-	}
-}
-
 static void kvmppc_start_thread(struct kvm_vcpu *vcpu, struct kvmppc_vcore *vc)
 {
 	int cpu;
@@ -3229,19 +3278,11 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	for (sub = 0; sub < core_info.n_subcores; ++sub)
 		spin_unlock(&core_info.vc[sub]->lock);
 
-	if (kvm_is_radix(vc->kvm)) {
-		/*
-		 * Do we need to flush the process scoped TLB for the LPAR?
-		 *
-		 * On POWER9, individual threads can come in here, but the
-		 * TLB is shared between the 4 threads in a core, hence
-		 * invalidating on one thread invalidates for all.
-		 * Thus we make all 4 threads use the same bit here.
-		 *
-		 * Hash must be flushed in realmode in order to use tlbiel.
-		 */
-		kvmppc_radix_check_need_tlb_flush(vc->kvm, pcpu, NULL);
-	}
+	guest_enter_irqoff();
+
+	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
+
+	this_cpu_disable_ftrace();
 
 	/*
 	 * Interrupts will be enabled once we get into the guest,
@@ -3249,19 +3290,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
 	 */
 	trace_hardirqs_on();
 
-	guest_enter_irqoff();
-
-	srcu_idx = srcu_read_lock(&vc->kvm->srcu);
-
-	this_cpu_disable_ftrace();
-
 	trap = __kvmppc_vcore_entry();
 
+	trace_hardirqs_off();
+
 	this_cpu_enable_ftrace();
 
 	srcu_read_unlock(&vc->kvm->srcu, srcu_idx);
 
-	trace_hardirqs_off();
 	set_irq_happened(trap);
 
 	spin_lock(&vc->lock);
@@ -3514,6 +3550,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 #ifdef CONFIG_ALTIVEC
 	load_vr_state(&vcpu->arch.vr);
 #endif
+	mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
 
 	mtspr(SPRN_DSCR, vcpu->arch.dscr);
 	mtspr(SPRN_IAMR, vcpu->arch.iamr);
@@ -3605,6 +3642,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 #ifdef CONFIG_ALTIVEC
 	store_vr_state(&vcpu->arch.vr);
 #endif
+	vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
 
 	if (cpu_has_feature(CPU_FTR_TM) ||
 	    cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST))
@@ -3970,7 +4008,7 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
 			  unsigned long lpcr)
 {
 	int trap, r, pcpu;
-	int srcu_idx;
+	int srcu_idx, lpid;
 	struct kvmppc_vcore *vc;
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_nested_guest *nested = vcpu->arch.nested;
@@ -4046,8 +4084,12 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
 	vc->vcore_state = VCORE_RUNNING;
 	trace_kvmppc_run_core(vc, 0);
 
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		kvmppc_radix_check_need_tlb_flush(kvm, pcpu, nested);
+	if (cpu_has_feature(CPU_FTR_HVMODE)) {
+		lpid = nested ? nested->shadow_lpid : kvm->arch.lpid;
+		mtspr(SPRN_LPID, lpid);
+		isync();
+		kvmppc_check_need_tlb_flush(kvm, pcpu, nested);
+	}
 
 	trace_hardirqs_on();
 	guest_enter_irqoff();
diff --git a/arch/powerpc/kvm/book3s_hv_builtin.c b/arch/powerpc/kvm/book3s_hv_builtin.c
index b0cf22477e87..6035d24f1d1d 100644
--- a/arch/powerpc/kvm/book3s_hv_builtin.c
+++ b/arch/powerpc/kvm/book3s_hv_builtin.c
@@ -805,3 +805,60 @@ void kvmppc_guest_entry_inject_int(struct kvm_vcpu *vcpu)
 		vcpu->arch.doorbell_request = 0;
 	}
 }
+
+static void flush_guest_tlb(struct kvm *kvm)
+{
+	unsigned long rb, set;
+
+	rb = PPC_BIT(52);	/* IS = 2 */
+	if (kvm_is_radix(kvm)) {
+		/* R=1 PRS=1 RIC=2 */
+		asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+			     : : "r" (rb), "i" (1), "i" (1), "i" (2),
+			       "r" (0) : "memory");
+		for (set = 1; set < kvm->arch.tlb_sets; ++set) {
+			rb += PPC_BIT(51);	/* increment set number */
+			/* R=1 PRS=1 RIC=0 */
+			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+				     : : "r" (rb), "i" (1), "i" (1), "i" (0),
+				       "r" (0) : "memory");
+		}
+	} else {
+		for (set = 0; set < kvm->arch.tlb_sets; ++set) {
+			/* R=0 PRS=0 RIC=0 */
+			asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+				     : : "r" (rb), "i" (0), "i" (0), "i" (0),
+				       "r" (0) : "memory");
+			rb += PPC_BIT(51);	/* increment set number */
+		}
+	}
+	asm volatile("ptesync": : :"memory");
+}
+
+void kvmppc_check_need_tlb_flush(struct kvm *kvm, int pcpu,
+				 struct kvm_nested_guest *nested)
+{
+	cpumask_t *need_tlb_flush;
+
+	/*
+	 * On POWER9, individual threads can come in here, but the
+	 * TLB is shared between the 4 threads in a core, hence
+	 * invalidating on one thread invalidates for all.
+	 * Thus we make all 4 threads use the same bit.
+	 */
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
+		pcpu = cpu_first_thread_sibling(pcpu);
+
+	if (nested)
+		need_tlb_flush = &nested->need_tlb_flush;
+	else
+		need_tlb_flush = &kvm->arch.need_tlb_flush;
+
+	if (cpumask_test_cpu(pcpu, need_tlb_flush)) {
+		flush_guest_tlb(kvm);
+
+		/* Clear the bit after the TLB flush */
+		cpumask_clear_cpu(pcpu, need_tlb_flush);
+	}
+}
+EXPORT_SYMBOL_GPL(kvmppc_check_need_tlb_flush);
diff --git a/arch/powerpc/kvm/book3s_hv_rm_mmu.c b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
index 3b3791ed74a6..8431ad1e8391 100644
--- a/arch/powerpc/kvm/book3s_hv_rm_mmu.c
+++ b/arch/powerpc/kvm/book3s_hv_rm_mmu.c
@@ -13,6 +13,7 @@
 #include <linux/hugetlb.h>
 #include <linux/module.h>
 #include <linux/log2.h>
+#include <linux/sizes.h>
 
 #include <asm/trace.h>
 #include <asm/kvm_ppc.h>
@@ -867,6 +868,149 @@ long kvmppc_h_clear_mod(struct kvm_vcpu *vcpu, unsigned long flags,
 	return ret;
 }
 
+static int kvmppc_get_hpa(struct kvm_vcpu *vcpu, unsigned long gpa,
+			  int writing, unsigned long *hpa,
+			  struct kvm_memory_slot **memslot_p)
+{
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_memory_slot *memslot;
+	unsigned long gfn, hva, pa, psize = PAGE_SHIFT;
+	unsigned int shift;
+	pte_t *ptep, pte;
+
+	/* Find the memslot for this address */
+	gfn = gpa >> PAGE_SHIFT;
+	memslot = __gfn_to_memslot(kvm_memslots_raw(kvm), gfn);
+	if (!memslot || (memslot->flags & KVM_MEMSLOT_INVALID))
+		return H_PARAMETER;
+
+	/* Translate to host virtual address */
+	hva = __gfn_to_hva_memslot(memslot, gfn);
+
+	/* Try to find the host pte for that virtual address */
+	ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+	if (!ptep)
+		return H_TOO_HARD;
+	pte = kvmppc_read_update_linux_pte(ptep, writing);
+	if (!pte_present(pte))
+		return H_TOO_HARD;
+
+	/* Convert to a physical address */
+	if (shift)
+		psize = 1UL << shift;
+	pa = pte_pfn(pte) << PAGE_SHIFT;
+	pa |= hva & (psize - 1);
+	pa |= gpa & ~PAGE_MASK;
+
+	if (hpa)
+		*hpa = pa;
+	if (memslot_p)
+		*memslot_p = memslot;
+
+	return H_SUCCESS;
+}
+
+static long kvmppc_do_h_page_init_zero(struct kvm_vcpu *vcpu,
+				       unsigned long dest)
+{
+	struct kvm_memory_slot *memslot;
+	struct kvm *kvm = vcpu->kvm;
+	unsigned long pa, mmu_seq;
+	long ret = H_SUCCESS;
+	int i;
+
+	/* Used later to detect if we might have been invalidated */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	ret = kvmppc_get_hpa(vcpu, dest, 1, &pa, &memslot);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	/* Check if we've been invalidated */
+	raw_spin_lock(&kvm->mmu_lock.rlock);
+	if (mmu_notifier_retry(kvm, mmu_seq)) {
+		ret = H_TOO_HARD;
+		goto out_unlock;
+	}
+
+	/* Zero the page */
+	for (i = 0; i < SZ_4K; i += L1_CACHE_BYTES, pa += L1_CACHE_BYTES)
+		dcbz((void *)pa);
+	kvmppc_update_dirty_map(memslot, dest >> PAGE_SHIFT, PAGE_SIZE);
+
+out_unlock:
+	raw_spin_unlock(&kvm->mmu_lock.rlock);
+	return ret;
+}
+
+static long kvmppc_do_h_page_init_copy(struct kvm_vcpu *vcpu,
+				       unsigned long dest, unsigned long src)
+{
+	unsigned long dest_pa, src_pa, mmu_seq;
+	struct kvm_memory_slot *dest_memslot;
+	struct kvm *kvm = vcpu->kvm;
+	long ret = H_SUCCESS;
+
+	/* Used later to detect if we might have been invalidated */
+	mmu_seq = kvm->mmu_notifier_seq;
+	smp_rmb();
+
+	ret = kvmppc_get_hpa(vcpu, dest, 1, &dest_pa, &dest_memslot);
+	if (ret != H_SUCCESS)
+		return ret;
+	ret = kvmppc_get_hpa(vcpu, src, 0, &src_pa, NULL);
+	if (ret != H_SUCCESS)
+		return ret;
+
+	/* Check if we've been invalidated */
+	raw_spin_lock(&kvm->mmu_lock.rlock);
+	if (mmu_notifier_retry(kvm, mmu_seq)) {
+		ret = H_TOO_HARD;
+		goto out_unlock;
+	}
+
+	/* Copy the page */
+	memcpy((void *)dest_pa, (void *)src_pa, SZ_4K);
+
+	kvmppc_update_dirty_map(dest_memslot, dest >> PAGE_SHIFT, PAGE_SIZE);
+
+out_unlock:
+	raw_spin_unlock(&kvm->mmu_lock.rlock);
+	return ret;
+}
+
+long kvmppc_rm_h_page_init(struct kvm_vcpu *vcpu, unsigned long flags,
+			   unsigned long dest, unsigned long src)
+{
+	struct kvm *kvm = vcpu->kvm;
+	u64 pg_mask = SZ_4K - 1;	/* 4K page size */
+	long ret = H_SUCCESS;
+
+	/* Don't handle radix mode here, go up to the virtual mode handler */
+	if (kvm_is_radix(kvm))
+		return H_TOO_HARD;
+
+	/* Check for invalid flags (H_PAGE_SET_LOANED covers all CMO flags) */
+	if (flags & ~(H_ICACHE_INVALIDATE | H_ICACHE_SYNCHRONIZE |
+		      H_ZERO_PAGE | H_COPY_PAGE | H_PAGE_SET_LOANED))
+		return H_PARAMETER;
+
+	/* dest (and src if copy_page flag set) must be page aligned */
+	if ((dest & pg_mask) || ((flags & H_COPY_PAGE) && (src & pg_mask)))
+		return H_PARAMETER;
+
+	/* zero and/or copy the page as determined by the flags */
+	if (flags & H_COPY_PAGE)
+		ret = kvmppc_do_h_page_init_copy(vcpu, dest, src);
+	else if (flags & H_ZERO_PAGE)
+		ret = kvmppc_do_h_page_init_zero(vcpu, dest);
+
+	/* We can ignore the other flags */
+
+	return ret;
+}
+
 void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
 			unsigned long pte_index)
 {
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index dd014308f065..f9b2620fbecd 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -589,11 +589,8 @@ kvmppc_hv_entry:
 1:
 #endif
 
-	/* Use cr7 as an indication of radix mode */
 	ld	r5, HSTATE_KVM_VCORE(r13)
 	ld	r9, VCORE_KVM(r5)	/* pointer to struct kvm */
-	lbz	r0, KVM_RADIX(r9)
-	cmpwi	cr7, r0, 0
 
 	/*
 	 * POWER7/POWER8 host -> guest partition switch code.
@@ -616,9 +613,6 @@ kvmppc_hv_entry:
 	cmpwi	r6,0
 	bne	10f
 
-	/* Radix has already switched LPID and flushed core TLB */
-	bne	cr7, 22f
-
 	lwz	r7,KVM_LPID(r9)
 BEGIN_FTR_SECTION
 	ld	r6,KVM_SDR1(r9)
@@ -630,41 +624,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_LPID,r7
 	isync
 
-	/* See if we need to flush the TLB. Hash has to be done in RM */
-	lhz	r6,PACAPACAINDEX(r13)	/* test_bit(cpu, need_tlb_flush) */
-BEGIN_FTR_SECTION
-	/*
-	 * On POWER9, individual threads can come in here, but the
-	 * TLB is shared between the 4 threads in a core, hence
-	 * invalidating on one thread invalidates for all.
-	 * Thus we make all 4 threads use the same bit here.
-	 */
-	clrrdi	r6,r6,2
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
-	clrldi	r7,r6,64-6		/* extract bit number (6 bits) */
-	srdi	r6,r6,6			/* doubleword number */
-	sldi	r6,r6,3			/* address offset */
-	add	r6,r6,r9
-	addi	r6,r6,KVM_NEED_FLUSH	/* dword in kvm->arch.need_tlb_flush */
-	li	r8,1
-	sld	r8,r8,r7
-	ld	r7,0(r6)
-	and.	r7,r7,r8
-	beq	22f
-	/* Flush the TLB of any entries for this LPID */
-	lwz	r0,KVM_TLB_SETS(r9)
-	mtctr	r0
-	li	r7,0x800		/* IS field = 0b10 */
-	ptesync
-	li	r0,0			/* RS for P9 version of tlbiel */
-28:	tlbiel	r7			/* On P9, rs=0, RIC=0, PRS=0, R=0 */
-	addi	r7,r7,0x1000
-	bdnz	28b
-	ptesync
-23:	ldarx	r7,0,r6			/* clear the bit after TLB flushed */
-	andc	r7,r7,r8
-	stdcx.	r7,0,r6
-	bne	23b
+	/* See if we need to flush the TLB. */
+	mr	r3, r9			/* kvm pointer */
+	lhz	r4, PACAPACAINDEX(r13)	/* physical cpu number */
+	li	r5, 0			/* nested vcpu pointer */
+	bl	kvmppc_check_need_tlb_flush
+	nop
+	ld	r5, HSTATE_KVM_VCORE(r13)
 
 	/* Add timebase offset onto timebase */
 22:	ld	r8,VCORE_TB_OFFSET(r5)
@@ -980,17 +946,27 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 
 #ifdef CONFIG_KVM_XICS
 	/* We are entering the guest on that thread, push VCPU to XIVE */
-	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
-	cmpldi	cr0, r10, 0
-	beq	no_xive
 	ld	r11, VCPU_XIVE_SAVED_STATE(r4)
 	li	r9, TM_QW1_OS
+	lwz	r8, VCPU_XIVE_CAM_WORD(r4)
+	li	r7, TM_QW1_OS + TM_WORD2
+	mfmsr	r0
+	andi.	r0, r0, MSR_DR		/* in real mode? */
+	beq	2f
+	ld	r10, HSTATE_XIVE_TIMA_VIRT(r13)
+	cmpldi	cr1, r10, 0
+	beq     cr1, no_xive
+	eieio
+	stdx	r11,r9,r10
+	stwx	r8,r7,r10
+	b	3f
+2:	ld	r10, HSTATE_XIVE_TIMA_PHYS(r13)
+	cmpldi	cr1, r10, 0
+	beq	cr1, no_xive
 	eieio
 	stdcix	r11,r9,r10
-	lwz	r11, VCPU_XIVE_CAM_WORD(r4)
-	li	r9, TM_QW1_OS + TM_WORD2
-	stwcix	r11,r9,r10
-	li	r9, 1
+	stwcix	r8,r7,r10
+3:	li	r9, 1
 	stb	r9, VCPU_XIVE_PUSHED(r4)
 	eieio
 
@@ -1009,12 +985,16 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	 * on, we mask it.
 	 */
 	lbz	r0, VCPU_XIVE_ESC_ON(r4)
-	cmpwi	r0,0
-	beq	1f
-	ld	r10, VCPU_XIVE_ESC_RADDR(r4)
+	cmpwi	cr1, r0,0
+	beq	cr1, 1f
 	li	r9, XIVE_ESB_SET_PQ_01
+	beq	4f			/* in real mode? */
+	ld	r10, VCPU_XIVE_ESC_VADDR(r4)
+	ldx	r0, r10, r9
+	b	5f
+4:	ld	r10, VCPU_XIVE_ESC_RADDR(r4)
 	ldcix	r0, r10, r9
-	sync
+5:	sync
 
 	/* We have a possible subtle race here: The escalation interrupt might
 	 * have fired and be on its way to the host queue while we mask it,
@@ -2292,7 +2272,7 @@ hcall_real_table:
 #endif
 	.long	0		/* 0x24 - H_SET_SPRG0 */
 	.long	DOTSYM(kvmppc_h_set_dabr) - hcall_real_table
-	.long	0		/* 0x2c */
+	.long	DOTSYM(kvmppc_rm_h_page_init) - hcall_real_table
 	.long	0		/* 0x30 */
 	.long	0		/* 0x34 */
 	.long	0		/* 0x38 */
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index f78d002f0fe0..4953957333b7 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -166,7 +166,8 @@ static irqreturn_t xive_esc_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
+int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
+				  bool single_escalation)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
 	struct xive_q *q = &xc->queues[prio];
@@ -185,7 +186,7 @@ static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
 		return -EIO;
 	}
 
-	if (xc->xive->single_escalation)
+	if (single_escalation)
 		name = kasprintf(GFP_KERNEL, "kvm-%d-%d",
 				 vcpu->kvm->arch.lpid, xc->server_num);
 	else
@@ -217,7 +218,7 @@ static int xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio)
 	 * interrupt, thus leaving it effectively masked after
 	 * it fires once.
 	 */
-	if (xc->xive->single_escalation) {
+	if (single_escalation) {
 		struct irq_data *d = irq_get_irq_data(xc->esc_virq[prio]);
 		struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
 
@@ -291,7 +292,8 @@ static int xive_check_provisioning(struct kvm *kvm, u8 prio)
 			continue;
 		rc = xive_provision_queue(vcpu, prio);
 		if (rc == 0 && !xive->single_escalation)
-			xive_attach_escalation(vcpu, prio);
+			kvmppc_xive_attach_escalation(vcpu, prio,
+						      xive->single_escalation);
 		if (rc)
 			return rc;
 	}
@@ -342,7 +344,7 @@ static int xive_try_pick_queue(struct kvm_vcpu *vcpu, u8 prio)
 	return atomic_add_unless(&q->count, 1, max) ? 0 : -EBUSY;
 }
 
-static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
+int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
 {
 	struct kvm_vcpu *vcpu;
 	int i, rc;
@@ -380,11 +382,6 @@ static int xive_select_target(struct kvm *kvm, u32 *server, u8 prio)
 	return -EBUSY;
 }
 
-static u32 xive_vp(struct kvmppc_xive *xive, u32 server)
-{
-	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
-}
-
 static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
 			     struct kvmppc_xive_src_block *sb,
 			     struct kvmppc_xive_irq_state *state)
@@ -430,8 +427,8 @@ static u8 xive_lock_and_mask(struct kvmppc_xive *xive,
 	 */
 	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
 		xive_native_configure_irq(hw_num,
-					  xive_vp(xive, state->act_server),
-					  MASKED, state->number);
+				kvmppc_xive_vp(xive, state->act_server),
+				MASKED, state->number);
 		/* set old_p so we can track if an H_EOI was done */
 		state->old_p = true;
 		state->old_q = false;
@@ -486,8 +483,8 @@ static void xive_finish_unmask(struct kvmppc_xive *xive,
 	 */
 	if (xd->flags & OPAL_XIVE_IRQ_MASK_VIA_FW) {
 		xive_native_configure_irq(hw_num,
-					  xive_vp(xive, state->act_server),
-					  state->act_priority, state->number);
+				kvmppc_xive_vp(xive, state->act_server),
+				state->act_priority, state->number);
 		/* If an EOI is needed, do it here */
 		if (!state->old_p)
 			xive_vm_source_eoi(hw_num, xd);
@@ -535,7 +532,7 @@ static int xive_target_interrupt(struct kvm *kvm,
 	 * priority. The count for that new target will have
 	 * already been incremented.
 	 */
-	rc = xive_select_target(kvm, &server, prio);
+	rc = kvmppc_xive_select_target(kvm, &server, prio);
 
 	/*
 	 * We failed to find a target ? Not much we can do
@@ -563,7 +560,7 @@ static int xive_target_interrupt(struct kvm *kvm,
 	kvmppc_xive_select_irq(state, &hw_num, NULL);
 
 	return xive_native_configure_irq(hw_num,
-					 xive_vp(xive, server),
+					 kvmppc_xive_vp(xive, server),
 					 prio, state->number);
 }
 
@@ -849,7 +846,8 @@ int kvmppc_xive_set_icp(struct kvm_vcpu *vcpu, u64 icpval)
 
 	/*
 	 * We can't update the state of a "pushed" VCPU, but that
-	 * shouldn't happen.
+	 * shouldn't happen because the vcpu->mutex makes running a
+	 * vcpu mutually exclusive with doing one_reg get/set on it.
 	 */
 	if (WARN_ON(vcpu->arch.xive_pushed))
 		return -EIO;
@@ -940,6 +938,13 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 	/* Turn the IPI hard off */
 	xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
 
+	/*
+	 * Reset ESB guest mapping. Needed when ESB pages are exposed
+	 * to the guest in XIVE native mode
+	 */
+	if (xive->ops && xive->ops->reset_mapped)
+		xive->ops->reset_mapped(kvm, guest_irq);
+
 	/* Grab info about irq */
 	state->pt_number = hw_irq;
 	state->pt_data = irq_data_get_irq_handler_data(host_data);
@@ -951,7 +956,7 @@ int kvmppc_xive_set_mapped(struct kvm *kvm, unsigned long guest_irq,
 	 * which is fine for a never started interrupt.
 	 */
 	xive_native_configure_irq(hw_irq,
-				  xive_vp(xive, state->act_server),
+				  kvmppc_xive_vp(xive, state->act_server),
 				  state->act_priority, state->number);
 
 	/*
@@ -1025,9 +1030,17 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
 	state->pt_number = 0;
 	state->pt_data = NULL;
 
+	/*
+	 * Reset ESB guest mapping. Needed when ESB pages are exposed
+	 * to the guest in XIVE native mode
+	 */
+	if (xive->ops && xive->ops->reset_mapped) {
+		xive->ops->reset_mapped(kvm, guest_irq);
+	}
+
 	/* Reconfigure the IPI */
 	xive_native_configure_irq(state->ipi_number,
-				  xive_vp(xive, state->act_server),
+				  kvmppc_xive_vp(xive, state->act_server),
 				  state->act_priority, state->number);
 
 	/*
@@ -1049,7 +1062,7 @@ int kvmppc_xive_clr_mapped(struct kvm *kvm, unsigned long guest_irq,
 }
 EXPORT_SYMBOL_GPL(kvmppc_xive_clr_mapped);
 
-static void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
+void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
 	struct kvm *kvm = vcpu->kvm;
@@ -1083,14 +1096,35 @@ static void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu)
 			arch_spin_unlock(&sb->lock);
 		}
 	}
+
+	/* Disable vcpu's escalation interrupt */
+	if (vcpu->arch.xive_esc_on) {
+		__raw_readq((void __iomem *)(vcpu->arch.xive_esc_vaddr +
+					     XIVE_ESB_SET_PQ_01));
+		vcpu->arch.xive_esc_on = false;
+	}
+
+	/*
+	 * Clear pointers to escalation interrupt ESB.
+	 * This is safe because the vcpu->mutex is held, preventing
+	 * any other CPU from concurrently executing a KVM_RUN ioctl.
+	 */
+	vcpu->arch.xive_esc_vaddr = 0;
+	vcpu->arch.xive_esc_raddr = 0;
 }
 
 void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
-	struct kvmppc_xive *xive = xc->xive;
+	struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
 	int i;
 
+	if (!kvmppc_xics_enabled(vcpu))
+		return;
+
+	if (!xc)
+		return;
+
 	pr_devel("cleanup_vcpu(cpu=%d)\n", xc->server_num);
 
 	/* Ensure no interrupt is still routed to that VP */
@@ -1129,6 +1163,10 @@ void kvmppc_xive_cleanup_vcpu(struct kvm_vcpu *vcpu)
 	}
 	/* Free the VP */
 	kfree(xc);
+
+	/* Cleanup the vcpu */
+	vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
+	vcpu->arch.xive_vcpu = NULL;
 }
 
 int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
@@ -1146,7 +1184,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	}
 	if (xive->kvm != vcpu->kvm)
 		return -EPERM;
-	if (vcpu->arch.irq_type)
+	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
 		return -EBUSY;
 	if (kvmppc_xive_find_server(vcpu->kvm, cpu)) {
 		pr_devel("Duplicate !\n");
@@ -1166,7 +1204,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	xc->xive = xive;
 	xc->vcpu = vcpu;
 	xc->server_num = cpu;
-	xc->vp_id = xive_vp(xive, cpu);
+	xc->vp_id = kvmppc_xive_vp(xive, cpu);
 	xc->mfrr = 0xff;
 	xc->valid = true;
 
@@ -1219,7 +1257,8 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 		if (xive->qmap & (1 << i)) {
 			r = xive_provision_queue(vcpu, i);
 			if (r == 0 && !xive->single_escalation)
-				xive_attach_escalation(vcpu, i);
+				kvmppc_xive_attach_escalation(
+					vcpu, i, xive->single_escalation);
 			if (r)
 				goto bail;
 		} else {
@@ -1234,7 +1273,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	}
 
 	/* If not done above, attach priority 0 escalation */
-	r = xive_attach_escalation(vcpu, 0);
+	r = kvmppc_xive_attach_escalation(vcpu, 0, xive->single_escalation);
 	if (r)
 		goto bail;
 
@@ -1485,8 +1524,8 @@ static int xive_get_source(struct kvmppc_xive *xive, long irq, u64 addr)
 	return 0;
 }
 
-static struct kvmppc_xive_src_block *xive_create_src_block(struct kvmppc_xive *xive,
-							   int irq)
+struct kvmppc_xive_src_block *kvmppc_xive_create_src_block(
+	struct kvmppc_xive *xive, int irq)
 {
 	struct kvm *kvm = xive->kvm;
 	struct kvmppc_xive_src_block *sb;
@@ -1509,6 +1548,7 @@ static struct kvmppc_xive_src_block *xive_create_src_block(struct kvmppc_xive *x
 
 	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
 		sb->irq_state[i].number = (bid << KVMPPC_XICS_ICS_SHIFT) | i;
+		sb->irq_state[i].eisn = 0;
 		sb->irq_state[i].guest_priority = MASKED;
 		sb->irq_state[i].saved_priority = MASKED;
 		sb->irq_state[i].act_priority = MASKED;
@@ -1565,7 +1605,7 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 	sb = kvmppc_xive_find_source(xive, irq, &idx);
 	if (!sb) {
 		pr_devel("No source, creating source block...\n");
-		sb = xive_create_src_block(xive, irq);
+		sb = kvmppc_xive_create_src_block(xive, irq);
 		if (!sb) {
 			pr_devel("Failed to create block...\n");
 			return -ENOMEM;
@@ -1789,7 +1829,7 @@ static void kvmppc_xive_cleanup_irq(u32 hw_num, struct xive_irq_data *xd)
 	xive_cleanup_irq_data(xd);
 }
 
-static void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
+void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
 {
 	int i;
 
@@ -1810,16 +1850,55 @@ static void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb)
 	}
 }
 
-static void kvmppc_xive_free(struct kvm_device *dev)
+/*
+ * Called when device fd is closed.  kvm->lock is held.
+ */
+static void kvmppc_xive_release(struct kvm_device *dev)
 {
 	struct kvmppc_xive *xive = dev->private;
 	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
 	int i;
+	int was_ready;
+
+	pr_devel("Releasing xive device\n");
 
 	debugfs_remove(xive->dentry);
 
-	if (kvm)
-		kvm->arch.xive = NULL;
+	/*
+	 * Clearing mmu_ready temporarily while holding kvm->lock
+	 * is a way of ensuring that no vcpus can enter the guest
+	 * until we drop kvm->lock.  Doing kick_all_cpus_sync()
+	 * ensures that any vcpu executing inside the guest has
+	 * exited the guest.  Once kick_all_cpus_sync() has finished,
+	 * we know that no vcpu can be executing the XIVE push or
+	 * pull code, or executing a XICS hcall.
+	 *
+	 * Since this is the device release function, we know that
+	 * userspace does not have any open fd referring to the
+	 * device.  Therefore there can not be any of the device
+	 * attribute set/get functions being executed concurrently,
+	 * and similarly, the connect_vcpu and set/clr_mapped
+	 * functions also cannot be being executed.
+	 */
+	was_ready = kvm->arch.mmu_ready;
+	kvm->arch.mmu_ready = 0;
+	kick_all_cpus_sync();
+
+	/*
+	 * We should clean up the vCPU interrupt presenters first.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		/*
+		 * Take vcpu->mutex to ensure that no one_reg get/set ioctl
+		 * (i.e. kvmppc_xive_[gs]et_icp) can be done concurrently.
+		 */
+		mutex_lock(&vcpu->mutex);
+		kvmppc_xive_cleanup_vcpu(vcpu);
+		mutex_unlock(&vcpu->mutex);
+	}
+
+	kvm->arch.xive = NULL;
 
 	/* Mask and free interrupts */
 	for (i = 0; i <= xive->max_sbid; i++) {
@@ -1832,11 +1911,47 @@ static void kvmppc_xive_free(struct kvm_device *dev)
 	if (xive->vp_base != XIVE_INVALID_VP)
 		xive_native_free_vp_block(xive->vp_base);
 
+	kvm->arch.mmu_ready = was_ready;
+
+	/*
+	 * A reference of the kvmppc_xive pointer is now kept under
+	 * the xive_devices struct of the machine for reuse. It is
+	 * freed when the VM is destroyed for now until we fix all the
+	 * execution paths.
+	 */
 
-	kfree(xive);
 	kfree(dev);
 }
 
+/*
+ * When the guest chooses the interrupt mode (XICS legacy or XIVE
+ * native), the VM will switch of KVM device. The previous device will
+ * be "released" before the new one is created.
+ *
+ * Until we are sure all execution paths are well protected, provide a
+ * fail safe (transitional) method for device destruction, in which
+ * the XIVE device pointer is recycled and not directly freed.
+ */
+struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type)
+{
+	struct kvmppc_xive **kvm_xive_device = type == KVM_DEV_TYPE_XIVE ?
+		&kvm->arch.xive_devices.native :
+		&kvm->arch.xive_devices.xics_on_xive;
+	struct kvmppc_xive *xive = *kvm_xive_device;
+
+	if (!xive) {
+		xive = kzalloc(sizeof(*xive), GFP_KERNEL);
+		*kvm_xive_device = xive;
+	} else {
+		memset(xive, 0, sizeof(*xive));
+	}
+
+	return xive;
+}
+
+/*
+ * Create a XICS device with XIVE backend.  kvm->lock is held.
+ */
 static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 {
 	struct kvmppc_xive *xive;
@@ -1845,7 +1960,7 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 
 	pr_devel("Creating xive for partition\n");
 
-	xive = kzalloc(sizeof(*xive), GFP_KERNEL);
+	xive = kvmppc_xive_get_device(kvm, type);
 	if (!xive)
 		return -ENOMEM;
 
@@ -1883,6 +1998,43 @@ static int kvmppc_xive_create(struct kvm_device *dev, u32 type)
 	return 0;
 }
 
+int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	unsigned int i;
+
+	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+		struct xive_q *q = &xc->queues[i];
+		u32 i0, i1, idx;
+
+		if (!q->qpage && !xc->esc_virq[i])
+			continue;
+
+		seq_printf(m, " [q%d]: ", i);
+
+		if (q->qpage) {
+			idx = q->idx;
+			i0 = be32_to_cpup(q->qpage + idx);
+			idx = (idx + 1) & q->msk;
+			i1 = be32_to_cpup(q->qpage + idx);
+			seq_printf(m, "T=%d %08x %08x...\n", q->toggle,
+				   i0, i1);
+		}
+		if (xc->esc_virq[i]) {
+			struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]);
+			struct xive_irq_data *xd =
+				irq_data_get_irq_handler_data(d);
+			u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
+
+			seq_printf(m, "E:%c%c I(%d:%llx:%llx)",
+				   (pq & XIVE_ESB_VAL_P) ? 'P' : 'p',
+				   (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q',
+				   xc->esc_virq[i], pq, xd->eoi_page);
+			seq_puts(m, "\n");
+		}
+	}
+	return 0;
+}
 
 static int xive_debug_show(struct seq_file *m, void *private)
 {
@@ -1908,7 +2060,6 @@ static int xive_debug_show(struct seq_file *m, void *private)
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
-		unsigned int i;
 
 		if (!xc)
 			continue;
@@ -1918,33 +2069,8 @@ static int xive_debug_show(struct seq_file *m, void *private)
 			   xc->server_num, xc->cppr, xc->hw_cppr,
 			   xc->mfrr, xc->pending,
 			   xc->stat_rm_h_xirr, xc->stat_vm_h_xirr);
-		for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
-			struct xive_q *q = &xc->queues[i];
-			u32 i0, i1, idx;
-
-			if (!q->qpage && !xc->esc_virq[i])
-				continue;
 
-			seq_printf(m, " [q%d]: ", i);
-
-			if (q->qpage) {
-				idx = q->idx;
-				i0 = be32_to_cpup(q->qpage + idx);
-				idx = (idx + 1) & q->msk;
-				i1 = be32_to_cpup(q->qpage + idx);
-				seq_printf(m, "T=%d %08x %08x... \n", q->toggle, i0, i1);
-			}
-			if (xc->esc_virq[i]) {
-				struct irq_data *d = irq_get_irq_data(xc->esc_virq[i]);
-				struct xive_irq_data *xd = irq_data_get_irq_handler_data(d);
-				u64 pq = xive_vm_esb_load(xd, XIVE_ESB_GET);
-				seq_printf(m, "E:%c%c I(%d:%llx:%llx)",
-					   (pq & XIVE_ESB_VAL_P) ? 'P' : 'p',
-					   (pq & XIVE_ESB_VAL_Q) ? 'Q' : 'q',
-					   xc->esc_virq[i], pq, xd->eoi_page);
-				seq_printf(m, "\n");
-			}
-		}
+		kvmppc_xive_debug_show_queues(m, vcpu);
 
 		t_rm_h_xirr += xc->stat_rm_h_xirr;
 		t_rm_h_ipoll += xc->stat_rm_h_ipoll;
@@ -1999,7 +2125,7 @@ struct kvm_device_ops kvm_xive_ops = {
 	.name = "kvm-xive",
 	.create = kvmppc_xive_create,
 	.init = kvmppc_xive_init,
-	.destroy = kvmppc_xive_free,
+	.release = kvmppc_xive_release,
 	.set_attr = xive_set_attr,
 	.get_attr = xive_get_attr,
 	.has_attr = xive_has_attr,
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index a08ae6fd4c51..426146332984 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -13,6 +13,13 @@
 #include "book3s_xics.h"
 
 /*
+ * The XIVE Interrupt source numbers are within the range 0 to
+ * KVMPPC_XICS_NR_IRQS.
+ */
+#define KVMPPC_XIVE_FIRST_IRQ	0
+#define KVMPPC_XIVE_NR_IRQS	KVMPPC_XICS_NR_IRQS
+
+/*
  * State for one guest irq source.
  *
  * For each guest source we allocate a HW interrupt in the XIVE
@@ -54,6 +61,9 @@ struct kvmppc_xive_irq_state {
 	bool saved_p;
 	bool saved_q;
 	u8 saved_scan_prio;
+
+	/* Xive native */
+	u32 eisn;			/* Guest Effective IRQ number */
 };
 
 /* Select the "right" interrupt (IPI vs. passthrough) */
@@ -84,6 +94,11 @@ struct kvmppc_xive_src_block {
 	struct kvmppc_xive_irq_state irq_state[KVMPPC_XICS_IRQ_PER_ICS];
 };
 
+struct kvmppc_xive;
+
+struct kvmppc_xive_ops {
+	int (*reset_mapped)(struct kvm *kvm, unsigned long guest_irq);
+};
 
 struct kvmppc_xive {
 	struct kvm *kvm;
@@ -122,6 +137,10 @@ struct kvmppc_xive {
 
 	/* Flags */
 	u8	single_escalation;
+
+	struct kvmppc_xive_ops *ops;
+	struct address_space   *mapping;
+	struct mutex mapping_lock;
 };
 
 #define KVMPPC_XIVE_Q_COUNT	8
@@ -198,6 +217,11 @@ static inline struct kvmppc_xive_src_block *kvmppc_xive_find_source(struct kvmpp
 	return xive->src_blocks[bid];
 }
 
+static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server)
+{
+	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
+}
+
 /*
  * Mapping between guest priorities and host priorities
  * is as follow.
@@ -248,5 +272,18 @@ extern int (*__xive_vm_h_ipi)(struct kvm_vcpu *vcpu, unsigned long server,
 extern int (*__xive_vm_h_cppr)(struct kvm_vcpu *vcpu, unsigned long cppr);
 extern int (*__xive_vm_h_eoi)(struct kvm_vcpu *vcpu, unsigned long xirr);
 
+/*
+ * Common Xive routines for XICS-over-XIVE and XIVE native
+ */
+void kvmppc_xive_disable_vcpu_interrupts(struct kvm_vcpu *vcpu);
+int kvmppc_xive_debug_show_queues(struct seq_file *m, struct kvm_vcpu *vcpu);
+struct kvmppc_xive_src_block *kvmppc_xive_create_src_block(
+	struct kvmppc_xive *xive, int irq);
+void kvmppc_xive_free_sources(struct kvmppc_xive_src_block *sb);
+int kvmppc_xive_select_target(struct kvm *kvm, u32 *server, u8 prio);
+int kvmppc_xive_attach_escalation(struct kvm_vcpu *vcpu, u8 prio,
+				  bool single_escalation);
+struct kvmppc_xive *kvmppc_xive_get_device(struct kvm *kvm, u32 type);
+
 #endif /* CONFIG_KVM_XICS */
 #endif /* _KVM_PPC_BOOK3S_XICS_H */
diff --git a/arch/powerpc/kvm/book3s_xive_native.c b/arch/powerpc/kvm/book3s_xive_native.c
new file mode 100644
index 000000000000..6a8e698c4b6e
--- /dev/null
+++ b/arch/powerpc/kvm/book3s_xive_native.c
@@ -0,0 +1,1249 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2019, IBM Corporation.
+ */
+
+#define pr_fmt(fmt) "xive-kvm: " fmt
+
+#include <linux/kernel.h>
+#include <linux/kvm_host.h>
+#include <linux/err.h>
+#include <linux/gfp.h>
+#include <linux/spinlock.h>
+#include <linux/delay.h>
+#include <linux/file.h>
+#include <asm/uaccess.h>
+#include <asm/kvm_book3s.h>
+#include <asm/kvm_ppc.h>
+#include <asm/hvcall.h>
+#include <asm/xive.h>
+#include <asm/xive-regs.h>
+#include <asm/debug.h>
+#include <asm/debugfs.h>
+#include <asm/opal.h>
+
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "book3s_xive.h"
+
+static u8 xive_vm_esb_load(struct xive_irq_data *xd, u32 offset)
+{
+	u64 val;
+
+	if (xd->flags & XIVE_IRQ_FLAG_SHIFT_BUG)
+		offset |= offset << 4;
+
+	val = in_be64(xd->eoi_mmio + offset);
+	return (u8)val;
+}
+
+static void kvmppc_xive_native_cleanup_queue(struct kvm_vcpu *vcpu, int prio)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	struct xive_q *q = &xc->queues[prio];
+
+	xive_native_disable_queue(xc->vp_id, q, prio);
+	if (q->qpage) {
+		put_page(virt_to_page(q->qpage));
+		q->qpage = NULL;
+	}
+}
+
+void kvmppc_xive_native_cleanup_vcpu(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	int i;
+
+	if (!kvmppc_xive_enabled(vcpu))
+		return;
+
+	if (!xc)
+		return;
+
+	pr_devel("native_cleanup_vcpu(cpu=%d)\n", xc->server_num);
+
+	/* Ensure no interrupt is still routed to that VP */
+	xc->valid = false;
+	kvmppc_xive_disable_vcpu_interrupts(vcpu);
+
+	/* Disable the VP */
+	xive_native_disable_vp(xc->vp_id);
+
+	/* Free the queues & associated interrupts */
+	for (i = 0; i < KVMPPC_XIVE_Q_COUNT; i++) {
+		/* Free the escalation irq */
+		if (xc->esc_virq[i]) {
+			free_irq(xc->esc_virq[i], vcpu);
+			irq_dispose_mapping(xc->esc_virq[i]);
+			kfree(xc->esc_virq_names[i]);
+			xc->esc_virq[i] = 0;
+		}
+
+		/* Free the queue */
+		kvmppc_xive_native_cleanup_queue(vcpu, i);
+	}
+
+	/* Free the VP */
+	kfree(xc);
+
+	/* Cleanup the vcpu */
+	vcpu->arch.irq_type = KVMPPC_IRQ_DEFAULT;
+	vcpu->arch.xive_vcpu = NULL;
+}
+
+int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
+				    struct kvm_vcpu *vcpu, u32 server_num)
+{
+	struct kvmppc_xive *xive = dev->private;
+	struct kvmppc_xive_vcpu *xc = NULL;
+	int rc;
+
+	pr_devel("native_connect_vcpu(server=%d)\n", server_num);
+
+	if (dev->ops != &kvm_xive_native_ops) {
+		pr_devel("Wrong ops !\n");
+		return -EPERM;
+	}
+	if (xive->kvm != vcpu->kvm)
+		return -EPERM;
+	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
+		return -EBUSY;
+	if (server_num >= KVM_MAX_VCPUS) {
+		pr_devel("Out of bounds !\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&vcpu->kvm->lock);
+
+	if (kvmppc_xive_find_server(vcpu->kvm, server_num)) {
+		pr_devel("Duplicate !\n");
+		rc = -EEXIST;
+		goto bail;
+	}
+
+	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
+	if (!xc) {
+		rc = -ENOMEM;
+		goto bail;
+	}
+
+	vcpu->arch.xive_vcpu = xc;
+	xc->xive = xive;
+	xc->vcpu = vcpu;
+	xc->server_num = server_num;
+
+	xc->vp_id = kvmppc_xive_vp(xive, server_num);
+	xc->valid = true;
+	vcpu->arch.irq_type = KVMPPC_IRQ_XIVE;
+
+	rc = xive_native_get_vp_info(xc->vp_id, &xc->vp_cam, &xc->vp_chip_id);
+	if (rc) {
+		pr_err("Failed to get VP info from OPAL: %d\n", rc);
+		goto bail;
+	}
+
+	/*
+	 * Enable the VP first as the single escalation mode will
+	 * affect escalation interrupts numbering
+	 */
+	rc = xive_native_enable_vp(xc->vp_id, xive->single_escalation);
+	if (rc) {
+		pr_err("Failed to enable VP in OPAL: %d\n", rc);
+		goto bail;
+	}
+
+	/* Configure VCPU fields for use by assembly push/pull */
+	vcpu->arch.xive_saved_state.w01 = cpu_to_be64(0xff000000);
+	vcpu->arch.xive_cam_word = cpu_to_be32(xc->vp_cam | TM_QW1W2_VO);
+
+	/* TODO: reset all queues to a clean state ? */
+bail:
+	mutex_unlock(&vcpu->kvm->lock);
+	if (rc)
+		kvmppc_xive_native_cleanup_vcpu(vcpu);
+
+	return rc;
+}
+
+/*
+ * Device passthrough support
+ */
+static int kvmppc_xive_native_reset_mapped(struct kvm *kvm, unsigned long irq)
+{
+	struct kvmppc_xive *xive = kvm->arch.xive;
+
+	if (irq >= KVMPPC_XIVE_NR_IRQS)
+		return -EINVAL;
+
+	/*
+	 * Clear the ESB pages of the IRQ number being mapped (or
+	 * unmapped) into the guest and let the the VM fault handler
+	 * repopulate with the appropriate ESB pages (device or IC)
+	 */
+	pr_debug("clearing esb pages for girq 0x%lx\n", irq);
+	mutex_lock(&xive->mapping_lock);
+	if (xive->mapping)
+		unmap_mapping_range(xive->mapping,
+				    irq * (2ull << PAGE_SHIFT),
+				    2ull << PAGE_SHIFT, 1);
+	mutex_unlock(&xive->mapping_lock);
+	return 0;
+}
+
+static struct kvmppc_xive_ops kvmppc_xive_native_ops =  {
+	.reset_mapped = kvmppc_xive_native_reset_mapped,
+};
+
+static vm_fault_t xive_native_esb_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct kvm_device *dev = vma->vm_file->private_data;
+	struct kvmppc_xive *xive = dev->private;
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	struct xive_irq_data *xd;
+	u32 hw_num;
+	u16 src;
+	u64 page;
+	unsigned long irq;
+	u64 page_offset;
+
+	/*
+	 * Linux/KVM uses a two pages ESB setting, one for trigger and
+	 * one for EOI
+	 */
+	page_offset = vmf->pgoff - vma->vm_pgoff;
+	irq = page_offset / 2;
+
+	sb = kvmppc_xive_find_source(xive, irq, &src);
+	if (!sb) {
+		pr_devel("%s: source %lx not found !\n", __func__, irq);
+		return VM_FAULT_SIGBUS;
+	}
+
+	state = &sb->irq_state[src];
+	kvmppc_xive_select_irq(state, &hw_num, &xd);
+
+	arch_spin_lock(&sb->lock);
+
+	/*
+	 * first/even page is for trigger
+	 * second/odd page is for EOI and management.
+	 */
+	page = page_offset % 2 ? xd->eoi_page : xd->trig_page;
+	arch_spin_unlock(&sb->lock);
+
+	if (WARN_ON(!page)) {
+		pr_err("%s: accessing invalid ESB page for source %lx !\n",
+		       __func__, irq);
+		return VM_FAULT_SIGBUS;
+	}
+
+	vmf_insert_pfn(vma, vmf->address, page >> PAGE_SHIFT);
+	return VM_FAULT_NOPAGE;
+}
+
+static const struct vm_operations_struct xive_native_esb_vmops = {
+	.fault = xive_native_esb_fault,
+};
+
+static vm_fault_t xive_native_tima_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+
+	switch (vmf->pgoff - vma->vm_pgoff) {
+	case 0: /* HW - forbid access */
+	case 1: /* HV - forbid access */
+		return VM_FAULT_SIGBUS;
+	case 2: /* OS */
+		vmf_insert_pfn(vma, vmf->address, xive_tima_os >> PAGE_SHIFT);
+		return VM_FAULT_NOPAGE;
+	case 3: /* USER - TODO */
+	default:
+		return VM_FAULT_SIGBUS;
+	}
+}
+
+static const struct vm_operations_struct xive_native_tima_vmops = {
+	.fault = xive_native_tima_fault,
+};
+
+static int kvmppc_xive_native_mmap(struct kvm_device *dev,
+				   struct vm_area_struct *vma)
+{
+	struct kvmppc_xive *xive = dev->private;
+
+	/* We only allow mappings at fixed offset for now */
+	if (vma->vm_pgoff == KVM_XIVE_TIMA_PAGE_OFFSET) {
+		if (vma_pages(vma) > 4)
+			return -EINVAL;
+		vma->vm_ops = &xive_native_tima_vmops;
+	} else if (vma->vm_pgoff == KVM_XIVE_ESB_PAGE_OFFSET) {
+		if (vma_pages(vma) > KVMPPC_XIVE_NR_IRQS * 2)
+			return -EINVAL;
+		vma->vm_ops = &xive_native_esb_vmops;
+	} else {
+		return -EINVAL;
+	}
+
+	vma->vm_flags |= VM_IO | VM_PFNMAP;
+	vma->vm_page_prot = pgprot_noncached_wc(vma->vm_page_prot);
+
+	/*
+	 * Grab the KVM device file address_space to be able to clear
+	 * the ESB pages mapping when a device is passed-through into
+	 * the guest.
+	 */
+	xive->mapping = vma->vm_file->f_mapping;
+	return 0;
+}
+
+static int kvmppc_xive_native_set_source(struct kvmppc_xive *xive, long irq,
+					 u64 addr)
+{
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	u64 __user *ubufp = (u64 __user *) addr;
+	u64 val;
+	u16 idx;
+	int rc;
+
+	pr_devel("%s irq=0x%lx\n", __func__, irq);
+
+	if (irq < KVMPPC_XIVE_FIRST_IRQ || irq >= KVMPPC_XIVE_NR_IRQS)
+		return -E2BIG;
+
+	sb = kvmppc_xive_find_source(xive, irq, &idx);
+	if (!sb) {
+		pr_debug("No source, creating source block...\n");
+		sb = kvmppc_xive_create_src_block(xive, irq);
+		if (!sb) {
+			pr_err("Failed to create block...\n");
+			return -ENOMEM;
+		}
+	}
+	state = &sb->irq_state[idx];
+
+	if (get_user(val, ubufp)) {
+		pr_err("fault getting user info !\n");
+		return -EFAULT;
+	}
+
+	arch_spin_lock(&sb->lock);
+
+	/*
+	 * If the source doesn't already have an IPI, allocate
+	 * one and get the corresponding data
+	 */
+	if (!state->ipi_number) {
+		state->ipi_number = xive_native_alloc_irq();
+		if (state->ipi_number == 0) {
+			pr_err("Failed to allocate IRQ !\n");
+			rc = -ENXIO;
+			goto unlock;
+		}
+		xive_native_populate_irq_data(state->ipi_number,
+					      &state->ipi_data);
+		pr_debug("%s allocated hw_irq=0x%x for irq=0x%lx\n", __func__,
+			 state->ipi_number, irq);
+	}
+
+	/* Restore LSI state */
+	if (val & KVM_XIVE_LEVEL_SENSITIVE) {
+		state->lsi = true;
+		if (val & KVM_XIVE_LEVEL_ASSERTED)
+			state->asserted = true;
+		pr_devel("  LSI ! Asserted=%d\n", state->asserted);
+	}
+
+	/* Mask IRQ to start with */
+	state->act_server = 0;
+	state->act_priority = MASKED;
+	xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+	xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
+
+	/* Increment the number of valid sources and mark this one valid */
+	if (!state->valid)
+		xive->src_count++;
+	state->valid = true;
+
+	rc = 0;
+
+unlock:
+	arch_spin_unlock(&sb->lock);
+
+	return rc;
+}
+
+static int kvmppc_xive_native_update_source_config(struct kvmppc_xive *xive,
+					struct kvmppc_xive_src_block *sb,
+					struct kvmppc_xive_irq_state *state,
+					u32 server, u8 priority, bool masked,
+					u32 eisn)
+{
+	struct kvm *kvm = xive->kvm;
+	u32 hw_num;
+	int rc = 0;
+
+	arch_spin_lock(&sb->lock);
+
+	if (state->act_server == server && state->act_priority == priority &&
+	    state->eisn == eisn)
+		goto unlock;
+
+	pr_devel("new_act_prio=%d new_act_server=%d mask=%d act_server=%d act_prio=%d\n",
+		 priority, server, masked, state->act_server,
+		 state->act_priority);
+
+	kvmppc_xive_select_irq(state, &hw_num, NULL);
+
+	if (priority != MASKED && !masked) {
+		rc = kvmppc_xive_select_target(kvm, &server, priority);
+		if (rc)
+			goto unlock;
+
+		state->act_priority = priority;
+		state->act_server = server;
+		state->eisn = eisn;
+
+		rc = xive_native_configure_irq(hw_num,
+					       kvmppc_xive_vp(xive, server),
+					       priority, eisn);
+	} else {
+		state->act_priority = MASKED;
+		state->act_server = 0;
+		state->eisn = 0;
+
+		rc = xive_native_configure_irq(hw_num, 0, MASKED, 0);
+	}
+
+unlock:
+	arch_spin_unlock(&sb->lock);
+	return rc;
+}
+
+static int kvmppc_xive_native_set_source_config(struct kvmppc_xive *xive,
+						long irq, u64 addr)
+{
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	u64 __user *ubufp = (u64 __user *) addr;
+	u16 src;
+	u64 kvm_cfg;
+	u32 server;
+	u8 priority;
+	bool masked;
+	u32 eisn;
+
+	sb = kvmppc_xive_find_source(xive, irq, &src);
+	if (!sb)
+		return -ENOENT;
+
+	state = &sb->irq_state[src];
+
+	if (!state->valid)
+		return -EINVAL;
+
+	if (get_user(kvm_cfg, ubufp))
+		return -EFAULT;
+
+	pr_devel("%s irq=0x%lx cfg=%016llx\n", __func__, irq, kvm_cfg);
+
+	priority = (kvm_cfg & KVM_XIVE_SOURCE_PRIORITY_MASK) >>
+		KVM_XIVE_SOURCE_PRIORITY_SHIFT;
+	server = (kvm_cfg & KVM_XIVE_SOURCE_SERVER_MASK) >>
+		KVM_XIVE_SOURCE_SERVER_SHIFT;
+	masked = (kvm_cfg & KVM_XIVE_SOURCE_MASKED_MASK) >>
+		KVM_XIVE_SOURCE_MASKED_SHIFT;
+	eisn = (kvm_cfg & KVM_XIVE_SOURCE_EISN_MASK) >>
+		KVM_XIVE_SOURCE_EISN_SHIFT;
+
+	if (priority != xive_prio_from_guest(priority)) {
+		pr_err("invalid priority for queue %d for VCPU %d\n",
+		       priority, server);
+		return -EINVAL;
+	}
+
+	return kvmppc_xive_native_update_source_config(xive, sb, state, server,
+						       priority, masked, eisn);
+}
+
+static int kvmppc_xive_native_sync_source(struct kvmppc_xive *xive,
+					  long irq, u64 addr)
+{
+	struct kvmppc_xive_src_block *sb;
+	struct kvmppc_xive_irq_state *state;
+	struct xive_irq_data *xd;
+	u32 hw_num;
+	u16 src;
+	int rc = 0;
+
+	pr_devel("%s irq=0x%lx", __func__, irq);
+
+	sb = kvmppc_xive_find_source(xive, irq, &src);
+	if (!sb)
+		return -ENOENT;
+
+	state = &sb->irq_state[src];
+
+	rc = -EINVAL;
+
+	arch_spin_lock(&sb->lock);
+
+	if (state->valid) {
+		kvmppc_xive_select_irq(state, &hw_num, &xd);
+		xive_native_sync_source(hw_num);
+		rc = 0;
+	}
+
+	arch_spin_unlock(&sb->lock);
+	return rc;
+}
+
+static int xive_native_validate_queue_size(u32 qshift)
+{
+	/*
+	 * We only support 64K pages for the moment. This is also
+	 * advertised in the DT property "ibm,xive-eq-sizes"
+	 */
+	switch (qshift) {
+	case 0: /* EQ reset */
+	case 16:
+		return 0;
+	case 12:
+	case 21:
+	case 24:
+	default:
+		return -EINVAL;
+	}
+}
+
+static int kvmppc_xive_native_set_queue_config(struct kvmppc_xive *xive,
+					       long eq_idx, u64 addr)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	struct kvmppc_xive_vcpu *xc;
+	void __user *ubufp = (void __user *) addr;
+	u32 server;
+	u8 priority;
+	struct kvm_ppc_xive_eq kvm_eq;
+	int rc;
+	__be32 *qaddr = 0;
+	struct page *page;
+	struct xive_q *q;
+	gfn_t gfn;
+	unsigned long page_size;
+
+	/*
+	 * Demangle priority/server tuple from the EQ identifier
+	 */
+	priority = (eq_idx & KVM_XIVE_EQ_PRIORITY_MASK) >>
+		KVM_XIVE_EQ_PRIORITY_SHIFT;
+	server = (eq_idx & KVM_XIVE_EQ_SERVER_MASK) >>
+		KVM_XIVE_EQ_SERVER_SHIFT;
+
+	if (copy_from_user(&kvm_eq, ubufp, sizeof(kvm_eq)))
+		return -EFAULT;
+
+	vcpu = kvmppc_xive_find_server(kvm, server);
+	if (!vcpu) {
+		pr_err("Can't find server %d\n", server);
+		return -ENOENT;
+	}
+	xc = vcpu->arch.xive_vcpu;
+
+	if (priority != xive_prio_from_guest(priority)) {
+		pr_err("Trying to restore invalid queue %d for VCPU %d\n",
+		       priority, server);
+		return -EINVAL;
+	}
+	q = &xc->queues[priority];
+
+	pr_devel("%s VCPU %d priority %d fl:%x shift:%d addr:%llx g:%d idx:%d\n",
+		 __func__, server, priority, kvm_eq.flags,
+		 kvm_eq.qshift, kvm_eq.qaddr, kvm_eq.qtoggle, kvm_eq.qindex);
+
+	/*
+	 * sPAPR specifies a "Unconditional Notify (n) flag" for the
+	 * H_INT_SET_QUEUE_CONFIG hcall which forces notification
+	 * without using the coalescing mechanisms provided by the
+	 * XIVE END ESBs. This is required on KVM as notification
+	 * using the END ESBs is not supported.
+	 */
+	if (kvm_eq.flags != KVM_XIVE_EQ_ALWAYS_NOTIFY) {
+		pr_err("invalid flags %d\n", kvm_eq.flags);
+		return -EINVAL;
+	}
+
+	rc = xive_native_validate_queue_size(kvm_eq.qshift);
+	if (rc) {
+		pr_err("invalid queue size %d\n", kvm_eq.qshift);
+		return rc;
+	}
+
+	/* reset queue and disable queueing */
+	if (!kvm_eq.qshift) {
+		q->guest_qaddr  = 0;
+		q->guest_qshift = 0;
+
+		rc = xive_native_configure_queue(xc->vp_id, q, priority,
+						 NULL, 0, true);
+		if (rc) {
+			pr_err("Failed to reset queue %d for VCPU %d: %d\n",
+			       priority, xc->server_num, rc);
+			return rc;
+		}
+
+		if (q->qpage) {
+			put_page(virt_to_page(q->qpage));
+			q->qpage = NULL;
+		}
+
+		return 0;
+	}
+
+	if (kvm_eq.qaddr & ((1ull << kvm_eq.qshift) - 1)) {
+		pr_err("queue page is not aligned %llx/%llx\n", kvm_eq.qaddr,
+		       1ull << kvm_eq.qshift);
+		return -EINVAL;
+	}
+
+	gfn = gpa_to_gfn(kvm_eq.qaddr);
+	page = gfn_to_page(kvm, gfn);
+	if (is_error_page(page)) {
+		pr_err("Couldn't get queue page %llx!\n", kvm_eq.qaddr);
+		return -EINVAL;
+	}
+
+	page_size = kvm_host_page_size(kvm, gfn);
+	if (1ull << kvm_eq.qshift > page_size) {
+		pr_warn("Incompatible host page size %lx!\n", page_size);
+		return -EINVAL;
+	}
+
+	qaddr = page_to_virt(page) + (kvm_eq.qaddr & ~PAGE_MASK);
+
+	/*
+	 * Backup the queue page guest address to the mark EQ page
+	 * dirty for migration.
+	 */
+	q->guest_qaddr  = kvm_eq.qaddr;
+	q->guest_qshift = kvm_eq.qshift;
+
+	 /*
+	  * Unconditional Notification is forced by default at the
+	  * OPAL level because the use of END ESBs is not supported by
+	  * Linux.
+	  */
+	rc = xive_native_configure_queue(xc->vp_id, q, priority,
+					 (__be32 *) qaddr, kvm_eq.qshift, true);
+	if (rc) {
+		pr_err("Failed to configure queue %d for VCPU %d: %d\n",
+		       priority, xc->server_num, rc);
+		put_page(page);
+		return rc;
+	}
+
+	/*
+	 * Only restore the queue state when needed. When doing the
+	 * H_INT_SET_SOURCE_CONFIG hcall, it should not.
+	 */
+	if (kvm_eq.qtoggle != 1 || kvm_eq.qindex != 0) {
+		rc = xive_native_set_queue_state(xc->vp_id, priority,
+						 kvm_eq.qtoggle,
+						 kvm_eq.qindex);
+		if (rc)
+			goto error;
+	}
+
+	rc = kvmppc_xive_attach_escalation(vcpu, priority,
+					   xive->single_escalation);
+error:
+	if (rc)
+		kvmppc_xive_native_cleanup_queue(vcpu, priority);
+	return rc;
+}
+
+static int kvmppc_xive_native_get_queue_config(struct kvmppc_xive *xive,
+					       long eq_idx, u64 addr)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	struct kvmppc_xive_vcpu *xc;
+	struct xive_q *q;
+	void __user *ubufp = (u64 __user *) addr;
+	u32 server;
+	u8 priority;
+	struct kvm_ppc_xive_eq kvm_eq;
+	u64 qaddr;
+	u64 qshift;
+	u64 qeoi_page;
+	u32 escalate_irq;
+	u64 qflags;
+	int rc;
+
+	/*
+	 * Demangle priority/server tuple from the EQ identifier
+	 */
+	priority = (eq_idx & KVM_XIVE_EQ_PRIORITY_MASK) >>
+		KVM_XIVE_EQ_PRIORITY_SHIFT;
+	server = (eq_idx & KVM_XIVE_EQ_SERVER_MASK) >>
+		KVM_XIVE_EQ_SERVER_SHIFT;
+
+	vcpu = kvmppc_xive_find_server(kvm, server);
+	if (!vcpu) {
+		pr_err("Can't find server %d\n", server);
+		return -ENOENT;
+	}
+	xc = vcpu->arch.xive_vcpu;
+
+	if (priority != xive_prio_from_guest(priority)) {
+		pr_err("invalid priority for queue %d for VCPU %d\n",
+		       priority, server);
+		return -EINVAL;
+	}
+	q = &xc->queues[priority];
+
+	memset(&kvm_eq, 0, sizeof(kvm_eq));
+
+	if (!q->qpage)
+		return 0;
+
+	rc = xive_native_get_queue_info(xc->vp_id, priority, &qaddr, &qshift,
+					&qeoi_page, &escalate_irq, &qflags);
+	if (rc)
+		return rc;
+
+	kvm_eq.flags = 0;
+	if (qflags & OPAL_XIVE_EQ_ALWAYS_NOTIFY)
+		kvm_eq.flags |= KVM_XIVE_EQ_ALWAYS_NOTIFY;
+
+	kvm_eq.qshift = q->guest_qshift;
+	kvm_eq.qaddr  = q->guest_qaddr;
+
+	rc = xive_native_get_queue_state(xc->vp_id, priority, &kvm_eq.qtoggle,
+					 &kvm_eq.qindex);
+	if (rc)
+		return rc;
+
+	pr_devel("%s VCPU %d priority %d fl:%x shift:%d addr:%llx g:%d idx:%d\n",
+		 __func__, server, priority, kvm_eq.flags,
+		 kvm_eq.qshift, kvm_eq.qaddr, kvm_eq.qtoggle, kvm_eq.qindex);
+
+	if (copy_to_user(ubufp, &kvm_eq, sizeof(kvm_eq)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static void kvmppc_xive_reset_sources(struct kvmppc_xive_src_block *sb)
+{
+	int i;
+
+	for (i = 0; i < KVMPPC_XICS_IRQ_PER_ICS; i++) {
+		struct kvmppc_xive_irq_state *state = &sb->irq_state[i];
+
+		if (!state->valid)
+			continue;
+
+		if (state->act_priority == MASKED)
+			continue;
+
+		state->eisn = 0;
+		state->act_server = 0;
+		state->act_priority = MASKED;
+		xive_vm_esb_load(&state->ipi_data, XIVE_ESB_SET_PQ_01);
+		xive_native_configure_irq(state->ipi_number, 0, MASKED, 0);
+		if (state->pt_number) {
+			xive_vm_esb_load(state->pt_data, XIVE_ESB_SET_PQ_01);
+			xive_native_configure_irq(state->pt_number,
+						  0, MASKED, 0);
+		}
+	}
+}
+
+static int kvmppc_xive_reset(struct kvmppc_xive *xive)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	unsigned int i;
+
+	pr_devel("%s\n", __func__);
+
+	mutex_lock(&kvm->lock);
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+		unsigned int prio;
+
+		if (!xc)
+			continue;
+
+		kvmppc_xive_disable_vcpu_interrupts(vcpu);
+
+		for (prio = 0; prio < KVMPPC_XIVE_Q_COUNT; prio++) {
+
+			/* Single escalation, no queue 7 */
+			if (prio == 7 && xive->single_escalation)
+				break;
+
+			if (xc->esc_virq[prio]) {
+				free_irq(xc->esc_virq[prio], vcpu);
+				irq_dispose_mapping(xc->esc_virq[prio]);
+				kfree(xc->esc_virq_names[prio]);
+				xc->esc_virq[prio] = 0;
+			}
+
+			kvmppc_xive_native_cleanup_queue(vcpu, prio);
+		}
+	}
+
+	for (i = 0; i <= xive->max_sbid; i++) {
+		struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+
+		if (sb) {
+			arch_spin_lock(&sb->lock);
+			kvmppc_xive_reset_sources(sb);
+			arch_spin_unlock(&sb->lock);
+		}
+	}
+
+	mutex_unlock(&kvm->lock);
+
+	return 0;
+}
+
+static void kvmppc_xive_native_sync_sources(struct kvmppc_xive_src_block *sb)
+{
+	int j;
+
+	for (j = 0; j < KVMPPC_XICS_IRQ_PER_ICS; j++) {
+		struct kvmppc_xive_irq_state *state = &sb->irq_state[j];
+		struct xive_irq_data *xd;
+		u32 hw_num;
+
+		if (!state->valid)
+			continue;
+
+		/*
+		 * The struct kvmppc_xive_irq_state reflects the state
+		 * of the EAS configuration and not the state of the
+		 * source. The source is masked setting the PQ bits to
+		 * '-Q', which is what is being done before calling
+		 * the KVM_DEV_XIVE_EQ_SYNC control.
+		 *
+		 * If a source EAS is configured, OPAL syncs the XIVE
+		 * IC of the source and the XIVE IC of the previous
+		 * target if any.
+		 *
+		 * So it should be fine ignoring MASKED sources as
+		 * they have been synced already.
+		 */
+		if (state->act_priority == MASKED)
+			continue;
+
+		kvmppc_xive_select_irq(state, &hw_num, &xd);
+		xive_native_sync_source(hw_num);
+		xive_native_sync_queue(hw_num);
+	}
+}
+
+static int kvmppc_xive_native_vcpu_eq_sync(struct kvm_vcpu *vcpu)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	unsigned int prio;
+
+	if (!xc)
+		return -ENOENT;
+
+	for (prio = 0; prio < KVMPPC_XIVE_Q_COUNT; prio++) {
+		struct xive_q *q = &xc->queues[prio];
+
+		if (!q->qpage)
+			continue;
+
+		/* Mark EQ page dirty for migration */
+		mark_page_dirty(vcpu->kvm, gpa_to_gfn(q->guest_qaddr));
+	}
+	return 0;
+}
+
+static int kvmppc_xive_native_eq_sync(struct kvmppc_xive *xive)
+{
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	unsigned int i;
+
+	pr_devel("%s\n", __func__);
+
+	mutex_lock(&kvm->lock);
+	for (i = 0; i <= xive->max_sbid; i++) {
+		struct kvmppc_xive_src_block *sb = xive->src_blocks[i];
+
+		if (sb) {
+			arch_spin_lock(&sb->lock);
+			kvmppc_xive_native_sync_sources(sb);
+			arch_spin_unlock(&sb->lock);
+		}
+	}
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		kvmppc_xive_native_vcpu_eq_sync(vcpu);
+	}
+	mutex_unlock(&kvm->lock);
+
+	return 0;
+}
+
+static int kvmppc_xive_native_set_attr(struct kvm_device *dev,
+				       struct kvm_device_attr *attr)
+{
+	struct kvmppc_xive *xive = dev->private;
+
+	switch (attr->group) {
+	case KVM_DEV_XIVE_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_XIVE_RESET:
+			return kvmppc_xive_reset(xive);
+		case KVM_DEV_XIVE_EQ_SYNC:
+			return kvmppc_xive_native_eq_sync(xive);
+		}
+		break;
+	case KVM_DEV_XIVE_GRP_SOURCE:
+		return kvmppc_xive_native_set_source(xive, attr->attr,
+						     attr->addr);
+	case KVM_DEV_XIVE_GRP_SOURCE_CONFIG:
+		return kvmppc_xive_native_set_source_config(xive, attr->attr,
+							    attr->addr);
+	case KVM_DEV_XIVE_GRP_EQ_CONFIG:
+		return kvmppc_xive_native_set_queue_config(xive, attr->attr,
+							   attr->addr);
+	case KVM_DEV_XIVE_GRP_SOURCE_SYNC:
+		return kvmppc_xive_native_sync_source(xive, attr->attr,
+						      attr->addr);
+	}
+	return -ENXIO;
+}
+
+static int kvmppc_xive_native_get_attr(struct kvm_device *dev,
+				       struct kvm_device_attr *attr)
+{
+	struct kvmppc_xive *xive = dev->private;
+
+	switch (attr->group) {
+	case KVM_DEV_XIVE_GRP_EQ_CONFIG:
+		return kvmppc_xive_native_get_queue_config(xive, attr->attr,
+							   attr->addr);
+	}
+	return -ENXIO;
+}
+
+static int kvmppc_xive_native_has_attr(struct kvm_device *dev,
+				       struct kvm_device_attr *attr)
+{
+	switch (attr->group) {
+	case KVM_DEV_XIVE_GRP_CTRL:
+		switch (attr->attr) {
+		case KVM_DEV_XIVE_RESET:
+		case KVM_DEV_XIVE_EQ_SYNC:
+			return 0;
+		}
+		break;
+	case KVM_DEV_XIVE_GRP_SOURCE:
+	case KVM_DEV_XIVE_GRP_SOURCE_CONFIG:
+	case KVM_DEV_XIVE_GRP_SOURCE_SYNC:
+		if (attr->attr >= KVMPPC_XIVE_FIRST_IRQ &&
+		    attr->attr < KVMPPC_XIVE_NR_IRQS)
+			return 0;
+		break;
+	case KVM_DEV_XIVE_GRP_EQ_CONFIG:
+		return 0;
+	}
+	return -ENXIO;
+}
+
+/*
+ * Called when device fd is closed
+ */
+static void kvmppc_xive_native_release(struct kvm_device *dev)
+{
+	struct kvmppc_xive *xive = dev->private;
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	int i;
+	int was_ready;
+
+	debugfs_remove(xive->dentry);
+
+	pr_devel("Releasing xive native device\n");
+
+	/*
+	 * Clearing mmu_ready temporarily while holding kvm->lock
+	 * is a way of ensuring that no vcpus can enter the guest
+	 * until we drop kvm->lock.  Doing kick_all_cpus_sync()
+	 * ensures that any vcpu executing inside the guest has
+	 * exited the guest.  Once kick_all_cpus_sync() has finished,
+	 * we know that no vcpu can be executing the XIVE push or
+	 * pull code or accessing the XIVE MMIO regions.
+	 *
+	 * Since this is the device release function, we know that
+	 * userspace does not have any open fd or mmap referring to
+	 * the device.  Therefore there can not be any of the
+	 * device attribute set/get, mmap, or page fault functions
+	 * being executed concurrently, and similarly, the
+	 * connect_vcpu and set/clr_mapped functions also cannot
+	 * be being executed.
+	 */
+	was_ready = kvm->arch.mmu_ready;
+	kvm->arch.mmu_ready = 0;
+	kick_all_cpus_sync();
+
+	/*
+	 * We should clean up the vCPU interrupt presenters first.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		/*
+		 * Take vcpu->mutex to ensure that no one_reg get/set ioctl
+		 * (i.e. kvmppc_xive_native_[gs]et_vp) can be being done.
+		 */
+		mutex_lock(&vcpu->mutex);
+		kvmppc_xive_native_cleanup_vcpu(vcpu);
+		mutex_unlock(&vcpu->mutex);
+	}
+
+	kvm->arch.xive = NULL;
+
+	for (i = 0; i <= xive->max_sbid; i++) {
+		if (xive->src_blocks[i])
+			kvmppc_xive_free_sources(xive->src_blocks[i]);
+		kfree(xive->src_blocks[i]);
+		xive->src_blocks[i] = NULL;
+	}
+
+	if (xive->vp_base != XIVE_INVALID_VP)
+		xive_native_free_vp_block(xive->vp_base);
+
+	kvm->arch.mmu_ready = was_ready;
+
+	/*
+	 * A reference of the kvmppc_xive pointer is now kept under
+	 * the xive_devices struct of the machine for reuse. It is
+	 * freed when the VM is destroyed for now until we fix all the
+	 * execution paths.
+	 */
+
+	kfree(dev);
+}
+
+/*
+ * Create a XIVE device.  kvm->lock is held.
+ */
+static int kvmppc_xive_native_create(struct kvm_device *dev, u32 type)
+{
+	struct kvmppc_xive *xive;
+	struct kvm *kvm = dev->kvm;
+	int ret = 0;
+
+	pr_devel("Creating xive native device\n");
+
+	if (kvm->arch.xive)
+		return -EEXIST;
+
+	xive = kvmppc_xive_get_device(kvm, type);
+	if (!xive)
+		return -ENOMEM;
+
+	dev->private = xive;
+	xive->dev = dev;
+	xive->kvm = kvm;
+	kvm->arch.xive = xive;
+	mutex_init(&xive->mapping_lock);
+
+	/*
+	 * Allocate a bunch of VPs. KVM_MAX_VCPUS is a large value for
+	 * a default. Getting the max number of CPUs the VM was
+	 * configured with would improve our usage of the XIVE VP space.
+	 */
+	xive->vp_base = xive_native_alloc_vp_block(KVM_MAX_VCPUS);
+	pr_devel("VP_Base=%x\n", xive->vp_base);
+
+	if (xive->vp_base == XIVE_INVALID_VP)
+		ret = -ENXIO;
+
+	xive->single_escalation = xive_native_has_single_escalation();
+	xive->ops = &kvmppc_xive_native_ops;
+
+	if (ret)
+		kfree(xive);
+
+	return ret;
+}
+
+/*
+ * Interrupt Pending Buffer (IPB) offset
+ */
+#define TM_IPB_SHIFT 40
+#define TM_IPB_MASK  (((u64) 0xFF) << TM_IPB_SHIFT)
+
+int kvmppc_xive_native_get_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	u64 opal_state;
+	int rc;
+
+	if (!kvmppc_xive_enabled(vcpu))
+		return -EPERM;
+
+	if (!xc)
+		return -ENOENT;
+
+	/* Thread context registers. We only care about IPB and CPPR */
+	val->xive_timaval[0] = vcpu->arch.xive_saved_state.w01;
+
+	/* Get the VP state from OPAL */
+	rc = xive_native_get_vp_state(xc->vp_id, &opal_state);
+	if (rc)
+		return rc;
+
+	/*
+	 * Capture the backup of IPB register in the NVT structure and
+	 * merge it in our KVM VP state.
+	 */
+	val->xive_timaval[0] |= cpu_to_be64(opal_state & TM_IPB_MASK);
+
+	pr_devel("%s NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x opal=%016llx\n",
+		 __func__,
+		 vcpu->arch.xive_saved_state.nsr,
+		 vcpu->arch.xive_saved_state.cppr,
+		 vcpu->arch.xive_saved_state.ipb,
+		 vcpu->arch.xive_saved_state.pipr,
+		 vcpu->arch.xive_saved_state.w01,
+		 (u32) vcpu->arch.xive_cam_word, opal_state);
+
+	return 0;
+}
+
+int kvmppc_xive_native_set_vp(struct kvm_vcpu *vcpu, union kvmppc_one_reg *val)
+{
+	struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+	struct kvmppc_xive *xive = vcpu->kvm->arch.xive;
+
+	pr_devel("%s w01=%016llx vp=%016llx\n", __func__,
+		 val->xive_timaval[0], val->xive_timaval[1]);
+
+	if (!kvmppc_xive_enabled(vcpu))
+		return -EPERM;
+
+	if (!xc || !xive)
+		return -ENOENT;
+
+	/* We can't update the state of a "pushed" VCPU	 */
+	if (WARN_ON(vcpu->arch.xive_pushed))
+		return -EBUSY;
+
+	/*
+	 * Restore the thread context registers. IPB and CPPR should
+	 * be the only ones that matter.
+	 */
+	vcpu->arch.xive_saved_state.w01 = val->xive_timaval[0];
+
+	/*
+	 * There is no need to restore the XIVE internal state (IPB
+	 * stored in the NVT) as the IPB register was merged in KVM VP
+	 * state when captured.
+	 */
+	return 0;
+}
+
+static int xive_native_debug_show(struct seq_file *m, void *private)
+{
+	struct kvmppc_xive *xive = m->private;
+	struct kvm *kvm = xive->kvm;
+	struct kvm_vcpu *vcpu;
+	unsigned int i;
+
+	if (!kvm)
+		return 0;
+
+	seq_puts(m, "=========\nVCPU state\n=========\n");
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		struct kvmppc_xive_vcpu *xc = vcpu->arch.xive_vcpu;
+
+		if (!xc)
+			continue;
+
+		seq_printf(m, "cpu server %#x NSR=%02x CPPR=%02x IBP=%02x PIPR=%02x w01=%016llx w2=%08x\n",
+			   xc->server_num,
+			   vcpu->arch.xive_saved_state.nsr,
+			   vcpu->arch.xive_saved_state.cppr,
+			   vcpu->arch.xive_saved_state.ipb,
+			   vcpu->arch.xive_saved_state.pipr,
+			   vcpu->arch.xive_saved_state.w01,
+			   (u32) vcpu->arch.xive_cam_word);
+
+		kvmppc_xive_debug_show_queues(m, vcpu);
+	}
+
+	return 0;
+}
+
+static int xive_native_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, xive_native_debug_show, inode->i_private);
+}
+
+static const struct file_operations xive_native_debug_fops = {
+	.open = xive_native_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static void xive_native_debugfs_init(struct kvmppc_xive *xive)
+{
+	char *name;
+
+	name = kasprintf(GFP_KERNEL, "kvm-xive-%p", xive);
+	if (!name) {
+		pr_err("%s: no memory for name\n", __func__);
+		return;
+	}
+
+	xive->dentry = debugfs_create_file(name, 0444, powerpc_debugfs_root,
+					   xive, &xive_native_debug_fops);
+
+	pr_debug("%s: created %s\n", __func__, name);
+	kfree(name);
+}
+
+static void kvmppc_xive_native_init(struct kvm_device *dev)
+{
+	struct kvmppc_xive *xive = (struct kvmppc_xive *)dev->private;
+
+	/* Register some debug interfaces */
+	xive_native_debugfs_init(xive);
+}
+
+struct kvm_device_ops kvm_xive_native_ops = {
+	.name = "kvm-xive-native",
+	.create = kvmppc_xive_native_create,
+	.init = kvmppc_xive_native_init,
+	.release = kvmppc_xive_native_release,
+	.set_attr = kvmppc_xive_native_set_attr,
+	.get_attr = kvmppc_xive_native_get_attr,
+	.has_attr = kvmppc_xive_native_has_attr,
+	.mmap = kvmppc_xive_native_mmap,
+};
+
+void kvmppc_xive_native_init_module(void)
+{
+	;
+}
+
+void kvmppc_xive_native_exit_module(void)
+{
+	;
+}
diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c
index 033363d6e764..0737acfd17f1 100644
--- a/arch/powerpc/kvm/book3s_xive_template.c
+++ b/arch/powerpc/kvm/book3s_xive_template.c
@@ -130,24 +130,14 @@ static u32 GLUE(X_PFX,scan_interrupts)(struct kvmppc_xive_vcpu *xc,
 		 */
 		prio = ffs(pending) - 1;
 
-		/*
-		 * If the most favoured prio we found pending is less
-		 * favored (or equal) than a pending IPI, we return
-		 * the IPI instead.
-		 *
-		 * Note: If pending was 0 and mfrr is 0xff, we will
-		 * not spurriously take an IPI because mfrr cannot
-		 * then be smaller than cppr.
-		 */
-		if (prio >= xc->mfrr && xc->mfrr < xc->cppr) {
-			prio = xc->mfrr;
-			hirq = XICS_IPI;
-			break;
-		}
-
 		/* Don't scan past the guest cppr */
-		if (prio >= xc->cppr || prio > 7)
+		if (prio >= xc->cppr || prio > 7) {
+			if (xc->mfrr < xc->cppr) {
+				prio = xc->mfrr;
+				hirq = XICS_IPI;
+			}
 			break;
+		}
 
 		/* Grab queue and pointers */
 		q = &xc->queues[prio];
@@ -184,9 +174,12 @@ skip_ipi:
 		 * been set and another occurrence of the IPI will trigger.
 		 */
 		if (hirq == XICS_IPI || (prio == 0 && !qpage)) {
-			if (scan_type == scan_fetch)
+			if (scan_type == scan_fetch) {
 				GLUE(X_PFX,source_eoi)(xc->vp_ipi,
 						       &xc->vp_ipi_data);
+				q->idx = idx;
+				q->toggle = toggle;
+			}
 			/* Loop back on same queue with updated idx/toggle */
 #ifdef XIVE_RUNTIME_CHECKS
 			WARN_ON(hirq && hirq != XICS_IPI);
@@ -199,32 +192,41 @@ skip_ipi:
 		if (hirq == XICS_DUMMY)
 			goto skip_ipi;
 
-		/* If fetching, update queue pointers */
-		if (scan_type == scan_fetch) {
-			q->idx = idx;
-			q->toggle = toggle;
-		}
-
-		/* Something found, stop searching */
-		if (hirq)
-			break;
-
-		/* Clear the pending bit on the now empty queue */
-		pending &= ~(1 << prio);
+		/* Clear the pending bit if the queue is now empty */
+		if (!hirq) {
+			pending &= ~(1 << prio);
 
-		/*
-		 * Check if the queue count needs adjusting due to
-		 * interrupts being moved away.
-		 */
-		if (atomic_read(&q->pending_count)) {
-			int p = atomic_xchg(&q->pending_count, 0);
-			if (p) {
+			/*
+			 * Check if the queue count needs adjusting due to
+			 * interrupts being moved away.
+			 */
+			if (atomic_read(&q->pending_count)) {
+				int p = atomic_xchg(&q->pending_count, 0);
+				if (p) {
 #ifdef XIVE_RUNTIME_CHECKS
-				WARN_ON(p > atomic_read(&q->count));
+					WARN_ON(p > atomic_read(&q->count));
 #endif
-				atomic_sub(p, &q->count);
+					atomic_sub(p, &q->count);
+				}
 			}
 		}
+
+		/*
+		 * If the most favoured prio we found pending is less
+		 * favored (or equal) than a pending IPI, we return
+		 * the IPI instead.
+		 */
+		if (prio >= xc->mfrr && xc->mfrr < xc->cppr) {
+			prio = xc->mfrr;
+			hirq = XICS_IPI;
+			break;
+		}
+
+		/* If fetching, update queue pointers */
+		if (scan_type == scan_fetch) {
+			q->idx = idx;
+			q->toggle = toggle;
+		}
 	}
 
 	/* If we are just taking a "peek", do nothing else */
diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
index 8885377ec3e0..3393b166817a 100644
--- a/arch/powerpc/kvm/powerpc.c
+++ b/arch/powerpc/kvm/powerpc.c
@@ -570,6 +570,16 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PPC_GET_CPU_CHAR:
 		r = 1;
 		break;
+#ifdef CONFIG_KVM_XIVE
+	case KVM_CAP_PPC_IRQ_XIVE:
+		/*
+		 * We need XIVE to be enabled on the platform (implies
+		 * a POWER9 processor) and the PowerNV platform, as
+		 * nested is not yet supported.
+		 */
+		r = xive_enabled() && !!cpu_has_feature(CPU_FTR_HVMODE);
+		break;
+#endif
 
 	case KVM_CAP_PPC_ALLOC_HTAB:
 		r = hv_enabled;
@@ -644,9 +654,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		else
 			r = num_online_cpus();
 		break;
-	case KVM_CAP_NR_MEMSLOTS:
-		r = KVM_USER_MEM_SLOTS;
-		break;
 	case KVM_CAP_MAX_VCPUS:
 		r = KVM_MAX_VCPUS;
 		break;
@@ -753,6 +760,9 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 		else
 			kvmppc_xics_free_icp(vcpu);
 		break;
+	case KVMPPC_IRQ_XIVE:
+		kvmppc_xive_native_cleanup_vcpu(vcpu);
+		break;
 	}
 
 	kvmppc_core_vcpu_free(vcpu);
@@ -1941,6 +1951,30 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		break;
 	}
 #endif /* CONFIG_KVM_XICS */
+#ifdef CONFIG_KVM_XIVE
+	case KVM_CAP_PPC_IRQ_XIVE: {
+		struct fd f;
+		struct kvm_device *dev;
+
+		r = -EBADF;
+		f = fdget(cap->args[0]);
+		if (!f.file)
+			break;
+
+		r = -ENXIO;
+		if (!xive_enabled())
+			break;
+
+		r = -EPERM;
+		dev = kvm_device_from_filp(f.file);
+		if (dev)
+			r = kvmppc_xive_native_connect_vcpu(dev, vcpu,
+							    cap->args[1]);
+
+		fdput(f);
+		break;
+	}
+#endif /* CONFIG_KVM_XIVE */
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 	case KVM_CAP_PPC_FWNMI:
 		r = -EINVAL;
author	Linus Torvalds <torvalds@linux-foundation.org>	2019-05-17 10:33:30 -0700
committer	Linus Torvalds <torvalds@linux-foundation.org>	2019-05-17 10:33:30 -0700
commit	0ef0fd351550130129bbdb77362488befd7b69d2 (patch)
tree	23186172f5f85c06e18e3ee1a9619879df03c5df /arch/powerpc/kvm
parent	4489da7183099f569a7d3dd819c975073c04bc72 (diff)
parent	c011d23ba046826ccf8c4a4a6c1d01c9ccaa1403 (diff)