Merge tag 'kvm-ppc-next-5.9-1' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into kvm-next-5.6

PPC KVM update for 5.9

- Improvements and bug-fixes for secure VM support, giving reduced startup
  time and memory hotplug support.
- Locking fixes in nested KVM code
- Increase number of guests supported by HV KVM to 4094
- Preliminary POWER10 support

1 files changed, 531 insertions, 169 deletions

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 6850bd04bcb9..7705d5557239 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -93,12 +93,133 @@
 #include <asm/ultravisor.h>
 #include <asm/mman.h>
 #include <asm/kvm_ppc.h>
+#include <asm/kvm_book3s_uvmem.h>
 
 static struct dev_pagemap kvmppc_uvmem_pgmap;
 static unsigned long *kvmppc_uvmem_bitmap;
 static DEFINE_SPINLOCK(kvmppc_uvmem_bitmap_lock);
 
-#define KVMPPC_UVMEM_PFN	(1UL << 63)
+/*
+ * States of a GFN
+ * ---------------
+ * The GFN can be in one of the following states.
+ *
+ * (a) Secure - The GFN is secure. The GFN is associated with
+ *	a Secure VM, the contents of the GFN is not accessible
+ *	to the Hypervisor.  This GFN can be backed by a secure-PFN,
+ *	or can be backed by a normal-PFN with contents encrypted.
+ *	The former is true when the GFN is paged-in into the
+ *	ultravisor. The latter is true when the GFN is paged-out
+ *	of the ultravisor.
+ *
+ * (b) Shared - The GFN is shared. The GFN is associated with a
+ *	a secure VM. The contents of the GFN is accessible to
+ *	Hypervisor. This GFN is backed by a normal-PFN and its
+ *	content is un-encrypted.
+ *
+ * (c) Normal - The GFN is a normal. The GFN is associated with
+ *	a normal VM. The contents of the GFN is accesible to
+ *	the Hypervisor. Its content is never encrypted.
+ *
+ * States of a VM.
+ * ---------------
+ *
+ * Normal VM:  A VM whose contents are always accessible to
+ *	the hypervisor.  All its GFNs are normal-GFNs.
+ *
+ * Secure VM: A VM whose contents are not accessible to the
+ *	hypervisor without the VM's consent.  Its GFNs are
+ *	either Shared-GFN or Secure-GFNs.
+ *
+ * Transient VM: A Normal VM that is transitioning to secure VM.
+ *	The transition starts on successful return of
+ *	H_SVM_INIT_START, and ends on successful return
+ *	of H_SVM_INIT_DONE. This transient VM, can have GFNs
+ *	in any of the three states; i.e Secure-GFN, Shared-GFN,
+ *	and Normal-GFN.	The VM never executes in this state
+ *	in supervisor-mode.
+ *
+ * Memory slot State.
+ * -----------------------------
+ *	The state of a memory slot mirrors the state of the
+ *	VM the memory slot is associated with.
+ *
+ * VM State transition.
+ * --------------------
+ *
+ *  A VM always starts in Normal Mode.
+ *
+ *  H_SVM_INIT_START moves the VM into transient state. During this
+ *  time the Ultravisor may request some of its GFNs to be shared or
+ *  secured. So its GFNs can be in one of the three GFN states.
+ *
+ *  H_SVM_INIT_DONE moves the VM entirely from transient state to
+ *  secure-state. At this point any left-over normal-GFNs are
+ *  transitioned to Secure-GFN.
+ *
+ *  H_SVM_INIT_ABORT moves the transient VM back to normal VM.
+ *  All its GFNs are moved to Normal-GFNs.
+ *
+ *  UV_TERMINATE transitions the secure-VM back to normal-VM. All
+ *  the secure-GFN and shared-GFNs are tranistioned to normal-GFN
+ *  Note: The contents of the normal-GFN is undefined at this point.
+ *
+ * GFN state implementation:
+ * -------------------------
+ *
+ * Secure GFN is associated with a secure-PFN; also called uvmem_pfn,
+ * when the GFN is paged-in. Its pfn[] has KVMPPC_GFN_UVMEM_PFN flag
+ * set, and contains the value of the secure-PFN.
+ * It is associated with a normal-PFN; also called mem_pfn, when
+ * the GFN is pagedout. Its pfn[] has KVMPPC_GFN_MEM_PFN flag set.
+ * The value of the normal-PFN is not tracked.
+ *
+ * Shared GFN is associated with a normal-PFN. Its pfn[] has
+ * KVMPPC_UVMEM_SHARED_PFN flag set. The value of the normal-PFN
+ * is not tracked.
+ *
+ * Normal GFN is associated with normal-PFN. Its pfn[] has
+ * no flag set. The value of the normal-PFN is not tracked.
+ *
+ * Life cycle of a GFN
+ * --------------------
+ *
+ * --------------------------------------------------------------
+ * |        |     Share  |  Unshare | SVM       |H_SVM_INIT_DONE|
+ * |        |operation   |operation | abort/    |               |
+ * |        |            |          | terminate |               |
+ * -------------------------------------------------------------
+ * |        |            |          |           |               |
+ * | Secure |     Shared | Secure   |Normal     |Secure         |
+ * |        |            |          |           |               |
+ * | Shared |     Shared | Secure   |Normal     |Shared         |
+ * |        |            |          |           |               |
+ * | Normal |     Shared | Secure   |Normal     |Secure         |
+ * --------------------------------------------------------------
+ *
+ * Life cycle of a VM
+ * --------------------
+ *
+ * --------------------------------------------------------------------
+ * |         |  start    |  H_SVM_  |H_SVM_   |H_SVM_     |UV_SVM_    |
+ * |         |  VM       |INIT_START|INIT_DONE|INIT_ABORT |TERMINATE  |
+ * |         |           |          |         |           |           |
+ * --------- ----------------------------------------------------------
+ * |         |           |          |         |           |           |
+ * | Normal  | Normal    | Transient|Error    |Error      |Normal     |
+ * |         |           |          |         |           |           |
+ * | Secure  |   Error   | Error    |Error    |Error      |Normal     |
+ * |         |           |          |         |           |           |
+ * |Transient|   N/A     | Error    |Secure   |Normal     |Normal     |
+ * --------------------------------------------------------------------
+ */
+
+#define KVMPPC_GFN_UVMEM_PFN	(1UL << 63)
+#define KVMPPC_GFN_MEM_PFN	(1UL << 62)
+#define KVMPPC_GFN_SHARED	(1UL << 61)
+#define KVMPPC_GFN_SECURE	(KVMPPC_GFN_UVMEM_PFN | KVMPPC_GFN_MEM_PFN)
+#define KVMPPC_GFN_FLAG_MASK	(KVMPPC_GFN_SECURE | KVMPPC_GFN_SHARED)
+#define KVMPPC_GFN_PFN_MASK	(~KVMPPC_GFN_FLAG_MASK)
 
 struct kvmppc_uvmem_slot {
 	struct list_head list;
@@ -106,11 +227,11 @@ struct kvmppc_uvmem_slot {
 	unsigned long base_pfn;
 	unsigned long *pfns;
 };
-
 struct kvmppc_uvmem_page_pvt {
 	struct kvm *kvm;
 	unsigned long gpa;
 	bool skip_page_out;
+	bool remove_gfn;
 };
 
 bool kvmppc_uvmem_available(void)
@@ -163,8 +284,8 @@ void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot)
 	mutex_unlock(&kvm->arch.uvmem_lock);
 }
 
-static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn,
-				    struct kvm *kvm)
+static void kvmppc_mark_gfn(unsigned long gfn, struct kvm *kvm,
+			unsigned long flag, unsigned long uvmem_pfn)
 {
 	struct kvmppc_uvmem_slot *p;
 
@@ -172,24 +293,41 @@ static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn,
 		if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
 			unsigned long index = gfn - p->base_pfn;
 
-			p->pfns[index] = uvmem_pfn | KVMPPC_UVMEM_PFN;
+			if (flag == KVMPPC_GFN_UVMEM_PFN)
+				p->pfns[index] = uvmem_pfn | flag;
+			else
+				p->pfns[index] = flag;
 			return;
 		}
 	}
 }
 
-static void kvmppc_uvmem_pfn_remove(unsigned long gfn, struct kvm *kvm)
+/* mark the GFN as secure-GFN associated with @uvmem pfn device-PFN. */
+static void kvmppc_gfn_secure_uvmem_pfn(unsigned long gfn,
+			unsigned long uvmem_pfn, struct kvm *kvm)
 {
-	struct kvmppc_uvmem_slot *p;
+	kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_UVMEM_PFN, uvmem_pfn);
+}
 
-	list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) {
-		if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
-			p->pfns[gfn - p->base_pfn] = 0;
-			return;
-		}
-	}
+/* mark the GFN as secure-GFN associated with a memory-PFN. */
+static void kvmppc_gfn_secure_mem_pfn(unsigned long gfn, struct kvm *kvm)
+{
+	kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_MEM_PFN, 0);
+}
+
+/* mark the GFN as a shared GFN. */
+static void kvmppc_gfn_shared(unsigned long gfn, struct kvm *kvm)
+{
+	kvmppc_mark_gfn(gfn, kvm, KVMPPC_GFN_SHARED, 0);
+}
+
+/* mark the GFN as a non-existent GFN. */
+static void kvmppc_gfn_remove(unsigned long gfn, struct kvm *kvm)
+{
+	kvmppc_mark_gfn(gfn, kvm, 0, 0);
 }
 
+/* return true, if the GFN is a secure-GFN backed by a secure-PFN */
 static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
 				    unsigned long *uvmem_pfn)
 {
@@ -199,10 +337,10 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
 		if (gfn >= p->base_pfn && gfn < p->base_pfn + p->nr_pfns) {
 			unsigned long index = gfn - p->base_pfn;
 
-			if (p->pfns[index] & KVMPPC_UVMEM_PFN) {
+			if (p->pfns[index] & KVMPPC_GFN_UVMEM_PFN) {
 				if (uvmem_pfn)
 					*uvmem_pfn = p->pfns[index] &
-						     ~KVMPPC_UVMEM_PFN;
+						     KVMPPC_GFN_PFN_MASK;
 				return true;
 			} else
 				return false;
@@ -211,10 +349,114 @@ static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
 	return false;
 }
 
+/*
+ * starting from *gfn search for the next available GFN that is not yet
+ * transitioned to a secure GFN.  return the value of that GFN in *gfn.  If a
+ * GFN is found, return true, else return false
+ *
+ * Must be called with kvm->arch.uvmem_lock  held.
+ */
+static bool kvmppc_next_nontransitioned_gfn(const struct kvm_memory_slot *memslot,
+		struct kvm *kvm, unsigned long *gfn)
+{
+	struct kvmppc_uvmem_slot *p;
+	bool ret = false;
+	unsigned long i;
+
+	list_for_each_entry(p, &kvm->arch.uvmem_pfns, list)
+		if (*gfn >= p->base_pfn && *gfn < p->base_pfn + p->nr_pfns)
+			break;
+	if (!p)
+		return ret;
+	/*
+	 * The code below assumes, one to one correspondence between
+	 * kvmppc_uvmem_slot and memslot.
+	 */
+	for (i = *gfn; i < p->base_pfn + p->nr_pfns; i++) {
+		unsigned long index = i - p->base_pfn;
+
+		if (!(p->pfns[index] & KVMPPC_GFN_FLAG_MASK)) {
+			*gfn = i;
+			ret = true;
+			break;
+		}
+	}
+	return ret;
+}
+
+static int kvmppc_memslot_page_merge(struct kvm *kvm,
+		const struct kvm_memory_slot *memslot, bool merge)
+{
+	unsigned long gfn = memslot->base_gfn;
+	unsigned long end, start = gfn_to_hva(kvm, gfn);
+	int ret = 0;
+	struct vm_area_struct *vma;
+	int merge_flag = (merge) ? MADV_MERGEABLE : MADV_UNMERGEABLE;
+
+	if (kvm_is_error_hva(start))
+		return H_STATE;
+
+	end = start + (memslot->npages << PAGE_SHIFT);
+
+	mmap_write_lock(kvm->mm);
+	do {
+		vma = find_vma_intersection(kvm->mm, start, end);
+		if (!vma) {
+			ret = H_STATE;
+			break;
+		}
+		ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
+			  merge_flag, &vma->vm_flags);
+		if (ret) {
+			ret = H_STATE;
+			break;
+		}
+		start = vma->vm_end;
+	} while (end > vma->vm_end);
+
+	mmap_write_unlock(kvm->mm);
+	return ret;
+}
+
+static void __kvmppc_uvmem_memslot_delete(struct kvm *kvm,
+		const struct kvm_memory_slot *memslot)
+{
+	uv_unregister_mem_slot(kvm->arch.lpid, memslot->id);
+	kvmppc_uvmem_slot_free(kvm, memslot);
+	kvmppc_memslot_page_merge(kvm, memslot, true);
+}
+
+static int __kvmppc_uvmem_memslot_create(struct kvm *kvm,
+		const struct kvm_memory_slot *memslot)
+{
+	int ret = H_PARAMETER;
+
+	if (kvmppc_memslot_page_merge(kvm, memslot, false))
+		return ret;
+
+	if (kvmppc_uvmem_slot_init(kvm, memslot))
+		goto out1;
+
+	ret = uv_register_mem_slot(kvm->arch.lpid,
+				   memslot->base_gfn << PAGE_SHIFT,
+				   memslot->npages * PAGE_SIZE,
+				   0, memslot->id);
+	if (ret < 0) {
+		ret = H_PARAMETER;
+		goto out;
+	}
+	return 0;
+out:
+	kvmppc_uvmem_slot_free(kvm, memslot);
+out1:
+	kvmppc_memslot_page_merge(kvm, memslot, true);
+	return ret;
+}
+
 unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 {
 	struct kvm_memslots *slots;
-	struct kvm_memory_slot *memslot;
+	struct kvm_memory_slot *memslot, *m;
 	int ret = H_SUCCESS;
 	int srcu_idx;
 
@@ -232,35 +474,117 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 		return H_AUTHORITY;
 
 	srcu_idx = srcu_read_lock(&kvm->srcu);
+
+	/* register the memslot */
 	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, slots) {
-		if (kvmppc_uvmem_slot_init(kvm, memslot)) {
-			ret = H_PARAMETER;
-			goto out;
-		}
-		ret = uv_register_mem_slot(kvm->arch.lpid,
-					   memslot->base_gfn << PAGE_SHIFT,
-					   memslot->npages * PAGE_SIZE,
-					   0, memslot->id);
-		if (ret < 0) {
-			kvmppc_uvmem_slot_free(kvm, memslot);
-			ret = H_PARAMETER;
-			goto out;
+		ret = __kvmppc_uvmem_memslot_create(kvm, memslot);
+		if (ret)
+			break;
+	}
+
+	if (ret) {
+		slots = kvm_memslots(kvm);
+		kvm_for_each_memslot(m, slots) {
+			if (m == memslot)
+				break;
+			__kvmppc_uvmem_memslot_delete(kvm, memslot);
 		}
 	}
-out:
+
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	return ret;
 }
 
-unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
+/*
+ * Provision a new page on HV side and copy over the contents
+ * from secure memory using UV_PAGE_OUT uvcall.
+ * Caller must held kvm->arch.uvmem_lock.
+ */
+static int __kvmppc_svm_page_out(struct vm_area_struct *vma,
+		unsigned long start,
+		unsigned long end, unsigned long page_shift,
+		struct kvm *kvm, unsigned long gpa)
 {
-	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
-		return H_UNSUPPORTED;
+	unsigned long src_pfn, dst_pfn = 0;
+	struct migrate_vma mig;
+	struct page *dpage, *spage;
+	struct kvmppc_uvmem_page_pvt *pvt;
+	unsigned long pfn;
+	int ret = U_SUCCESS;
 
-	kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE;
-	pr_info("LPID %d went secure\n", kvm->arch.lpid);
-	return H_SUCCESS;
+	memset(&mig, 0, sizeof(mig));
+	mig.vma = vma;
+	mig.start = start;
+	mig.end = end;
+	mig.src = &src_pfn;
+	mig.dst = &dst_pfn;
+	mig.pgmap_owner = &kvmppc_uvmem_pgmap;
+	mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
+
+	/* The requested page is already paged-out, nothing to do */
+	if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
+		return ret;
+
+	ret = migrate_vma_setup(&mig);
+	if (ret)
+		return -1;
+
+	spage = migrate_pfn_to_page(*mig.src);
+	if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE))
+		goto out_finalize;
+
+	if (!is_zone_device_page(spage))
+		goto out_finalize;
+
+	dpage = alloc_page_vma(GFP_HIGHUSER, vma, start);
+	if (!dpage) {
+		ret = -1;
+		goto out_finalize;
+	}
+
+	lock_page(dpage);
+	pvt = spage->zone_device_data;
+	pfn = page_to_pfn(dpage);
+
+	/*
+	 * This function is used in two cases:
+	 * - When HV touches a secure page, for which we do UV_PAGE_OUT
+	 * - When a secure page is converted to shared page, we *get*
+	 *   the page to essentially unmap the device page. In this
+	 *   case we skip page-out.
+	 */
+	if (!pvt->skip_page_out)
+		ret = uv_page_out(kvm->arch.lpid, pfn << page_shift,
+				  gpa, 0, page_shift);
+
+	if (ret == U_SUCCESS)
+		*mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED;
+	else {
+		unlock_page(dpage);
+		__free_page(dpage);
+		goto out_finalize;
+	}
+
+	migrate_vma_pages(&mig);
+
+out_finalize:
+	migrate_vma_finalize(&mig);
+	return ret;
+}
+
+static inline int kvmppc_svm_page_out(struct vm_area_struct *vma,
+				      unsigned long start, unsigned long end,
+				      unsigned long page_shift,
+				      struct kvm *kvm, unsigned long gpa)
+{
+	int ret;
+
+	mutex_lock(&kvm->arch.uvmem_lock);
+	ret = __kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa);
+	mutex_unlock(&kvm->arch.uvmem_lock);
+
+	return ret;
 }
 
 /*
@@ -271,33 +595,53 @@ unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
  * fault on them, do fault time migration to replace the device PTEs in
  * QEMU page table with normal PTEs from newly allocated pages.
  */
-void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
+void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *slot,
 			     struct kvm *kvm, bool skip_page_out)
 {
 	int i;
 	struct kvmppc_uvmem_page_pvt *pvt;
-	unsigned long pfn, uvmem_pfn;
-	unsigned long gfn = free->base_gfn;
+	struct page *uvmem_page;
+	struct vm_area_struct *vma = NULL;
+	unsigned long uvmem_pfn, gfn;
+	unsigned long addr;
 
-	for (i = free->npages; i; --i, ++gfn) {
-		struct page *uvmem_page;
+	mmap_read_lock(kvm->mm);
+
+	addr = slot->userspace_addr;
+
+	gfn = slot->base_gfn;
+	for (i = slot->npages; i; --i, ++gfn, addr += PAGE_SIZE) {
+
+		/* Fetch the VMA if addr is not in the latest fetched one */
+		if (!vma || addr >= vma->vm_end) {
+			vma = find_vma_intersection(kvm->mm, addr, addr+1);
+			if (!vma) {
+				pr_err("Can't find VMA for gfn:0x%lx\n", gfn);
+				break;
+			}
+		}
 
 		mutex_lock(&kvm->arch.uvmem_lock);
-		if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
-			mutex_unlock(&kvm->arch.uvmem_lock);
-			continue;
+
+		if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+			uvmem_page = pfn_to_page(uvmem_pfn);
+			pvt = uvmem_page->zone_device_data;
+			pvt->skip_page_out = skip_page_out;
+			pvt->remove_gfn = true;
+
+			if (__kvmppc_svm_page_out(vma, addr, addr + PAGE_SIZE,
+						  PAGE_SHIFT, kvm, pvt->gpa))
+				pr_err("Can't page out gpa:0x%lx addr:0x%lx\n",
+				       pvt->gpa, addr);
+		} else {
+			/* Remove the shared flag if any */
+			kvmppc_gfn_remove(gfn, kvm);
 		}
 
-		uvmem_page = pfn_to_page(uvmem_pfn);
-		pvt = uvmem_page->zone_device_data;
-		pvt->skip_page_out = skip_page_out;
 		mutex_unlock(&kvm->arch.uvmem_lock);
-
-		pfn = gfn_to_pfn(kvm, gfn);
-		if (is_error_noslot_pfn(pfn))
-			continue;
-		kvm_release_pfn_clean(pfn);
 	}
+
+	mmap_read_unlock(kvm->mm);
 }
 
 unsigned long kvmppc_h_svm_init_abort(struct kvm *kvm)
@@ -360,7 +704,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
 		goto out_clear;
 
 	uvmem_pfn = bit + pfn_first;
-	kvmppc_uvmem_pfn_insert(gpa >> PAGE_SHIFT, uvmem_pfn, kvm);
+	kvmppc_gfn_secure_uvmem_pfn(gpa >> PAGE_SHIFT, uvmem_pfn, kvm);
 
 	pvt->gpa = gpa;
 	pvt->kvm = kvm;
@@ -379,13 +723,14 @@ out:
 }
 
 /*
- * Alloc a PFN from private device memory pool and copy page from normal
- * memory to secure memory using UV_PAGE_IN uvcall.
+ * Alloc a PFN from private device memory pool. If @pagein is true,
+ * copy page from normal memory to secure memory using UV_PAGE_IN uvcall.
  */
-static int
-kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
-		   unsigned long end, unsigned long gpa, struct kvm *kvm,
-		   unsigned long page_shift, bool *downgrade)
+static int kvmppc_svm_page_in(struct vm_area_struct *vma,
+		unsigned long start,
+		unsigned long end, unsigned long gpa, struct kvm *kvm,
+		unsigned long page_shift,
+		bool pagein)
 {
 	unsigned long src_pfn, dst_pfn = 0;
 	struct migrate_vma mig;
@@ -402,18 +747,6 @@ kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
 	mig.dst = &dst_pfn;
 	mig.flags = MIGRATE_VMA_SELECT_SYSTEM;
 
-	/*
-	 * We come here with mmap_lock write lock held just for
-	 * ksm_madvise(), otherwise we only need read mmap_lock.
-	 * Hence downgrade to read lock once ksm_madvise() is done.
-	 */
-	ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
-			  MADV_UNMERGEABLE, &vma->vm_flags);
-	mmap_write_downgrade(kvm->mm);
-	*downgrade = true;
-	if (ret)
-		return ret;
-
 	ret = migrate_vma_setup(&mig);
 	if (ret)
 		return ret;
@@ -429,11 +762,16 @@ kvmppc_svm_page_in(struct vm_area_struct *vma, unsigned long start,
 		goto out_finalize;
 	}
 
-	pfn = *mig.src >> MIGRATE_PFN_SHIFT;
-	spage = migrate_pfn_to_page(*mig.src);
-	if (spage)
-		uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0,
-			   page_shift);
+	if (pagein) {
+		pfn = *mig.src >> MIGRATE_PFN_SHIFT;
+		spage = migrate_pfn_to_page(*mig.src);
+		if (spage) {
+			ret = uv_page_in(kvm->arch.lpid, pfn << page_shift,
+					gpa, 0, page_shift);
+			if (ret)
+				goto out_finalize;
+		}
+	}
 
 	*mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
 	migrate_vma_pages(&mig);
@@ -442,6 +780,80 @@ out_finalize:
 	return ret;
 }
 
+static int kvmppc_uv_migrate_mem_slot(struct kvm *kvm,
+		const struct kvm_memory_slot *memslot)
+{
+	unsigned long gfn = memslot->base_gfn;
+	struct vm_area_struct *vma;
+	unsigned long start, end;
+	int ret = 0;
+
+	mmap_read_lock(kvm->mm);
+	mutex_lock(&kvm->arch.uvmem_lock);
+	while (kvmppc_next_nontransitioned_gfn(memslot, kvm, &gfn)) {
+		ret = H_STATE;
+		start = gfn_to_hva(kvm, gfn);
+		if (kvm_is_error_hva(start))
+			break;
+
+		end = start + (1UL << PAGE_SHIFT);
+		vma = find_vma_intersection(kvm->mm, start, end);
+		if (!vma || vma->vm_start > start || vma->vm_end < end)
+			break;
+
+		ret = kvmppc_svm_page_in(vma, start, end,
+				(gfn << PAGE_SHIFT), kvm, PAGE_SHIFT, false);
+		if (ret) {
+			ret = H_STATE;
+			break;
+		}
+
+		/* relinquish the cpu if needed */
+		cond_resched();
+	}
+	mutex_unlock(&kvm->arch.uvmem_lock);
+	mmap_read_unlock(kvm->mm);
+	return ret;
+}
+
+unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int srcu_idx;
+	long ret = H_SUCCESS;
+
+	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
+		return H_UNSUPPORTED;
+
+	/* migrate any unmoved normal pfn to device pfns*/
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	slots = kvm_memslots(kvm);
+	kvm_for_each_memslot(memslot, slots) {
+		ret = kvmppc_uv_migrate_mem_slot(kvm, memslot);
+		if (ret) {
+			/*
+			 * The pages will remain transitioned.
+			 * Its the callers responsibility to
+			 * terminate the VM, which will undo
+			 * all state of the VM. Till then
+			 * this VM is in a erroneous state.
+			 * Its KVMPPC_SECURE_INIT_DONE will
+			 * remain unset.
+			 */
+			ret = H_STATE;
+			goto out;
+		}
+	}
+
+	kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE;
+	pr_info("LPID %d went secure\n", kvm->arch.lpid);
+
+out:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	return ret;
+}
+
 /*
  * Shares the page with HV, thus making it a normal page.
  *
@@ -451,8 +863,8 @@ out_finalize:
  * In the former case, uses dev_pagemap_ops.migrate_to_ram handler
  * to unmap the device page from QEMU's page tables.
  */
-static unsigned long
-kvmppc_share_page(struct kvm *kvm, unsigned long gpa, unsigned long page_shift)
+static unsigned long kvmppc_share_page(struct kvm *kvm, unsigned long gpa,
+		unsigned long page_shift)
 {
 
 	int ret = H_PARAMETER;
@@ -469,6 +881,11 @@ kvmppc_share_page(struct kvm *kvm, unsigned long gpa, unsigned long page_shift)
 		uvmem_page = pfn_to_page(uvmem_pfn);
 		pvt = uvmem_page->zone_device_data;
 		pvt->skip_page_out = true;
+		/*
+		 * do not drop the GFN. It is a valid GFN
+		 * that is transitioned to a shared GFN.
+		 */
+		pvt->remove_gfn = false;
 	}
 
 retry:
@@ -482,12 +899,16 @@ retry:
 		uvmem_page = pfn_to_page(uvmem_pfn);
 		pvt = uvmem_page->zone_device_data;
 		pvt->skip_page_out = true;
+		pvt->remove_gfn = false; /* it continues to be a valid GFN */
 		kvm_release_pfn_clean(pfn);
 		goto retry;
 	}
 
-	if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, page_shift))
+	if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0,
+				page_shift)) {
+		kvmppc_gfn_shared(gfn, kvm);
 		ret = H_SUCCESS;
+	}
 	kvm_release_pfn_clean(pfn);
 	mutex_unlock(&kvm->arch.uvmem_lock);
 out:
@@ -501,11 +922,10 @@ out:
  * H_PAGE_IN_SHARED flag makes the page shared which means that the same
  * memory in is visible from both UV and HV.
  */
-unsigned long
-kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
-		     unsigned long flags, unsigned long page_shift)
+unsigned long kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
+		unsigned long flags,
+		unsigned long page_shift)
 {
-	bool downgrade = false;
 	unsigned long start, end;
 	struct vm_area_struct *vma;
 	int srcu_idx;
@@ -526,7 +946,7 @@ kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 
 	ret = H_PARAMETER;
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	mmap_write_lock(kvm->mm);
+	mmap_read_lock(kvm->mm);
 
 	start = gfn_to_hva(kvm, gfn);
 	if (kvm_is_error_hva(start))
@@ -542,97 +962,20 @@ kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gpa,
 	if (!vma || vma->vm_start > start || vma->vm_end < end)
 		goto out_unlock;
 
-	if (!kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift,
-				&downgrade))
-		ret = H_SUCCESS;
+	if (kvmppc_svm_page_in(vma, start, end, gpa, kvm, page_shift,
+				true))
+		goto out_unlock;
+
+	ret = H_SUCCESS;
+
 out_unlock:
 	mutex_unlock(&kvm->arch.uvmem_lock);
 out:
-	if (downgrade)
-		mmap_read_unlock(kvm->mm);
-	else
-		mmap_write_unlock(kvm->mm);
+	mmap_read_unlock(kvm->mm);
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	return ret;
 }
 
-/*
- * Provision a new page on HV side and copy over the contents
- * from secure memory using UV_PAGE_OUT uvcall.
- */
-static int
-kvmppc_svm_page_out(struct vm_area_struct *vma, unsigned long start,
-		    unsigned long end, unsigned long page_shift,
-		    struct kvm *kvm, unsigned long gpa)
-{
-	unsigned long src_pfn, dst_pfn = 0;
-	struct migrate_vma mig;
-	struct page *dpage, *spage;
-	struct kvmppc_uvmem_page_pvt *pvt;
-	unsigned long pfn;
-	int ret = U_SUCCESS;
-
-	memset(&mig, 0, sizeof(mig));
-	mig.vma = vma;
-	mig.start = start;
-	mig.end = end;
-	mig.src = &src_pfn;
-	mig.dst = &dst_pfn;
-	mig.pgmap_owner = &kvmppc_uvmem_pgmap;
-	mig.flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE;
-
-	mutex_lock(&kvm->arch.uvmem_lock);
-	/* The requested page is already paged-out, nothing to do */
-	if (!kvmppc_gfn_is_uvmem_pfn(gpa >> page_shift, kvm, NULL))
-		goto out;
-
-	ret = migrate_vma_setup(&mig);
-	if (ret)
-		goto out;
-
-	spage = migrate_pfn_to_page(*mig.src);
-	if (!spage || !(*mig.src & MIGRATE_PFN_MIGRATE))
-		goto out_finalize;
-
-	if (!is_zone_device_page(spage))
-		goto out_finalize;
-
-	dpage = alloc_page_vma(GFP_HIGHUSER, vma, start);
-	if (!dpage) {
-		ret = -1;
-		goto out_finalize;
-	}
-
-	lock_page(dpage);
-	pvt = spage->zone_device_data;
-	pfn = page_to_pfn(dpage);
-
-	/*
-	 * This function is used in two cases:
-	 * - When HV touches a secure page, for which we do UV_PAGE_OUT
-	 * - When a secure page is converted to shared page, we *get*
-	 *   the page to essentially unmap the device page. In this
-	 *   case we skip page-out.
-	 */
-	if (!pvt->skip_page_out)
-		ret = uv_page_out(kvm->arch.lpid, pfn << page_shift,
-				  gpa, 0, page_shift);
-
-	if (ret == U_SUCCESS)
-		*mig.dst = migrate_pfn(pfn) | MIGRATE_PFN_LOCKED;
-	else {
-		unlock_page(dpage);
-		__free_page(dpage);
-		goto out_finalize;
-	}
-
-	migrate_vma_pages(&mig);
-out_finalize:
-	migrate_vma_finalize(&mig);
-out:
-	mutex_unlock(&kvm->arch.uvmem_lock);
-	return ret;
-}
 
 /*
  * Fault handler callback that gets called when HV touches any page that
@@ -657,7 +1000,8 @@ static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
 /*
  * Release the device PFN back to the pool
  *
- * Gets called when secure page becomes a normal page during H_SVM_PAGE_OUT.
+ * Gets called when secure GFN tranistions from a secure-PFN
+ * to a normal PFN during H_SVM_PAGE_OUT.
  * Gets called with kvm->arch.uvmem_lock held.
  */
 static void kvmppc_uvmem_page_free(struct page *page)
@@ -672,7 +1016,10 @@ static void kvmppc_uvmem_page_free(struct page *page)
 
 	pvt = page->zone_device_data;
 	page->zone_device_data = NULL;
-	kvmppc_uvmem_pfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
+	if (pvt->remove_gfn)
+		kvmppc_gfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
+	else
+		kvmppc_gfn_secure_mem_pfn(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
 	kfree(pvt);
 }
 
@@ -744,6 +1091,21 @@ out:
 	return (ret == U_SUCCESS) ? RESUME_GUEST : -EFAULT;
 }
 
+int kvmppc_uvmem_memslot_create(struct kvm *kvm, const struct kvm_memory_slot *new)
+{
+	int ret = __kvmppc_uvmem_memslot_create(kvm, new);
+
+	if (!ret)
+		ret = kvmppc_uv_migrate_mem_slot(kvm, new);
+
+	return ret;
+}
+
+void kvmppc_uvmem_memslot_delete(struct kvm *kvm, const struct kvm_memory_slot *old)
+{
+	__kvmppc_uvmem_memslot_delete(kvm, old);
+}
+
 static u64 kvmppc_get_secmem_size(void)
 {
 	struct device_node *np;