Merge tag 'kvm-ppc-uvmem-5.5-2' of...

Merge tag 'kvm-ppc-uvmem-5.5-2' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD

KVM: Add support for secure guests under the Protected Execution
Framework (PEF) Ultravisor on POWER.

This enables secure memory to be represented as device memory,
which provides a way for the host to keep track of which pages of a
secure guest have been moved into secure memory managed by the
ultravisor and are no longer accessible by the host, and manage
movement of pages between secure and normal memory.

Documentation/virt/kvm/api.txt

@@ -4149,6 +4149,24 @@ Valid values for 'action':
 #define KVM_PMU_EVENT_ALLOW 0
 #define KVM_PMU_EVENT_DENY 1
 
+4.121 KVM_PPC_SVM_OFF
+
+Capability: basic
+Architectures: powerpc
+Type: vm ioctl
+Parameters: none
+Returns: 0 on successful completion,
+Errors:
+  EINVAL:    if ultravisor failed to terminate the secure guest
+  ENOMEM:    if hypervisor failed to allocate new radix page tables for guest
+
+This ioctl is used to turn off the secure mode of the guest or transition
+the guest from secure mode to normal mode. This is invoked when the guest
+is reset. This has no effect if called for a normal guest.
+
+This ioctl issues an ultravisor call to terminate the secure guest,
+unpins the VPA pages and releases all the device pages that are used to
+track the secure pages by hypervisor.
 
 5. The kvm_run structure
 ------------------------

arch/powerpc/Kconfig

@@ -451,6 +451,23 @@ config PPC_TRANSACTIONAL_MEM
 	help
 	  Support user-mode Transactional Memory on POWERPC.
 
+config PPC_UV
+	bool "Ultravisor support"
+	depends on KVM_BOOK3S_HV_POSSIBLE
+	select ZONE_DEVICE
+	select DEV_PAGEMAP_OPS
+	select DEVICE_PRIVATE
+	select MEMORY_HOTPLUG
+	select MEMORY_HOTREMOVE
+	default n
+	help
+	  This option paravirtualizes the kernel to run in POWER platforms that
+	  supports the Protected Execution Facility (PEF). On such platforms,
+	  the ultravisor firmware runs at a privilege level above the
+	  hypervisor.
+
+	  If unsure, say "N".
+
 config LD_HEAD_STUB_CATCH
 	bool "Reserve 256 bytes to cope with linker stubs in HEAD text" if EXPERT
 	depends on PPC64

arch/powerpc/include/asm/hvcall.h

@@ -342,6 +342,15 @@
 #define H_TLB_INVALIDATE	0xF808
 #define H_COPY_TOFROM_GUEST	0xF80C
 
+/* Flags for H_SVM_PAGE_IN */
+#define H_PAGE_IN_SHARED        0x1
+
+/* Platform-specific hcalls used by the Ultravisor */
+#define H_SVM_PAGE_IN		0xEF00
+#define H_SVM_PAGE_OUT		0xEF04
+#define H_SVM_INIT_START	0xEF08
+#define H_SVM_INIT_DONE		0xEF0C
+
 /* Values for 2nd argument to H_SET_MODE */
 #define H_SET_MODE_RESOURCE_SET_CIABR		1
 #define H_SET_MODE_RESOURCE_SET_DAWR		2

arch/powerpc/include/asm/kvm_book3s_uvmem.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_KVM_BOOK3S_UVMEM_H__
+#define __ASM_KVM_BOOK3S_UVMEM_H__
+
+#ifdef CONFIG_PPC_UV
+int kvmppc_uvmem_init(void);
+void kvmppc_uvmem_free(void);
+int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot);
+void kvmppc_uvmem_slot_free(struct kvm *kvm,
+			    const struct kvm_memory_slot *slot);
+unsigned long kvmppc_h_svm_page_in(struct kvm *kvm,
+				   unsigned long gra,
+				   unsigned long flags,
+				   unsigned long page_shift);
+unsigned long kvmppc_h_svm_page_out(struct kvm *kvm,
+				    unsigned long gra,
+				    unsigned long flags,
+				    unsigned long page_shift);
+unsigned long kvmppc_h_svm_init_start(struct kvm *kvm);
+unsigned long kvmppc_h_svm_init_done(struct kvm *kvm);
+int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn);
+void kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
+			     struct kvm *kvm);
+#else
+static inline int kvmppc_uvmem_init(void)
+{
+	return 0;
+}
+
+static inline void kvmppc_uvmem_free(void) { }
+
+static inline int
+kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot)
+{
+	return 0;
+}
+
+static inline void
+kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot) { }
+
+static inline unsigned long
+kvmppc_h_svm_page_in(struct kvm *kvm, unsigned long gra,
+		     unsigned long flags, unsigned long page_shift)
+{
+	return H_UNSUPPORTED;
+}
+
+static inline unsigned long
+kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gra,
+		      unsigned long flags, unsigned long page_shift)
+{
+	return H_UNSUPPORTED;
+}
+
+static inline unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
+{
+	return H_UNSUPPORTED;
+}
+
+static inline unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
+{
+	return H_UNSUPPORTED;
+}
+
+static inline int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
+{
+	return -EFAULT;
+}
+
+static inline void
+kvmppc_uvmem_drop_pages(const struct kvm_memory_slot *free,
+			struct kvm *kvm) { }
+#endif /* CONFIG_PPC_UV */
+#endif /* __ASM_KVM_BOOK3S_UVMEM_H__ */

arch/powerpc/include/asm/kvm_host.h

@@ -275,6 +275,10 @@ struct kvm_hpt_info {
 
 struct kvm_resize_hpt;
 
+/* Flag values for kvm_arch.secure_guest */
+#define KVMPPC_SECURE_INIT_START 0x1 /* H_SVM_INIT_START has been called */
+#define KVMPPC_SECURE_INIT_DONE  0x2 /* H_SVM_INIT_DONE completed */
+
 struct kvm_arch {
 	unsigned int lpid;
 	unsigned int smt_mode;		/* # vcpus per virtual core */
@@ -330,6 +334,8 @@ struct kvm_arch {
 #endif
 	struct kvmppc_ops *kvm_ops;
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	struct mutex uvmem_lock;
+	struct list_head uvmem_pfns;
 	struct mutex mmu_setup_lock;	/* nests inside vcpu mutexes */
 	u64 l1_ptcr;
 	int max_nested_lpid;

arch/powerpc/include/asm/kvm_ppc.h

@@ -322,6 +322,7 @@ struct kvmppc_ops {
 			       int size);
 	int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
 			      int size);
+	int (*svm_off)(struct kvm *kvm);
 };
 
 extern struct kvmppc_ops *kvmppc_hv_ops;

arch/powerpc/include/asm/ultravisor-api.h

@@ -26,8 +26,14 @@
 #define UV_WRITE_PATE			0xF104
 #define UV_RETURN			0xF11C
 #define UV_ESM				0xF110
+#define UV_REGISTER_MEM_SLOT		0xF120
+#define UV_UNREGISTER_MEM_SLOT		0xF124
+#define UV_PAGE_IN			0xF128
+#define UV_PAGE_OUT			0xF12C
 #define UV_SHARE_PAGE			0xF130
 #define UV_UNSHARE_PAGE			0xF134
 #define UV_UNSHARE_ALL_PAGES		0xF140
+#define UV_PAGE_INVAL			0xF138
+#define UV_SVM_TERMINATE		0xF13C
 
 #endif /* _ASM_POWERPC_ULTRAVISOR_API_H */

arch/powerpc/include/asm/ultravisor.h

@@ -46,4 +46,40 @@ static inline int uv_unshare_all_pages(void)
 	return ucall_norets(UV_UNSHARE_ALL_PAGES);
 }
 
+static inline int uv_page_in(u64 lpid, u64 src_ra, u64 dst_gpa, u64 flags,
+			     u64 page_shift)
+{
+	return ucall_norets(UV_PAGE_IN, lpid, src_ra, dst_gpa, flags,
+			    page_shift);
+}
+
+static inline int uv_page_out(u64 lpid, u64 dst_ra, u64 src_gpa, u64 flags,
+			      u64 page_shift)
+{
+	return ucall_norets(UV_PAGE_OUT, lpid, dst_ra, src_gpa, flags,
+			    page_shift);
+}
+
+static inline int uv_register_mem_slot(u64 lpid, u64 start_gpa, u64 size,
+				       u64 flags, u64 slotid)
+{
+	return ucall_norets(UV_REGISTER_MEM_SLOT, lpid, start_gpa,
+			    size, flags, slotid);
+}
+
+static inline int uv_unregister_mem_slot(u64 lpid, u64 slotid)
+{
+	return ucall_norets(UV_UNREGISTER_MEM_SLOT, lpid, slotid);
+}
+
+static inline int uv_page_inval(u64 lpid, u64 gpa, u64 page_shift)
+{
+	return ucall_norets(UV_PAGE_INVAL, lpid, gpa, page_shift);
+}
+
+static inline int uv_svm_terminate(u64 lpid)
+{
+	return ucall_norets(UV_SVM_TERMINATE, lpid);
+}
+
 #endif	/* _ASM_POWERPC_ULTRAVISOR_H */

arch/powerpc/kvm/Makefile

@@ -71,6 +71,9 @@ kvm-hv-y += \
 	book3s_64_mmu_radix.o \
 	book3s_hv_nested.o
 
+kvm-hv-$(CONFIG_PPC_UV) += \
+	book3s_hv_uvmem.o
+
 kvm-hv-$(CONFIG_PPC_TRANSACTIONAL_MEM) += \
 	book3s_hv_tm.o
 

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -19,6 +19,8 @@
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/pte-walk.h>
+#include <asm/ultravisor.h>
+#include <asm/kvm_book3s_uvmem.h>
 
 /*
  * Supported radix tree geometry.
@@ -915,6 +917,9 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	if (!(dsisr & DSISR_PRTABLE_FAULT))
 		gpa |= ea & 0xfff;
 
+	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+		return kvmppc_send_page_to_uv(kvm, gfn);
+
 	/* Get the corresponding memslot */
 	memslot = gfn_to_memslot(kvm, gfn);
 
@@ -972,6 +977,11 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	unsigned long gpa = gfn << PAGE_SHIFT;
 	unsigned int shift;
 
+	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) {
+		uv_page_inval(kvm->arch.lpid, gpa, PAGE_SHIFT);
+		return 0;
+	}
+
 	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep))
 		kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot,
@@ -989,6 +999,9 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	int ref = 0;
 	unsigned long old, *rmapp;
 
+	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+		return ref;
+
 	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_young(*ptep)) {
 		old = kvmppc_radix_update_pte(kvm, ptep, _PAGE_ACCESSED, 0,
@@ -1013,6 +1026,9 @@ int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	unsigned int shift;
 	int ref = 0;
 
+	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+		return ref;
+
 	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_young(*ptep))
 		ref = 1;
@@ -1030,6 +1046,9 @@ static int kvm_radix_test_clear_dirty(struct kvm *kvm,
 	int ret = 0;
 	unsigned long old, *rmapp;
 
+	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+		return ret;
+
 	ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
 	if (ptep && pte_present(*ptep) && pte_dirty(*ptep)) {
 		ret = 1;
@@ -1082,6 +1101,12 @@ void kvmppc_radix_flush_memslot(struct kvm *kvm,
 	unsigned long gpa;
 	unsigned int shift;
 
+	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START)
+		kvmppc_uvmem_drop_pages(memslot, kvm);
+
+	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE)
+		return;
+
 	gpa = memslot->base_gfn << PAGE_SHIFT;
 	spin_lock(&kvm->mmu_lock);
 	for (n = memslot->npages; n; --n) {

arch/powerpc/kvm/book3s_hv.c

@@ -72,6 +72,9 @@
 #include <asm/xics.h>
 #include <asm/xive.h>
 #include <asm/hw_breakpoint.h>
+#include <asm/kvm_host.h>
+#include <asm/kvm_book3s_uvmem.h>
+#include <asm/ultravisor.h>
 
 #include "book3s.h"
 
@@ -1070,6 +1073,25 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 					 kvmppc_get_gpr(vcpu, 5),
 					 kvmppc_get_gpr(vcpu, 6));
 		break;
+	case H_SVM_PAGE_IN:
+		ret = kvmppc_h_svm_page_in(vcpu->kvm,
+					   kvmppc_get_gpr(vcpu, 4),
+					   kvmppc_get_gpr(vcpu, 5),
+					   kvmppc_get_gpr(vcpu, 6));
+		break;
+	case H_SVM_PAGE_OUT:
+		ret = kvmppc_h_svm_page_out(vcpu->kvm,
+					    kvmppc_get_gpr(vcpu, 4),
+					    kvmppc_get_gpr(vcpu, 5),
+					    kvmppc_get_gpr(vcpu, 6));
+		break;
+	case H_SVM_INIT_START:
+		ret = kvmppc_h_svm_init_start(vcpu->kvm);
+		break;
+	case H_SVM_INIT_DONE:
+		ret = kvmppc_h_svm_init_done(vcpu->kvm);
+		break;
+
 	default:
 		return RESUME_HOST;
 	}
@@ -4494,6 +4516,29 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
 	if (change == KVM_MR_FLAGS_ONLY && kvm_is_radix(kvm) &&
 	    ((new->flags ^ old->flags) & KVM_MEM_LOG_DIRTY_PAGES))
 		kvmppc_radix_flush_memslot(kvm, old);
+	/*
+	 * If UV hasn't yet called H_SVM_INIT_START, don't register memslots.
+	 */
+	if (!kvm->arch.secure_guest)
+		return;
+
+	switch (change) {
+	case KVM_MR_CREATE:
+		if (kvmppc_uvmem_slot_init(kvm, new))
+			return;
+		uv_register_mem_slot(kvm->arch.lpid,
+				     new->base_gfn << PAGE_SHIFT,
+				     new->npages * PAGE_SIZE,
+				     0, new->id);
+		break;
+	case KVM_MR_DELETE:
+		uv_unregister_mem_slot(kvm->arch.lpid, old->id);
+		kvmppc_uvmem_slot_free(kvm, old);
+		break;
+	default:
+		/* TODO: Handle KVM_MR_MOVE */
+		break;
+	}
 }
 
 /*
@@ -4767,6 +4812,8 @@ static int kvmppc_core_init_vm_hv(struct kvm *kvm)
 	char buf[32];
 	int ret;
 
+	mutex_init(&kvm->arch.uvmem_lock);
+	INIT_LIST_HEAD(&kvm->arch.uvmem_pfns);
 	mutex_init(&kvm->arch.mmu_setup_lock);
 
 	/* Allocate the guest's logical partition ID */
@@ -4936,8 +4983,10 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
 		if (nesting_enabled(kvm))
 			kvmhv_release_all_nested(kvm);
 		kvm->arch.process_table = 0;
+		uv_svm_terminate(kvm->arch.lpid);
 		kvmhv_set_ptbl_entry(kvm->arch.lpid, 0, 0);
 	}
+
 	kvmppc_free_lpid(kvm->arch.lpid);
 
 	kvmppc_free_pimap(kvm);
@@ -5377,6 +5426,94 @@ static int kvmhv_store_to_eaddr(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
 	return rc;
 }
 
+static void unpin_vpa_reset(struct kvm *kvm, struct kvmppc_vpa *vpa)
+{
+	unpin_vpa(kvm, vpa);
+	vpa->gpa = 0;
+	vpa->pinned_addr = NULL;
+	vpa->dirty = false;
+	vpa->update_pending = 0;
+}
+
+/*
+ *  IOCTL handler to turn off secure mode of guest
+ *
+ * - Release all device pages
+ * - Issue ucall to terminate the guest on the UV side
+ * - Unpin the VPA pages.
+ * - Reinit the partition scoped page tables
+ */
+static int kvmhv_svm_off(struct kvm *kvm)
+{
+	struct kvm_vcpu *vcpu;
+	int mmu_was_ready;
+	int srcu_idx;
+	int ret = 0;
+	int i;
+
+	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
+		return ret;
+
+	mutex_lock(&kvm->arch.mmu_setup_lock);
+	mmu_was_ready = kvm->arch.mmu_ready;
+	if (kvm->arch.mmu_ready) {
+		kvm->arch.mmu_ready = 0;
+		/* order mmu_ready vs. vcpus_running */
+		smp_mb();
+		if (atomic_read(&kvm->arch.vcpus_running)) {
+			kvm->arch.mmu_ready = 1;
+			ret = -EBUSY;
+			goto out;
+		}
+	}
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		struct kvm_memory_slot *memslot;
+		struct kvm_memslots *slots = __kvm_memslots(kvm, i);
+
+		if (!slots)
+			continue;
+
+		kvm_for_each_memslot(memslot, slots) {
+			kvmppc_uvmem_drop_pages(memslot, kvm);
+			uv_unregister_mem_slot(kvm->arch.lpid, memslot->id);
+		}
+	}
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+	ret = uv_svm_terminate(kvm->arch.lpid);
+	if (ret != U_SUCCESS) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * When secure guest is reset, all the guest pages are sent
+	 * to UV via UV_PAGE_IN before the non-boot vcpus get a
+	 * chance to run and unpin their VPA pages. Unpinning of all
+	 * VPA pages is done here explicitly so that VPA pages
+	 * can be migrated to the secure side.
+	 *
+	 * This is required to for the secure SMP guest to reboot
+	 * correctly.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		spin_lock(&vcpu->arch.vpa_update_lock);
+		unpin_vpa_reset(kvm, &vcpu->arch.dtl);
+		unpin_vpa_reset(kvm, &vcpu->arch.slb_shadow);
+		unpin_vpa_reset(kvm, &vcpu->arch.vpa);
+		spin_unlock(&vcpu->arch.vpa_update_lock);
+	}
+
+	kvmppc_setup_partition_table(kvm);
+	kvm->arch.secure_guest = 0;
+	kvm->arch.mmu_ready = mmu_was_ready;
+out:
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
+	return ret;
+}
+
 static struct kvmppc_ops kvm_ops_hv = {
 	.get_sregs = kvm_arch_vcpu_ioctl_get_sregs_hv,
 	.set_sregs = kvm_arch_vcpu_ioctl_set_sregs_hv,
@@ -5420,6 +5557,7 @@ static struct kvmppc_ops kvm_ops_hv = {
 	.enable_nested = kvmhv_enable_nested,
 	.load_from_eaddr = kvmhv_load_from_eaddr,
 	.store_to_eaddr = kvmhv_store_to_eaddr,
+	.svm_off = kvmhv_svm_off,
 };
 
 static int kvm_init_subcore_bitmap(void)
@@ -5528,11 +5666,16 @@ static int kvmppc_book3s_init_hv(void)
 			no_mixing_hpt_and_radix = true;
 	}
 
+	r = kvmppc_uvmem_init();
+	if (r < 0)
+		pr_err("KVM-HV: kvmppc_uvmem_init failed %d\n", r);
+
 	return r;
 }
 
 static void kvmppc_book3s_exit_hv(void)
 {
+	kvmppc_uvmem_free();
 	kvmppc_free_host_rm_ops();
 	if (kvmppc_radix_possible())
 		kvmppc_radix_exit();

arch/powerpc/kvm/book3s_hv_uvmem.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Secure pages management: Migration of pages between normal and secure
+ * memory of KVM guests.
+ *
+ * Copyright 2018 Bharata B Rao, IBM Corp. <bharata@linux.ibm.com>
+ */
+
+/*
+ * A pseries guest can be run as secure guest on Ultravisor-enabled
+ * POWER platforms. On such platforms, this driver will be used to manage
+ * the movement of guest pages between the normal memory managed by
+ * hypervisor (HV) and secure memory managed by Ultravisor (UV).
+ *
+ * The page-in or page-out requests from UV will come to HV as hcalls and
+ * HV will call back into UV via ultracalls to satisfy these page requests.
+ *
+ * Private ZONE_DEVICE memory equal to the amount of secure memory
+ * available in the platform for running secure guests is hotplugged.
+ * Whenever a page belonging to the guest becomes secure, a page from this
+ * private device memory is used to represent and track that secure page
+ * on the HV side. Some pages (like virtio buffers, VPA pages etc) are
+ * shared between UV and HV. However such pages aren't represented by
+ * device private memory and mappings to shared memory exist in both
+ * UV and HV page tables.
+ */
+
+/*
+ * Notes on locking
+ *
+ * kvm->arch.uvmem_lock is a per-guest lock that prevents concurrent
+ * page-in and page-out requests for the same GPA. Concurrent accesses
+ * can either come via UV (guest vCPUs requesting for same page)
+ * or when HV and guest simultaneously access the same page.
+ * This mutex serializes the migration of page from HV(normal) to
+ * UV(secure) and vice versa. So the serialization points are around
+ * migrate_vma routines and page-in/out routines.
+ *
+ * Per-guest mutex comes with a cost though. Mainly it serializes the
+ * fault path as page-out can occur when HV faults on accessing secure
+ * guest pages. Currently UV issues page-in requests for all the guest
+ * PFNs one at a time during early boot (UV_ESM uvcall), so this is
+ * not a cause for concern. Also currently the number of page-outs caused
+ * by HV touching secure pages is very very low. If an when UV supports
+ * overcommitting, then we might see concurrent guest driven page-outs.
+ *
+ * Locking order
+ *
+ * 1. kvm->srcu - Protects KVM memslots
+ * 2. kvm->mm->mmap_sem - find_vma, migrate_vma_pages and helpers, ksm_madvise
+ * 3. kvm->arch.uvmem_lock - protects read/writes to uvmem slots thus acting
+ *			     as sync-points for page-in/out
+ */
+
+/*
+ * Notes on page size
+ *
+ * Currently UV uses 2MB mappings internally, but will issue H_SVM_PAGE_IN
+ * and H_SVM_PAGE_OUT hcalls in PAGE_SIZE(64K) granularity. HV tracks
+ * secure GPAs at 64K page size and maintains one device PFN for each
+ * 64K secure GPA. UV_PAGE_IN and UV_PAGE_OUT calls by HV are also issued
+ * for 64K page at a time.
+ *
+ * HV faulting on secure pages: When HV touches any secure page, it
+ * faults and issues a UV_PAGE_OUT request with 64K page size. Currently
+ * UV splits and remaps the 2MB page if necessary and copies out the
+ * required 64K page contents.
+ *
+ * Shared pages: Whenever guest shares a secure page, UV will split and
+ * remap the 2MB page if required and issue H_SVM_PAGE_IN with 64K page size.
+ *
+ * HV invalidating a page: When a regular page belonging to secure
+ * guest gets unmapped, HV informs UV with UV_PAGE_INVAL of 64K
+ * page size. Using 64K page size is correct here because any non-secure
+ * page will essentially be of 64K page size. Splitting by UV during sharing
+ * and page-out ensures this.
+ *
+ * Page fault handling: When HV handles page fault of a page belonging
+ * to secure guest, it sends that to UV with a 64K UV_PAGE_IN request.
+ * Using 64K size is correct here too as UV would have split the 2MB page
+ * into 64k mappings and would have done page-outs earlier.
+ *
+ * In summary, the current secure pages handling code in HV assumes
+ * 64K page size and in fact fails any page-in/page-out requests of
+ * non-64K size upfront. If and when UV starts supporting multiple
+ * page-sizes, we need to break this assumption.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/migrate.h>
+#include <linux/kvm_host.h>
+#include <linux/ksm.h>
+#include <asm/ultravisor.h>
+#include <asm/mman.h>
+#include <asm/kvm_ppc.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)
+
+struct kvmppc_uvmem_slot {
+	struct list_head list;
+	unsigned long nr_pfns;
+	unsigned long base_pfn;
+	unsigned long *pfns;
+};
+
+struct kvmppc_uvmem_page_pvt {
+	struct kvm *kvm;
+	unsigned long gpa;
+	bool skip_page_out;
+};
+
+int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot)
+{
+	struct kvmppc_uvmem_slot *p;
+
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+	p->pfns = vzalloc(array_size(slot->npages, sizeof(*p->pfns)));
+	if (!p->pfns) {
+		kfree(p);
+		return -ENOMEM;
+	}
+	p->nr_pfns = slot->npages;
+	p->base_pfn = slot->base_gfn;
+
+	mutex_lock(&kvm->arch.uvmem_lock);
+	list_add(&p->list, &kvm->arch.uvmem_pfns);
+	mutex_unlock(&kvm->arch.uvmem_lock);
+
+	return 0;
+}
+
+/*
+ * All device PFNs are already released by the time we come here.
+ */
+void kvmppc_uvmem_slot_free(struct kvm *kvm, const struct kvm_memory_slot *slot)
+{
+	struct kvmppc_uvmem_slot *p, *next;
+
+	mutex_lock(&kvm->arch.uvmem_lock);
+	list_for_each_entry_safe(p, next, &kvm->arch.uvmem_pfns, list) {
+		if (p->base_pfn == slot->base_gfn) {
+			vfree(p->pfns);
+			list_del(&p->list);
+			kfree(p);
+			break;
+		}
+	}
+	mutex_unlock(&kvm->arch.uvmem_lock);
+}
+
+static void kvmppc_uvmem_pfn_insert(unsigned long gfn, unsigned long uvmem_pfn,
+				    struct kvm *kvm)
+{
+	struct kvmppc_uvmem_slot *p;
+
+	list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) {
+		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;
+			return;
+		}
+	}
+}
+
+static void kvmppc_uvmem_pfn_remove(unsigned long gfn, struct kvm *kvm)
+{
+	struct kvmppc_uvmem_slot *p;
+
+	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;
+		}
+	}
+}
+
+static bool kvmppc_gfn_is_uvmem_pfn(unsigned long gfn, struct kvm *kvm,
+				    unsigned long *uvmem_pfn)
+{
+	struct kvmppc_uvmem_slot *p;
+
+	list_for_each_entry(p, &kvm->arch.uvmem_pfns, list) {
+		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 (uvmem_pfn)
+					*uvmem_pfn = p->pfns[index] &
+						     ~KVMPPC_UVMEM_PFN;
+				return true;
+			} else
+				return false;
+		}
+	}
+	return false;
+}
+
+unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
+{
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *memslot;
+	int ret = H_SUCCESS;
+	int srcu_idx;
+
+	if (!kvmppc_uvmem_bitmap)
+		return H_UNSUPPORTED;
+
+	/* Only radix guests can be secure guests */
+	if (!kvm_is_radix(kvm))
+		return H_UNSUPPORTED;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	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;
+		}
+	}
+	kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_START;
+out:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	return ret;
+}
+
+unsigned long kvmppc_h_svm_init_done(struct kvm *kvm)
+{
+	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
+		return H_UNSUPPORTED;
+
+	kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_DONE;
+	pr_info("LPID %d went secure\n", kvm->arch.lpid);
+	return H_SUCCESS;
+}
+
+/*
+ * Drop device pages that we maintain for the secure guest
+ *
+ * We first mark the pages to be skipped from UV_PAGE_OUT when there
+ * is HV side fault on these pages. Next we *get* these pages, forcing
+ * 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,
+			     struct kvm *kvm)
+{
+	int i;
+	struct kvmppc_uvmem_page_pvt *pvt;
+	unsigned long pfn, uvmem_pfn;
+	unsigned long gfn = free->base_gfn;
+
+	for (i = free->npages; i; --i, ++gfn) {
+		struct page *uvmem_page;
+
+		mutex_lock(&kvm->arch.uvmem_lock);
+		if (!kvmppc_gfn_is_uvmem_pfn(gfn, kvm, &uvmem_pfn)) {
+			mutex_unlock(&kvm->arch.uvmem_lock);
+			continue;
+		}
+
+		uvmem_page = pfn_to_page(uvmem_pfn);
+		pvt = uvmem_page->zone_device_data;
+		pvt->skip_page_out = true;
+		mutex_unlock(&kvm->arch.uvmem_lock);
+
+		pfn = gfn_to_pfn(kvm, gfn);
+		if (is_error_noslot_pfn(pfn))
+			continue;
+		kvm_release_pfn_clean(pfn);
+	}
+}
+
+/*
+ * Get a free device PFN from the pool
+ *
+ * Called when a normal page is moved to secure memory (UV_PAGE_IN). Device
+ * PFN will be used to keep track of the secure page on HV side.
+ *
+ * Called with kvm->arch.uvmem_lock held
+ */
+static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
+{
+	struct page *dpage = NULL;
+	unsigned long bit, uvmem_pfn;
+	struct kvmppc_uvmem_page_pvt *pvt;
+	unsigned long pfn_last, pfn_first;
+
+	pfn_first = kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT;
+	pfn_last = pfn_first +
+		   (resource_size(&kvmppc_uvmem_pgmap.res) >> PAGE_SHIFT);
+
+	spin_lock(&kvmppc_uvmem_bitmap_lock);
+	bit = find_first_zero_bit(kvmppc_uvmem_bitmap,
+				  pfn_last - pfn_first);
+	if (bit >= (pfn_last - pfn_first))
+		goto out;
+	bitmap_set(kvmppc_uvmem_bitmap, bit, 1);
+	spin_unlock(&kvmppc_uvmem_bitmap_lock);
+
+	pvt = kzalloc(sizeof(*pvt), GFP_KERNEL);
+	if (!pvt)
+		goto out_clear;
+
+	uvmem_pfn = bit + pfn_first;
+	kvmppc_uvmem_pfn_insert(gpa >> PAGE_SHIFT, uvmem_pfn, kvm);
+
+	pvt->gpa = gpa;
+	pvt->kvm = kvm;
+
+	dpage = pfn_to_page(uvmem_pfn);
+	dpage->zone_device_data = pvt;
+	get_page(dpage);
+	lock_page(dpage);
+	return dpage;
+out_clear:
+	spin_lock(&kvmppc_uvmem_bitmap_lock);
+	bitmap_clear(kvmppc_uvmem_bitmap, bit, 1);
+out:
+	spin_unlock(&kvmppc_uvmem_bitmap_lock);
+	return NULL;
+}
+
+/*
+ * Alloc a PFN from private device memory pool and 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)
+{
+	unsigned long src_pfn, dst_pfn = 0;
+	struct migrate_vma mig;
+	struct page *spage;
+	unsigned long pfn;
+	struct page *dpage;
+	int ret = 0;
+
+	memset(&mig, 0, sizeof(mig));
+	mig.vma = vma;
+	mig.start = start;
+	mig.end = end;
+	mig.src = &src_pfn;
+	mig.dst = &dst_pfn;
+
+	/*
+	 * We come here with mmap_sem write lock held just for
+	 * ksm_madvise(), otherwise we only need read mmap_sem.
+	 * 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);
+	downgrade_write(&kvm->mm->mmap_sem);
+	*downgrade = true;
+	if (ret)
+		return ret;
+
+	ret = migrate_vma_setup(&mig);
+	if (ret)
+		return ret;
+
+	if (!(*mig.src & MIGRATE_PFN_MIGRATE)) {
+		ret = -1;
+		goto out_finalize;
+	}
+
+	dpage = kvmppc_uvmem_get_page(gpa, kvm);
+	if (!dpage) {
+		ret = -1;
+		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);
+
+	*mig.dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
+	migrate_vma_pages(&mig);
+out_finalize:
+	migrate_vma_finalize(&mig);
+	return ret;
+}
+
+/*
+ * Shares the page with HV, thus making it a normal page.
+ *
+ * - If the page is already secure, then provision a new page and share
+ * - If the page is a normal page, share the existing page
+ *
+ * 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)
+{
+
+	int ret = H_PARAMETER;
+	struct page *uvmem_page;
+	struct kvmppc_uvmem_page_pvt *pvt;
+	unsigned long pfn;
+	unsigned long gfn = gpa >> page_shift;
+	int srcu_idx;
+	unsigned long uvmem_pfn;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	mutex_lock(&kvm->arch.uvmem_lock);
+	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 = true;
+	}
+
+retry:
+	mutex_unlock(&kvm->arch.uvmem_lock);
+	pfn = gfn_to_pfn(kvm, gfn);
+	if (is_error_noslot_pfn(pfn))
+		goto out;
+
+	mutex_lock(&kvm->arch.uvmem_lock);
+	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 = true;
+		kvm_release_pfn_clean(pfn);
+		goto retry;
+	}
+
+	if (!uv_page_in(kvm->arch.lpid, pfn << page_shift, gpa, 0, page_shift))
+		ret = H_SUCCESS;
+	kvm_release_pfn_clean(pfn);
+	mutex_unlock(&kvm->arch.uvmem_lock);
+out:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	return ret;
+}
+
+/*
+ * H_SVM_PAGE_IN: Move page from normal memory to secure memory.
+ *
+ * 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)
+{
+	bool downgrade = false;
+	unsigned long start, end;
+	struct vm_area_struct *vma;
+	int srcu_idx;
+	unsigned long gfn = gpa >> page_shift;
+	int ret;
+
+	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
+		return H_UNSUPPORTED;
+
+	if (page_shift != PAGE_SHIFT)
+		return H_P3;
+
+	if (flags & ~H_PAGE_IN_SHARED)
+		return H_P2;
+
+	if (flags & H_PAGE_IN_SHARED)
+		return kvmppc_share_page(kvm, gpa, page_shift);
+
+	ret = H_PARAMETER;
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	down_write(&kvm->mm->mmap_sem);
+
+	start = gfn_to_hva(kvm, gfn);
+	if (kvm_is_error_hva(start))
+		goto out;
+
+	mutex_lock(&kvm->arch.uvmem_lock);
+	/* Fail the page-in request of an already paged-in page */
+	if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL))
+		goto out_unlock;
+
+	end = start + (1UL << page_shift);
+	vma = find_vma_intersection(kvm->mm, start, end);
+	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;
+out_unlock:
+	mutex_unlock(&kvm->arch.uvmem_lock);
+out:
+	if (downgrade)
+		up_read(&kvm->mm->mmap_sem);
+	else
+		up_write(&kvm->mm->mmap_sem);
+	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;
+
+	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)
+		return ret;
+
+	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
+ * has been moved to secure memory, we ask UV to give back the page by
+ * issuing UV_PAGE_OUT uvcall.
+ *
+ * This eventually results in dropping of device PFN and the newly
+ * provisioned page/PFN gets populated in QEMU page tables.
+ */
+static vm_fault_t kvmppc_uvmem_migrate_to_ram(struct vm_fault *vmf)
+{
+	struct kvmppc_uvmem_page_pvt *pvt = vmf->page->zone_device_data;
+
+	if (kvmppc_svm_page_out(vmf->vma, vmf->address,
+				vmf->address + PAGE_SIZE, PAGE_SHIFT,
+				pvt->kvm, pvt->gpa))
+		return VM_FAULT_SIGBUS;
+	else
+		return 0;
+}
+
+/*
+ * Release the device PFN back to the pool
+ *
+ * Gets called when secure page becomes a normal page during H_SVM_PAGE_OUT.
+ * Gets called with kvm->arch.uvmem_lock held.
+ */
+static void kvmppc_uvmem_page_free(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page) -
+			(kvmppc_uvmem_pgmap.res.start >> PAGE_SHIFT);
+	struct kvmppc_uvmem_page_pvt *pvt;
+
+	spin_lock(&kvmppc_uvmem_bitmap_lock);
+	bitmap_clear(kvmppc_uvmem_bitmap, pfn, 1);
+	spin_unlock(&kvmppc_uvmem_bitmap_lock);
+
+	pvt = page->zone_device_data;
+	page->zone_device_data = NULL;
+	kvmppc_uvmem_pfn_remove(pvt->gpa >> PAGE_SHIFT, pvt->kvm);
+	kfree(pvt);
+}
+
+static const struct dev_pagemap_ops kvmppc_uvmem_ops = {
+	.page_free = kvmppc_uvmem_page_free,
+	.migrate_to_ram	= kvmppc_uvmem_migrate_to_ram,
+};
+
+/*
+ * H_SVM_PAGE_OUT: Move page from secure memory to normal memory.
+ */
+unsigned long
+kvmppc_h_svm_page_out(struct kvm *kvm, unsigned long gpa,
+		      unsigned long flags, unsigned long page_shift)
+{
+	unsigned long gfn = gpa >> page_shift;
+	unsigned long start, end;
+	struct vm_area_struct *vma;
+	int srcu_idx;
+	int ret;
+
+	if (!(kvm->arch.secure_guest & KVMPPC_SECURE_INIT_START))
+		return H_UNSUPPORTED;
+
+	if (page_shift != PAGE_SHIFT)
+		return H_P3;
+
+	if (flags)
+		return H_P2;
+
+	ret = H_PARAMETER;
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+	down_read(&kvm->mm->mmap_sem);
+	start = gfn_to_hva(kvm, gfn);
+	if (kvm_is_error_hva(start))
+		goto out;
+
+	end = start + (1UL << page_shift);
+	vma = find_vma_intersection(kvm->mm, start, end);
+	if (!vma || vma->vm_start > start || vma->vm_end < end)
+		goto out;
+
+	if (!kvmppc_svm_page_out(vma, start, end, page_shift, kvm, gpa))
+		ret = H_SUCCESS;
+out:
+	up_read(&kvm->mm->mmap_sem);
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	return ret;
+}
+
+int kvmppc_send_page_to_uv(struct kvm *kvm, unsigned long gfn)
+{
+	unsigned long pfn;
+	int ret = U_SUCCESS;
+
+	pfn = gfn_to_pfn(kvm, gfn);
+	if (is_error_noslot_pfn(pfn))
+		return -EFAULT;
+
+	mutex_lock(&kvm->arch.uvmem_lock);
+	if (kvmppc_gfn_is_uvmem_pfn(gfn, kvm, NULL))
+		goto out;
+
+	ret = uv_page_in(kvm->arch.lpid, pfn << PAGE_SHIFT, gfn << PAGE_SHIFT,
+			 0, PAGE_SHIFT);
+out:
+	kvm_release_pfn_clean(pfn);
+	mutex_unlock(&kvm->arch.uvmem_lock);
+	return (ret == U_SUCCESS) ? RESUME_GUEST : -EFAULT;
+}
+
+static u64 kvmppc_get_secmem_size(void)
+{
+	struct device_node *np;
+	int i, len;
+	const __be32 *prop;
+	u64 size = 0;
+
+	np = of_find_compatible_node(NULL, NULL, "ibm,uv-firmware");
+	if (!np)
+		goto out;
+
+	prop = of_get_property(np, "secure-memory-ranges", &len);
+	if (!prop)
+		goto out_put;
+
+	for (i = 0; i < len / (sizeof(*prop) * 4); i++)
+		size += of_read_number(prop + (i * 4) + 2, 2);
+
+out_put:
+	of_node_put(np);
+out:
+	return size;
+}
+
+int kvmppc_uvmem_init(void)
+{
+	int ret = 0;
+	unsigned long size;
+	struct resource *res;
+	void *addr;
+	unsigned long pfn_last, pfn_first;
+
+	size = kvmppc_get_secmem_size();
+	if (!size) {
+		/*
+		 * Don't fail the initialization of kvm-hv module if
+		 * the platform doesn't export ibm,uv-firmware node.
+		 * Let normal guests run on such PEF-disabled platform.
+		 */
+		pr_info("KVMPPC-UVMEM: No support for secure guests\n");
+		goto out;
+	}
+
+	res = request_free_mem_region(&iomem_resource, size, "kvmppc_uvmem");
+	if (IS_ERR(res)) {
+		ret = PTR_ERR(res);
+		goto out;
+	}
+
+	kvmppc_uvmem_pgmap.type = MEMORY_DEVICE_PRIVATE;
+	kvmppc_uvmem_pgmap.res = *res;
+	kvmppc_uvmem_pgmap.ops = &kvmppc_uvmem_ops;
+	addr = memremap_pages(&kvmppc_uvmem_pgmap, NUMA_NO_NODE);
+	if (IS_ERR(addr)) {
+		ret = PTR_ERR(addr);
+		goto out_free_region;
+	}
+
+	pfn_first = res->start >> PAGE_SHIFT;
+	pfn_last = pfn_first + (resource_size(res) >> PAGE_SHIFT);
+	kvmppc_uvmem_bitmap = kcalloc(BITS_TO_LONGS(pfn_last - pfn_first),
+				      sizeof(unsigned long), GFP_KERNEL);
+	if (!kvmppc_uvmem_bitmap) {
+		ret = -ENOMEM;
+		goto out_unmap;
+	}
+
+	pr_info("KVMPPC-UVMEM: Secure Memory size 0x%lx\n", size);
+	return ret;
+out_unmap:
+	memunmap_pages(&kvmppc_uvmem_pgmap);
+out_free_region:
+	release_mem_region(res->start, size);
+out:
+	return ret;
+}
+
+void kvmppc_uvmem_free(void)
+{
+	memunmap_pages(&kvmppc_uvmem_pgmap);
+	release_mem_region(kvmppc_uvmem_pgmap.res.start,
+			   resource_size(&kvmppc_uvmem_pgmap.res));
+	kfree(kvmppc_uvmem_bitmap);
+}

arch/powerpc/kvm/powerpc.c

@@ -31,6 +31,8 @@
 #include <asm/hvcall.h>
 #include <asm/plpar_wrappers.h>
 #endif
+#include <asm/ultravisor.h>
+#include <asm/kvm_host.h>
 
 #include "timing.h"
 #include "irq.h"
@@ -2413,6 +2415,16 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = -EFAULT;
 		break;
 	}
+	case KVM_PPC_SVM_OFF: {
+		struct kvm *kvm = filp->private_data;
+
+		r = 0;
+		if (!kvm->arch.kvm_ops->svm_off)
+			goto out;
+
+		r = kvm->arch.kvm_ops->svm_off(kvm);
+		break;
+	}
 	default: {
 		struct kvm *kvm = filp->private_data;
 		r = kvm->arch.kvm_ops->arch_vm_ioctl(filp, ioctl, arg);

include/uapi/linux/kvm.h

@@ -1348,6 +1348,7 @@ struct kvm_s390_ucas_mapping {
 #define KVM_PPC_GET_CPU_CHAR	  _IOR(KVMIO,  0xb1, struct kvm_ppc_cpu_char)
 /* Available with KVM_CAP_PMU_EVENT_FILTER */
 #define KVM_SET_PMU_EVENT_FILTER  _IOW(KVMIO,  0xb2, struct kvm_pmu_event_filter)
+#define KVM_PPC_SVM_OFF		  _IO(KVMIO,  0xb3)
 
 /* ioctl for vm fd */
 #define KVM_CREATE_DEVICE	  _IOWR(KVMIO,  0xe0, struct kvm_create_device)

mm/ksm.c

@@ -2478,6 +2478,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ksm_madvise);
 
 int __ksm_enter(struct mm_struct *mm)
 {