Merge tag 'kvm-ppc-next-5.7-1' of...

Merge tag 'kvm-ppc-next-5.7-1' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc into HEAD

KVM PPC update for 5.7

* Add a capability for enabling secure guests under the Protected
  Execution Framework ultravisor

* Various bug fixes and cleanups.

Documentation/virt/kvm/api.rst

@@ -5785,6 +5785,23 @@ it hard or impossible to use it correctly.  The availability of
 KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 signals that those bugs are fixed.
 Userspace should not try to use KVM_CAP_MANUAL_DIRTY_LOG_PROTECT.
 
+7.19 KVM_CAP_PPC_SECURE_GUEST
+------------------------------
+
+:Architectures: ppc
+
+This capability indicates that KVM is running on a host that has
+ultravisor firmware and thus can support a secure guest.  On such a
+system, a guest can ask the ultravisor to make it a secure guest,
+one whose memory is inaccessible to the host except for pages which
+are explicitly requested to be shared with the host.  The ultravisor
+notifies KVM when a guest requests to become a secure guest, and KVM
+has the opportunity to veto the transition.
+
+If present, this capability can be enabled for a VM, meaning that KVM
+will allow the transition to secure guest mode.  Otherwise KVM will
+veto the transition.
+
 8. Other capabilities.
 ======================
 

arch/powerpc/include/asm/kvm_asm.h

@@ -150,4 +150,7 @@
 
 #define KVM_INST_FETCH_FAILED	-1
 
+/* Extract PO and XOP opcode fields */
+#define PO_XOP_OPCODE_MASK 0xfc0007fe
+
 #endif /* __POWERPC_KVM_ASM_H__ */

arch/powerpc/include/asm/kvm_book3s_uvmem.h

@@ -5,6 +5,7 @@
 #ifdef CONFIG_PPC_UV
 int kvmppc_uvmem_init(void);
 void kvmppc_uvmem_free(void);
+bool kvmppc_uvmem_available(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);
@@ -30,6 +31,11 @@ static inline int kvmppc_uvmem_init(void)
 
 static inline void kvmppc_uvmem_free(void) { }
 
+static inline bool kvmppc_uvmem_available(void)
+{
+	return false;
+}
+
 static inline int
 kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot)
 {

arch/powerpc/include/asm/kvm_host.h

@@ -303,6 +303,7 @@ struct kvm_arch {
 	u8 radix;
 	u8 fwnmi_enabled;
 	u8 secure_guest;
+	u8 svm_enabled;
 	bool threads_indep;
 	bool nested_enable;
 	pgd_t *pgtable;

arch/powerpc/include/asm/kvm_ppc.h

@@ -107,8 +107,6 @@ extern void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
                            unsigned int gtlb_idx);
 extern void kvmppc_mmu_priv_switch(struct kvm_vcpu *vcpu, int usermode);
 extern void kvmppc_mmu_switch_pid(struct kvm_vcpu *vcpu, u32 pid);
-extern void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu);
-extern int kvmppc_mmu_init(struct kvm_vcpu *vcpu);
 extern int kvmppc_mmu_dtlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
 extern int kvmppc_mmu_itlb_index(struct kvm_vcpu *vcpu, gva_t eaddr);
 extern gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int gtlb_index,
@@ -289,7 +287,6 @@ struct kvmppc_ops {
 	int (*age_hva)(struct kvm *kvm, unsigned long start, unsigned long end);
 	int (*test_age_hva)(struct kvm *kvm, unsigned long hva);
 	void (*set_spte_hva)(struct kvm *kvm, unsigned long hva, pte_t pte);
-	void (*mmu_destroy)(struct kvm_vcpu *vcpu);
 	void (*free_memslot)(struct kvm_memory_slot *slot);
 	int (*init_vm)(struct kvm *kvm);
 	void (*destroy_vm)(struct kvm *kvm);
@@ -316,6 +313,7 @@ struct kvmppc_ops {
 			       int size);
 	int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
 			      int size);
+	int (*enable_svm)(struct kvm *kvm);
 	int (*svm_off)(struct kvm *kvm);
 };
 

arch/powerpc/kvm/book3s.c

@@ -858,11 +858,6 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
 	return 0;
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
-{
-	vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu);
-}
-
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
 

arch/powerpc/kvm/book3s.h

@@ -16,6 +16,7 @@ extern int kvm_age_hva_hv(struct kvm *kvm, unsigned long start,
 extern int kvm_test_age_hva_hv(struct kvm *kvm, unsigned long hva);
 extern void kvm_set_spte_hva_hv(struct kvm *kvm, unsigned long hva, pte_t pte);
 
+extern int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu);
 extern void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_emulate_op_pr(struct kvm_run *run, struct kvm_vcpu *vcpu,
 				     unsigned int inst, int *advance);

arch/powerpc/kvm/book3s_32_mmu.c

@@ -234,7 +234,7 @@ static int kvmppc_mmu_book3s_32_xlate_pte(struct kvm_vcpu *vcpu, gva_t eaddr,
 				case 2:
 				case 6:
 					pte->may_write = true;
-					/* fall through */
+					fallthrough;
 				case 3:
 				case 5:
 				case 7:

arch/powerpc/kvm/book3s_32_mmu_host.c

@@ -356,7 +356,7 @@ void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu)
 /* From mm/mmu_context_hash32.c */
 #define CTX_TO_VSID(c, id)	((((c) * (897 * 16)) + (id * 0x111)) & 0xffffff)
 
-int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
+int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	int err;

arch/powerpc/kvm/book3s_64_mmu.c

@@ -311,7 +311,7 @@ static int kvmppc_mmu_book3s_64_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	case 2:
 	case 6:
 		gpte->may_write = true;
-		/* fall through */
+		fallthrough;
 	case 3:
 	case 5:
 	case 7:

arch/powerpc/kvm/book3s_64_mmu_host.c

@@ -384,7 +384,7 @@ void kvmppc_mmu_destroy_pr(struct kvm_vcpu *vcpu)
 	__destroy_context(to_book3s(vcpu)->context_id[0]);
 }
 
-int kvmppc_mmu_init(struct kvm_vcpu *vcpu)
+int kvmppc_mmu_init_pr(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_book3s *vcpu3s = to_book3s(vcpu);
 	int err;

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -485,18 +485,18 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	__be64 *hptep;
 	unsigned long mmu_seq, psize, pte_size;
 	unsigned long gpa_base, gfn_base;
-	unsigned long gpa, gfn, hva, pfn;
+	unsigned long gpa, gfn, hva, pfn, hpa;
 	struct kvm_memory_slot *memslot;
 	unsigned long *rmap;
 	struct revmap_entry *rev;
-	struct page *page, *pages[1];
-	long index, ret, npages;
+	struct page *page;
+	long index, ret;
 	bool is_ci;
-	unsigned int writing, write_ok;
-	struct vm_area_struct *vma;
+	bool writing, write_ok;
+	unsigned int shift;
 	unsigned long rcbits;
 	long mmio_update;
-	struct mm_struct *mm;
+	pte_t pte, *ptep;
 
 	if (kvm_is_radix(kvm))
 		return kvmppc_book3s_radix_page_fault(run, vcpu, ea, dsisr);
@@ -570,59 +570,62 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	smp_rmb();
 
 	ret = -EFAULT;
-	is_ci = false;
-	pfn = 0;
 	page = NULL;
-	mm = kvm->mm;
-	pte_size = PAGE_SIZE;
 	writing = (dsisr & DSISR_ISSTORE) != 0;
 	/* If writing != 0, then the HPTE must allow writing, if we get here */
 	write_ok = writing;
 	hva = gfn_to_hva_memslot(memslot, gfn);
-	npages = get_user_pages_fast(hva, 1, writing ? FOLL_WRITE : 0, pages);
-	if (npages < 1) {
-		/* Check if it's an I/O mapping */
-		down_read(&mm->mmap_sem);
-		vma = find_vma(mm, hva);
-		if (vma && vma->vm_start <= hva && hva + psize <= vma->vm_end &&
-		    (vma->vm_flags & VM_PFNMAP)) {
-			pfn = vma->vm_pgoff +
-				((hva - vma->vm_start) >> PAGE_SHIFT);
-			pte_size = psize;
-			is_ci = pte_ci(__pte((pgprot_val(vma->vm_page_prot))));
-			write_ok = vma->vm_flags & VM_WRITE;
-		}
-		up_read(&mm->mmap_sem);
-		if (!pfn)
-			goto out_put;
+
+	/*
+	 * Do a fast check first, since __gfn_to_pfn_memslot doesn't
+	 * do it with !atomic && !async, which is how we call it.
+	 * We always ask for write permission since the common case
+	 * is that the page is writable.
+	 */
+	if (__get_user_pages_fast(hva, 1, 1, &page) == 1) {
+		write_ok = true;
 	} else {
-		page = pages[0];
-		pfn = page_to_pfn(page);
-		if (PageHuge(page)) {
-			page = compound_head(page);
-			pte_size <<= compound_order(page);
-		}
-		/* if the guest wants write access, see if that is OK */
-		if (!writing && hpte_is_writable(r)) {
-			pte_t *ptep, pte;
-			unsigned long flags;
-			/*
-			 * We need to protect against page table destruction
-			 * hugepage split and collapse.
-			 */
-			local_irq_save(flags);
-			ptep = find_current_mm_pte(mm->pgd, hva, NULL, NULL);
-			if (ptep) {
-				pte = kvmppc_read_update_linux_pte(ptep, 1);
-				if (__pte_write(pte))
-					write_ok = 1;
-			}
-			local_irq_restore(flags);
+		/* Call KVM generic code to do the slow-path check */
+		pfn = __gfn_to_pfn_memslot(memslot, gfn, false, NULL,
+					   writing, &write_ok);
+		if (is_error_noslot_pfn(pfn))
+			return -EFAULT;
+		page = NULL;
+		if (pfn_valid(pfn)) {
+			page = pfn_to_page(pfn);
+			if (PageReserved(page))
+				page = NULL;
 		}
 	}
 
+	/*
+	 * Read the PTE from the process' radix tree and use that
+	 * so we get the shift and attribute bits.
+	 */
+	local_irq_disable();
+	ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+	/*
+	 * If the PTE disappeared temporarily due to a THP
+	 * collapse, just return and let the guest try again.
+	 */
+	if (!ptep) {
+		local_irq_enable();
+		if (page)
+			put_page(page);
+		return RESUME_GUEST;
+	}
+	pte = *ptep;
+	local_irq_enable();
+	hpa = pte_pfn(pte) << PAGE_SHIFT;
+	pte_size = PAGE_SIZE;
+	if (shift)
+		pte_size = 1ul << shift;
+	is_ci = pte_ci(pte);
+
 	if (psize > pte_size)
 		goto out_put;
+	if (pte_size > psize)
+		hpa |= hva & (pte_size - psize);
 
 	/* Check WIMG vs. the actual page we're accessing */
 	if (!hpte_cache_flags_ok(r, is_ci)) {
@@ -636,14 +639,13 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	}
 
 	/*
-	 * Set the HPTE to point to pfn.
-	 * Since the pfn is at PAGE_SIZE granularity, make sure we
+	 * Set the HPTE to point to hpa.
+	 * Since the hpa is at PAGE_SIZE granularity, make sure we
 	 * don't mask out lower-order bits if psize < PAGE_SIZE.
 	 */
 	if (psize < PAGE_SIZE)
 		psize = PAGE_SIZE;
-	r = (r & HPTE_R_KEY_HI) | (r & ~(HPTE_R_PP0 - psize)) |
-					((pfn << PAGE_SHIFT) & ~(psize - 1));
+	r = (r & HPTE_R_KEY_HI) | (r & ~(HPTE_R_PP0 - psize)) | hpa;
 	if (hpte_is_writable(r) && !write_ok)
 		r = hpte_make_readonly(r);
 	ret = RESUME_GUEST;
@@ -708,20 +710,13 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	asm volatile("ptesync" : : : "memory");
 	preempt_enable();
 	if (page && hpte_is_writable(r))
-		SetPageDirty(page);
+		set_page_dirty_lock(page);
 
  out_put:
 	trace_kvm_page_fault_exit(vcpu, hpte, ret);
 
-	if (page) {
-		/*
-		 * We drop pages[0] here, not page because page might
-		 * have been set to the head page of a compound, but
-		 * we have to drop the reference on the correct tail
-		 * page to match the get inside gup()
-		 */
-		put_page(pages[0]);
-	}
+	if (page)
+		put_page(page);
 	return ret;
 
  out_unlock:

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -425,7 +425,7 @@ static void kvmppc_unmap_free_pte(struct kvm *kvm, pte_t *pte, bool full,
 				  unsigned int lpid)
 {
 	if (full) {
-		memset(pte, 0, sizeof(long) << PTE_INDEX_SIZE);
+		memset(pte, 0, sizeof(long) << RADIX_PTE_INDEX_SIZE);
 	} else {
 		pte_t *p = pte;
 		unsigned long it;

arch/powerpc/kvm/book3s_hv.c

@@ -1073,25 +1073,35 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 					 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));
+		ret = H_UNSUPPORTED;
+		if (kvmppc_get_srr1(vcpu) & MSR_S)
+			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));
+		ret = H_UNSUPPORTED;
+		if (kvmppc_get_srr1(vcpu) & MSR_S)
+			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);
+		ret = H_UNSUPPORTED;
+		if (kvmppc_get_srr1(vcpu) & MSR_S)
+			ret = kvmppc_h_svm_init_start(vcpu->kvm);
 		break;
 	case H_SVM_INIT_DONE:
-		ret = kvmppc_h_svm_init_done(vcpu->kvm);
+		ret = H_UNSUPPORTED;
+		if (kvmppc_get_srr1(vcpu) & MSR_S)
+			ret = kvmppc_h_svm_init_done(vcpu->kvm);
 		break;
 	case H_SVM_INIT_ABORT:
-		ret = kvmppc_h_svm_init_abort(vcpu->kvm);
+		ret = H_UNSUPPORTED;
+		if (kvmppc_get_srr1(vcpu) & MSR_S)
+			ret = kvmppc_h_svm_init_abort(vcpu->kvm);
 		break;
 
 	default:
@@ -3615,6 +3625,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 		if (trap == BOOK3S_INTERRUPT_SYSCALL && !vcpu->arch.nested &&
 		    kvmppc_get_gpr(vcpu, 3) == H_CEDE) {
 			kvmppc_nested_cede(vcpu);
+			kvmppc_set_gpr(vcpu, 3, 0);
 			trap = 0;
 		}
 	} else {
@@ -4554,11 +4565,6 @@ void kvmppc_update_lpcr(struct kvm *kvm, unsigned long lpcr, unsigned long mask)
 	}
 }
 
-static void kvmppc_mmu_destroy_hv(struct kvm_vcpu *vcpu)
-{
-	return;
-}
-
 void kvmppc_setup_partition_table(struct kvm *kvm)
 {
 	unsigned long dw0, dw1;
@@ -5422,6 +5428,21 @@ static void unpin_vpa_reset(struct kvm *kvm, struct kvmppc_vpa *vpa)
 	vpa->update_pending = 0;
 }
 
+/*
+ * Enable a guest to become a secure VM, or test whether
+ * that could be enabled.
+ * Called when the KVM_CAP_PPC_SECURE_GUEST capability is
+ * tested (kvm == NULL) or enabled (kvm != NULL).
+ */
+static int kvmhv_enable_svm(struct kvm *kvm)
+{
+	if (!kvmppc_uvmem_available())
+		return -EINVAL;
+	if (kvm)
+		kvm->arch.svm_enabled = 1;
+	return 0;
+}
+
 /*
  *  IOCTL handler to turn off secure mode of guest
  *
@@ -5522,7 +5543,6 @@ static struct kvmppc_ops kvm_ops_hv = {
 	.age_hva  = kvm_age_hva_hv,
 	.test_age_hva = kvm_test_age_hva_hv,
 	.set_spte_hva = kvm_set_spte_hva_hv,
-	.mmu_destroy  = kvmppc_mmu_destroy_hv,
 	.free_memslot = kvmppc_core_free_memslot_hv,
 	.init_vm =  kvmppc_core_init_vm_hv,
 	.destroy_vm = kvmppc_core_destroy_vm_hv,
@@ -5543,6 +5563,7 @@ 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,
+	.enable_svm = kvmhv_enable_svm,
 	.svm_off = kvmhv_svm_off,
 };
 

arch/powerpc/kvm/book3s_hv_tm.c

@@ -3,6 +3,8 @@
  * Copyright 2017 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kvm_host.h>
 
 #include <asm/kvm_ppc.h>
@@ -44,7 +46,18 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 	u64 newmsr, bescr;
 	int ra, rs;
 
-	switch (instr & 0xfc0007ff) {
+	/*
+	 * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit
+	 * in these instructions, so masking bit 31 out doesn't change these
+	 * instructions. For treclaim., tsr., and trechkpt. instructions if bit
+	 * 31 = 0 then they are per ISA invalid forms, however P9 UM, in section
+	 * 4.6.10 Book II Invalid Forms, informs specifically that ignoring bit
+	 * 31 is an acceptable way to handle these invalid forms that have
+	 * bit 31 = 0. Moreover, for emulation purposes both forms (w/ and wo/
+	 * bit 31 set) can generate a softpatch interrupt. Hence both forms
+	 * are handled below for these instructions so they behave the same way.
+	 */
+	switch (instr & PO_XOP_OPCODE_MASK) {
 	case PPC_INST_RFID:
 		/* XXX do we need to check for PR=0 here? */
 		newmsr = vcpu->arch.shregs.srr1;
@@ -105,7 +118,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.shregs.msr = newmsr;
 		return RESUME_GUEST;
 
-	case PPC_INST_TSR:
+	/* ignore bit 31, see comment above */
+	case (PPC_INST_TSR & PO_XOP_OPCODE_MASK):
 		/* check for PR=1 and arch 2.06 bit set in PCR */
 		if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) {
 			/* generate an illegal instruction interrupt */
@@ -140,7 +154,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.shregs.msr = msr;
 		return RESUME_GUEST;
 
-	case PPC_INST_TRECLAIM:
+	/* ignore bit 31, see comment above */
+	case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK):
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
 			/* generate an illegal instruction interrupt */
@@ -176,7 +191,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 		vcpu->arch.shregs.msr &= ~MSR_TS_MASK;
 		return RESUME_GUEST;
 
-	case PPC_INST_TRECHKPT:
+	/* ignore bit 31, see comment above */
+	case (PPC_INST_TRECHKPT & PO_XOP_OPCODE_MASK):
 		/* XXX do we need to check for PR=0 here? */
 		/* check for TM disabled in the HFSCR or MSR */
 		if (!(vcpu->arch.hfscr & HFSCR_TM)) {
@@ -208,6 +224,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu)
 	}
 
 	/* What should we do here? We didn't recognize the instruction */
-	WARN_ON_ONCE(1);
+	kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
+	pr_warn_ratelimited("Unrecognized TM-related instruction %#x for emulation", instr);
+
 	return RESUME_GUEST;
 }

arch/powerpc/kvm/book3s_hv_tm_builtin.c

@@ -23,7 +23,18 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu)
 	u64 newmsr, msr, bescr;
 	int rs;
 
-	switch (instr & 0xfc0007ff) {
+	/*
+	 * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit
+	 * in these instructions, so masking bit 31 out doesn't change these
+	 * instructions. For the tsr. instruction if bit 31 = 0 then it is per
+	 * ISA an invalid form, however P9 UM, in section 4.6.10 Book II Invalid
+	 * Forms, informs specifically that ignoring bit 31 is an acceptable way
+	 * to handle TM-related invalid forms that have bit 31 = 0. Moreover,
+	 * for emulation purposes both forms (w/ and wo/ bit 31 set) can
+	 * generate a softpatch interrupt. Hence both forms are handled below
+	 * for tsr. to make them behave the same way.
+	 */
+	switch (instr & PO_XOP_OPCODE_MASK) {
 	case PPC_INST_RFID:
 		/* XXX do we need to check for PR=0 here? */
 		newmsr = vcpu->arch.shregs.srr1;
@@ -73,7 +84,8 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu)
 		vcpu->arch.shregs.msr = newmsr;
 		return 1;
 
-	case PPC_INST_TSR:
+	/* ignore bit 31, see comment above */
+	case (PPC_INST_TSR & PO_XOP_OPCODE_MASK):
 		/* we know the MSR has the TS field = S (0b01) here */
 		msr = vcpu->arch.shregs.msr;
 		/* check for PR=1 and arch 2.06 bit set in PCR */

arch/powerpc/kvm/book3s_hv_uvmem.c

@@ -113,6 +113,15 @@ struct kvmppc_uvmem_page_pvt {
 	bool skip_page_out;
 };
 
+bool kvmppc_uvmem_available(void)
+{
+	/*
+	 * If kvmppc_uvmem_bitmap != NULL, then there is an ultravisor
+	 * and our data structures have been initialized successfully.
+	 */
+	return !!kvmppc_uvmem_bitmap;
+}
+
 int kvmppc_uvmem_slot_init(struct kvm *kvm, const struct kvm_memory_slot *slot)
 {
 	struct kvmppc_uvmem_slot *p;
@@ -209,6 +218,8 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 	int ret = H_SUCCESS;
 	int srcu_idx;
 
+	kvm->arch.secure_guest = KVMPPC_SECURE_INIT_START;
+
 	if (!kvmppc_uvmem_bitmap)
 		return H_UNSUPPORTED;
 
@@ -216,6 +227,10 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 	if (!kvm_is_radix(kvm))
 		return H_UNSUPPORTED;
 
+	/* NAK the transition to secure if not enabled */
+	if (!kvm->arch.svm_enabled)
+		return H_AUTHORITY;
+
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, slots) {
@@ -233,7 +248,6 @@ unsigned long kvmppc_h_svm_init_start(struct kvm *kvm)
 			goto out;
 		}
 	}
-	kvm->arch.secure_guest |= KVMPPC_SECURE_INIT_START;
 out:
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	return ret;
@@ -806,6 +820,9 @@ int kvmppc_uvmem_init(void)
 
 void kvmppc_uvmem_free(void)
 {
+	if (!kvmppc_uvmem_bitmap)
+		return;
+
 	memunmap_pages(&kvmppc_uvmem_pgmap);
 	release_mem_region(kvmppc_uvmem_pgmap.res.start,
 			   resource_size(&kvmppc_uvmem_pgmap.res));

arch/powerpc/kvm/book3s_pr.c

@@ -740,7 +740,7 @@ int kvmppc_handle_pagefault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 		    (vcpu->arch.hflags & BOOK3S_HFLAG_SPLIT_HACK) &&
 		    ((pte.raddr & SPLIT_HACK_MASK) == SPLIT_HACK_OFFS))
 			pte.raddr &= ~SPLIT_HACK_MASK;
-		/* fall through */
+		fallthrough;
 	case MSR_IR:
 		vcpu->arch.mmu.esid_to_vsid(vcpu, eaddr >> SID_SHIFT, &vsid);
 
@@ -1795,7 +1795,7 @@ static int kvmppc_core_vcpu_create_pr(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.shadow_msr = MSR_USER64 & ~MSR_LE;
 
-	err = kvmppc_mmu_init(vcpu);
+	err = kvmppc_mmu_init_pr(vcpu);
 	if (err < 0)
 		goto free_shared_page;
 
@@ -1817,6 +1817,7 @@ static void kvmppc_core_vcpu_free_pr(struct kvm_vcpu *vcpu)
 {
 	struct kvmppc_vcpu_book3s *vcpu_book3s = to_book3s(vcpu);
 
+	kvmppc_mmu_destroy_pr(vcpu);
 	free_page((unsigned long)vcpu->arch.shared & PAGE_MASK);
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	kfree(vcpu->arch.shadow_vcpu);
@@ -2086,7 +2087,6 @@ static struct kvmppc_ops kvm_ops_pr = {
 	.age_hva  = kvm_age_hva_pr,
 	.test_age_hva = kvm_test_age_hva_pr,
 	.set_spte_hva = kvm_set_spte_hva_pr,
-	.mmu_destroy  = kvmppc_mmu_destroy_pr,
 	.free_memslot = kvmppc_core_free_memslot_pr,
 	.init_vm = kvmppc_core_init_vm_pr,
 	.destroy_vm = kvmppc_core_destroy_vm_pr,

arch/powerpc/kvm/booke.c

@@ -421,11 +421,11 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	case BOOKE_IRQPRIO_DATA_STORAGE:
 	case BOOKE_IRQPRIO_ALIGNMENT:
 		update_dear = true;
-		/* fall through */
+		fallthrough;
 	case BOOKE_IRQPRIO_INST_STORAGE:
 	case BOOKE_IRQPRIO_PROGRAM:
 		update_esr = true;
-		/* fall through */
+		fallthrough;
 	case BOOKE_IRQPRIO_ITLB_MISS:
 	case BOOKE_IRQPRIO_SYSCALL:
 	case BOOKE_IRQPRIO_FP_UNAVAIL:
@@ -459,7 +459,7 @@ static int kvmppc_booke_irqprio_deliver(struct kvm_vcpu *vcpu,
 	case BOOKE_IRQPRIO_DECREMENTER:
 	case BOOKE_IRQPRIO_FIT:
 		keep_irq = true;
-		/* fall through */
+		fallthrough;
 	case BOOKE_IRQPRIO_EXTERNAL:
 	case BOOKE_IRQPRIO_DBELL:
 		allowed = vcpu->arch.shared->msr & MSR_EE;
@@ -2073,11 +2073,6 @@ void kvmppc_booke_vcpu_put(struct kvm_vcpu *vcpu)
 	kvmppc_clear_dbsr();
 }
 
-void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)
-{
-	vcpu->kvm->arch.kvm_ops->mmu_destroy(vcpu);
-}
-
 int kvmppc_core_init_vm(struct kvm *kvm)
 {
 	return kvm->arch.kvm_ops->init_vm(kvm);

arch/powerpc/kvm/booke.h

@@ -94,7 +94,6 @@ enum int_class {
 
 void kvmppc_set_pending_interrupt(struct kvm_vcpu *vcpu, enum int_class type);
 
-extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_emulate_op_e500(struct kvm_run *run,
 				       struct kvm_vcpu *vcpu,
 				       unsigned int inst, int *advance);
@@ -102,7 +101,6 @@ extern int kvmppc_core_emulate_mtspr_e500(struct kvm_vcpu *vcpu, int sprn,
 					  ulong spr_val);
 extern int kvmppc_core_emulate_mfspr_e500(struct kvm_vcpu *vcpu, int sprn,
 					  ulong *spr_val);
-extern void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_emulate_op_e500(struct kvm_run *run,
 				       struct kvm_vcpu *vcpu,
 				       unsigned int inst, int *advance);

arch/powerpc/kvm/e500.c

@@ -490,7 +490,6 @@ static struct kvmppc_ops kvm_ops_e500 = {
 	.vcpu_put    = kvmppc_core_vcpu_put_e500,
 	.vcpu_create = kvmppc_core_vcpu_create_e500,
 	.vcpu_free   = kvmppc_core_vcpu_free_e500,
-	.mmu_destroy  = kvmppc_mmu_destroy_e500,
 	.init_vm = kvmppc_core_init_vm_e500,
 	.destroy_vm = kvmppc_core_destroy_vm_e500,
 	.emulate_op = kvmppc_core_emulate_op_e500,

arch/powerpc/kvm/e500_mmu.c

@@ -533,10 +533,6 @@ gpa_t kvmppc_mmu_xlate(struct kvm_vcpu *vcpu, unsigned int index,
 	return get_tlb_raddr(gtlbe) | (eaddr & pgmask);
 }
 
-void kvmppc_mmu_destroy_e500(struct kvm_vcpu *vcpu)
-{
-}
-
 /*****************************************/
 
 static void free_gtlb(struct kvmppc_vcpu_e500 *vcpu_e500)

arch/powerpc/kvm/e500mc.c

@@ -376,7 +376,6 @@ static struct kvmppc_ops kvm_ops_e500mc = {
 	.vcpu_put    = kvmppc_core_vcpu_put_e500mc,
 	.vcpu_create = kvmppc_core_vcpu_create_e500mc,
 	.vcpu_free   = kvmppc_core_vcpu_free_e500mc,
-	.mmu_destroy  = kvmppc_mmu_destroy_e500,
 	.init_vm = kvmppc_core_init_vm_e500mc,
 	.destroy_vm = kvmppc_core_destroy_vm_e500mc,
 	.emulate_op = kvmppc_core_emulate_op_e500,

arch/powerpc/kvm/powerpc.c

@@ -524,7 +524,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = 1;
 		break;
 	case KVM_CAP_PPC_GUEST_DEBUG_SSTEP:
-		/* fall through */
 	case KVM_CAP_PPC_PAIRED_SINGLES:
 	case KVM_CAP_PPC_OSI:
 	case KVM_CAP_PPC_GET_PVINFO:
@@ -669,6 +668,12 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = !!(cur_cpu_spec->cpu_user_features2 & PPC_FEATURE2_HTM) ||
 		     (hv_enabled && cpu_has_feature(CPU_FTR_P9_TM_HV_ASSIST));
 		break;
+#endif
+#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
+	case KVM_CAP_PPC_SECURE_GUEST:
+		r = hv_enabled && kvmppc_hv_ops->enable_svm &&
+			!kvmppc_hv_ops->enable_svm(NULL);
+		break;
 #endif
 	default:
 		r = 0;
@@ -751,7 +756,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	return 0;
 
 out_vcpu_uninit:
-	kvmppc_mmu_destroy(vcpu);
 	kvmppc_subarch_vcpu_uninit(vcpu);
 	return err;
 }
@@ -784,7 +788,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 	kvmppc_core_vcpu_free(vcpu);
 
-	kvmppc_mmu_destroy(vcpu);
 	kvmppc_subarch_vcpu_uninit(vcpu);
 }
 
@@ -2169,6 +2172,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 			break;
 		r = kvm->arch.kvm_ops->enable_nested(kvm);
 		break;
+#endif
+#if defined(CONFIG_KVM_BOOK3S_HV_POSSIBLE)
+	case KVM_CAP_PPC_SECURE_GUEST:
+		r = -EINVAL;
+		if (!is_kvmppc_hv_enabled(kvm) || !kvm->arch.kvm_ops->enable_svm)
+			break;
+		r = kvm->arch.kvm_ops->enable_svm(kvm);
+		break;
 #endif
 	default:
 		r = -EINVAL;

include/uapi/linux/kvm.h

@@ -1016,6 +1016,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_INJECT_EXT_DABT 178
 #define KVM_CAP_S390_VCPU_RESETS 179
 #define KVM_CAP_S390_PROTECTED 180
+#define KVM_CAP_PPC_SECURE_GUEST 181
 
 #ifdef KVM_CAP_IRQ_ROUTING