Merge tag 'kvm-ppc-next-4.21-1' of git://git.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc

PPC KVM update for 4.21 from Paul Mackerras

The main new feature this time is support in HV nested KVM for passing
a device that is emulated by a level 0 hypervisor and presented to
level 1 as a PCI device through to a level 2 guest using VFIO.

Apart from that there are improvements for migration of radix guests
under HV KVM and some other fixes and cleanups.

arch/powerpc/include/asm/hvcall.h

@@ -335,6 +335,7 @@
 #define H_SET_PARTITION_TABLE	0xF800
 #define H_ENTER_NESTED		0xF804
 #define H_TLB_INVALIDATE	0xF808
+#define H_COPY_TOFROM_GUEST	0xF80C
 
 /* Values for 2nd argument to H_SET_MODE */
 #define H_SET_MODE_RESOURCE_SET_CIABR		1

arch/powerpc/include/asm/kvm_book3s.h

@@ -188,6 +188,13 @@ extern int kvmppc_book3s_hcall_implemented(struct kvm *kvm, unsigned long hc);
 extern int kvmppc_book3s_radix_page_fault(struct kvm_run *run,
 			struct kvm_vcpu *vcpu,
 			unsigned long ea, unsigned long dsisr);
+extern unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
+					gva_t eaddr, void *to, void *from,
+					unsigned long n);
+extern long kvmhv_copy_from_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
+					void *to, unsigned long n);
+extern long kvmhv_copy_to_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
+				      void *from, unsigned long n);
 extern int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
 				      struct kvmppc_pte *gpte, u64 root,
 				      u64 *pte_ret_p);
@@ -197,7 +204,8 @@ extern int kvmppc_mmu_radix_translate_table(struct kvm_vcpu *vcpu, gva_t eaddr,
 extern int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 			struct kvmppc_pte *gpte, bool data, bool iswrite);
 extern void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
-			unsigned int shift, struct kvm_memory_slot *memslot,
+			unsigned int shift,
+			const struct kvm_memory_slot *memslot,
 			unsigned int lpid);
 extern bool kvmppc_hv_handle_set_rc(struct kvm *kvm, pgd_t *pgtable,
 				    bool writing, unsigned long gpa,
@@ -215,16 +223,14 @@ extern int kvmppc_radix_init(void);
 extern void kvmppc_radix_exit(void);
 extern int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			unsigned long gfn);
-extern void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte,
-			     unsigned long gpa, unsigned int shift,
-			     struct kvm_memory_slot *memslot,
-			     unsigned int lpid);
 extern int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			unsigned long gfn);
 extern int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			unsigned long gfn);
 extern long kvmppc_hv_get_dirty_log_radix(struct kvm *kvm,
 			struct kvm_memory_slot *memslot, unsigned long *map);
+extern void kvmppc_radix_flush_memslot(struct kvm *kvm,
+			const struct kvm_memory_slot *memslot);
 extern int kvmhv_get_rmmu_info(struct kvm *kvm, struct kvm_ppc_rmmu_info *info);
 
 /* XXX remove this export when load_last_inst() is generic */
@@ -242,7 +248,7 @@ extern kvm_pfn_t kvmppc_gpa_to_pfn(struct kvm_vcpu *vcpu, gpa_t gpa,
 			bool writing, bool *writable);
 extern void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
 			unsigned long *rmap, long pte_index, int realmode);
-extern void kvmppc_update_dirty_map(struct kvm_memory_slot *memslot,
+extern void kvmppc_update_dirty_map(const struct kvm_memory_slot *memslot,
 			unsigned long gfn, unsigned long psize);
 extern void kvmppc_invalidate_hpte(struct kvm *kvm, __be64 *hptep,
 			unsigned long pte_index);
@@ -298,6 +304,7 @@ long kvmhv_nested_init(void);
 void kvmhv_nested_exit(void);
 void kvmhv_vm_nested_init(struct kvm *kvm);
 long kvmhv_set_partition_table(struct kvm_vcpu *vcpu);
+long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu);
 void kvmhv_set_ptbl_entry(unsigned int lpid, u64 dw0, u64 dw1);
 void kvmhv_release_all_nested(struct kvm *kvm);
 long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu);
@@ -307,7 +314,7 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu,
 void kvmhv_save_hv_regs(struct kvm_vcpu *vcpu, struct hv_guest_state *hr);
 void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
 				   struct hv_guest_state *hr);
-long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu);
+long int kvmhv_nested_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu);
 
 void kvmppc_giveup_fac(struct kvm_vcpu *vcpu, ulong fac);
 

arch/powerpc/include/asm/kvm_book3s_64.h

@@ -55,6 +55,7 @@ struct kvm_nested_guest {
 	cpumask_t need_tlb_flush;
 	cpumask_t cpu_in_guest;
 	short prev_cpu[NR_CPUS];
+	u8 radix;			/* is this nested guest radix */
 };
 
 /*
@@ -150,6 +151,18 @@ static inline bool kvm_is_radix(struct kvm *kvm)
 	return kvm->arch.radix;
 }
 
+static inline bool kvmhv_vcpu_is_radix(struct kvm_vcpu *vcpu)
+{
+	bool radix;
+
+	if (vcpu->arch.nested)
+		radix = vcpu->arch.nested->radix;
+	else
+		radix = kvm_is_radix(vcpu->kvm);
+
+	return radix;
+}
+
 #define KVM_DEFAULT_HPT_ORDER	24	/* 16MB HPT by default */
 #endif
 
@@ -625,7 +638,7 @@ extern int kvmppc_create_pte(struct kvm *kvm, pgd_t *pgtable, pte_t pte,
 extern void kvmhv_insert_nest_rmap(struct kvm *kvm, unsigned long *rmapp,
 				   struct rmap_nested **n_rmap);
 extern void kvmhv_remove_nest_rmap_range(struct kvm *kvm,
-				struct kvm_memory_slot *memslot,
+				const struct kvm_memory_slot *memslot,
 				unsigned long gpa, unsigned long hpa,
 				unsigned long nbytes);
 

arch/powerpc/include/asm/kvm_host.h

@@ -793,6 +793,7 @@ struct kvm_vcpu_arch {
 	/* For support of nested guests */
 	struct kvm_nested_guest *nested;
 	u32 nested_vcpu_id;
+	gpa_t nested_io_gpr;
 #endif
 
 #ifdef CONFIG_KVM_BOOK3S_HV_EXIT_TIMING
@@ -827,6 +828,8 @@ struct kvm_vcpu_arch {
 #define KVM_MMIO_REG_FQPR	0x00c0
 #define KVM_MMIO_REG_VSX	0x0100
 #define KVM_MMIO_REG_VMX	0x0180
+#define KVM_MMIO_REG_NESTED_GPR	0xffc0
+
 
 #define __KVM_HAVE_ARCH_WQP
 #define __KVM_HAVE_CREATE_DEVICE

arch/powerpc/include/asm/kvm_ppc.h

@@ -224,7 +224,8 @@ extern int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 extern void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new);
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change);
 extern int kvm_vm_ioctl_get_smmu_info(struct kvm *kvm,
 				      struct kvm_ppc_smmu_info *info);
 extern void kvmppc_core_flush_memslot(struct kvm *kvm,
@@ -294,7 +295,8 @@ struct kvmppc_ops {
 	void (*commit_memory_region)(struct kvm *kvm,
 				     const struct kvm_userspace_memory_region *mem,
 				     const struct kvm_memory_slot *old,
-				     const struct kvm_memory_slot *new);
+				     const struct kvm_memory_slot *new,
+				     enum kvm_mr_change change);
 	int (*unmap_hva_range)(struct kvm *kvm, unsigned long start,
 			   unsigned long end);
 	int (*age_hva)(struct kvm *kvm, unsigned long start, unsigned long end);
@@ -326,6 +328,10 @@ struct kvmppc_ops {
 			    unsigned long flags);
 	void (*giveup_ext)(struct kvm_vcpu *vcpu, ulong msr);
 	int (*enable_nested)(struct kvm *kvm);
+	int (*load_from_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
+			       int size);
+	int (*store_to_eaddr)(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
+			      int size);
 };
 
 extern struct kvmppc_ops *kvmppc_hv_ops;

arch/powerpc/kernel/exceptions-64s.S

@@ -995,7 +995,16 @@ EXC_COMMON_BEGIN(h_data_storage_common)
 	bl      save_nvgprs
 	RECONCILE_IRQ_STATE(r10, r11)
 	addi    r3,r1,STACK_FRAME_OVERHEAD
+BEGIN_MMU_FTR_SECTION
+	ld	r4,PACA_EXGEN+EX_DAR(r13)
+	lwz	r5,PACA_EXGEN+EX_DSISR(r13)
+	std	r4,_DAR(r1)
+	std	r5,_DSISR(r1)
+	li	r5,SIGSEGV
+	bl      bad_page_fault
+MMU_FTR_SECTION_ELSE
 	bl      unknown_exception
+ALT_MMU_FTR_SECTION_END_IFSET(MMU_FTR_TYPE_RADIX)
 	b       ret_from_except
 
 

arch/powerpc/kvm/book3s.c

@@ -830,9 +830,10 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new)
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
-	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new);
+	kvm->arch.kvm_ops->commit_memory_region(kvm, mem, old, new, change);
 }
 
 int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end)

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -743,12 +743,15 @@ void kvmppc_rmap_reset(struct kvm *kvm)
 	srcu_idx = srcu_read_lock(&kvm->srcu);
 	slots = kvm_memslots(kvm);
 	kvm_for_each_memslot(memslot, slots) {
+		/* Mutual exclusion with kvm_unmap_hva_range etc. */
+		spin_lock(&kvm->mmu_lock);
 		/*
 		 * This assumes it is acceptable to lose reference and
 		 * change bits across a reset.
 		 */
 		memset(memslot->arch.rmap, 0,
 		       memslot->npages * sizeof(*memslot->arch.rmap));
+		spin_unlock(&kvm->mmu_lock);
 	}
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 }
@@ -896,11 +899,12 @@ void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
 
 	gfn = memslot->base_gfn;
 	rmapp = memslot->arch.rmap;
-	for (n = memslot->npages; n; --n, ++gfn) {
 	if (kvm_is_radix(kvm)) {
-			kvm_unmap_radix(kvm, memslot, gfn);
-			continue;
+		kvmppc_radix_flush_memslot(kvm, memslot);
+		return;
 	}
+
+	for (n = memslot->npages; n; --n, ++gfn) {
 		/*
 		 * Testing the present bit without locking is OK because
 		 * the memslot has been marked invalid already, and hence

arch/powerpc/kvm/book3s_64_mmu_radix.c

@@ -29,6 +29,103 @@
  */
 static int p9_supported_radix_bits[4] = { 5, 9, 9, 13 };
 
+unsigned long __kvmhv_copy_tofrom_guest_radix(int lpid, int pid,
+					      gva_t eaddr, void *to, void *from,
+					      unsigned long n)
+{
+	unsigned long quadrant, ret = n;
+	int old_pid, old_lpid;
+	bool is_load = !!to;
+
+	/* Can't access quadrants 1 or 2 in non-HV mode, call the HV to do it */
+	if (kvmhv_on_pseries())
+		return plpar_hcall_norets(H_COPY_TOFROM_GUEST, lpid, pid, eaddr,
+					  __pa(to), __pa(from), n);
+
+	quadrant = 1;
+	if (!pid)
+		quadrant = 2;
+	if (is_load)
+		from = (void *) (eaddr | (quadrant << 62));
+	else
+		to = (void *) (eaddr | (quadrant << 62));
+
+	preempt_disable();
+
+	/* switch the lpid first to avoid running host with unallocated pid */
+	old_lpid = mfspr(SPRN_LPID);
+	if (old_lpid != lpid)
+		mtspr(SPRN_LPID, lpid);
+	if (quadrant == 1) {
+		old_pid = mfspr(SPRN_PID);
+		if (old_pid != pid)
+			mtspr(SPRN_PID, pid);
+	}
+	isync();
+
+	pagefault_disable();
+	if (is_load)
+		ret = raw_copy_from_user(to, from, n);
+	else
+		ret = raw_copy_to_user(to, from, n);
+	pagefault_enable();
+
+	/* switch the pid first to avoid running host with unallocated pid */
+	if (quadrant == 1 && pid != old_pid)
+		mtspr(SPRN_PID, old_pid);
+	if (lpid != old_lpid)
+		mtspr(SPRN_LPID, old_lpid);
+	isync();
+
+	preempt_enable();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__kvmhv_copy_tofrom_guest_radix);
+
+static long kvmhv_copy_tofrom_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr,
+					  void *to, void *from, unsigned long n)
+{
+	int lpid = vcpu->kvm->arch.lpid;
+	int pid = vcpu->arch.pid;
+
+	/* This would cause a data segment intr so don't allow the access */
+	if (eaddr & (0x3FFUL << 52))
+		return -EINVAL;
+
+	/* Should we be using the nested lpid */
+	if (vcpu->arch.nested)
+		lpid = vcpu->arch.nested->shadow_lpid;
+
+	/* If accessing quadrant 3 then pid is expected to be 0 */
+	if (((eaddr >> 62) & 0x3) == 0x3)
+		pid = 0;
+
+	eaddr &= ~(0xFFFUL << 52);
+
+	return __kvmhv_copy_tofrom_guest_radix(lpid, pid, eaddr, to, from, n);
+}
+
+long kvmhv_copy_from_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr, void *to,
+				 unsigned long n)
+{
+	long ret;
+
+	ret = kvmhv_copy_tofrom_guest_radix(vcpu, eaddr, to, NULL, n);
+	if (ret > 0)
+		memset(to + (n - ret), 0, ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kvmhv_copy_from_guest_radix);
+
+long kvmhv_copy_to_guest_radix(struct kvm_vcpu *vcpu, gva_t eaddr, void *from,
+			       unsigned long n)
+{
+	return kvmhv_copy_tofrom_guest_radix(vcpu, eaddr, NULL, from, n);
+}
+EXPORT_SYMBOL_GPL(kvmhv_copy_to_guest_radix);
+
 int kvmppc_mmu_walk_radix_tree(struct kvm_vcpu *vcpu, gva_t eaddr,
 			       struct kvmppc_pte *gpte, u64 root,
 			       u64 *pte_ret_p)
@@ -284,7 +381,8 @@ static void kvmppc_pmd_free(pmd_t *pmdp)
 
 /* Called with kvm->mmu_lock held */
 void kvmppc_unmap_pte(struct kvm *kvm, pte_t *pte, unsigned long gpa,
-		      unsigned int shift, struct kvm_memory_slot *memslot,
+		      unsigned int shift,
+		      const struct kvm_memory_slot *memslot,
 		      unsigned int lpid)
 
 {
@@ -683,6 +781,7 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 	pte_t pte, *ptep;
 	unsigned int shift, level;
 	int ret;
+	bool large_enable;
 
 	/* used to check for invalidations in progress */
 	mmu_seq = kvm->mmu_notifier_seq;
@@ -732,12 +831,15 @@ int kvmppc_book3s_instantiate_page(struct kvm_vcpu *vcpu,
 	pte = *ptep;
 	local_irq_enable();
 
+	/* If we're logging dirty pages, always map single pages */
+	large_enable = !(memslot->flags & KVM_MEM_LOG_DIRTY_PAGES);
+
 	/* Get pte level from shift/size */
-	if (shift == PUD_SHIFT &&
+	if (large_enable && shift == PUD_SHIFT &&
 	    (gpa & (PUD_SIZE - PAGE_SIZE)) ==
 	    (hva & (PUD_SIZE - PAGE_SIZE))) {
 		level = 2;
-	} else if (shift == PMD_SHIFT &&
+	} else if (large_enable && shift == PMD_SHIFT &&
 		   (gpa & (PMD_SIZE - PAGE_SIZE)) ==
 		   (hva & (PMD_SIZE - PAGE_SIZE))) {
 		level = 1;
@@ -857,7 +959,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return ret;
 }
 
-/* Called with kvm->lock held */
+/* Called with kvm->mmu_lock held */
 int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		    unsigned long gfn)
 {
@@ -872,7 +974,7 @@ int kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	return 0;				
 }
 
-/* Called with kvm->lock held */
+/* Called with kvm->mmu_lock held */
 int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		  unsigned long gfn)
 {
@@ -891,7 +993,7 @@ int kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 	return ref;
 }
 
-/* Called with kvm->lock held */
+/* Called with kvm->mmu_lock held */
 int kvm_test_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		       unsigned long gfn)
 {
@@ -953,6 +1055,26 @@ long kvmppc_hv_get_dirty_log_radix(struct kvm *kvm,
 	return 0;
 }
 
+void kvmppc_radix_flush_memslot(struct kvm *kvm,
+				const struct kvm_memory_slot *memslot)
+{
+	unsigned long n;
+	pte_t *ptep;
+	unsigned long gpa;
+	unsigned int shift;
+
+	gpa = memslot->base_gfn << PAGE_SHIFT;
+	spin_lock(&kvm->mmu_lock);
+	for (n = memslot->npages; n; --n) {
+		ptep = __find_linux_pte(kvm->arch.pgtable, gpa, NULL, &shift);
+		if (ptep && pte_present(*ptep))
+			kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot,
+					 kvm->arch.lpid);
+		gpa += PAGE_SIZE;
+	}
+	spin_unlock(&kvm->mmu_lock);
+}
+
 static void add_rmmu_ap_encoding(struct kvm_ppc_rmmu_info *info,
 				 int psize, int *indexp)
 {

arch/powerpc/kvm/book3s_hv.c

@@ -985,6 +985,10 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 			kvmppc_set_gpr(vcpu, 3, 0);
 			vcpu->arch.hcall_needed = 0;
 			return -EINTR;
+		} else if (ret == H_TOO_HARD) {
+			kvmppc_set_gpr(vcpu, 3, 0);
+			vcpu->arch.hcall_needed = 0;
+			return RESUME_HOST;
 		}
 		break;
 	case H_TLB_INVALIDATE:
@@ -992,7 +996,11 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		if (nesting_enabled(vcpu->kvm))
 			ret = kvmhv_do_nested_tlbie(vcpu);
 		break;
-
+	case H_COPY_TOFROM_GUEST:
+		ret = H_FUNCTION;
+		if (nesting_enabled(vcpu->kvm))
+			ret = kvmhv_copy_tofrom_guest_nested(vcpu);
+		break;
 	default:
 		return RESUME_HOST;
 	}
@@ -1336,7 +1344,7 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	return r;
 }
 
-static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
+static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int r;
 	int srcu_idx;
@@ -1394,7 +1402,7 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 	 */
 	case BOOK3S_INTERRUPT_H_DATA_STORAGE:
 		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = kvmhv_nested_page_fault(vcpu);
+		r = kvmhv_nested_page_fault(run, vcpu);
 		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 		break;
 	case BOOK3S_INTERRUPT_H_INST_STORAGE:
@@ -1404,7 +1412,7 @@ static int kvmppc_handle_nested_exit(struct kvm_vcpu *vcpu)
 		if (vcpu->arch.shregs.msr & HSRR1_HISI_WRITE)
 			vcpu->arch.fault_dsisr |= DSISR_ISSTORE;
 		srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = kvmhv_nested_page_fault(vcpu);
+		r = kvmhv_nested_page_fault(run, vcpu);
 		srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 		break;
 
@@ -4059,7 +4067,7 @@ int kvmhv_run_single_vcpu(struct kvm_run *kvm_run,
 		if (!nested)
 			r = kvmppc_handle_exit_hv(kvm_run, vcpu, current);
 		else
-			r = kvmppc_handle_nested_exit(vcpu);
+			r = kvmppc_handle_nested_exit(kvm_run, vcpu);
 	}
 	vcpu->arch.ret = r;
 
@@ -4371,7 +4379,8 @@ static int kvmppc_core_prepare_memory_region_hv(struct kvm *kvm,
 static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new)
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
 	unsigned long npages = mem->memory_size >> PAGE_SHIFT;
 
@@ -4383,6 +4392,23 @@ static void kvmppc_core_commit_memory_region_hv(struct kvm *kvm,
 	 */
 	if (npages)
 		atomic64_inc(&kvm->arch.mmio_update);
+
+	/*
+	 * For change == KVM_MR_MOVE or KVM_MR_DELETE, higher levels
+	 * have already called kvm_arch_flush_shadow_memslot() to
+	 * flush shadow mappings.  For KVM_MR_CREATE we have no
+	 * previous mappings.  So the only case to handle is
+	 * KVM_MR_FLAGS_ONLY when the KVM_MEM_LOG_DIRTY_PAGES bit
+	 * has been changed.
+	 * For radix guests, we flush on setting KVM_MEM_LOG_DIRTY_PAGES
+	 * to get rid of any THP PTEs in the partition-scoped page tables
+	 * so we can track dirtiness at the page level; we flush when
+	 * clearing KVM_MEM_LOG_DIRTY_PAGES so that we can go back to
+	 * using THP PTEs.
+	 */
+	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);
 }
 
 /*
@@ -4532,12 +4558,15 @@ int kvmppc_switch_mmu_to_hpt(struct kvm *kvm)
 {
 	if (nesting_enabled(kvm))
 		kvmhv_release_all_nested(kvm);
+	kvmppc_rmap_reset(kvm);
+	kvm->arch.process_table = 0;
+	/* Mutual exclusion with kvm_unmap_hva_range etc. */
+	spin_lock(&kvm->mmu_lock);
+	kvm->arch.radix = 0;
+	spin_unlock(&kvm->mmu_lock);
 	kvmppc_free_radix(kvm);
 	kvmppc_update_lpcr(kvm, LPCR_VPM1,
 			   LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR);
-	kvmppc_rmap_reset(kvm);
-	kvm->arch.radix = 0;
-	kvm->arch.process_table = 0;
 	return 0;
 }
 
@@ -4549,12 +4578,14 @@ int kvmppc_switch_mmu_to_radix(struct kvm *kvm)
 	err = kvmppc_init_vm_radix(kvm);
 	if (err)
 		return err;
-
+	kvmppc_rmap_reset(kvm);
+	/* Mutual exclusion with kvm_unmap_hva_range etc. */
+	spin_lock(&kvm->mmu_lock);
+	kvm->arch.radix = 1;
+	spin_unlock(&kvm->mmu_lock);
 	kvmppc_free_hpt(&kvm->arch.hpt);
 	kvmppc_update_lpcr(kvm, LPCR_UPRT | LPCR_GTSE | LPCR_HR,
 			   LPCR_VPM1 | LPCR_UPRT | LPCR_GTSE | LPCR_HR);
-	kvmppc_rmap_reset(kvm);
-	kvm->arch.radix = 1;
 	return 0;
 }
 
@@ -5214,6 +5245,44 @@ static int kvmhv_enable_nested(struct kvm *kvm)
 	return 0;
 }
 
+static int kvmhv_load_from_eaddr(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
+				 int size)
+{
+	int rc = -EINVAL;
+
+	if (kvmhv_vcpu_is_radix(vcpu)) {
+		rc = kvmhv_copy_from_guest_radix(vcpu, *eaddr, ptr, size);
+
+		if (rc > 0)
+			rc = -EINVAL;
+	}
+
+	/* For now quadrants are the only way to access nested guest memory */
+	if (rc && vcpu->arch.nested)
+		rc = -EAGAIN;
+
+	return rc;
+}
+
+static int kvmhv_store_to_eaddr(struct kvm_vcpu *vcpu, ulong *eaddr, void *ptr,
+				int size)
+{
+	int rc = -EINVAL;
+
+	if (kvmhv_vcpu_is_radix(vcpu)) {
+		rc = kvmhv_copy_to_guest_radix(vcpu, *eaddr, ptr, size);
+
+		if (rc > 0)
+			rc = -EINVAL;
+	}
+
+	/* For now quadrants are the only way to access nested guest memory */
+	if (rc && vcpu->arch.nested)
+		rc = -EAGAIN;
+
+	return rc;
+}
+
 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,
@@ -5254,6 +5323,8 @@ static struct kvmppc_ops kvm_ops_hv = {
 	.get_rmmu_info = kvmhv_get_rmmu_info,
 	.set_smt_mode = kvmhv_set_smt_mode,
 	.enable_nested = kvmhv_enable_nested,
+	.load_from_eaddr = kvmhv_load_from_eaddr,
+	.store_to_eaddr = kvmhv_store_to_eaddr,
 };
 
 static int kvm_init_subcore_bitmap(void)

arch/powerpc/kvm/book3s_hv_nested.c

@@ -195,6 +195,26 @@ void kvmhv_restore_hv_return_state(struct kvm_vcpu *vcpu,
 	vcpu->arch.ppr = hr->ppr;
 }
 
+static void kvmhv_nested_mmio_needed(struct kvm_vcpu *vcpu, u64 regs_ptr)
+{
+	/* No need to reflect the page fault to L1, we've handled it */
+	vcpu->arch.trap = 0;
+
+	/*
+	 * Since the L2 gprs have already been written back into L1 memory when
+	 * we complete the mmio, store the L1 memory location of the L2 gpr
+	 * being loaded into by the mmio so that the loaded value can be
+	 * written there in kvmppc_complete_mmio_load()
+	 */
+	if (((vcpu->arch.io_gpr & KVM_MMIO_REG_EXT_MASK) == KVM_MMIO_REG_GPR)
+	    && (vcpu->mmio_is_write == 0)) {
+		vcpu->arch.nested_io_gpr = (gpa_t) regs_ptr +
+					   offsetof(struct pt_regs,
+						    gpr[vcpu->arch.io_gpr]);
+		vcpu->arch.io_gpr = KVM_MMIO_REG_NESTED_GPR;
+	}
+}
+
 long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 {
 	long int err, r;
@@ -316,6 +336,11 @@ long kvmhv_enter_nested_guest(struct kvm_vcpu *vcpu)
 	if (r == -EINTR)
 		return H_INTERRUPT;
 
+	if (vcpu->mmio_needed) {
+		kvmhv_nested_mmio_needed(vcpu, regs_ptr);
+		return H_TOO_HARD;
+	}
+
 	return vcpu->arch.trap;
 }
 
@@ -436,6 +461,81 @@ long kvmhv_set_partition_table(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
+/*
+ * Handle the H_COPY_TOFROM_GUEST hcall.
+ * r4 = L1 lpid of nested guest
+ * r5 = pid
+ * r6 = eaddr to access
+ * r7 = to buffer (L1 gpa)
+ * r8 = from buffer (L1 gpa)
+ * r9 = n bytes to copy
+ */
+long kvmhv_copy_tofrom_guest_nested(struct kvm_vcpu *vcpu)
+{
+	struct kvm_nested_guest *gp;
+	int l1_lpid = kvmppc_get_gpr(vcpu, 4);
+	int pid = kvmppc_get_gpr(vcpu, 5);
+	gva_t eaddr = kvmppc_get_gpr(vcpu, 6);
+	gpa_t gp_to = (gpa_t) kvmppc_get_gpr(vcpu, 7);
+	gpa_t gp_from = (gpa_t) kvmppc_get_gpr(vcpu, 8);
+	void *buf;
+	unsigned long n = kvmppc_get_gpr(vcpu, 9);
+	bool is_load = !!gp_to;
+	long rc;
+
+	if (gp_to && gp_from) /* One must be NULL to determine the direction */
+		return H_PARAMETER;
+
+	if (eaddr & (0xFFFUL << 52))
+		return H_PARAMETER;
+
+	buf = kzalloc(n, GFP_KERNEL);
+	if (!buf)
+		return H_NO_MEM;
+
+	gp = kvmhv_get_nested(vcpu->kvm, l1_lpid, false);
+	if (!gp) {
+		rc = H_PARAMETER;
+		goto out_free;
+	}
+
+	mutex_lock(&gp->tlb_lock);
+
+	if (is_load) {
+		/* Load from the nested guest into our buffer */
+		rc = __kvmhv_copy_tofrom_guest_radix(gp->shadow_lpid, pid,
+						     eaddr, buf, NULL, n);
+		if (rc)
+			goto not_found;
+
+		/* Write what was loaded into our buffer back to the L1 guest */
+		rc = kvm_vcpu_write_guest(vcpu, gp_to, buf, n);
+		if (rc)
+			goto not_found;
+	} else {
+		/* Load the data to be stored from the L1 guest into our buf */
+		rc = kvm_vcpu_read_guest(vcpu, gp_from, buf, n);
+		if (rc)
+			goto not_found;
+
+		/* Store from our buffer into the nested guest */
+		rc = __kvmhv_copy_tofrom_guest_radix(gp->shadow_lpid, pid,
+						     eaddr, NULL, buf, n);
+		if (rc)
+			goto not_found;
+	}
+
+out_unlock:
+	mutex_unlock(&gp->tlb_lock);
+	kvmhv_put_nested(gp);
+out_free:
+	kfree(buf);
+	return rc;
+not_found:
+	rc = H_NOT_FOUND;
+	goto out_unlock;
+}
+
 /*
  * Reload the partition table entry for a guest.
  * Caller must hold gp->tlb_lock.
@@ -480,6 +580,7 @@ struct kvm_nested_guest *kvmhv_alloc_nested(struct kvm *kvm, unsigned int lpid)
 	if (shadow_lpid < 0)
 		goto out_free2;
 	gp->shadow_lpid = shadow_lpid;
+	gp->radix = 1;
 
 	memset(gp->prev_cpu, -1, sizeof(gp->prev_cpu));
 
@@ -723,7 +824,7 @@ static void kvmhv_remove_nest_rmap_list(struct kvm *kvm, unsigned long *rmapp,
 
 /* called with kvm->mmu_lock held */
 void kvmhv_remove_nest_rmap_range(struct kvm *kvm,
-				  struct kvm_memory_slot *memslot,
+				  const struct kvm_memory_slot *memslot,
 				  unsigned long gpa, unsigned long hpa,
 				  unsigned long nbytes)
 {
@@ -1099,7 +1200,8 @@ static inline int kvmppc_radix_shift_to_level(int shift)
 }
 
 /* called with gp->tlb_lock held */
-static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
+static long int __kvmhv_nested_page_fault(struct kvm_run *run,
+					  struct kvm_vcpu *vcpu,
 					  struct kvm_nested_guest *gp)
 {
 	struct kvm *kvm = vcpu->kvm;
@@ -1180,9 +1282,9 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
 			kvmppc_core_queue_data_storage(vcpu, ea, dsisr);
 			return RESUME_GUEST;
 		}
-		/* passthrough of emulated MMIO case... */
-		pr_err("emulated MMIO passthrough?\n");
-		return -EINVAL;
+
+		/* passthrough of emulated MMIO case */
+		return kvmppc_hv_emulate_mmio(run, vcpu, gpa, ea, writing);
 	}
 	if (memslot->flags & KVM_MEM_READONLY) {
 		if (writing) {
@@ -1264,13 +1366,13 @@ static long int __kvmhv_nested_page_fault(struct kvm_vcpu *vcpu,
 	return RESUME_GUEST;
 }
 
-long int kvmhv_nested_page_fault(struct kvm_vcpu *vcpu)
+long int kvmhv_nested_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	struct kvm_nested_guest *gp = vcpu->arch.nested;
 	long int ret;
 
 	mutex_lock(&gp->tlb_lock);
-	ret = __kvmhv_nested_page_fault(vcpu, gp);
+	ret = __kvmhv_nested_page_fault(run, vcpu, gp);
 	mutex_unlock(&gp->tlb_lock);
 	return ret;
 }

arch/powerpc/kvm/book3s_hv_rm_mmu.c

@@ -107,7 +107,7 @@ void kvmppc_add_revmap_chain(struct kvm *kvm, struct revmap_entry *rev,
 EXPORT_SYMBOL_GPL(kvmppc_add_revmap_chain);
 
 /* Update the dirty bitmap of a memslot */
-void kvmppc_update_dirty_map(struct kvm_memory_slot *memslot,
+void kvmppc_update_dirty_map(const struct kvm_memory_slot *memslot,
 			     unsigned long gfn, unsigned long psize)
 {
 	unsigned long npages;

arch/powerpc/kvm/book3s_pr.c

@@ -587,6 +587,7 @@ void kvmppc_set_pvr_pr(struct kvm_vcpu *vcpu, u32 pvr)
 	case PVR_POWER8:
 	case PVR_POWER8E:
 	case PVR_POWER8NVL:
+	case PVR_POWER9:
 		vcpu->arch.hflags |= BOOK3S_HFLAG_MULTI_PGSIZE |
 			BOOK3S_HFLAG_NEW_TLBIE;
 		break;
@@ -1913,7 +1914,8 @@ static int kvmppc_core_prepare_memory_region_pr(struct kvm *kvm,
 static void kvmppc_core_commit_memory_region_pr(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new)
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
 	return;
 }

arch/powerpc/kvm/book3s_xics.c

@@ -1015,17 +1015,7 @@ static int xics_debug_show(struct seq_file *m, void *private)
 	return 0;
 }
 
-static int xics_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, xics_debug_show, inode->i_private);
-}
-
-static const struct file_operations xics_debug_fops = {
-	.open = xics_debug_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(xics_debug);
 
 static void xics_debugfs_init(struct kvmppc_xics *xics)
 {

arch/powerpc/kvm/book3s_xive.c

@@ -1968,17 +1968,7 @@ static int xive_debug_show(struct seq_file *m, void *private)
 	return 0;
 }
 
-static int xive_debug_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, xive_debug_show, inode->i_private);
-}
-
-static const struct file_operations xive_debug_fops = {
-	.open = xive_debug_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(xive_debug);
 
 static void xive_debugfs_init(struct kvmppc_xive *xive)
 {

arch/powerpc/kvm/booke.c

@@ -1833,7 +1833,8 @@ int kvmppc_core_prepare_memory_region(struct kvm *kvm,
 void kvmppc_core_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
 				const struct kvm_memory_slot *old,
-				const struct kvm_memory_slot *new)
+				const struct kvm_memory_slot *new,
+				enum kvm_mr_change change)
 {
 }
 

arch/powerpc/kvm/powerpc.c

@@ -331,10 +331,17 @@ int kvmppc_st(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM & PAGE_MASK;
 	struct kvmppc_pte pte;
-	int r;
+	int r = -EINVAL;
 
 	vcpu->stat.st++;
 
+	if (vcpu->kvm->arch.kvm_ops && vcpu->kvm->arch.kvm_ops->store_to_eaddr)
+		r = vcpu->kvm->arch.kvm_ops->store_to_eaddr(vcpu, eaddr, ptr,
+							    size);
+
+	if ((!r) || (r == -EAGAIN))
+		return r;
+
 	r = kvmppc_xlate(vcpu, *eaddr, data ? XLATE_DATA : XLATE_INST,
 			 XLATE_WRITE, &pte);
 	if (r < 0)
@@ -367,10 +374,17 @@ int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr,
 {
 	ulong mp_pa = vcpu->arch.magic_page_pa & KVM_PAM & PAGE_MASK;
 	struct kvmppc_pte pte;
-	int rc;
+	int rc = -EINVAL;
 
 	vcpu->stat.ld++;
 
+	if (vcpu->kvm->arch.kvm_ops && vcpu->kvm->arch.kvm_ops->load_from_eaddr)
+		rc = vcpu->kvm->arch.kvm_ops->load_from_eaddr(vcpu, eaddr, ptr,
+							      size);
+
+	if ((!rc) || (rc == -EAGAIN))
+		return rc;
+
 	rc = kvmppc_xlate(vcpu, *eaddr, data ? XLATE_DATA : XLATE_INST,
 			  XLATE_READ, &pte);
 	if (rc)
@@ -542,8 +556,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
 	case KVM_CAP_SPAPR_TCE_64:
-		/* fallthrough */
+		r = 1;
+		break;
 	case KVM_CAP_SPAPR_TCE_VFIO:
+		r = !!cpu_has_feature(CPU_FTR_HVMODE);
+		break;
 	case KVM_CAP_PPC_RTAS:
 	case KVM_CAP_PPC_FIXUP_HCALL:
 	case KVM_CAP_PPC_ENABLE_HCALL:
@@ -695,7 +712,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   const struct kvm_memory_slot *new,
 				   enum kvm_mr_change change)
 {
-	kvmppc_core_commit_memory_region(kvm, mem, old, new);
+	kvmppc_core_commit_memory_region(kvm, mem, old, new, change);
 }
 
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
@@ -1190,6 +1207,14 @@ static void kvmppc_complete_mmio_load(struct kvm_vcpu *vcpu,
 				KVMPPC_VMX_COPY_BYTE)
 			kvmppc_set_vmx_byte(vcpu, gpr);
 		break;
+#endif
+#ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
+	case KVM_MMIO_REG_NESTED_GPR:
+		if (kvmppc_need_byteswap(vcpu))
+			gpr = swab64(gpr);
+		kvm_vcpu_write_guest(vcpu, vcpu->arch.nested_io_gpr, &gpr,
+				     sizeof(gpr));
+		break;
 #endif
 	default:
 		BUG();

arch/powerpc/mm/fault.c

@@ -636,6 +636,7 @@ void bad_page_fault(struct pt_regs *regs, unsigned long address, int sig)
 	switch (TRAP(regs)) {
 	case 0x300:
 	case 0x380:
+	case 0xe00:
 		printk(KERN_ALERT "Unable to handle kernel paging request for "
 			"data at address 0x%08lx\n", regs->dar);
 		break;