KVM: PPC: Book3S HV: Page table construction and page faults for radix guests

This adds the code to construct the second-level ("partition-scoped" in
architecturese) page tables for guests using the radix MMU.  Apart from
the PGD level, which is allocated when the guest is created, the rest
of the tree is all constructed in response to hypervisor page faults.

As well as hypervisor page faults for missing pages, we also get faults
for reference/change (RC) bits needing to be set, as well as various
other error conditions.  For now, we only set the R or C bit in the
guest page table if the same bit is set in the host PTE for the
backing page.

This code can take advantage of the guest being backed with either
transparent or ordinary 2MB huge pages, and insert 2MB page entries
into the guest page tables.  There is no support for 1GB huge pages
yet.
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/kvm_book3s.h

@@ -170,6 +170,8 @@ extern int kvmppc_book3s_hv_page_fault(struct kvm_run *run,
 			unsigned long status);
 extern long kvmppc_hv_find_lock_hpte(struct kvm *kvm, gva_t eaddr,
 			unsigned long slb_v, unsigned long valid);
+extern int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
+			unsigned long gpa, gva_t ea, int is_store);
 
 extern void kvmppc_mmu_hpte_cache_map(struct kvm_vcpu *vcpu, struct hpte_cache *pte);
 extern struct hpte_cache *kvmppc_mmu_hpte_cache_next(struct kvm_vcpu *vcpu);
@@ -182,8 +184,14 @@ extern void kvmppc_mmu_hpte_sysexit(void);
 extern int kvmppc_mmu_hv_init(void);
 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 int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 			struct kvmppc_pte *gpte, bool data, bool iswrite);
+extern void kvmppc_free_radix(struct kvm *kvm);
+extern int kvmppc_radix_init(void);
+extern void kvmppc_radix_exit(void);
 
 /* XXX remove this export when load_last_inst() is generic */
 extern int kvmppc_ld(struct kvm_vcpu *vcpu, ulong *eaddr, int size, void *ptr, bool data);

arch/powerpc/kvm/book3s.c

@@ -239,6 +239,7 @@ void kvmppc_core_queue_data_storage(struct kvm_vcpu *vcpu, ulong dar,
 	kvmppc_set_dsisr(vcpu, flags);
 	kvmppc_book3s_queue_irqprio(vcpu, BOOK3S_INTERRUPT_DATA_STORAGE);
 }
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_data_storage);	/* used by kvm_hv */
 
 void kvmppc_core_queue_inst_storage(struct kvm_vcpu *vcpu, ulong flags)
 {

arch/powerpc/kvm/book3s_64_mmu_hv.c

@@ -395,7 +395,7 @@ static int instruction_is_store(unsigned int instr)
 	return (instr & mask) != 0;
 }
 
-static int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
+int kvmppc_hv_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			   unsigned long gpa, gva_t ea, int is_store)
 {
 	u32 last_inst;
@@ -461,6 +461,9 @@ int kvmppc_book3s_hv_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	unsigned long rcbits;
 	long mmio_update;
 
+	if (kvm_is_radix(kvm))
+		return kvmppc_book3s_radix_page_fault(run, vcpu, ea, dsisr);
+
 	/*
 	 * Real-mode code has already searched the HPT and found the
 	 * entry we're interested in.  Lock the entry and check that

arch/powerpc/kvm/book3s_hv.c

@@ -3356,6 +3356,9 @@ static void kvmppc_core_destroy_vm_hv(struct kvm *kvm)
 
 	kvmppc_free_vcores(kvm);
 
+	if (kvm_is_radix(kvm))
+		kvmppc_free_radix(kvm);
+	else
 		kvmppc_free_hpt(kvm);
 
 	kvmppc_free_pimap(kvm);
@@ -3768,6 +3771,11 @@ static int kvm_init_subcore_bitmap(void)
 	return 0;
 }
 
+static int kvmppc_radix_possible(void)
+{
+	return cpu_has_feature(CPU_FTR_ARCH_300) && radix_enabled();
+}
+
 static int kvmppc_book3s_init_hv(void)
 {
 	int r;
@@ -3807,12 +3815,19 @@ static int kvmppc_book3s_init_hv(void)
 	init_vcore_lists();
 
 	r = kvmppc_mmu_hv_init();
+	if (r)
+		return r;
+
+	if (kvmppc_radix_possible())
+		r = kvmppc_radix_init();
 	return r;
 }
 
 static void kvmppc_book3s_exit_hv(void)
 {
 	kvmppc_free_host_rm_ops();
+	if (kvmppc_radix_possible())
+		kvmppc_radix_exit();
 	kvmppc_hv_ops = NULL;
 }