KVM: s390: arm64: Implement vm/vcpu create destroy

Implement init and destroy IOCTLS for vcpu and vm.
Implement arch vm IOCTL. Use s390 gmap and gmap plumbing.
Implement function (stubs) required by gmap.

Co-developed-by: Janosch Frank <frankja@linux.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Co-developed-by: Andreas Grapentin <gra@linux.ibm.com>
Signed-off-by: Andreas Grapentin <gra@linux.ibm.com>
Co-developed-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Signed-off-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Signed-off-by: Steffen Eiden <seiden@linux.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>

arch/s390/kvm/arm64/arm.c

@@ -7,6 +7,9 @@
 #include <linux/kvm_types.h>
 #include <linux/kvm_host.h>
 
+#include <gmap.h>
+#include <kvm_mmu.h>
+
 #include "arm.h"
 
 #define CREATE_TRACE_POINTS
@@ -18,6 +21,8 @@ static unsigned long system_supported_vcpu_features(struct kvm_vcpu *vcpu);
 #include "generated/arm.inc"
 #undef __INCL_GEN_ARM_FILE
 
+#define KVM_PHYS_SHIFT (40)
+
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int ret;
@@ -51,6 +56,83 @@ static u64 kvm_max_guest_address(void)
 	return ALIGN_DOWN(max_addr + 1, SZ_1G) - 1;
 }
 
+static int kvm_gmap_init(struct kvm *kvm)
+{
+	struct crst_table *table;
+
+	kvm->arch.gmap = gmap_new(kvm, gpa_to_gfn(kvm->arch.guest_phys_size));
+
+	if (!kvm->arch.gmap)
+		return -ENOMEM;
+
+	/* arm64 (on s390) do not have pfault */
+	clear_bit(GMAP_FLAG_PFAULT_ENABLED, &kvm->arch.gmap->flags);
+	set_bit(GMAP_FLAG_ALLOW_HPAGE_1M, &kvm->arch.gmap->flags);
+
+	table = dereference_asce(kvm->arch.gmap->asce);
+	crst_table_init((void *)table, _CRSTE_HOLE(table->crstes[0].h.tt).val);
+
+	return 0;
+}
+
+static int kvm_vm_type_ipa_size_shift(unsigned long type)
+{
+	int phys_shift;
+
+	phys_shift = KVM_VM_TYPE_ARM_IPA_SIZE(type);
+	if (phys_shift) {
+		if (phys_shift > get_kvm_ipa_limit() ||
+		    phys_shift < ARM64_MIN_PARANGE_BITS)
+			return -EINVAL;
+	} else {
+		phys_shift = KVM_PHYS_SHIFT;
+		if (phys_shift > get_kvm_ipa_limit()) {
+			pr_warn_once("%s using unsupported default IPA limit\n",
+				     current->comm);
+			return -EINVAL;
+		}
+	}
+
+	return phys_shift;
+}
+
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
+{
+	char debug_name[32];
+	int ret;
+
+	if (type & ~KVM_VM_TYPE_ARM_IPA_SIZE_MASK)
+		return -EINVAL;
+
+	ret = kvm_vm_type_ipa_size_shift(type);
+	if (ret < 0)
+		return ret;
+	kvm->arch.guest_phys_size = 1UL << ret;
+
+	mutex_init(&kvm->arch.config_lock);
+	bitmap_zero(kvm->arch.vcpu_features, KVM_VCPU_MAX_FEATURES);
+
+	snprintf(debug_name, sizeof(debug_name), "kvm-arm64-%u-%u",
+		 current->pid, get_random_u32());
+	kvm->arch.dbf = debug_register(debug_name, 32, 1, 7 * sizeof(long));
+	if (!kvm->arch.dbf)
+		return -ENOMEM;
+	debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
+
+	ret = kvm_gmap_init(kvm);
+	if (ret)
+		goto out_err;
+	kvm->arch.mem_limit = kvm->arch.guest_phys_size;
+
+	VM_EVENT(kvm, 3, "vm created with type %lu", type);
+	return 0;
+
+out_err:
+	debug_unregister(kvm->arch.dbf);
+
+	return ret;
+}
+
 vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 {
 	return VM_FAULT_SIGBUS;
@@ -62,6 +144,13 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	return -EINVAL;
 }
 
+void kvm_arch_destroy_vm(struct kvm *kvm)
+{
+	kvm_destroy_vcpus(kvm);
+	debug_unregister(kvm->arch.dbf);
+	kvm->arch.gmap = gmap_put(kvm->arch.gmap);
+}
+
 u32 get_kvm_ipa_limit(void)
 {
 	return fls64(kvm_max_guest_address() + 1) - 1;
@@ -72,10 +161,45 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 	return 0;
 }
 
+int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
+{
+	struct kvm_sae_block *sae_block = &vcpu->arch.sae_block;
+	struct kvm_sae_save_area *save_area = &vcpu->arch.save_area;
+
+	spin_lock_init(&vcpu->arch.mp_state_lock);
+
+	/* Force users to call KVM_ARM_VCPU_INIT */
+	vcpu_clear_flag(vcpu, VCPU_INITIALIZED);
+
+	vcpu->arch.mc = kvm_s390_new_mmu_cache();
+	if (!vcpu->arch.mc)
+		return -ENOMEM;
+
+	save_area->sdo = virt_to_phys(sae_block);
+
+	sae_block->hbasce = vcpu->kvm->arch.gmap->asce.val;
+	sae_block->mso = 0L;
+	sae_block->msl = vcpu->kvm->arch.mem_limit - 1;
+	sae_block->save_area = virt_to_phys(save_area);
+
+	VM_EVENT(vcpu->kvm, 3,
+		 "create cpu %d at 0x%p, sae block at 0x%p, satellite at 0x%p",
+		 vcpu->vcpu_id, vcpu, &vcpu->arch.sae_block,
+		 &vcpu->arch.save_area);
+	return 0;
+}
+
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
 }
 
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+	kvm_s390_free_mmu_cache(vcpu->arch.mc);
+
+	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
+}
+
 int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
 				    struct kvm_mp_state *mp_state)
 {
@@ -101,6 +225,72 @@ static unsigned long system_supported_vcpu_features(struct kvm_vcpu *vcpu)
 	return features;
 }
 
+int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
+			       struct kvm_dirty_log *log)
+{
+	return s390_kvm_mmu_get_dirty_log(kvm, log);
+}
+
+bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	scoped_guard(read_lock, &kvm->mmu_lock)
+		return gmap_age_gfn(kvm->arch.gmap, range->start, range->end);
+}
+
+void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
+{
+	gfn_t last_gfn = memslot->base_gfn + memslot->npages;
+
+	scoped_guard(read_lock, &kvm->mmu_lock)
+		gmap_sync_dirty_log(kvm->arch.gmap, memslot->base_gfn, last_gfn);
+}
+
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+				   const struct kvm_memory_slot *old,
+				   struct kvm_memory_slot *new,
+				   enum kvm_mr_change change)
+{
+	return s390_kvm_mmu_prepare_memory_region(kvm, old, new, change);
+}
+
+void kvm_arch_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old,
+				   const struct kvm_memory_slot *new,
+				   enum kvm_mr_change change)
+{
+}
+
+bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	return gmap_unmap_gfn_range(kvm->arch.gmap, range->slot, range->start, range->end);
+}
+
+bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range)
+{
+	scoped_guard(read_lock, &kvm->mmu_lock)
+		return dat_test_age_gfn(kvm->arch.gmap->asce, range->start, range->end);
+}
+
+int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+	void __user *argp = (void __user *)arg;
+
+	switch (ioctl) {
+	case KVM_ARM_PREFERRED_TARGET: {
+		struct kvm_vcpu_init init = {
+			.target = KVM_ARM_TARGET_GENERIC_V8,
+		};
+
+		if (copy_to_user(argp, &init, sizeof(init)))
+			return -EFAULT;
+
+		return 0;
+	}
+
+	default:
+		return -EINVAL;
+	}
+}
+
 bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
 {
 	return false;

arch/s390/kvm/arm64/arm.h

@@ -2,6 +2,20 @@
 #ifndef ARCH_S390_KVM_ARM64_H
 #define ARCH_S390_KVM_ARM64_H
 
+#include <linux/compiler_attributes.h>
+#include <linux/kvm_host.h>
+
+#define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)			\
+	debug_sprintf_event((d_kvm)->arch.dbf, d_loglevel,			\
+			    __stringify(KVM_DEV_NAME) ": " d_string "\n",	\
+			    d_args)
+
+#define VCPU_EVENT(d_vcpu, d_loglevel, d_string, d_args...)				\
+	debug_sprintf_event((d_vcpu)->kvm->arch.dbf, d_loglevel,			\
+		__stringify(KVM_DEV_NAME) " %02d[%016llx-%016llx]: " d_string "\n",	\
+		(d_vcpu)->vcpu_id, (d_vcpu)->arch.sae_block.pstate,			\
+		(d_vcpu)->arch.sae_block.pc, d_args)
+
 static __always_inline int kvm_is_ucontrol(struct kvm *kvm)
 {
 	return 0;

arch/s390/kvm/gmap/faultin.c

@@ -10,6 +10,11 @@
 
 #include "gmap.h"
 #include "faultin.h"
+#ifdef KVM_S390_ARM64
+#include "arm.h"
+#else
+#include "s390.h"
+#endif
 
 bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu);
 #define CREATE_TRACE_POINTS

arch/s390/kvm/gmap/gmap.c

@@ -21,7 +21,11 @@
 
 #include "dat.h"
 #include "gmap.h"
+#ifdef KVM_S390_ARM64
+#include "arm.h"
+#else
 #include "s390.h"
+#endif
 #include "faultin.h"
 
 static int gmap_limit_to_type(gfn_t limit)

arch/s390/kvm/gmap/kvm_mmu.c

@@ -3,7 +3,11 @@
 #include <linux/kvm_types.h>
 #include <linux/kvm_host.h>
 
+#ifdef KVM_S390_ARM64
+#include "arm.h"
+#else
 #include "s390.h"
+#endif
 #include "gmap.h"
 #include "dat.h"
 #include "kvm_mmu.h"

arch/s390/kvm/gmap/trace_gmap.h

@@ -13,6 +13,18 @@
 #undef TRACE_INCLUDE_FILE
 #define TRACE_INCLUDE_FILE trace_gmap
 
+#ifdef KVM_S390_ARM64
+#define __KVM_FIELDS \
+	__field(unsigned long, pstate) \
+	__field(unsigned long, pc)
+#define __KVM_ASSIGN ({\
+	__entry->pstate = vcpu->arch.sae_block.pstate; \
+	__entry->pc = vcpu->arch.sae_block.pc; \
+	})
+#define __KVM_PRINT \
+	__entry->pstate, \
+	__entry->pc
+#else
 #define __KVM_FIELDS \
 	__field(unsigned long, pswmask) \
 	__field(unsigned long, pswaddr)
@@ -23,6 +35,7 @@
 #define __KVM_PRINT \
 	__entry->pswmask,\
 	__entry->pswaddr
+#endif
 
 TRACE_EVENT(kvm_s390_major_guest_pfault,
 	    TP_PROTO(struct kvm_vcpu *vcpu),