Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "ARM:
   - GICv4.1 support

   - 32bit host removal

  PPC:
   - secure (encrypted) using under the Protected Execution Framework
     ultravisor

  s390:
   - allow disabling GISA (hardware interrupt injection) and protected
     VMs/ultravisor support.

  x86:
   - New dirty bitmap flag that sets all bits in the bitmap when dirty
     page logging is enabled; this is faster because it doesn't require
     bulk modification of the page tables.

   - Initial work on making nested SVM event injection more similar to
     VMX, and less buggy.

   - Various cleanups to MMU code (though the big ones and related
     optimizations were delayed to 5.8). Instead of using cr3 in
     function names which occasionally means eptp, KVM too has
     standardized on "pgd".

   - A large refactoring of CPUID features, which now use an array that
     parallels the core x86_features.

   - Some removal of pointer chasing from kvm_x86_ops, which will also
     be switched to static calls as soon as they are available.

   - New Tigerlake CPUID features.

   - More bugfixes, optimizations and cleanups.

  Generic:
   - selftests: cleanups, new MMU notifier stress test, steal-time test

   - CSV output for kvm_stat"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (277 commits)
  x86/kvm: fix a missing-prototypes "vmread_error"
  KVM: x86: Fix BUILD_BUG() in __cpuid_entry_get_reg() w/ CONFIG_UBSAN=y
  KVM: VMX: Add a trampoline to fix VMREAD error handling
  KVM: SVM: Annotate svm_x86_ops as __initdata
  KVM: VMX: Annotate vmx_x86_ops as __initdata
  KVM: x86: Drop __exit from kvm_x86_ops' hardware_unsetup()
  KVM: x86: Copy kvm_x86_ops by value to eliminate layer of indirection
  KVM: x86: Set kvm_x86_ops only after ->hardware_setup() completes
  KVM: VMX: Configure runtime hooks using vmx_x86_ops
  KVM: VMX: Move hardware_setup() definition below vmx_x86_ops
  KVM: x86: Move init-only kvm_x86_ops to separate struct
  KVM: Pass kvm_init()'s opaque param to additional arch funcs
  s390/gmap: return proper error code on ksm unsharing
  KVM: selftests: Fix cosmetic copy-paste error in vm_mem_region_move()
  KVM: Fix out of range accesses to memslots
  KVM: X86: Micro-optimize IPI fastpath delay
  KVM: X86: Delay read msr data iff writes ICR MSR
  KVM: PPC: Book3S HV: Add a capability for enabling secure guests
  KVM: arm64: GICv4.1: Expose HW-based SGIs in debugfs
  KVM: arm64: GICv4.1: Allow non-trapping WFI when using HW SGIs
  ...

1 files changed, 508 insertions, 89 deletions

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c2e6d4ba4e23..19a81024fe16 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2,7 +2,7 @@
 /*
  * hosting IBM Z kernel virtual machines (s390x)
  *
- * Copyright IBM Corp. 2008, 2018
+ * Copyright IBM Corp. 2008, 2020
  *
  *    Author(s): Carsten Otte <cotte@de.ibm.com>
  *               Christian Borntraeger <borntraeger@de.ibm.com>
@@ -44,6 +44,7 @@
 #include <asm/cpacf.h>
 #include <asm/timex.h>
 #include <asm/ap.h>
+#include <asm/uv.h>
 #include "kvm-s390.h"
 #include "gaccess.h"
 
@@ -184,6 +185,11 @@ static u8 halt_poll_max_steal = 10;
 module_param(halt_poll_max_steal, byte, 0644);
 MODULE_PARM_DESC(halt_poll_max_steal, "Maximum percentage of steal time to allow polling");
 
+/* if set to true, the GISA will be initialized and used if available */
+static bool use_gisa  = true;
+module_param(use_gisa, bool, 0644);
+MODULE_PARM_DESC(use_gisa, "Use the GISA if the host supports it.");
+
 /*
  * For now we handle at most 16 double words as this is what the s390 base
  * kernel handles and stores in the prefix page. If we ever need to go beyond
@@ -220,6 +226,7 @@ static struct kvm_s390_vm_cpu_subfunc kvm_s390_available_subfunc;
 static struct gmap_notifier gmap_notifier;
 static struct gmap_notifier vsie_gmap_notifier;
 debug_info_t *kvm_s390_dbf;
+debug_info_t *kvm_s390_dbf_uv;
 
 /* Section: not file related */
 int kvm_arch_hardware_enable(void)
@@ -228,13 +235,15 @@ int kvm_arch_hardware_enable(void)
 	return 0;
 }
 
-int kvm_arch_check_processor_compat(void)
+int kvm_arch_check_processor_compat(void *opaque)
 {
 	return 0;
 }
 
+/* forward declarations */
 static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
 			      unsigned long end);
+static int sca_switch_to_extended(struct kvm *kvm);
 
 static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta)
 {
@@ -293,7 +302,7 @@ static struct notifier_block kvm_clock_notifier = {
 	.notifier_call = kvm_clock_sync,
 };
 
-int kvm_arch_hardware_setup(void)
+int kvm_arch_hardware_setup(void *opaque)
 {
 	gmap_notifier.notifier_call = kvm_gmap_notifier;
 	gmap_register_pte_notifier(&gmap_notifier);
@@ -460,7 +469,12 @@ int kvm_arch_init(void *opaque)
 	if (!kvm_s390_dbf)
 		return -ENOMEM;
 
-	if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view))
+	kvm_s390_dbf_uv = debug_register("kvm-uv", 32, 1, 7 * sizeof(long));
+	if (!kvm_s390_dbf_uv)
+		goto out;
+
+	if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view) ||
+	    debug_register_view(kvm_s390_dbf_uv, &debug_sprintf_view))
 		goto out;
 
 	kvm_s390_cpu_feat_init();
@@ -487,6 +501,7 @@ void kvm_arch_exit(void)
 {
 	kvm_s390_gib_destroy();
 	debug_unregister(kvm_s390_dbf);
+	debug_unregister(kvm_s390_dbf_uv);
 }
 
 /* Section: device related */
@@ -564,14 +579,16 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_BPB:
 		r = test_facility(82);
 		break;
+	case KVM_CAP_S390_PROTECTED:
+		r = is_prot_virt_host();
+		break;
 	default:
 		r = 0;
 	}
 	return r;
 }
 
-static void kvm_s390_sync_dirty_log(struct kvm *kvm,
-				    struct kvm_memory_slot *memslot)
+void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 	int i;
 	gfn_t cur_gfn, last_gfn;
@@ -612,9 +629,8 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 {
 	int r;
 	unsigned long n;
-	struct kvm_memslots *slots;
 	struct kvm_memory_slot *memslot;
-	int is_dirty = 0;
+	int is_dirty;
 
 	if (kvm_is_ucontrol(kvm))
 		return -EINVAL;
@@ -625,14 +641,7 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
 	if (log->slot >= KVM_USER_MEM_SLOTS)
 		goto out;
 
-	slots = kvm_memslots(kvm);
-	memslot = id_to_memslot(slots, log->slot);
-	r = -ENOENT;
-	if (!memslot->dirty_bitmap)
-		goto out;
-
-	kvm_s390_sync_dirty_log(kvm, memslot);
-	r = kvm_get_dirty_log(kvm, log, &is_dirty);
+	r = kvm_get_dirty_log(kvm, log, &is_dirty, &memslot);
 	if (r)
 		goto out;
 
@@ -1993,6 +2002,9 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	struct kvm_memory_slot *ms;
 
+	if (unlikely(!slots->used_slots))
+		return 0;
+
 	cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn);
 	ms = gfn_to_memslot(kvm, cur_gfn);
 	args->count = 0;
@@ -2158,6 +2170,194 @@ out:
 	return r;
 }
 
+static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp)
+{
+	struct kvm_vcpu *vcpu;
+	u16 rc, rrc;
+	int ret = 0;
+	int i;
+
+	/*
+	 * We ignore failures and try to destroy as many CPUs as possible.
+	 * At the same time we must not free the assigned resources when
+	 * this fails, as the ultravisor has still access to that memory.
+	 * So kvm_s390_pv_destroy_cpu can leave a "wanted" memory leak
+	 * behind.
+	 * We want to return the first failure rc and rrc, though.
+	 */
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		mutex_lock(&vcpu->mutex);
+		if (kvm_s390_pv_destroy_cpu(vcpu, &rc, &rrc) && !ret) {
+			*rcp = rc;
+			*rrcp = rrc;
+			ret = -EIO;
+		}
+		mutex_unlock(&vcpu->mutex);
+	}
+	return ret;
+}
+
+static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+	int i, r = 0;
+	u16 dummy;
+
+	struct kvm_vcpu *vcpu;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		mutex_lock(&vcpu->mutex);
+		r = kvm_s390_pv_create_cpu(vcpu, rc, rrc);
+		mutex_unlock(&vcpu->mutex);
+		if (r)
+			break;
+	}
+	if (r)
+		kvm_s390_cpus_from_pv(kvm, &dummy, &dummy);
+	return r;
+}
+
+static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
+{
+	int r = 0;
+	u16 dummy;
+	void __user *argp = (void __user *)cmd->data;
+
+	switch (cmd->cmd) {
+	case KVM_PV_ENABLE: {
+		r = -EINVAL;
+		if (kvm_s390_pv_is_protected(kvm))
+			break;
+
+		/*
+		 *  FMT 4 SIE needs esca. As we never switch back to bsca from
+		 *  esca, we need no cleanup in the error cases below
+		 */
+		r = sca_switch_to_extended(kvm);
+		if (r)
+			break;
+
+		down_write(&current->mm->mmap_sem);
+		r = gmap_mark_unmergeable();
+		up_write(&current->mm->mmap_sem);
+		if (r)
+			break;
+
+		r = kvm_s390_pv_init_vm(kvm, &cmd->rc, &cmd->rrc);
+		if (r)
+			break;
+
+		r = kvm_s390_cpus_to_pv(kvm, &cmd->rc, &cmd->rrc);
+		if (r)
+			kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy);
+
+		/* we need to block service interrupts from now on */
+		set_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs);
+		break;
+	}
+	case KVM_PV_DISABLE: {
+		r = -EINVAL;
+		if (!kvm_s390_pv_is_protected(kvm))
+			break;
+
+		r = kvm_s390_cpus_from_pv(kvm, &cmd->rc, &cmd->rrc);
+		/*
+		 * If a CPU could not be destroyed, destroy VM will also fail.
+		 * There is no point in trying to destroy it. Instead return
+		 * the rc and rrc from the first CPU that failed destroying.
+		 */
+		if (r)
+			break;
+		r = kvm_s390_pv_deinit_vm(kvm, &cmd->rc, &cmd->rrc);
+
+		/* no need to block service interrupts any more */
+		clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs);
+		break;
+	}
+	case KVM_PV_SET_SEC_PARMS: {
+		struct kvm_s390_pv_sec_parm parms = {};
+		void *hdr;
+
+		r = -EINVAL;
+		if (!kvm_s390_pv_is_protected(kvm))
+			break;
+
+		r = -EFAULT;
+		if (copy_from_user(&parms, argp, sizeof(parms)))
+			break;
+
+		/* Currently restricted to 8KB */
+		r = -EINVAL;
+		if (parms.length > PAGE_SIZE * 2)
+			break;
+
+		r = -ENOMEM;
+		hdr = vmalloc(parms.length);
+		if (!hdr)
+			break;
+
+		r = -EFAULT;
+		if (!copy_from_user(hdr, (void __user *)parms.origin,
+				    parms.length))
+			r = kvm_s390_pv_set_sec_parms(kvm, hdr, parms.length,
+						      &cmd->rc, &cmd->rrc);
+
+		vfree(hdr);
+		break;
+	}
+	case KVM_PV_UNPACK: {
+		struct kvm_s390_pv_unp unp = {};
+
+		r = -EINVAL;
+		if (!kvm_s390_pv_is_protected(kvm))
+			break;
+
+		r = -EFAULT;
+		if (copy_from_user(&unp, argp, sizeof(unp)))
+			break;
+
+		r = kvm_s390_pv_unpack(kvm, unp.addr, unp.size, unp.tweak,
+				       &cmd->rc, &cmd->rrc);
+		break;
+	}
+	case KVM_PV_VERIFY: {
+		r = -EINVAL;
+		if (!kvm_s390_pv_is_protected(kvm))
+			break;
+
+		r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
+				  UVC_CMD_VERIFY_IMG, &cmd->rc, &cmd->rrc);
+		KVM_UV_EVENT(kvm, 3, "PROTVIRT VERIFY: rc %x rrc %x", cmd->rc,
+			     cmd->rrc);
+		break;
+	}
+	case KVM_PV_PREP_RESET: {
+		r = -EINVAL;
+		if (!kvm_s390_pv_is_protected(kvm))
+			break;
+
+		r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
+				  UVC_CMD_PREPARE_RESET, &cmd->rc, &cmd->rrc);
+		KVM_UV_EVENT(kvm, 3, "PROTVIRT PREP RESET: rc %x rrc %x",
+			     cmd->rc, cmd->rrc);
+		break;
+	}
+	case KVM_PV_UNSHARE_ALL: {
+		r = -EINVAL;
+		if (!kvm_s390_pv_is_protected(kvm))
+			break;
+
+		r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
+				  UVC_CMD_SET_UNSHARE_ALL, &cmd->rc, &cmd->rrc);
+		KVM_UV_EVENT(kvm, 3, "PROTVIRT UNSHARE: rc %x rrc %x",
+			     cmd->rc, cmd->rrc);
+		break;
+	}
+	default:
+		r = -ENOTTY;
+	}
+	return r;
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg)
 {
@@ -2255,6 +2455,33 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		mutex_unlock(&kvm->slots_lock);
 		break;
 	}
+	case KVM_S390_PV_COMMAND: {
+		struct kvm_pv_cmd args;
+
+		/* protvirt means user sigp */
+		kvm->arch.user_cpu_state_ctrl = 1;
+		r = 0;
+		if (!is_prot_virt_host()) {
+			r = -EINVAL;
+			break;
+		}
+		if (copy_from_user(&args, argp, sizeof(args))) {
+			r = -EFAULT;
+			break;
+		}
+		if (args.flags) {
+			r = -EINVAL;
+			break;
+		}
+		mutex_lock(&kvm->lock);
+		r = kvm_s390_handle_pv(kvm, &args);
+		mutex_unlock(&kvm->lock);
+		if (copy_to_user(argp, &args, sizeof(args))) {
+			r = -EFAULT;
+			break;
+		}
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
@@ -2504,7 +2731,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.use_skf = sclp.has_skey;
 	spin_lock_init(&kvm->arch.start_stop_lock);
 	kvm_s390_vsie_init(kvm);
-	kvm_s390_gisa_init(kvm);
+	if (use_gisa)
+		kvm_s390_gisa_init(kvm);
 	KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
 
 	return 0;
@@ -2518,6 +2746,8 @@ out_err:
 
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 {
+	u16 rc, rrc;
+
 	VCPU_EVENT(vcpu, 3, "%s", "free cpu");
 	trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
 	kvm_s390_clear_local_irqs(vcpu);
@@ -2530,6 +2760,9 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
 
 	if (vcpu->kvm->arch.use_cmma)
 		kvm_s390_vcpu_unsetup_cmma(vcpu);
+	/* We can not hold the vcpu mutex here, we are already dying */
+	if (kvm_s390_pv_cpu_get_handle(vcpu))
+		kvm_s390_pv_destroy_cpu(vcpu, &rc, &rrc);
 	free_page((unsigned long)(vcpu->arch.sie_block));
 }
 
@@ -2551,10 +2784,20 @@ static void kvm_free_vcpus(struct kvm *kvm)
 
 void kvm_arch_destroy_vm(struct kvm *kvm)
 {
+	u16 rc, rrc;
+
 	kvm_free_vcpus(kvm);
 	sca_dispose(kvm);
-	debug_unregister(kvm->arch.dbf);
 	kvm_s390_gisa_destroy(kvm);
+	/*
+	 * We are already at the end of life and kvm->lock is not taken.
+	 * This is ok as the file descriptor is closed by now and nobody
+	 * can mess with the pv state. To avoid lockdep_assert_held from
+	 * complaining we do not use kvm_s390_pv_is_protected.
+	 */
+	if (kvm_s390_pv_get_handle(kvm))
+		kvm_s390_pv_deinit_vm(kvm, &rc, &rrc);
+	debug_unregister(kvm->arch.dbf);
 	free_page((unsigned long)kvm->arch.sie_page2);
 	if (!kvm_is_ucontrol(kvm))
 		gmap_remove(kvm->arch.gmap);
@@ -2650,6 +2893,9 @@ static int sca_switch_to_extended(struct kvm *kvm)
 	unsigned int vcpu_idx;
 	u32 scaol, scaoh;
 
+	if (kvm->arch.use_esca)
+		return 0;
+
 	new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO);
 	if (!new_sca)
 		return -ENOMEM;
@@ -2901,6 +3147,7 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
 static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
 {
 	int rc = 0;
+	u16 uvrc, uvrrc;
 
 	atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
 						    CPUSTAT_SM |
@@ -2968,6 +3215,14 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvm_s390_vcpu_crypto_setup(vcpu);
 
+	mutex_lock(&vcpu->kvm->lock);
+	if (kvm_s390_pv_is_protected(vcpu->kvm)) {
+		rc = kvm_s390_pv_create_cpu(vcpu, &uvrc, &uvrrc);
+		if (rc)
+			kvm_s390_vcpu_unsetup_cmma(vcpu);
+	}
+	mutex_unlock(&vcpu->kvm->lock);
+
 	return rc;
 }
 
@@ -3277,7 +3532,6 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
 	kvm_s390_set_prefix(vcpu, 0);
 	kvm_s390_set_cpu_timer(vcpu, 0);
 	vcpu->arch.sie_block->ckc = 0;
-	vcpu->arch.sie_block->todpr = 0;
 	memset(vcpu->arch.sie_block->gcr, 0, sizeof(vcpu->arch.sie_block->gcr));
 	vcpu->arch.sie_block->gcr[0] = CR0_INITIAL_MASK;
 	vcpu->arch.sie_block->gcr[14] = CR14_INITIAL_MASK;
@@ -3295,9 +3549,17 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
 	vcpu->run->s.regs.pp = 0;
 	vcpu->run->s.regs.gbea = 1;
 	vcpu->run->s.regs.fpc = 0;
-	vcpu->arch.sie_block->gbea = 1;
-	vcpu->arch.sie_block->pp = 0;
-	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+	/*
+	 * Do not reset these registers in the protected case, as some of
+	 * them are overlayed and they are not accessible in this case
+	 * anyway.
+	 */
+	if (!kvm_s390_pv_cpu_is_protected(vcpu)) {
+		vcpu->arch.sie_block->gbea = 1;
+		vcpu->arch.sie_block->pp = 0;
+		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+		vcpu->arch.sie_block->todpr = 0;
+	}
 }
 
 static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu)
@@ -3487,14 +3749,20 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 
 	switch (mp_state->mp_state) {
 	case KVM_MP_STATE_STOPPED:
-		kvm_s390_vcpu_stop(vcpu);
+		rc = kvm_s390_vcpu_stop(vcpu);
 		break;
 	case KVM_MP_STATE_OPERATING:
-		kvm_s390_vcpu_start(vcpu);
+		rc = kvm_s390_vcpu_start(vcpu);
 		break;
 	case KVM_MP_STATE_LOAD:
+		if (!kvm_s390_pv_cpu_is_protected(vcpu)) {
+			rc = -ENXIO;
+			break;
+		}
+		rc = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_OPR_LOAD);
+		break;
 	case KVM_MP_STATE_CHECK_STOP:
-		/* fall through - CHECK_STOP and LOAD are not supported yet */
+		fallthrough;	/* CHECK_STOP and LOAD are not supported yet */
 	default:
 		rc = -ENXIO;
 	}
@@ -3844,9 +4112,11 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 	return vcpu_post_run_fault_in_sie(vcpu);
 }
 
+#define PSW_INT_MASK (PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_MCHECK)
 static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
 	int rc, exit_reason;
+	struct sie_page *sie_page = (struct sie_page *)vcpu->arch.sie_block;
 
 	/*
 	 * We try to hold kvm->srcu during most of vcpu_run (except when run-
@@ -3868,8 +4138,28 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 		guest_enter_irqoff();
 		__disable_cpu_timer_accounting(vcpu);
 		local_irq_enable();
+		if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+			memcpy(sie_page->pv_grregs,
+			       vcpu->run->s.regs.gprs,
+			       sizeof(sie_page->pv_grregs));
+		}
 		exit_reason = sie64a(vcpu->arch.sie_block,
 				     vcpu->run->s.regs.gprs);
+		if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+			memcpy(vcpu->run->s.regs.gprs,
+			       sie_page->pv_grregs,
+			       sizeof(sie_page->pv_grregs));
+			/*
+			 * We're not allowed to inject interrupts on intercepts
+			 * that leave the guest state in an "in-between" state
+			 * where the next SIE entry will do a continuation.
+			 * Fence interrupts in our "internal" PSW.
+			 */
+			if (vcpu->arch.sie_block->icptcode == ICPT_PV_INSTR ||
+			    vcpu->arch.sie_block->icptcode == ICPT_PV_PREF) {
+				vcpu->arch.sie_block->gpsw.mask &= ~PSW_INT_MASK;
+			}
+		}
 		local_irq_disable();
 		__enable_cpu_timer_accounting(vcpu);
 		guest_exit_irqoff();
@@ -3883,7 +4173,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
 	return rc;
 }
 
-static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static void sync_regs_fmt2(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct runtime_instr_cb *riccb;
 	struct gs_cb *gscb;
@@ -3892,16 +4182,7 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	gscb = (struct gs_cb *) &kvm_run->s.regs.gscb;
 	vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
 	vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
-	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX)
-		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
-	if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
-		memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
-		/* some control register changes require a tlb flush */
-		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
-	}
 	if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
-		kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm);
-		vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
 		vcpu->arch.sie_block->todpr = kvm_run->s.regs.todpr;
 		vcpu->arch.sie_block->pp = kvm_run->s.regs.pp;
 		vcpu->arch.sie_block->gbea = kvm_run->s.regs.gbea;
@@ -3942,6 +4223,36 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
 		vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
 	}
+	if (MACHINE_HAS_GS) {
+		preempt_disable();
+		__ctl_set_bit(2, 4);
+		if (current->thread.gs_cb) {
+			vcpu->arch.host_gscb = current->thread.gs_cb;
+			save_gs_cb(vcpu->arch.host_gscb);
+		}
+		if (vcpu->arch.gs_enabled) {
+			current->thread.gs_cb = (struct gs_cb *)
+						&vcpu->run->s.regs.gscb;
+			restore_gs_cb(current->thread.gs_cb);
+		}
+		preempt_enable();
+	}
+	/* SIE will load etoken directly from SDNX and therefore kvm_run */
+}
+
+static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	if (kvm_run->kvm_dirty_regs & KVM_SYNC_PREFIX)
+		kvm_s390_set_prefix(vcpu, kvm_run->s.regs.prefix);
+	if (kvm_run->kvm_dirty_regs & KVM_SYNC_CRS) {
+		memcpy(&vcpu->arch.sie_block->gcr, &kvm_run->s.regs.crs, 128);
+		/* some control register changes require a tlb flush */
+		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+	}
+	if (kvm_run->kvm_dirty_regs & KVM_SYNC_ARCH0) {
+		kvm_s390_set_cpu_timer(vcpu, kvm_run->s.regs.cputm);
+		vcpu->arch.sie_block->ckc = kvm_run->s.regs.ckc;
+	}
 	save_access_regs(vcpu->arch.host_acrs);
 	restore_access_regs(vcpu->run->s.regs.acrs);
 	/* save host (userspace) fprs/vrs */
@@ -3956,23 +4267,47 @@ static void sync_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (test_fp_ctl(current->thread.fpu.fpc))
 		/* User space provided an invalid FPC, let's clear it */
 		current->thread.fpu.fpc = 0;
+
+	/* Sync fmt2 only data */
+	if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) {
+		sync_regs_fmt2(vcpu, kvm_run);
+	} else {
+		/*
+		 * In several places we have to modify our internal view to
+		 * not do things that are disallowed by the ultravisor. For
+		 * example we must not inject interrupts after specific exits
+		 * (e.g. 112 prefix page not secure). We do this by turning
+		 * off the machine check, external and I/O interrupt bits
+		 * of our PSW copy. To avoid getting validity intercepts, we
+		 * do only accept the condition code from userspace.
+		 */
+		vcpu->arch.sie_block->gpsw.mask &= ~PSW_MASK_CC;
+		vcpu->arch.sie_block->gpsw.mask |= kvm_run->psw_mask &
+						   PSW_MASK_CC;
+	}
+
+	kvm_run->kvm_dirty_regs = 0;
+}
+
+static void store_regs_fmt2(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr;
+	kvm_run->s.regs.pp = vcpu->arch.sie_block->pp;
+	kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea;
+	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 	if (MACHINE_HAS_GS) {
-		preempt_disable();
 		__ctl_set_bit(2, 4);
-		if (current->thread.gs_cb) {
-			vcpu->arch.host_gscb = current->thread.gs_cb;
-			save_gs_cb(vcpu->arch.host_gscb);
-		}
-		if (vcpu->arch.gs_enabled) {
-			current->thread.gs_cb = (struct gs_cb *)
-						&vcpu->run->s.regs.gscb;
-			restore_gs_cb(current->thread.gs_cb);
-		}
+		if (vcpu->arch.gs_enabled)
+			save_gs_cb(current->thread.gs_cb);
+		preempt_disable();
+		current->thread.gs_cb = vcpu->arch.host_gscb;
+		restore_gs_cb(vcpu->arch.host_gscb);
 		preempt_enable();
+		if (!vcpu->arch.host_gscb)
+			__ctl_clear_bit(2, 4);
+		vcpu->arch.host_gscb = NULL;
 	}
-	/* SIE will load etoken directly from SDNX and therefore kvm_run */
-
-	kvm_run->kvm_dirty_regs = 0;
+	/* SIE will save etoken directly into SDNX and therefore kvm_run */
 }
 
 static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
@@ -3983,13 +4318,9 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	memcpy(&kvm_run->s.regs.crs, &vcpu->arch.sie_block->gcr, 128);
 	kvm_run->s.regs.cputm = kvm_s390_get_cpu_timer(vcpu);
 	kvm_run->s.regs.ckc = vcpu->arch.sie_block->ckc;
-	kvm_run->s.regs.todpr = vcpu->arch.sie_block->todpr;
-	kvm_run->s.regs.pp = vcpu->arch.sie_block->pp;
-	kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea;
 	kvm_run->s.regs.pft = vcpu->arch.pfault_token;
 	kvm_run->s.regs.pfs = vcpu->arch.pfault_select;
 	kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
-	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 	save_access_regs(vcpu->run->s.regs.acrs);
 	restore_access_regs(vcpu->arch.host_acrs);
 	/* Save guest register state */
@@ -3998,19 +4329,8 @@ static void store_regs(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	/* Restore will be done lazily at return */
 	current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
 	current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
-	if (MACHINE_HAS_GS) {
-		__ctl_set_bit(2, 4);
-		if (vcpu->arch.gs_enabled)
-			save_gs_cb(current->thread.gs_cb);
-		preempt_disable();
-		current->thread.gs_cb = vcpu->arch.host_gscb;
-		restore_gs_cb(vcpu->arch.host_gscb);
-		preempt_enable();
-		if (!vcpu->arch.host_gscb)
-			__ctl_clear_bit(2, 4);
-		vcpu->arch.host_gscb = NULL;
-	}
-	/* SIE will save etoken directly into SDNX and therefore kvm_run */
+	if (likely(!kvm_s390_pv_cpu_is_protected(vcpu)))
+		store_regs_fmt2(vcpu, kvm_run);
 }
 
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
@@ -4034,6 +4354,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	kvm_sigset_activate(vcpu);
 
+	/*
+	 * no need to check the return value of vcpu_start as it can only have
+	 * an error for protvirt, but protvirt means user cpu state
+	 */
 	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm)) {
 		kvm_s390_vcpu_start(vcpu);
 	} else if (is_vcpu_stopped(vcpu)) {
@@ -4171,18 +4495,27 @@ static void __enable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
 	kvm_s390_sync_request(KVM_REQ_ENABLE_IBS, vcpu);
 }
 
-void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
+int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
 {
-	int i, online_vcpus, started_vcpus = 0;
+	int i, online_vcpus, r = 0, started_vcpus = 0;
 
 	if (!is_vcpu_stopped(vcpu))
-		return;
+		return 0;
 
 	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 1);
 	/* Only one cpu at a time may enter/leave the STOPPED state. */
 	spin_lock(&vcpu->kvm->arch.start_stop_lock);
 	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);
 
+	/* Let's tell the UV that we want to change into the operating state */
+	if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+		r = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_OPR);
+		if (r) {
+			spin_unlock(&vcpu->kvm->arch.start_stop_lock);
+			return r;
+		}
+	}
+
 	for (i = 0; i < online_vcpus; i++) {
 		if (!is_vcpu_stopped(vcpu->kvm->vcpus[i]))
 			started_vcpus++;
@@ -4202,27 +4535,43 @@ void kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
 
 	kvm_s390_clear_cpuflags(vcpu, CPUSTAT_STOPPED);
 	/*
+	 * The real PSW might have changed due to a RESTART interpreted by the
+	 * ultravisor. We block all interrupts and let the next sie exit
+	 * refresh our view.
+	 */
+	if (kvm_s390_pv_cpu_is_protected(vcpu))
+		vcpu->arch.sie_block->gpsw.mask &= ~PSW_INT_MASK;
+	/*
 	 * Another VCPU might have used IBS while we were offline.
 	 * Let's play safe and flush the VCPU at startup.
 	 */
 	kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
-	return;
+	return 0;
 }
 
-void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
+int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 {
-	int i, online_vcpus, started_vcpus = 0;
+	int i, online_vcpus, r = 0, started_vcpus = 0;
 	struct kvm_vcpu *started_vcpu = NULL;
 
 	if (is_vcpu_stopped(vcpu))
-		return;
+		return 0;
 
 	trace_kvm_s390_vcpu_start_stop(vcpu->vcpu_id, 0);
 	/* Only one cpu at a time may enter/leave the STOPPED state. */
 	spin_lock(&vcpu->kvm->arch.start_stop_lock);
 	online_vcpus = atomic_read(&vcpu->kvm->online_vcpus);
 
+	/* Let's tell the UV that we want to change into the stopped state */
+	if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+		r = kvm_s390_pv_set_cpu_state(vcpu, PV_CPU_STATE_STP);
+		if (r) {
+			spin_unlock(&vcpu->kvm->arch.start_stop_lock);
+			return r;
+		}
+	}
+
 	/* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
 	kvm_s390_clear_stop_irq(vcpu);
 
@@ -4245,7 +4594,7 @@ void kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
 	}
 
 	spin_unlock(&vcpu->kvm->arch.start_stop_lock);
-	return;
+	return 0;
 }
 
 static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
@@ -4272,12 +4621,40 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 	return r;
 }
 
+static long kvm_s390_guest_sida_op(struct kvm_vcpu *vcpu,
+				   struct kvm_s390_mem_op *mop)
+{
+	void __user *uaddr = (void __user *)mop->buf;
+	int r = 0;
+
+	if (mop->flags || !mop->size)
+		return -EINVAL;
+	if (mop->size + mop->sida_offset < mop->size)
+		return -EINVAL;
+	if (mop->size + mop->sida_offset > sida_size(vcpu->arch.sie_block))
+		return -E2BIG;
+
+	switch (mop->op) {
+	case KVM_S390_MEMOP_SIDA_READ:
+		if (copy_to_user(uaddr, (void *)(sida_origin(vcpu->arch.sie_block) +
+				 mop->sida_offset), mop->size))
+			r = -EFAULT;
+
+		break;
+	case KVM_S390_MEMOP_SIDA_WRITE:
+		if (copy_from_user((void *)(sida_origin(vcpu->arch.sie_block) +
+				   mop->sida_offset), uaddr, mop->size))
+			r = -EFAULT;
+		break;
+	}
+	return r;
+}
 static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
 				  struct kvm_s390_mem_op *mop)
 {
 	void __user *uaddr = (void __user *)mop->buf;
 	void *tmpbuf = NULL;
-	int r, srcu_idx;
+	int r = 0;
 	const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION
 				    | KVM_S390_MEMOP_F_CHECK_ONLY;
 
@@ -4287,14 +4664,15 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
 	if (mop->size > MEM_OP_MAX_SIZE)
 		return -E2BIG;
 
+	if (kvm_s390_pv_cpu_is_protected(vcpu))
+		return -EINVAL;
+
 	if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) {
 		tmpbuf = vmalloc(mop->size);
 		if (!tmpbuf)
 			return -ENOMEM;
 	}
 
-	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
-
 	switch (mop->op) {
 	case KVM_S390_MEMOP_LOGICAL_READ:
 		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
@@ -4320,12 +4698,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
 		}
 		r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
 		break;
-	default:
-		r = -EINVAL;
 	}
 
-	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
-
 	if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0)
 		kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
 
@@ -4333,6 +4707,31 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
 	return r;
 }
 
+static long kvm_s390_guest_memsida_op(struct kvm_vcpu *vcpu,
+				      struct kvm_s390_mem_op *mop)
+{
+	int r, srcu_idx;
+
+	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+
+	switch (mop->op) {
+	case KVM_S390_MEMOP_LOGICAL_READ:
+	case KVM_S390_MEMOP_LOGICAL_WRITE:
+		r = kvm_s390_guest_mem_op(vcpu, mop);
+		break;
+	case KVM_S390_MEMOP_SIDA_READ:
+	case KVM_S390_MEMOP_SIDA_WRITE:
+		/* we are locked against sida going away by the vcpu->mutex */
+		r = kvm_s390_guest_sida_op(vcpu, mop);
+		break;
+	default:
+		r = -EINVAL;
+	}
+
+	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
+	return r;
+}
+
 long kvm_arch_vcpu_async_ioctl(struct file *filp,
 			       unsigned int ioctl, unsigned long arg)
 {
@@ -4368,6 +4767,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	void __user *argp = (void __user *)arg;
 	int idx;
 	long r;
+	u16 rc, rrc;
 
 	vcpu_load(vcpu);
 
@@ -4389,18 +4789,40 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	case KVM_S390_CLEAR_RESET:
 		r = 0;
 		kvm_arch_vcpu_ioctl_clear_reset(vcpu);
+		if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+			r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu),
+					  UVC_CMD_CPU_RESET_CLEAR, &rc, &rrc);
+			VCPU_EVENT(vcpu, 3, "PROTVIRT RESET CLEAR VCPU: rc %x rrc %x",
+				   rc, rrc);
+		}
 		break;
 	case KVM_S390_INITIAL_RESET:
 		r = 0;
 		kvm_arch_vcpu_ioctl_initial_reset(vcpu);
+		if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+			r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu),
+					  UVC_CMD_CPU_RESET_INITIAL,
+					  &rc, &rrc);
+			VCPU_EVENT(vcpu, 3, "PROTVIRT RESET INITIAL VCPU: rc %x rrc %x",
+				   rc, rrc);
+		}
 		break;
 	case KVM_S390_NORMAL_RESET:
 		r = 0;
 		kvm_arch_vcpu_ioctl_normal_reset(vcpu);
+		if (kvm_s390_pv_cpu_is_protected(vcpu)) {
+			r = uv_cmd_nodata(kvm_s390_pv_cpu_get_handle(vcpu),
+					  UVC_CMD_CPU_RESET, &rc, &rrc);
+			VCPU_EVENT(vcpu, 3, "PROTVIRT RESET NORMAL VCPU: rc %x rrc %x",
+				   rc, rrc);
+		}
 		break;
 	case KVM_SET_ONE_REG:
 	case KVM_GET_ONE_REG: {
 		struct kvm_one_reg reg;
+		r = -EINVAL;
+		if (kvm_s390_pv_cpu_is_protected(vcpu))
+			break;
 		r = -EFAULT;
 		if (copy_from_user(&reg, argp, sizeof(reg)))
 			break;
@@ -4463,7 +4885,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_s390_mem_op mem_op;
 
 		if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0)
-			r = kvm_s390_guest_mem_op(vcpu, &mem_op);
+			r = kvm_s390_guest_memsida_op(vcpu, &mem_op);
 		else
 			r = -EFAULT;
 		break;
@@ -4523,12 +4945,6 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
-int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
-			    unsigned long npages)
-{
-	return 0;
-}
-
 /* Section: memory related */
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *memslot,
@@ -4549,12 +4965,15 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
 		return -EINVAL;
 
+	/* When we are protected, we should not change the memory slots */
+	if (kvm_s390_pv_get_handle(kvm))
+		return -EINVAL;
 	return 0;
 }
 
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				const struct kvm_userspace_memory_region *mem,
-				const struct kvm_memory_slot *old,
+				struct kvm_memory_slot *old,
 				const struct kvm_memory_slot *new,
 				enum kvm_mr_change change)
 {
@@ -4570,7 +4989,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 					old->npages * PAGE_SIZE);
 		if (rc)
 			break;
-		/* FALLTHROUGH */
+		fallthrough;
 	case KVM_MR_CREATE:
 		rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
 				      mem->guest_phys_addr, mem->memory_size);