1 files changed, 340 insertions, 17 deletions

diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 7cb7799a0acb..e032ebbf51b9 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -18,6 +18,29 @@
 #include <linux/mmu_notifier.h>
 #include "kvm-s390.h"
 
+/**
+ * struct pv_vm_to_be_destroyed - Represents a protected VM that needs to
+ * be destroyed
+ *
+ * @list: list head for the list of leftover VMs
+ * @old_gmap_table: the gmap table of the leftover protected VM
+ * @handle: the handle of the leftover protected VM
+ * @stor_var: pointer to the variable storage of the leftover protected VM
+ * @stor_base: address of the base storage of the leftover protected VM
+ *
+ * Represents a protected VM that is still registered with the Ultravisor,
+ * but which does not correspond any longer to an active KVM VM. It should
+ * be destroyed at some point later, either asynchronously or when the
+ * process terminates.
+ */
+struct pv_vm_to_be_destroyed {
+	struct list_head list;
+	unsigned long old_gmap_table;
+	u64 handle;
+	void *stor_var;
+	unsigned long stor_base;
+};
+
 static void kvm_s390_clear_pv_state(struct kvm *kvm)
 {
 	kvm->arch.pv.handle = 0;
@@ -44,7 +67,7 @@ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
 		free_pages(vcpu->arch.pv.stor_base,
 			   get_order(uv_info.guest_cpu_stor_len));
 
-	free_page(sida_origin(vcpu->arch.sie_block));
+	free_page((unsigned long)sida_addr(vcpu->arch.sie_block));
 	vcpu->arch.sie_block->pv_handle_cpu = 0;
 	vcpu->arch.sie_block->pv_handle_config = 0;
 	memset(&vcpu->arch.pv, 0, sizeof(vcpu->arch.pv));
@@ -66,6 +89,7 @@ int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
 		.header.cmd = UVC_CMD_CREATE_SEC_CPU,
 		.header.len = sizeof(uvcb),
 	};
+	void *sida_addr;
 	int cc;
 
 	if (kvm_s390_pv_cpu_get_handle(vcpu))
@@ -79,16 +103,17 @@ int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
 	/* Input */
 	uvcb.guest_handle = kvm_s390_pv_get_handle(vcpu->kvm);
 	uvcb.num = vcpu->arch.sie_block->icpua;
-	uvcb.state_origin = (u64)vcpu->arch.sie_block;
-	uvcb.stor_origin = (u64)vcpu->arch.pv.stor_base;
+	uvcb.state_origin = virt_to_phys(vcpu->arch.sie_block);
+	uvcb.stor_origin = virt_to_phys((void *)vcpu->arch.pv.stor_base);
 
 	/* Alloc Secure Instruction Data Area Designation */
-	vcpu->arch.sie_block->sidad = __get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
-	if (!vcpu->arch.sie_block->sidad) {
+	sida_addr = (void *)__get_free_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	if (!sida_addr) {
 		free_pages(vcpu->arch.pv.stor_base,
 			   get_order(uv_info.guest_cpu_stor_len));
 		return -ENOMEM;
 	}
+	vcpu->arch.sie_block->sidad = virt_to_phys(sida_addr);
 
 	cc = uv_call(0, (u64)&uvcb);
 	*rc = uvcb.header.rc;
@@ -159,23 +184,192 @@ out_err:
 	return -ENOMEM;
 }
 
-/* this should not fail, but if it does, we must not free the donated memory */
-int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
+/**
+ * kvm_s390_pv_dispose_one_leftover - Clean up one leftover protected VM.
+ * @kvm: the KVM that was associated with this leftover protected VM
+ * @leftover: details about the leftover protected VM that needs a clean up
+ * @rc: the RC code of the Destroy Secure Configuration UVC
+ * @rrc: the RRC code of the Destroy Secure Configuration UVC
+ *
+ * Destroy one leftover protected VM.
+ * On success, kvm->mm->context.protected_count will be decremented atomically
+ * and all other resources used by the VM will be freed.
+ *
+ * Return: 0 in case of success, otherwise 1
+ */
+static int kvm_s390_pv_dispose_one_leftover(struct kvm *kvm,
+					    struct pv_vm_to_be_destroyed *leftover,
+					    u16 *rc, u16 *rrc)
 {
 	int cc;
 
-	cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
-			   UVC_CMD_DESTROY_SEC_CONF, rc, rrc);
+	/* It used the destroy-fast UVC, nothing left to do here */
+	if (!leftover->handle)
+		goto done_fast;
+	cc = uv_cmd_nodata(leftover->handle, UVC_CMD_DESTROY_SEC_CONF, rc, rrc);
+	KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY LEFTOVER VM: rc %x rrc %x", *rc, *rrc);
+	WARN_ONCE(cc, "protvirt destroy leftover vm failed rc %x rrc %x", *rc, *rrc);
+	if (cc)
+		return cc;
+	/*
+	 * Intentionally leak unusable memory. If the UVC fails, the memory
+	 * used for the VM and its metadata is permanently unusable.
+	 * This can only happen in case of a serious KVM or hardware bug; it
+	 * is not expected to happen in normal operation.
+	 */
+	free_pages(leftover->stor_base, get_order(uv_info.guest_base_stor_len));
+	free_pages(leftover->old_gmap_table, CRST_ALLOC_ORDER);
+	vfree(leftover->stor_var);
+done_fast:
+	atomic_dec(&kvm->mm->context.protected_count);
+	return 0;
+}
+
+/**
+ * kvm_s390_destroy_lower_2g - Destroy the first 2GB of protected guest memory.
+ * @kvm: the VM whose memory is to be cleared.
+ *
+ * Destroy the first 2GB of guest memory, to avoid prefix issues after reboot.
+ * The CPUs of the protected VM need to be destroyed beforehand.
+ */
+static void kvm_s390_destroy_lower_2g(struct kvm *kvm)
+{
+	const unsigned long pages_2g = SZ_2G / PAGE_SIZE;
+	struct kvm_memory_slot *slot;
+	unsigned long len;
+	int srcu_idx;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+
+	/* Take the memslot containing guest absolute address 0 */
+	slot = gfn_to_memslot(kvm, 0);
+	/* Clear all slots or parts thereof that are below 2GB */
+	while (slot && slot->base_gfn < pages_2g) {
+		len = min_t(u64, slot->npages, pages_2g - slot->base_gfn) * PAGE_SIZE;
+		s390_uv_destroy_range(kvm->mm, slot->userspace_addr, slot->userspace_addr + len);
+		/* Take the next memslot */
+		slot = gfn_to_memslot(kvm, slot->base_gfn + slot->npages);
+	}
+
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+}
+
+static int kvm_s390_pv_deinit_vm_fast(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+	struct uv_cb_destroy_fast uvcb = {
+		.header.cmd = UVC_CMD_DESTROY_SEC_CONF_FAST,
+		.header.len = sizeof(uvcb),
+		.handle = kvm_s390_pv_get_handle(kvm),
+	};
+	int cc;
+
+	cc = uv_call_sched(0, (u64)&uvcb);
+	if (rc)
+		*rc = uvcb.header.rc;
+	if (rrc)
+		*rrc = uvcb.header.rrc;
 	WRITE_ONCE(kvm->arch.gmap->guest_handle, 0);
+	KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM FAST: rc %x rrc %x",
+		     uvcb.header.rc, uvcb.header.rrc);
+	WARN_ONCE(cc, "protvirt destroy vm fast failed handle %llx rc %x rrc %x",
+		  kvm_s390_pv_get_handle(kvm), uvcb.header.rc, uvcb.header.rrc);
+	/* Inteded memory leak on "impossible" error */
+	if (!cc)
+		kvm_s390_pv_dealloc_vm(kvm);
+	return cc ? -EIO : 0;
+}
+
+static inline bool is_destroy_fast_available(void)
+{
+	return test_bit_inv(BIT_UVC_CMD_DESTROY_SEC_CONF_FAST, uv_info.inst_calls_list);
+}
+
+/**
+ * kvm_s390_pv_set_aside - Set aside a protected VM for later teardown.
+ * @kvm: the VM
+ * @rc: return value for the RC field of the UVCB
+ * @rrc: return value for the RRC field of the UVCB
+ *
+ * Set aside the protected VM for a subsequent teardown. The VM will be able
+ * to continue immediately as a non-secure VM, and the information needed to
+ * properly tear down the protected VM is set aside. If another protected VM
+ * was already set aside without starting its teardown, this function will
+ * fail.
+ * The CPUs of the protected VM need to be destroyed beforehand.
+ *
+ * Context: kvm->lock needs to be held
+ *
+ * Return: 0 in case of success, -EINVAL if another protected VM was already set
+ * aside, -ENOMEM if the system ran out of memory.
+ */
+int kvm_s390_pv_set_aside(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+	struct pv_vm_to_be_destroyed *priv;
+	int res = 0;
+
+	lockdep_assert_held(&kvm->lock);
 	/*
-	 * if the mm still has a mapping, make all its pages accessible
-	 * before destroying the guest
+	 * If another protected VM was already prepared for teardown, refuse.
+	 * A normal deinitialization has to be performed instead.
 	 */
-	if (mmget_not_zero(kvm->mm)) {
-		s390_uv_destroy_range(kvm->mm, 0, TASK_SIZE);
-		mmput(kvm->mm);
+	if (kvm->arch.pv.set_aside)
+		return -EINVAL;
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	if (is_destroy_fast_available()) {
+		res = kvm_s390_pv_deinit_vm_fast(kvm, rc, rrc);
+	} else {
+		priv->stor_var = kvm->arch.pv.stor_var;
+		priv->stor_base = kvm->arch.pv.stor_base;
+		priv->handle = kvm_s390_pv_get_handle(kvm);
+		priv->old_gmap_table = (unsigned long)kvm->arch.gmap->table;
+		WRITE_ONCE(kvm->arch.gmap->guest_handle, 0);
+		if (s390_replace_asce(kvm->arch.gmap))
+			res = -ENOMEM;
 	}
 
+	if (res) {
+		kfree(priv);
+		return res;
+	}
+
+	kvm_s390_destroy_lower_2g(kvm);
+	kvm_s390_clear_pv_state(kvm);
+	kvm->arch.pv.set_aside = priv;
+
+	*rc = UVC_RC_EXECUTED;
+	*rrc = 42;
+	return 0;
+}
+
+/**
+ * kvm_s390_pv_deinit_vm - Deinitialize the current protected VM
+ * @kvm: the KVM whose protected VM needs to be deinitialized
+ * @rc: the RC code of the UVC
+ * @rrc: the RRC code of the UVC
+ *
+ * Deinitialize the current protected VM. This function will destroy and
+ * cleanup the current protected VM, but it will not cleanup the guest
+ * memory. This function should only be called when the protected VM has
+ * just been created and therefore does not have any guest memory, or when
+ * the caller cleans up the guest memory separately.
+ *
+ * This function should not fail, but if it does, the donated memory must
+ * not be freed.
+ *
+ * Context: kvm->lock needs to be held
+ *
+ * Return: 0 in case of success, otherwise -EIO
+ */
+int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+	int cc;
+
+	cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
+			   UVC_CMD_DESTROY_SEC_CONF, rc, rrc);
+	WRITE_ONCE(kvm->arch.gmap->guest_handle, 0);
 	if (!cc) {
 		atomic_dec(&kvm->mm->context.protected_count);
 		kvm_s390_pv_dealloc_vm(kvm);
@@ -189,11 +383,137 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 	return cc ? -EIO : 0;
 }
 
+/**
+ * kvm_s390_pv_deinit_cleanup_all - Clean up all protected VMs associated
+ * with a specific KVM.
+ * @kvm: the KVM to be cleaned up
+ * @rc: the RC code of the first failing UVC
+ * @rrc: the RRC code of the first failing UVC
+ *
+ * This function will clean up all protected VMs associated with a KVM.
+ * This includes the active one, the one prepared for deinitialization with
+ * kvm_s390_pv_set_aside, and any still pending in the need_cleanup list.
+ *
+ * Context: kvm->lock needs to be held unless being called from
+ * kvm_arch_destroy_vm.
+ *
+ * Return: 0 if all VMs are successfully cleaned up, otherwise -EIO
+ */
+int kvm_s390_pv_deinit_cleanup_all(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+	struct pv_vm_to_be_destroyed *cur;
+	bool need_zap = false;
+	u16 _rc, _rrc;
+	int cc = 0;
+
+	/* Make sure the counter does not reach 0 before calling s390_uv_destroy_range */
+	atomic_inc(&kvm->mm->context.protected_count);
+
+	*rc = 1;
+	/* If the current VM is protected, destroy it */
+	if (kvm_s390_pv_get_handle(kvm)) {
+		cc = kvm_s390_pv_deinit_vm(kvm, rc, rrc);
+		need_zap = true;
+	}
+
+	/* If a previous protected VM was set aside, put it in the need_cleanup list */
+	if (kvm->arch.pv.set_aside) {
+		list_add(kvm->arch.pv.set_aside, &kvm->arch.pv.need_cleanup);
+		kvm->arch.pv.set_aside = NULL;
+	}
+
+	/* Cleanup all protected VMs in the need_cleanup list */
+	while (!list_empty(&kvm->arch.pv.need_cleanup)) {
+		cur = list_first_entry(&kvm->arch.pv.need_cleanup, typeof(*cur), list);
+		need_zap = true;
+		if (kvm_s390_pv_dispose_one_leftover(kvm, cur, &_rc, &_rrc)) {
+			cc = 1;
+			/*
+			 * Only return the first error rc and rrc, so make
+			 * sure it is not overwritten. All destroys will
+			 * additionally be reported via KVM_UV_EVENT().
+			 */
+			if (*rc == UVC_RC_EXECUTED) {
+				*rc = _rc;
+				*rrc = _rrc;
+			}
+		}
+		list_del(&cur->list);
+		kfree(cur);
+	}
+
+	/*
+	 * If the mm still has a mapping, try to mark all its pages as
+	 * accessible. The counter should not reach zero before this
+	 * cleanup has been performed.
+	 */
+	if (need_zap && mmget_not_zero(kvm->mm)) {
+		s390_uv_destroy_range(kvm->mm, 0, TASK_SIZE);
+		mmput(kvm->mm);
+	}
+
+	/* Now the counter can safely reach 0 */
+	atomic_dec(&kvm->mm->context.protected_count);
+	return cc ? -EIO : 0;
+}
+
+/**
+ * kvm_s390_pv_deinit_aside_vm - Teardown a previously set aside protected VM.
+ * @kvm: the VM previously associated with the protected VM
+ * @rc: return value for the RC field of the UVCB
+ * @rrc: return value for the RRC field of the UVCB
+ *
+ * Tear down the protected VM that had been previously prepared for teardown
+ * using kvm_s390_pv_set_aside_vm. Ideally this should be called by
+ * userspace asynchronously from a separate thread.
+ *
+ * Context: kvm->lock must not be held.
+ *
+ * Return: 0 in case of success, -EINVAL if no protected VM had been
+ * prepared for asynchronous teardowm, -EIO in case of other errors.
+ */
+int kvm_s390_pv_deinit_aside_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+	struct pv_vm_to_be_destroyed *p;
+	int ret = 0;
+
+	lockdep_assert_not_held(&kvm->lock);
+	mutex_lock(&kvm->lock);
+	p = kvm->arch.pv.set_aside;
+	kvm->arch.pv.set_aside = NULL;
+	mutex_unlock(&kvm->lock);
+	if (!p)
+		return -EINVAL;
+
+	/* When a fatal signal is received, stop immediately */
+	if (s390_uv_destroy_range_interruptible(kvm->mm, 0, TASK_SIZE_MAX))
+		goto done;
+	if (kvm_s390_pv_dispose_one_leftover(kvm, p, rc, rrc))
+		ret = -EIO;
+	kfree(p);
+	p = NULL;
+done:
+	/*
+	 * p is not NULL if we aborted because of a fatal signal, in which
+	 * case queue the leftover for later cleanup.
+	 */
+	if (p) {
+		mutex_lock(&kvm->lock);
+		list_add(&p->list, &kvm->arch.pv.need_cleanup);
+		mutex_unlock(&kvm->lock);
+		/* Did not finish, but pretend things went well */
+		*rc = UVC_RC_EXECUTED;
+		*rrc = 42;
+	}
+	return ret;
+}
+
 static void kvm_s390_pv_mmu_notifier_release(struct mmu_notifier *subscription,
 					     struct mm_struct *mm)
 {
 	struct kvm *kvm = container_of(subscription, struct kvm, arch.pv.mmu_notifier);
 	u16 dummy;
+	int r;
 
 	/*
 	 * No locking is needed since this is the last thread of the last user of this
@@ -202,7 +522,9 @@ static void kvm_s390_pv_mmu_notifier_release(struct mmu_notifier *subscription,
 	 * unregistered. This means that if this notifier runs, then the
 	 * struct kvm is still valid.
 	 */
-	kvm_s390_cpus_from_pv(kvm, &dummy, &dummy);
+	r = kvm_s390_cpus_from_pv(kvm, &dummy, &dummy);
+	if (!r && is_destroy_fast_available() && kvm_s390_pv_get_handle(kvm))
+		kvm_s390_pv_deinit_vm_fast(kvm, &dummy, &dummy);
 }
 
 static const struct mmu_notifier_ops kvm_s390_pv_mmu_notifier_ops = {
@@ -226,8 +548,9 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
 	uvcb.guest_stor_origin = 0; /* MSO is 0 for KVM */
 	uvcb.guest_stor_len = kvm->arch.pv.guest_len;
 	uvcb.guest_asce = kvm->arch.gmap->asce;
-	uvcb.guest_sca = (unsigned long)kvm->arch.sca;
-	uvcb.conf_base_stor_origin = (u64)kvm->arch.pv.stor_base;
+	uvcb.guest_sca = virt_to_phys(kvm->arch.sca);
+	uvcb.conf_base_stor_origin =
+		virt_to_phys((void *)kvm->arch.pv.stor_base);
 	uvcb.conf_virt_stor_origin = (u64)kvm->arch.pv.stor_var;
 
 	cc = uv_call_sched(0, (u64)&uvcb);