1 files changed, 209 insertions, 140 deletions

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index e4890e04b210..1eeb9ae57879 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -256,17 +256,6 @@ debug_info_t *kvm_s390_dbf;
 debug_info_t *kvm_s390_dbf_uv;
 
 /* Section: not file related */
-int kvm_arch_hardware_enable(void)
-{
-	/* every s390 is virtualization enabled ;-) */
-	return 0;
-}
-
-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);
@@ -329,25 +318,6 @@ static struct notifier_block kvm_clock_notifier = {
 	.notifier_call = kvm_clock_sync,
 };
 
-int kvm_arch_hardware_setup(void *opaque)
-{
-	gmap_notifier.notifier_call = kvm_gmap_notifier;
-	gmap_register_pte_notifier(&gmap_notifier);
-	vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier;
-	gmap_register_pte_notifier(&vsie_gmap_notifier);
-	atomic_notifier_chain_register(&s390_epoch_delta_notifier,
-				       &kvm_clock_notifier);
-	return 0;
-}
-
-void kvm_arch_hardware_unsetup(void)
-{
-	gmap_unregister_pte_notifier(&gmap_notifier);
-	gmap_unregister_pte_notifier(&vsie_gmap_notifier);
-	atomic_notifier_chain_unregister(&s390_epoch_delta_notifier,
-					 &kvm_clock_notifier);
-}
-
 static void allow_cpu_feat(unsigned long nr)
 {
 	set_bit_inv(nr, kvm_s390_available_cpu_feat);
@@ -385,7 +355,7 @@ static __always_inline void __insn32_query(unsigned int opcode, u8 *query)
 #define INSN_SORTL 0xb938
 #define INSN_DFLTCC 0xb939
 
-static void kvm_s390_cpu_feat_init(void)
+static void __init kvm_s390_cpu_feat_init(void)
 {
 	int i;
 
@@ -488,7 +458,7 @@ static void kvm_s390_cpu_feat_init(void)
 	 */
 }
 
-int kvm_arch_init(void *opaque)
+static int __init __kvm_s390_init(void)
 {
 	int rc = -ENOMEM;
 
@@ -498,11 +468,11 @@ int kvm_arch_init(void *opaque)
 
 	kvm_s390_dbf_uv = debug_register("kvm-uv", 32, 1, 7 * sizeof(long));
 	if (!kvm_s390_dbf_uv)
-		goto out;
+		goto err_kvm_uv;
 
 	if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view) ||
 	    debug_register_view(kvm_s390_dbf_uv, &debug_sprintf_view))
-		goto out;
+		goto err_debug_view;
 
 	kvm_s390_cpu_feat_init();
 
@@ -510,30 +480,49 @@ int kvm_arch_init(void *opaque)
 	rc = kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
 	if (rc) {
 		pr_err("A FLIC registration call failed with rc=%d\n", rc);
-		goto out;
+		goto err_flic;
 	}
 
 	if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) {
 		rc = kvm_s390_pci_init();
 		if (rc) {
 			pr_err("Unable to allocate AIFT for PCI\n");
-			goto out;
+			goto err_pci;
 		}
 	}
 
 	rc = kvm_s390_gib_init(GAL_ISC);
 	if (rc)
-		goto out;
+		goto err_gib;
+
+	gmap_notifier.notifier_call = kvm_gmap_notifier;
+	gmap_register_pte_notifier(&gmap_notifier);
+	vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier;
+	gmap_register_pte_notifier(&vsie_gmap_notifier);
+	atomic_notifier_chain_register(&s390_epoch_delta_notifier,
+				       &kvm_clock_notifier);
 
 	return 0;
 
-out:
-	kvm_arch_exit();
+err_gib:
+	if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
+		kvm_s390_pci_exit();
+err_pci:
+err_flic:
+err_debug_view:
+	debug_unregister(kvm_s390_dbf_uv);
+err_kvm_uv:
+	debug_unregister(kvm_s390_dbf);
 	return rc;
 }
 
-void kvm_arch_exit(void)
+static void __kvm_s390_exit(void)
 {
+	gmap_unregister_pte_notifier(&gmap_notifier);
+	gmap_unregister_pte_notifier(&vsie_gmap_notifier);
+	atomic_notifier_chain_unregister(&s390_epoch_delta_notifier,
+					 &kvm_clock_notifier);
+
 	kvm_s390_gib_destroy();
 	if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
 		kvm_s390_pci_exit();
@@ -584,7 +573,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_VCPU_RESETS:
 	case KVM_CAP_SET_GUEST_DEBUG:
 	case KVM_CAP_S390_DIAG318:
-	case KVM_CAP_S390_MEM_OP_EXTENSION:
+	case KVM_CAP_IRQFD_RESAMPLE:
 		r = 1;
 		break;
 	case KVM_CAP_SET_GUEST_DEBUG2:
@@ -598,6 +587,15 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_MEM_OP:
 		r = MEM_OP_MAX_SIZE;
 		break;
+	case KVM_CAP_S390_MEM_OP_EXTENSION:
+		/*
+		 * Flag bits indicating which extensions are supported.
+		 * If r > 0, the base extension must also be supported/indicated,
+		 * in order to maintain backwards compatibility.
+		 */
+		r = KVM_S390_MEMOP_EXTENSION_CAP_BASE |
+		    KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG;
+		break;
 	case KVM_CAP_NR_VCPUS:
 	case KVM_CAP_MAX_VCPUS:
 	case KVM_CAP_MAX_VCPU_ID:
@@ -2764,41 +2762,33 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
 	return r;
 }
 
-static bool access_key_invalid(u8 access_key)
-{
-	return access_key > 0xf;
-}
-
-static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop)
+static int mem_op_validate_common(struct kvm_s390_mem_op *mop, u64 supported_flags)
 {
-	void __user *uaddr = (void __user *)mop->buf;
-	u64 supported_flags;
-	void *tmpbuf = NULL;
-	int r, srcu_idx;
-
-	supported_flags = KVM_S390_MEMOP_F_SKEY_PROTECTION
-			  | KVM_S390_MEMOP_F_CHECK_ONLY;
 	if (mop->flags & ~supported_flags || !mop->size)
 		return -EINVAL;
 	if (mop->size > MEM_OP_MAX_SIZE)
 		return -E2BIG;
-	/*
-	 * This is technically a heuristic only, if the kvm->lock is not
-	 * taken, it is not guaranteed that the vm is/remains non-protected.
-	 * This is ok from a kernel perspective, wrongdoing is detected
-	 * on the access, -EFAULT is returned and the vm may crash the
-	 * next time it accesses the memory in question.
-	 * There is no sane usecase to do switching and a memop on two
-	 * different CPUs at the same time.
-	 */
-	if (kvm_s390_pv_get_handle(kvm))
-		return -EINVAL;
 	if (mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) {
-		if (access_key_invalid(mop->key))
+		if (mop->key > 0xf)
 			return -EINVAL;
 	} else {
 		mop->key = 0;
 	}
+	return 0;
+}
+
+static int kvm_s390_vm_mem_op_abs(struct kvm *kvm, struct kvm_s390_mem_op *mop)
+{
+	void __user *uaddr = (void __user *)mop->buf;
+	enum gacc_mode acc_mode;
+	void *tmpbuf = NULL;
+	int r, srcu_idx;
+
+	r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_SKEY_PROTECTION |
+					KVM_S390_MEMOP_F_CHECK_ONLY);
+	if (r)
+		return r;
+
 	if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) {
 		tmpbuf = vmalloc(mop->size);
 		if (!tmpbuf)
@@ -2812,35 +2802,25 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop)
 		goto out_unlock;
 	}
 
-	switch (mop->op) {
-	case KVM_S390_MEMOP_ABSOLUTE_READ: {
-		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
-			r = check_gpa_range(kvm, mop->gaddr, mop->size, GACC_FETCH, mop->key);
-		} else {
-			r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf,
-						      mop->size, GACC_FETCH, mop->key);
-			if (r == 0) {
-				if (copy_to_user(uaddr, tmpbuf, mop->size))
-					r = -EFAULT;
-			}
-		}
-		break;
+	acc_mode = mop->op == KVM_S390_MEMOP_ABSOLUTE_READ ? GACC_FETCH : GACC_STORE;
+	if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
+		r = check_gpa_range(kvm, mop->gaddr, mop->size, acc_mode, mop->key);
+		goto out_unlock;
 	}
-	case KVM_S390_MEMOP_ABSOLUTE_WRITE: {
-		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
-			r = check_gpa_range(kvm, mop->gaddr, mop->size, GACC_STORE, mop->key);
-		} else {
-			if (copy_from_user(tmpbuf, uaddr, mop->size)) {
-				r = -EFAULT;
-				break;
-			}
-			r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf,
-						      mop->size, GACC_STORE, mop->key);
+	if (acc_mode == GACC_FETCH) {
+		r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf,
+					      mop->size, GACC_FETCH, mop->key);
+		if (r)
+			goto out_unlock;
+		if (copy_to_user(uaddr, tmpbuf, mop->size))
+			r = -EFAULT;
+	} else {
+		if (copy_from_user(tmpbuf, uaddr, mop->size)) {
+			r = -EFAULT;
+			goto out_unlock;
 		}
-		break;
-	}
-	default:
-		r = -EINVAL;
+		r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf,
+					      mop->size, GACC_STORE, mop->key);
 	}
 
 out_unlock:
@@ -2850,6 +2830,75 @@ out_unlock:
 	return r;
 }
 
+static int kvm_s390_vm_mem_op_cmpxchg(struct kvm *kvm, struct kvm_s390_mem_op *mop)
+{
+	void __user *uaddr = (void __user *)mop->buf;
+	void __user *old_addr = (void __user *)mop->old_addr;
+	union {
+		__uint128_t quad;
+		char raw[sizeof(__uint128_t)];
+	} old = { .quad = 0}, new = { .quad = 0 };
+	unsigned int off_in_quad = sizeof(new) - mop->size;
+	int r, srcu_idx;
+	bool success;
+
+	r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_SKEY_PROTECTION);
+	if (r)
+		return r;
+	/*
+	 * This validates off_in_quad. Checking that size is a power
+	 * of two is not necessary, as cmpxchg_guest_abs_with_key
+	 * takes care of that
+	 */
+	if (mop->size > sizeof(new))
+		return -EINVAL;
+	if (copy_from_user(&new.raw[off_in_quad], uaddr, mop->size))
+		return -EFAULT;
+	if (copy_from_user(&old.raw[off_in_quad], old_addr, mop->size))
+		return -EFAULT;
+
+	srcu_idx = srcu_read_lock(&kvm->srcu);
+
+	if (kvm_is_error_gpa(kvm, mop->gaddr)) {
+		r = PGM_ADDRESSING;
+		goto out_unlock;
+	}
+
+	r = cmpxchg_guest_abs_with_key(kvm, mop->gaddr, mop->size, &old.quad,
+				       new.quad, mop->key, &success);
+	if (!success && copy_to_user(old_addr, &old.raw[off_in_quad], mop->size))
+		r = -EFAULT;
+
+out_unlock:
+	srcu_read_unlock(&kvm->srcu, srcu_idx);
+	return r;
+}
+
+static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop)
+{
+	/*
+	 * This is technically a heuristic only, if the kvm->lock is not
+	 * taken, it is not guaranteed that the vm is/remains non-protected.
+	 * This is ok from a kernel perspective, wrongdoing is detected
+	 * on the access, -EFAULT is returned and the vm may crash the
+	 * next time it accesses the memory in question.
+	 * There is no sane usecase to do switching and a memop on two
+	 * different CPUs at the same time.
+	 */
+	if (kvm_s390_pv_get_handle(kvm))
+		return -EINVAL;
+
+	switch (mop->op) {
+	case KVM_S390_MEMOP_ABSOLUTE_READ:
+	case KVM_S390_MEMOP_ABSOLUTE_WRITE:
+		return kvm_s390_vm_mem_op_abs(kvm, mop);
+	case KVM_S390_MEMOP_ABSOLUTE_CMPXCHG:
+		return kvm_s390_vm_mem_op_cmpxchg(kvm, mop);
+	default:
+		return -EINVAL;
+	}
+}
+
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg)
 {
@@ -5249,62 +5298,54 @@ static long kvm_s390_vcpu_mem_op(struct kvm_vcpu *vcpu,
 				 struct kvm_s390_mem_op *mop)
 {
 	void __user *uaddr = (void __user *)mop->buf;
+	enum gacc_mode acc_mode;
 	void *tmpbuf = NULL;
-	int r = 0;
-	const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION
-				    | KVM_S390_MEMOP_F_CHECK_ONLY
-				    | KVM_S390_MEMOP_F_SKEY_PROTECTION;
+	int r;
 
-	if (mop->flags & ~supported_flags || mop->ar >= NUM_ACRS || !mop->size)
+	r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_INJECT_EXCEPTION |
+					KVM_S390_MEMOP_F_CHECK_ONLY |
+					KVM_S390_MEMOP_F_SKEY_PROTECTION);
+	if (r)
+		return r;
+	if (mop->ar >= NUM_ACRS)
 		return -EINVAL;
-	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_SKEY_PROTECTION) {
-		if (access_key_invalid(mop->key))
-			return -EINVAL;
-	} else {
-		mop->key = 0;
-	}
 	if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) {
 		tmpbuf = vmalloc(mop->size);
 		if (!tmpbuf)
 			return -ENOMEM;
 	}
 
-	switch (mop->op) {
-	case KVM_S390_MEMOP_LOGICAL_READ:
-		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
-			r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size,
-					    GACC_FETCH, mop->key);
-			break;
-		}
+	acc_mode = mop->op == KVM_S390_MEMOP_LOGICAL_READ ? GACC_FETCH : GACC_STORE;
+	if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
+		r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size,
+				    acc_mode, mop->key);
+		goto out_inject;
+	}
+	if (acc_mode == GACC_FETCH) {
 		r = read_guest_with_key(vcpu, mop->gaddr, mop->ar, tmpbuf,
 					mop->size, mop->key);
-		if (r == 0) {
-			if (copy_to_user(uaddr, tmpbuf, mop->size))
-				r = -EFAULT;
-		}
-		break;
-	case KVM_S390_MEMOP_LOGICAL_WRITE:
-		if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
-			r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size,
-					    GACC_STORE, mop->key);
-			break;
+		if (r)
+			goto out_inject;
+		if (copy_to_user(uaddr, tmpbuf, mop->size)) {
+			r = -EFAULT;
+			goto out_free;
 		}
+	} else {
 		if (copy_from_user(tmpbuf, uaddr, mop->size)) {
 			r = -EFAULT;
-			break;
+			goto out_free;
 		}
 		r = write_guest_with_key(vcpu, mop->gaddr, mop->ar, tmpbuf,
 					 mop->size, mop->key);
-		break;
 	}
 
+out_inject:
 	if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0)
 		kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
 
+out_free:
 	vfree(tmpbuf);
 	return r;
 }
@@ -5633,23 +5674,40 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	if (kvm_s390_pv_get_handle(kvm))
 		return -EINVAL;
 
-	if (change == KVM_MR_DELETE || change == KVM_MR_FLAGS_ONLY)
-		return 0;
+	if (change != KVM_MR_DELETE && change != KVM_MR_FLAGS_ONLY) {
+		/*
+		 * A few sanity checks. We can have memory slots which have to be
+		 * located/ended at a segment boundary (1MB). The memory in userland is
+		 * ok to be fragmented into various different vmas. It is okay to mmap()
+		 * and munmap() stuff in this slot after doing this call at any time
+		 */
 
-	/* A few sanity checks. We can have memory slots which have to be
-	   located/ended at a segment boundary (1MB). The memory in userland is
-	   ok to be fragmented into various different vmas. It is okay to mmap()
-	   and munmap() stuff in this slot after doing this call at any time */
+		if (new->userspace_addr & 0xffffful)
+			return -EINVAL;
 
-	if (new->userspace_addr & 0xffffful)
-		return -EINVAL;
+		size = new->npages * PAGE_SIZE;
+		if (size & 0xffffful)
+			return -EINVAL;
 
-	size = new->npages * PAGE_SIZE;
-	if (size & 0xffffful)
-		return -EINVAL;
+		if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit)
+			return -EINVAL;
+	}
 
-	if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit)
-		return -EINVAL;
+	if (!kvm->arch.migration_mode)
+		return 0;
+
+	/*
+	 * Turn off migration mode when:
+	 * - userspace creates a new memslot with dirty logging off,
+	 * - userspace modifies an existing memslot (MOVE or FLAGS_ONLY) and
+	 *   dirty logging is turned off.
+	 * Migration mode expects dirty page logging being enabled to store
+	 * its dirty bitmap.
+	 */
+	if (change != KVM_MR_DELETE &&
+	    !(new->flags & KVM_MEM_LOG_DIRTY_PAGES))
+		WARN(kvm_s390_vm_stop_migration(kvm),
+		     "Failed to stop migration mode");
 
 	return 0;
 }
@@ -5696,7 +5754,7 @@ static inline unsigned long nonhyp_mask(int i)
 
 static int __init kvm_s390_init(void)
 {
-	int i;
+	int i, r;
 
 	if (!sclp.has_sief2) {
 		pr_info("SIE is not available\n");
@@ -5712,12 +5770,23 @@ static int __init kvm_s390_init(void)
 		kvm_s390_fac_base[i] |=
 			stfle_fac_list[i] & nonhyp_mask(i);
 
-	return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	r = __kvm_s390_init();
+	if (r)
+		return r;
+
+	r = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+	if (r) {
+		__kvm_s390_exit();
+		return r;
+	}
+	return 0;
 }
 
 static void __exit kvm_s390_exit(void)
 {
 	kvm_exit();
+
+	__kvm_s390_exit();
 }
 
 module_init(kvm_s390_init);