[PATCH v8 20/22] KVM: s390: add KVM_S390_ZPCI_OP to manage guest zPCI devices

[Matthew Rosato <mjrosato@linux.ibm.com>]

The KVM_S390_ZPCI_OP ioctl provides a mechanism for managing
hardware-assisted virtualization features for s390x zPCI passthrough.
Add the first 2 operations, which can be used to enable/disable
the specified device for Adapter Event Notification interpretation.

Signed-off-by: Matthew Rosato <mjrosato@linux.ibm.com>
---
 Documentation/virt/kvm/api.rst | 46 ++++++++++++++++++
 arch/s390/kvm/kvm-s390.c       | 16 +++++++
 arch/s390/kvm/pci.c            | 85 ++++++++++++++++++++++++++++++++++
 arch/s390/kvm/pci.h            |  2 +
 include/uapi/linux/kvm.h       | 32 +++++++++++++
 5 files changed, 181 insertions(+)

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 4a900cdbc62e..321571ca6e56 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -5645,6 +5645,52 @@ enabled with ``arch_prctl()``, but this may change in the future.
 The offsets of the state save areas in struct kvm_xsave follow the contents
 of CPUID leaf 0xD on the host.
 
+4.135 KVM_S390_ZPCI_OP
+--------------------
+
+:Capability: KVM_CAP_S390_ZPCI_OP
+:Architectures: s390
+:Type: vm ioctl
+:Parameters: struct kvm_s390_zpci_op (in)
+:Returns: 0 on success, <0 on error
+
+Used to manage hardware-assisted virtualization features for zPCI devices.
+
+Parameters are specified via the following structure::
+
+  struct kvm_s390_zpci_op {
+	/* in */
+	__u32 fh;		/* target device */
+	__u8  op;		/* operation to perform */
+	__u8  pad[3];
+	union {
+		/* for KVM_S390_ZPCIOP_REG_AEN */
+		struct {
+			__u64 ibv;	/* Guest addr of interrupt bit vector */
+			__u64 sb;	/* Guest addr of summary bit */
+			__u32 flags;
+			__u32 noi;	/* Number of interrupts */
+			__u8 isc;	/* Guest interrupt subclass */
+			__u8 sbo;	/* Offset of guest summary bit vector */
+			__u16 pad;
+		} reg_aen;
+		__u64 reserved[8];
+	} u;
+  };
+
+The type of operation is specified in the "op" field.
+KVM_S390_ZPCIOP_REG_AEN is used to register the VM for adapter event
+notification interpretation, which will allow firmware delivery of adapter
+events directly to the vm, with KVM providing a backup delivery mechanism;
+KVM_S390_ZPCIOP_DEREG_AEN is used to subsequently disable interpretation of
+adapter event notifications.
+
+The target zPCI function must also be specified via the "fh" field.  For the
+KVM_S390_ZPCIOP_REG_AEN operation, additional information to establish firmware
+delivery must be provided via the "reg_aen" struct.
+
+The "pad" and "reserved" fields may be used for future extensions and should be
+set to 0s by userspace.
 
 5. The kvm_run structure
 ========================
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index b8dd1587c125..af96b613d7e7 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -618,6 +618,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_PROTECTED:
 		r = is_prot_virt_host();
 		break;
+	case KVM_CAP_S390_ZPCI_OP:
+		r = kvm_s390_pci_interp_allowed();
+		break;
 	default:
 		r = 0;
 	}
@@ -2633,6 +2636,19 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			r = -EFAULT;
 		break;
 	}
+	case KVM_S390_ZPCI_OP: {
+		struct kvm_s390_zpci_op args;
+
+		r = -EINVAL;
+		if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
+			break;
+		if (copy_from_user(&args, argp, sizeof(args))) {
+			r = -EFAULT;
+			break;
+		}
+		r = kvm_s390_pci_zpci_op(kvm, &args);
+		break;
+	}
 	default:
 		r = -ENOTTY;
 	}
diff --git a/arch/s390/kvm/pci.c b/arch/s390/kvm/pci.c
index 29166683998f..a7d4d8fbfc3c 100644
--- a/arch/s390/kvm/pci.c
+++ b/arch/s390/kvm/pci.c
@@ -590,6 +590,91 @@ void kvm_s390_pci_clear_list(struct kvm *kvm)
 	spin_unlock(&kvm->arch.kzdev_list_lock);
 }
 
+static struct zpci_dev *get_zdev_from_kvm_by_fh(struct kvm *kvm, u32 fh)
+{
+	struct zpci_dev *zdev = NULL;
+	struct kvm_zdev *kzdev;
+
+	spin_lock(&kvm->arch.kzdev_list_lock);
+	list_for_each_entry(kzdev, &kvm->arch.kzdev_list, entry) {
+		if (kzdev->zdev->fh == fh) {
+			zdev = kzdev->zdev;
+			break;
+		}
+	}
+	spin_unlock(&kvm->arch.kzdev_list_lock);
+
+	return zdev;
+}
+
+static int kvm_s390_pci_zpci_reg_aen(struct zpci_dev *zdev,
+				     struct kvm_s390_zpci_op *args)
+{
+	struct zpci_fib fib = {};
+	bool hostflag;
+
+	fib.fmt0.aibv = args->u.reg_aen.ibv;
+	fib.fmt0.isc = args->u.reg_aen.isc;
+	fib.fmt0.noi = args->u.reg_aen.noi;
+	if (args->u.reg_aen.sb != 0) {
+		fib.fmt0.aisb = args->u.reg_aen.sb;
+		fib.fmt0.aisbo = args->u.reg_aen.sbo;
+		fib.fmt0.sum = 1;
+	} else {
+		fib.fmt0.aisb = 0;
+		fib.fmt0.aisbo = 0;
+		fib.fmt0.sum = 0;
+	}
+
+	hostflag = !(args->u.reg_aen.flags & KVM_S390_ZPCIOP_REGAEN_HOST);
+	return kvm_s390_pci_aif_enable(zdev, &fib, hostflag);
+}
+
+int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args)
+{
+	struct kvm_zdev *kzdev;
+	struct zpci_dev *zdev;
+	int r;
+
+	zdev = get_zdev_from_kvm_by_fh(kvm, args->fh);
+	if (!zdev)
+		return -ENODEV;
+
+	mutex_lock(&zdev->kzdev_lock);
+	mutex_lock(&kvm->lock);
+
+	kzdev = zdev->kzdev;
+	if (!kzdev) {
+		r = -ENODEV;
+		goto out;
+	}
+	if (kzdev->kvm != kvm) {
+		r = -EPERM;
+		goto out;
+	}
+
+	switch (args->op) {
+	case KVM_S390_ZPCIOP_REG_AEN:
+		/* Fail on unknown flags */
+		if (args->u.reg_aen.flags & ~KVM_S390_ZPCIOP_REGAEN_HOST) {
+			r = -EINVAL;
+			break;
+		}
+		r = kvm_s390_pci_zpci_reg_aen(zdev, args);
+		break;
+	case KVM_S390_ZPCIOP_DEREG_AEN:
+		r = kvm_s390_pci_aif_disable(zdev, false);
+		break;
+	default:
+		r = -EINVAL;
+	}
+
+out:
+	mutex_unlock(&kvm->lock);
+	mutex_unlock(&zdev->kzdev_lock);
+	return r;
+}
+
 int kvm_s390_pci_init(void)
 {
 	aift = kzalloc(sizeof(struct zpci_aift), GFP_KERNEL);
diff --git a/arch/s390/kvm/pci.h b/arch/s390/kvm/pci.h
index fb2b91b76e0c..0351382e990f 100644
--- a/arch/s390/kvm/pci.h
+++ b/arch/s390/kvm/pci.h
@@ -59,6 +59,8 @@ void kvm_s390_pci_aen_exit(void);
 void kvm_s390_pci_init_list(struct kvm *kvm);
 void kvm_s390_pci_clear_list(struct kvm *kvm);
 
+int kvm_s390_pci_zpci_op(struct kvm *kvm, struct kvm_s390_zpci_op *args);
+
 int kvm_s390_pci_init(void);
 void kvm_s390_pci_exit(void);
 
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 6a184d260c7f..39ca2a9acad2 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -1152,6 +1152,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_DISABLE_QUIRKS2 213
 /* #define KVM_CAP_VM_TSC_CONTROL 214 */
 #define KVM_CAP_SYSTEM_EVENT_DATA 215
+#define KVM_CAP_S390_ZPCI_OP 216
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -2068,4 +2069,35 @@ struct kvm_stats_desc {
 /* Available with KVM_CAP_XSAVE2 */
 #define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
 
+/* Available with KVM_CAP_S390_ZPCI_OP */
+#define KVM_S390_ZPCI_OP         _IOW(KVMIO,  0xd0, struct kvm_s390_zpci_op)
+
+struct kvm_s390_zpci_op {
+	/* in */
+	__u32 fh;               /* target device */
+	__u8  op;               /* operation to perform */
+	__u8  pad[3];
+	union {
+		/* for KVM_S390_ZPCIOP_REG_AEN */
+		struct {
+			__u64 ibv;      /* Guest addr of interrupt bit vector */
+			__u64 sb;       /* Guest addr of summary bit */
+			__u32 flags;
+			__u32 noi;      /* Number of interrupts */
+			__u8 isc;       /* Guest interrupt subclass */
+			__u8 sbo;       /* Offset of guest summary bit vector */
+			__u16 pad;
+		} reg_aen;
+		__u64 reserved[8];
+	} u;
+};
+
+/* types for kvm_s390_zpci_op->op */
+#define KVM_S390_ZPCIOP_REG_AEN                0
+#define KVM_S390_ZPCIOP_DEREG_AEN      1
+
+/* flags for kvm_s390_zpci_op->u.reg_aen.flags */
+#define KVM_S390_ZPCIOP_REGAEN_HOST    (1 << 0)
+
+
 #endif /* __LINUX_KVM_H */
-- 
2.27.0