KVM: Introduce direct MSI message injection for in-kernel irqchips

Currently, MSI messages can only be injected to in-kernel irqchips by
defining a corresponding IRQ route for each message. This is not only
unhandy if the MSI messages are generated "on the fly" by user space,
IRQ routes are a limited resource that user space has to manage
carefully.

By providing a direct injection path, we can both avoid using up limited
resources and simplify the necessary steps for user land.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

Documentation/virtual/kvm/api.txt

@@ -1689,6 +1689,27 @@ where the guest will clear the flag: when the soft lockup watchdog timer resets
 itself or when a soft lockup is detected.  This ioctl can be called any time
 after pausing the vcpu, but before it is resumed.
 
+4.71 KVM_SIGNAL_MSI
+
+Capability: KVM_CAP_SIGNAL_MSI
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_msi (in)
+Returns: >0 on delivery, 0 if guest blocked the MSI, and -1 on error
+
+Directly inject a MSI message. Only valid with in-kernel irqchip that handles
+MSI messages.
+
+struct kvm_msi {
+	__u32 address_lo;
+	__u32 address_hi;
+	__u32 data;
+	__u32 flags;
+	__u8  pad[16];
+};
+
+No flags are defined so far. The corresponding field must be 0.
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by

arch/x86/kvm/Kconfig

@@ -36,6 +36,7 @@ config KVM
 	select TASKSTATS
 	select TASK_DELAY_ACCT
 	select PERF_EVENTS
+	select HAVE_KVM_MSI
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent

include/linux/kvm.h

@@ -590,6 +590,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_SYNC_REGS 74
 #define KVM_CAP_PCI_2_3 75
 #define KVM_CAP_KVMCLOCK_CTRL 76
+#define KVM_CAP_SIGNAL_MSI 77
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -715,6 +716,14 @@ struct kvm_one_reg {
 	__u64 addr;
 };
 
+struct kvm_msi {
+	__u32 address_lo;
+	__u32 address_hi;
+	__u32 data;
+	__u32 flags;
+	__u8  pad[16];
+};
+
 /*
  * ioctls for VM fds
  */
@@ -789,6 +798,8 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_PCI_2_3 */
 #define KVM_ASSIGN_SET_INTX_MASK  _IOW(KVMIO,  0xa4, \
 				       struct kvm_assigned_pci_dev)
+/* Available with KVM_CAP_SIGNAL_MSI */
+#define KVM_SIGNAL_MSI            _IOW(KVMIO,  0xa5, struct kvm_msi)
 
 /*
  * ioctls for vcpu fds

include/linux/kvm_host.h

@@ -802,6 +802,8 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			unsigned flags);
 void kvm_free_irq_routing(struct kvm *kvm);
 
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
+
 #else
 
 static inline void kvm_free_irq_routing(struct kvm *kvm) {}

virt/kvm/Kconfig

@@ -18,3 +18,6 @@ config KVM_MMIO
 
 config KVM_ASYNC_PF
        bool
+
+config HAVE_KVM_MSI
+       bool

virt/kvm/irq_comm.c

@@ -138,6 +138,20 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
+int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
+{
+	struct kvm_kernel_irq_routing_entry route;
+
+	if (!irqchip_in_kernel(kvm) || msi->flags != 0)
+		return -EINVAL;
+
+	route.msi.address_lo = msi->address_lo;
+	route.msi.address_hi = msi->address_hi;
+	route.msi.data = msi->data;
+
+	return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1);
+}
+
 /*
  * Return value:
  *  < 0   Interrupt was ignored (masked or not delivered for other reasons)

virt/kvm/kvm_main.c

@@ -2059,6 +2059,17 @@ static long kvm_vm_ioctl(struct file *filp,
 			kvm->bsp_vcpu_id = arg;
 		mutex_unlock(&kvm->lock);
 		break;
+#endif
+#ifdef CONFIG_HAVE_KVM_MSI
+	case KVM_SIGNAL_MSI: {
+		struct kvm_msi msi;
+
+		r = -EFAULT;
+		if (copy_from_user(&msi, argp, sizeof msi))
+			goto out;
+		r = kvm_send_userspace_msi(kvm, &msi);
+		break;
+	}
 #endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
@@ -2188,6 +2199,9 @@ static long kvm_dev_ioctl_check_extension_generic(long arg)
 	case KVM_CAP_SET_BOOT_CPU_ID:
 #endif
 	case KVM_CAP_INTERNAL_ERROR_DATA:
+#ifdef CONFIG_HAVE_KVM_MSI
+	case KVM_CAP_SIGNAL_MSI:
+#endif
 		return 1;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	case KVM_CAP_IRQ_ROUTING: