[PATCH 8/8] KVM: Emulation MSI-X mask bits for assigned devices

[Sheng Yang <sheng@linux.intel.com>]

This patch enable per-vector mask for assigned devices using MSI-X.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 Documentation/kvm/api.txt |   22 ++++++++++++++++
 arch/x86/kvm/x86.c        |    6 ++++
 include/linux/kvm.h       |    8 +++++-
 virt/kvm/assigned-dev.c   |   60 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 95 insertions(+), 1 deletions(-)

diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index d82d637..f324a50 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -1087,6 +1087,28 @@ of 4 instructions that make up a hypercall.
 If any additional field gets added to this structure later on, a bit for that
 additional piece of information will be set in the flags bitmap.
 
+4.47 KVM_ASSIGN_REG_MSIX_MMIO
+
+Capability: KVM_CAP_DEVICE_MSIX_MASK
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_assigned_msix_mmio (in)
+Returns: 0 on success, !0 on error
+
+struct kvm_assigned_msix_mmio {
+	/* Assigned device's ID */
+	__u32 assigned_dev_id;
+	/* MSI-X table MMIO address */
+	__u64 base_addr;
+	/* Must be 0 */
+	__u32 flags;
+	/* Must be 0, reserved for future use */
+	__u64 reserved;
+};
+
+This ioctl would enable in-kernel MSI-X emulation, which would handle MSI-X
+mask bit in the kernel.
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index fc62546..ba07a2f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1927,6 +1927,8 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
 	case KVM_CAP_XSAVE:
 	case KVM_CAP_ENABLE_CAP:
+	case KVM_CAP_DEVICE_MSIX_EXT:
+	case KVM_CAP_DEVICE_MSIX_MASK:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -2717,6 +2719,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 
 	switch (cap->cap) {
+	case KVM_CAP_DEVICE_MSIX_EXT:
+		vcpu->kvm->arch.msix_flags_enabled = true;
+		r = 0;
+		break;
 	default:
 		r = -EINVAL;
 		break;
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 0a7bd34..1494ed0 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -540,6 +540,10 @@ struct kvm_ppc_pvinfo {
 #endif
 #define KVM_CAP_PPC_GET_PVINFO 57
 #define KVM_CAP_PPC_IRQ_LEVEL 58
+#ifdef __KVM_HAVE_MSIX
+#define KVM_CAP_DEVICE_MSIX_EXT 59
+#define KVM_CAP_DEVICE_MSIX_MASK 60
+#endif
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -671,6 +675,8 @@ struct kvm_clock_data {
 #define KVM_XEN_HVM_CONFIG        _IOW(KVMIO,  0x7a, struct kvm_xen_hvm_config)
 #define KVM_SET_CLOCK             _IOW(KVMIO,  0x7b, struct kvm_clock_data)
 #define KVM_GET_CLOCK             _IOR(KVMIO,  0x7c, struct kvm_clock_data)
+#define KVM_ASSIGN_REG_MSIX_MMIO  _IOW(KVMIO,  0x7d, \
+					struct kvm_assigned_msix_mmio)
 /* Available with KVM_CAP_PIT_STATE2 */
 #define KVM_GET_PIT2              _IOR(KVMIO,  0x9f, struct kvm_pit_state2)
 #define KVM_SET_PIT2              _IOW(KVMIO,  0xa0, struct kvm_pit_state2)
@@ -802,7 +808,7 @@ struct kvm_assigned_msix_mmio {
 	__u32 assigned_dev_id;
 	__u64 base_addr;
 	__u32 flags;
-	__u32 reserved[2];
+	__u64 reserved;
 };
 
 #endif /* __LINUX_KVM_H */
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 5d2adc4..9573194 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -17,6 +17,8 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/slab.h>
+#include <linux/irqnr.h>
+
 #include "irq.h"
 
 static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
@@ -169,6 +171,14 @@ static void deassign_host_irq(struct kvm *kvm,
 	 */
 	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
 		int i;
+#ifdef __KVM_HAVE_MSIX
+		if (assigned_dev->msix_mmio_base) {
+			mutex_lock(&kvm->slots_lock);
+			kvm_io_bus_unregister_dev(kvm, KVM_MMIO_BUS,
+					&assigned_dev->msix_mmio_dev);
+			mutex_unlock(&kvm->slots_lock);
+		}
+#endif
 		for (i = 0; i < assigned_dev->entries_nr; i++)
 			disable_irq_nosync(assigned_dev->
 					   host_msix_entries[i].vector);
@@ -318,6 +328,15 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
 			goto err;
 	}
 
+	if (dev->msix_mmio_base) {
+		mutex_lock(&kvm->slots_lock);
+		r = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS,
+				&dev->msix_mmio_dev);
+		mutex_unlock(&kvm->slots_lock);
+		if (r)
+			goto err;
+	}
+
 	return 0;
 err:
 	for (i -= 1; i >= 0; i--)
@@ -870,6 +889,31 @@ static const struct kvm_io_device_ops msix_mmio_ops = {
 	.write    = msix_mmio_write,
 };
 
+static int kvm_vm_ioctl_register_msix_mmio(struct kvm *kvm,
+				struct kvm_assigned_msix_mmio *msix_mmio)
+{
+	int r = 0;
+	struct kvm_assigned_dev_kernel *adev;
+
+	mutex_lock(&kvm->lock);
+	adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+				      msix_mmio->assigned_dev_id);
+	if (!adev) {
+		r = -EINVAL;
+		goto out;
+	}
+	if (msix_mmio->base_addr == 0) {
+		r = -EINVAL;
+		goto out;
+	}
+	adev->msix_mmio_base = msix_mmio->base_addr;
+
+	kvm_iodevice_init(&adev->msix_mmio_dev, &msix_mmio_ops);
+out:
+	mutex_unlock(&kvm->lock);
+
+	return r;
+}
 #endif
 
 long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
@@ -982,6 +1026,22 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 			goto out;
 		break;
 	}
+	case KVM_ASSIGN_REG_MSIX_MMIO: {
+		struct kvm_assigned_msix_mmio msix_mmio;
+
+		r = -EFAULT;
+		if (copy_from_user(&msix_mmio, argp, sizeof(msix_mmio)))
+			goto out;
+
+		r = -EINVAL;
+		if (msix_mmio.flags != 0 || msix_mmio.reserved != 0)
+			goto out;
+
+		r = kvm_vm_ioctl_register_msix_mmio(kvm, &msix_mmio);
+		if (r)
+			goto out;
+		break;
+	}
 #endif
 	}
 out:
-- 
1.7.0.1