KVM: Ioctls for init MSI-X entry

Introduce KVM_SET_MSIX_NR and KVM_SET_MSIX_ENTRY two ioctls.

This two ioctls are used by userspace to specific guest device MSI-X entry
number and correlate MSI-X entry with GSI during the initialization stage.

MSI-X should be well initialzed before enabling.

Don't support change MSI-X entry number for now.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

3 files changed, 132 insertions, 0 deletions

diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 8cc137911b34..78cdee8c6355 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -487,6 +487,10 @@ struct kvm_irq_routing {
 #define KVM_REINJECT_CONTROL      _IO(KVMIO, 0x71)
 #define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \
                                      struct kvm_assigned_pci_dev)
+#define KVM_ASSIGN_SET_MSIX_NR \
+                        _IOW(KVMIO, 0x73, struct kvm_assigned_msix_nr)
+#define KVM_ASSIGN_SET_MSIX_ENTRY \
+                        _IOW(KVMIO, 0x74, struct kvm_assigned_msix_entry)
 
 /*
  * ioctls for vcpu fds
@@ -607,4 +611,18 @@ struct kvm_assigned_irq {
 #define KVM_DEV_IRQ_ASSIGN_MSI_ACTION   KVM_DEV_IRQ_ASSIGN_ENABLE_MSI
 #define KVM_DEV_IRQ_ASSIGN_ENABLE_MSI   (1 << 0)
 
+struct kvm_assigned_msix_nr {
+        __u32 assigned_dev_id;
+        __u16 entry_nr;
+        __u16 padding;
+};
+
+#define KVM_MAX_MSIX_PER_DEV            512
+struct kvm_assigned_msix_entry {
+        __u32 assigned_dev_id;
+        __u32 gsi;
+        __u16 entry; /* The index of entry in the MSI-X table */
+        __u16 padding[3];
+};
+
 #endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1a2f98fbecea..432edc27e82b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -319,6 +319,12 @@ struct kvm_irq_ack_notifier {
         void (*irq_acked)(struct kvm_irq_ack_notifier *kian);
 };
 
+struct kvm_guest_msix_entry {
+        u32 vector;
+        u16 entry;
+        u16 flags;
+};
+
 struct kvm_assigned_dev_kernel {
         struct kvm_irq_ack_notifier ack_notifier;
         struct work_struct interrupt_work;
@@ -326,13 +332,17 @@ struct kvm_assigned_dev_kernel {
         int assigned_dev_id;
         int host_busnr;
         int host_devfn;
+        unsigned int entries_nr;
         int host_irq;
         bool host_irq_disabled;
+        struct msix_entry *host_msix_entries;
         int guest_irq;
+        struct kvm_guest_msix_entry *guest_msix_entries;
 #define KVM_ASSIGNED_DEV_GUEST_INTX     (1 << 0)
 #define KVM_ASSIGNED_DEV_GUEST_MSI      (1 << 1)
 #define KVM_ASSIGNED_DEV_HOST_INTX      (1 << 8)
 #define KVM_ASSIGNED_DEV_HOST_MSI       (1 << 9)
+#define KVM_ASSIGNED_DEV_MSIX           ((1 << 2) | (1 << 10))
         unsigned long irq_requested_type;
         int irq_source_id;
         int flags;
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 4d0dd390aa50..1ceb96901f32 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1593,6 +1593,88 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
         return 0;
 }
 
+#ifdef __KVM_HAVE_MSIX
+static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
+                                    struct kvm_assigned_msix_nr *entry_nr)
+{
+        int r = 0;
+        struct kvm_assigned_dev_kernel *adev;
+
+        mutex_lock(&kvm->lock);
+
+        adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+                                      entry_nr->assigned_dev_id);
+        if (!adev) {
+                r = -EINVAL;
+                goto msix_nr_out;
+        }
+
+        if (adev->entries_nr == 0) {
+                adev->entries_nr = entry_nr->entry_nr;
+                if (adev->entries_nr == 0 ||
+                    adev->entries_nr >= KVM_MAX_MSIX_PER_DEV) {
+                        r = -EINVAL;
+                        goto msix_nr_out;
+                }
+
+                adev->host_msix_entries = kzalloc(sizeof(struct msix_entry) *
+                                                entry_nr->entry_nr,
+                                                GFP_KERNEL);
+                if (!adev->host_msix_entries) {
+                        r = -ENOMEM;
+                        goto msix_nr_out;
+                }
+                adev->guest_msix_entries = kzalloc(
+                                sizeof(struct kvm_guest_msix_entry) *
+                                entry_nr->entry_nr, GFP_KERNEL);
+                if (!adev->guest_msix_entries) {
+                        kfree(adev->host_msix_entries);
+                        r = -ENOMEM;
+                        goto msix_nr_out;
+                }
+        } else /* Not allowed set MSI-X number twice */
+                r = -EINVAL;
+msix_nr_out:
+        mutex_unlock(&kvm->lock);
+        return r;
+}
+
+static int kvm_vm_ioctl_set_msix_entry(struct kvm *kvm,
+                                       struct kvm_assigned_msix_entry *entry)
+{
+        int r = 0, i;
+        struct kvm_assigned_dev_kernel *adev;
+
+        mutex_lock(&kvm->lock);
+
+        adev = kvm_find_assigned_dev(&kvm->arch.assigned_dev_head,
+                                      entry->assigned_dev_id);
+
+        if (!adev) {
+                r = -EINVAL;
+                goto msix_entry_out;
+        }
+
+        for (i = 0; i < adev->entries_nr; i++)
+                if (adev->guest_msix_entries[i].vector == 0 ||
+                    adev->guest_msix_entries[i].entry == entry->entry) {
+                        adev->guest_msix_entries[i].entry = entry->entry;
+                        adev->guest_msix_entries[i].vector = entry->gsi;
+                        adev->host_msix_entries[i].entry = entry->entry;
+                        break;
+                }
+        if (i == adev->entries_nr) {
+                r = -ENOSPC;
+                goto msix_entry_out;
+        }
+
+msix_entry_out:
+        mutex_unlock(&kvm->lock);
+
+        return r;
+}
+#endif
+
 static long kvm_vcpu_ioctl(struct file *filp,
                            unsigned int ioctl, unsigned long arg)
 {
@@ -1917,7 +1999,29 @@ static long kvm_vm_ioctl(struct file *filp,
                 vfree(entries);
                 break;
         }
+#ifdef __KVM_HAVE_MSIX
+        case KVM_ASSIGN_SET_MSIX_NR: {
+                struct kvm_assigned_msix_nr entry_nr;
+                r = -EFAULT;
+                if (copy_from_user(&entry_nr, argp, sizeof entry_nr))
+                        goto out;
+                r = kvm_vm_ioctl_set_msix_nr(kvm, &entry_nr);
+                if (r)
+                        goto out;
+                break;
+        }
+        case KVM_ASSIGN_SET_MSIX_ENTRY: {
+                struct kvm_assigned_msix_entry entry;
+                r = -EFAULT;
+                if (copy_from_user(&entry, argp, sizeof entry))
+                        goto out;
+                r = kvm_vm_ioctl_set_msix_entry(kvm, &entry);
+                if (r)
+                        goto out;
+                break;
+        }
 #endif
+#endif /* KVM_CAP_IRQ_ROUTING */
         default:
                 r = kvm_arch_vm_ioctl(filp, ioctl, arg);
         }