[PATCH 4/8] KVM: Add a route layer to convert MSI message to GSI

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

Avi's purpose, to use single kvm_set_irq() to deal with all interrupt, including
MSI. So here is it.

struct gsi_msg is a mapping from a special gsi(with KVM_GSI_MSG_MASK) to
MSI/MSI-X message address/data.

Now we support up to 256 gsi_msg mapping, and gsi_msg is allocated by kernel and
provide two ioctls to userspace, which is more flexiable.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
---
 include/linux/kvm.h      |   12 ++++++++
 include/linux/kvm_host.h |   16 ++++++++++
 virt/kvm/irq_comm.c      |   70 ++++++++++++++++++++++++++++++++++++++++++++++
 virt/kvm/kvm_main.c      |   63 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 161 insertions(+), 0 deletions(-)

diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 5b965f6..b091a86 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -394,6 +394,7 @@ struct kvm_trace_rec {
 #define KVM_CAP_USER_NMI 22
 #endif
 #define KVM_CAP_SET_GUEST_DEBUG 23
+#define KVM_CAP_GSI_MSG 24
 
 /*
  * ioctls for VM fds
@@ -427,6 +428,8 @@ struct kvm_trace_rec {
 				   struct kvm_assigned_pci_dev)
 #define KVM_ASSIGN_IRQ _IOR(KVMIO, 0x70, \
 			    struct kvm_assigned_irq)
+#define KVM_REQUEST_GSI_MSG _IOWR(KVMIO, 0x71, struct kvm_assigned_gsi_msg)
+#define KVM_FREE_GSI_MSG _IOR(KVMIO, 0x72, __u32)
 
 /*
  * ioctls for vcpu fds
@@ -547,4 +550,13 @@ struct kvm_assigned_irq {
 #define KVM_DEV_IRQ_ASSIGN_MSI_ACTION	(1 << 0)
 #define KVM_DEV_IRQ_ASSIGN_ENABLE_MSI	(1 << 1)
 
+struct kvm_assigned_gsi_msg {
+	__u32 gsi;
+	struct {
+		__u32 addr_lo;
+		__u32 addr_hi;
+		__u32 data;
+	} msg;
+};
+
 #endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d63e9a4..0e5741a 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -132,6 +132,10 @@ struct kvm {
 	unsigned long mmu_notifier_seq;
 	long mmu_notifier_count;
 #endif
+	struct hlist_head gsi_msg_list;
+	struct mutex gsi_msg_lock;
+#define KVM_NR_GSI_MSG	    256
+	DECLARE_BITMAP(gsi_msg_bitmap, KVM_NR_GSI_MSG);
 };
 
 /* The guest did something we don't support. */
@@ -319,6 +323,14 @@ struct kvm_assigned_dev_kernel {
 	struct pci_dev *dev;
 	struct kvm *kvm;
 };
+
+#define KVM_GSI_MSG_MASK    0x1000000ull
+struct kvm_gsi_msg {
+	u32 gsi;
+	struct msi_msg msg;
+	struct hlist_node link;
+};
+
 void kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level);
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned gsi);
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
@@ -326,6 +338,10 @@ void kvm_register_irq_ack_notifier(struct kvm *kvm,
 void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian);
 int kvm_request_irq_source_id(struct kvm *kvm);
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
+int kvm_update_gsi_msg(struct kvm *kvm, struct kvm_gsi_msg *gsi_msg);
+struct kvm_gsi_msg *kvm_find_gsi_msg(struct kvm *kvm, u32 gsi);
+void kvm_free_gsi_msg(struct kvm *kvm, struct kvm_gsi_msg *gsi_msg);
+void kvm_free_gsi_msg_list(struct kvm *kvm);
 
 #ifdef CONFIG_DMAR
 int kvm_iommu_map_pages(struct kvm *kvm, gfn_t base_gfn,
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index aa5d1e5..e95ec3f 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -99,3 +99,73 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 		clear_bit(irq_source_id, &kvm->arch.irq_states[i]);
 	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
 }
+
+int kvm_update_gsi_msg(struct kvm *kvm, struct kvm_gsi_msg *gsi_msg)
+{
+	struct kvm_gsi_msg *found_msg, *new_gsi_msg;
+	int r, gsi;
+
+	mutex_lock(&kvm->gsi_msg_lock);
+	/* Find whether we need a update or a new entry */
+	found_msg = kvm_find_gsi_msg(kvm, gsi_msg->gsi);
+	if (found_msg)
+		*found_msg = *gsi_msg;
+	else {
+		gsi = find_first_zero_bit(kvm->gsi_msg_bitmap, KVM_NR_GSI_MSG);
+		if (gsi >= KVM_NR_GSI_MSG) {
+			r = -EFAULT;
+			goto out;
+		}
+		__set_bit(gsi, kvm->gsi_msg_bitmap);
+		gsi_msg->gsi = gsi | KVM_GSI_MSG_MASK;
+		new_gsi_msg = kzalloc(sizeof(*new_gsi_msg), GFP_KERNEL);
+		if (!new_gsi_msg) {
+			r = -ENOMEM;
+			goto out;
+		}
+		*new_gsi_msg = *gsi_msg;
+		hlist_add_head(&new_gsi_msg->link, &kvm->gsi_msg_list);
+	}
+	r = 0;
+out:
+	mutex_unlock(&kvm->gsi_msg_lock);
+	return r;
+}
+
+/* Call with kvm->gsi_msg_lock hold */
+struct kvm_gsi_msg *kvm_find_gsi_msg(struct kvm *kvm, u32 gsi)
+{
+	struct kvm_gsi_msg *gsi_msg;
+	struct hlist_node *n;
+
+	if (!(gsi & KVM_GSI_MSG_MASK))
+		return NULL;
+	hlist_for_each_entry(gsi_msg, n, &kvm->gsi_msg_list, link)
+		if (gsi_msg->gsi == gsi)
+			goto out;
+	gsi_msg = NULL;
+out:
+	return gsi_msg;
+}
+
+/* Call with kvm->gsi_msg_lock hold */
+void kvm_free_gsi_msg(struct kvm *kvm, struct kvm_gsi_msg *gsi_msg)
+{
+	if (!gsi_msg)
+		return;
+	__clear_bit(gsi_msg->gsi & ~KVM_GSI_MSG_MASK, kvm->gsi_msg_bitmap);
+	hlist_del(&gsi_msg->link);
+	kfree(gsi_msg);
+}
+
+void kvm_free_gsi_msg_list(struct kvm *kvm)
+{
+	struct kvm_gsi_msg *gsi_msg;
+	struct hlist_node *pos, *n;
+
+	mutex_lock(&kvm->gsi_msg_lock);
+	hlist_for_each_entry_safe(gsi_msg, pos, n, &kvm->gsi_msg_list, link)
+		kvm_free_gsi_msg(kvm, gsi_msg);
+	mutex_unlock(&kvm->gsi_msg_lock);
+}
+
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 10cf7e1..db9de47 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -814,6 +814,8 @@ static struct kvm *kvm_create_vm(void)
 #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET
 	kvm_coalesced_mmio_init(kvm);
 #endif
+	INIT_HLIST_HEAD(&kvm->gsi_msg_list);
+	mutex_init(&kvm->gsi_msg_lock);
 out:
 	return kvm;
 }
@@ -851,6 +853,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 {
 	struct mm_struct *mm = kvm->mm;
 
+	kvm_free_gsi_msg_list(kvm);
 	spin_lock(&kvm_lock);
 	list_del(&kvm->vm_list);
 	spin_unlock(&kvm_lock);
@@ -1579,6 +1582,42 @@ static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
 	return 0;
 }
 
+static int kvm_vm_ioctl_request_gsi_msg(struct kvm *kvm,
+					struct kvm_assigned_gsi_msg *agsi_msg)
+{
+	struct kvm_gsi_msg gsi_msg;
+	int r;
+
+	gsi_msg.gsi = agsi_msg->gsi;
+	gsi_msg.msg.address_lo = agsi_msg->msg.addr_lo;
+	gsi_msg.msg.address_hi = agsi_msg->msg.addr_hi;
+	gsi_msg.msg.data = agsi_msg->msg.data;
+
+	r = kvm_update_gsi_msg(kvm, &gsi_msg);
+	if (r == 0)
+		agsi_msg->gsi = gsi_msg.gsi;
+	return r;
+}
+
+static int kvm_vm_ioctl_free_gsi_msg(struct kvm *kvm, u32 gsi)
+{
+	struct kvm_gsi_msg *gsi_msg;
+	int r;
+
+	mutex_lock(&kvm->gsi_msg_lock);
+	gsi_msg = kvm_find_gsi_msg(kvm, gsi);
+	if (!gsi_msg) {
+		printk(KERN_WARNING "kvm: non-exist gsi->msi_msg mapping!");
+		r = -EINVAL;
+		goto out;
+	}
+	kvm_free_gsi_msg(kvm, gsi_msg);
+	r = 0;
+out:
+	mutex_unlock(&kvm->gsi_msg_lock);
+	return r;
+}
+
 static long kvm_vcpu_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -1861,6 +1900,30 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif
+	case KVM_REQUEST_GSI_MSG: {
+		struct kvm_assigned_gsi_msg agsi_msg;
+		r = -EFAULT;
+		if (copy_from_user(&agsi_msg, argp, sizeof agsi_msg))
+			goto out;
+		r = kvm_vm_ioctl_request_gsi_msg(kvm, &agsi_msg);
+		if (r)
+			goto out;
+		r = -EFAULT;
+		if (copy_to_user(argp, &agsi_msg, sizeof agsi_msg))
+			goto out;
+		r = 0;
+		break;
+	}
+	case KVM_FREE_GSI_MSG: {
+		unsigned long guest_gsi;
+		r = -EFAULT;
+		if (copy_from_user(&guest_gsi, argp, sizeof guest_gsi))
+			goto out;
+		r = kvm_vm_ioctl_free_gsi_msg(kvm, guest_gsi);
+		if (r)
+			goto out;
+		break;
+	}
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}
-- 
1.5.4.5