[PATCHv4 1/2] kvm: add kvm_set_irq_inatomic

["Michael S. Tsirkin" <mst@redhat.com>]

Add an API to inject IRQ from atomic context.
Return EWOULDBLOCK if impossible (e.g. for multicast).
Only MSI is supported ATM.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/kvm_host.h |  1 +
 virt/kvm/irq_comm.c      | 83 +++++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 72 insertions(+), 12 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 93bfc9f..e165c09 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -677,6 +677,7 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic,
 				   unsigned long *deliver_bitmask);
 #endif
 int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level);
+int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level);
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
 		int irq_source_id, int level);
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 2eb58af..656fa45 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -102,6 +102,23 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	return r;
 }
 
+static inline void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+				   struct kvm_lapic_irq *irq)
+{
+	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+
+	irq->dest_id = (e->msi.address_lo &
+			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+	irq->vector = (e->msi.data &
+			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
+	irq->dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
+	irq->trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
+	irq->delivery_mode = e->msi.data & 0x700;
+	irq->level = 1;
+	irq->shorthand = 0;
+	/* TODO Deal with RH bit of MSI message address */
+}
+
 int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 		struct kvm *kvm, int irq_source_id, int level)
 {
@@ -110,22 +127,26 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	if (!level)
 		return -1;
 
-	trace_kvm_msi_set_irq(e->msi.address_lo, e->msi.data);
+	kvm_set_msi_irq(e, &irq);
 
-	irq.dest_id = (e->msi.address_lo &
-			MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
-	irq.vector = (e->msi.data &
-			MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
-	irq.dest_mode = (1 << MSI_ADDR_DEST_MODE_SHIFT) & e->msi.address_lo;
-	irq.trig_mode = (1 << MSI_DATA_TRIGGER_SHIFT) & e->msi.data;
-	irq.delivery_mode = e->msi.data & 0x700;
-	irq.level = 1;
-	irq.shorthand = 0;
-
-	/* TODO Deal with RH bit of MSI message address */
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
+
+static int kvm_set_msi_inatomic(struct kvm_kernel_irq_routing_entry *e,
+			 struct kvm *kvm)
+{
+	struct kvm_lapic_irq irq;
+	int r;
+
+	kvm_set_msi_irq(e, &irq);
+
+	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r))
+		return r;
+	else
+		return -EWOULDBLOCK;
+}
+
 int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi)
 {
 	struct kvm_kernel_irq_routing_entry route;
@@ -178,6 +199,44 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level)
 	return ret;
 }
 
+/*
+ * Deliver an IRQ in an atomic context if we can, or return a failure,
+ * user can retry in a process context.
+ * Return value:
+ *  -EWOULDBLOCK - Can't deliver in atomic context: retry in a process context.
+ *  Other values - No need to retry.
+ */
+int kvm_set_irq_inatomic(struct kvm *kvm, int irq_source_id, u32 irq, int level)
+{
+	struct kvm_kernel_irq_routing_entry *e;
+	int ret = -EINVAL;
+	struct kvm_irq_routing_table *irq_rt;
+	struct hlist_node *n;
+
+	trace_kvm_set_irq(irq, level, irq_source_id);
+
+	/*
+	 * Injection into either PIC or IOAPIC might need to scan all CPUs,
+	 * which would need to be retried from thread context;  when same GSI
+	 * is connected to both PIC and IOAPIC, we'd have to report a
+	 * partial failure here.
+	 * Since there's no easy way to do this, we only support injecting MSI
+	 * which is limited to 1:1 GSI mapping.
+	 */
+	rcu_read_lock();
+	irq_rt = rcu_dereference(kvm->irq_routing);
+	if (irq < irq_rt->nr_rt_entries)
+		hlist_for_each_entry(e, n, &irq_rt->map[irq], link) {
+			if (likely(e->type == KVM_IRQ_ROUTING_MSI))
+				ret = kvm_set_msi_inatomic(e, kvm);
+			else
+				ret = -EWOULDBLOCK;
+			break;
+		}
+	rcu_read_unlock();
+	return ret;
+}
+
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 {
 	struct kvm_irq_ack_notifier *kian;
-- 
MST