With Posted-Interrupts support in Intel CPU and IOMMU, an external
interrupt from assigned-devices could be directly delivered to a
virtual CPU in a virtual machine. Instead of hacking KVM and Intel
IOMMU drivers, we propose a platform independent interface to target
an interrupt to a specific virtual CPU in a virtual machine, or set
virtual CPU affinity for an interrupt.
By adopting this new interface and the hierarchy irqdomain, we could
easily support posted-interrupts on Intel platforms, and also provide
flexible enough interfaces for other platforms to support similar
features.
We may also cooperate between set_affinity() and set_vcpu_affinity()
in IRQ core or irq chip drivers.
Here is the usage scenario for this interface:
Guest update MSI/MSI-X interrupt configuration
-->QEMU and KVM handle this
-->KVM call this interface (passing posted interrupts descriptor
and guest vector)
-->irq core will transfer the control to IOMMU
-->IOMMU will do the real work of updating IRTE (IRTE has new
format for VT-d Posted-Interrupts)
Signed-off-by: Jiang Liu <jiang.liu@xxxxxxxxxxxxxxx>
Signed-off-by: Feng Wu <feng.wu@xxxxxxxxx>
---
include/linux/irq.h | 4 ++++
kernel/irq/chip.c | 14 ++++++++++++++
kernel/irq/manage.c | 20 ++++++++++++++++++++
3 files changed, 38 insertions(+)
diff --git a/include/linux/irq.h b/include/linux/irq.h
index f26e736..83abafc 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -324,6 +324,8 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
* irq_request_resources
* @irq_compose_msi_msg: optional to compose message content for MSI
* @irq_write_msi_msg: optional to write message content for MSI
+ * @irq_set_vcpu_affinity: optional to target a virtual CPU in a virtual
+ * machine
* @flags: chip specific flags
*/
struct irq_chip {
@@ -362,6 +364,7 @@ struct irq_chip {
void (*irq_compose_msi_msg)(struct irq_data *data, struct msi_msg *msg);
void (*irq_write_msi_msg)(struct irq_data *data, struct msi_msg *msg);
+ int (*irq_set_vcpu_affinity)(struct irq_data *data, void *vcpu_info);
unsigned long flags;
};
@@ -416,6 +419,7 @@ extern void irq_cpu_online(void);
extern void irq_cpu_offline(void);
extern int irq_set_affinity_locked(struct irq_data *data,
const struct cpumask *cpumask, bool force);
+extern int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info);
#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
void irq_move_irq(struct irq_data *data);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 6f1c7a5..fe0908f 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -948,6 +948,20 @@ int irq_chip_retrigger_hierarchy(struct irq_data *data)
return -ENOSYS;
}
+
+/**
+ * irq_chip_set_vcpu_affinity_parent - Set vcpu affinity on the parent interrupt
+ * @data: Pointer to interrupt specific data
+ * @dest: The vcpu affinity information
+ */
+int irq_chip_set_vcpu_affinity_parent(struct irq_data *data, void *vcpu_info)
+{
+ data = data->parent_data;
+ if (data->chip->irq_set_vcpu_affinity)
+ return data->chip->irq_set_vcpu_affinity(data, vcpu_info);
+
+ return -ENOSYS;
+}
#endif
/**
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 8069237..bd3a1ba 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -247,6 +247,26 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
}
EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
+int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info)
+{
+ struct irq_desc *desc = irq_to_desc(irq);
+ struct irq_chip *chip;
+ unsigned long flags;
+ int ret = -ENOSYS;
+
+ if (!desc)
+ return -EINVAL;
+
+ raw_spin_lock_irqsave(&desc->lock, flags);
+ chip = desc->irq_data.chip;
+ if (chip && chip->irq_set_vcpu_affinity)
+ ret = chip->irq_set_vcpu_affinity(irq_desc_get_irq_data(desc),
+ vcpu_info);
+ raw_spin_unlock_irqrestore(&desc->lock, flags);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity);
+
static void irq_affinity_notify(struct work_struct *work)
{
struct irq_affinity_notify *notify =
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
