genirq: Introduce irq_set_vcpu_affinity() to target an interrupt to a VCPU

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.

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@linux.intel.com>
Signed-off-by: Feng Wu <feng.wu@intel.com>
Link: http://lkml.kernel.org/r/1432026437-16560-2-git-send-email-feng.wu@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

3 files changed, 51 insertions, 0 deletions

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 62c6901cab55..48cb7d1aa58f 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -327,6 +327,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  * @irq_write_msi_msg:  optional to write message content for MSI
  * @irq_get_irqchip_state:      return the internal state of an interrupt
  * @irq_set_irqchip_state:      set the internal state of a interrupt
+ * @irq_set_vcpu_affinity:      optional to target a vCPU in a virtual machine
  * @flags:              chip specific flags
  */
 struct irq_chip {
@@ -369,6 +370,8 @@ struct irq_chip {
         int             (*irq_get_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool *state);
         int             (*irq_set_irqchip_state)(struct irq_data *data, enum irqchip_irq_state which, bool state);
 
+        int             (*irq_set_vcpu_affinity)(struct irq_data *data, void *vcpu_info);
+
         unsigned long   flags;
 };
 
@@ -422,6 +425,7 @@ 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);
@@ -467,6 +471,8 @@ extern int irq_chip_set_affinity_parent(struct irq_data *data,
                                         const struct cpumask *dest,
                                         bool force);
 extern int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on);
+extern int irq_chip_set_vcpu_affinity_parent(struct irq_data *data,
+                                             void *vcpu_info);
 #endif
 
 /* Handling of unhandled and spurious interrupts: */
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index eb9a4ea394ab..55016b2151f3 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -950,6 +950,20 @@ int irq_chip_retrigger_hierarchy(struct irq_data *data)
 }
 
 /**
+ * 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;
+}
+
+/**
  * irq_chip_set_wake_parent - Set/reset wake-up on the parent interrupt
  * @data:       Pointer to interrupt specific data
  * @on:         Whether to set or reset the wake-up capability of this irq
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index e68932bb308e..b1c7e8f46bfb 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -256,6 +256,37 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
 }
 EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
 
+/**
+ *      irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
+ *      @irq: interrupt number to set affinity
+ *      @vcpu_info: vCPU specific data
+ *
+ *      This function uses the vCPU specific data to set the vCPU
+ *      affinity for an irq. The vCPU specific data is passed from
+ *      outside, such as KVM. One example code path is as below:
+ *      KVM -> IOMMU -> irq_set_vcpu_affinity().
+ */
+int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info)
+{
+        unsigned long flags;
+        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
+        struct irq_data *data;
+        struct irq_chip *chip;
+        int ret = -ENOSYS;
+
+        if (!desc)
+                return -EINVAL;
+
+        data = irq_desc_get_irq_data(desc);
+        chip = irq_data_get_irq_chip(data);
+        if (chip && chip->irq_set_vcpu_affinity)
+                ret = chip->irq_set_vcpu_affinity(data, vcpu_info);
+        irq_put_desc_unlock(desc, flags);
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity);
+
 static void irq_affinity_notify(struct work_struct *work)
 {
         struct irq_affinity_notify *notify =