Linux Virtualization - Oct 2014 - [RFC PATCH 2/2] Assign a new irq handler while irqfd enabled

From: Li Liu <john.liuli at huawei.com>

This irq handler will get the interrupt reason from a
shared memory. And will be assigned only while irqfd
enabled.

Signed-off-by: Li Liu <john.liuli at huawei.com>
---
 drivers/virtio/virtio_mmio.c |   34 ++++++++++++++++++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 28ddb55..7229605 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -259,7 +259,31 @@ static irqreturn_t vm_interrupt(int irq, void *opaque)
 	return ret;
 }
 
+/* Notify all virtqueues on an interrupt. */
+static irqreturn_t vm_interrupt_irqfd(int irq, void *opaque)
+{
+	struct virtio_mmio_device *vm_dev = opaque;
+	struct virtio_mmio_vq_info *info;
+	unsigned long status;
+	unsigned long flags;
+	irqreturn_t ret = IRQ_NONE;
 
+	/* Read the interrupt reason and reset it */
+	status = *vm_dev->isr_mem;
+	*vm_dev->isr_mem = 0x0;
+
+	if (unlikely(status & VIRTIO_MMIO_INT_CONFIG)) {
+		virtio_config_changed(&vm_dev->vdev);
+		ret = IRQ_HANDLED;
+	}
+
+	spin_lock_irqsave(&vm_dev->lock, flags);
+	list_for_each_entry(info, &vm_dev->virtqueues, node)
+		ret |= vring_interrupt(irq, info->vq);
+	spin_unlock_irqrestore(&vm_dev->lock, flags);
+
+	return ret;
+}
 
 static void vm_del_vq(struct virtqueue *vq)
 {
@@ -391,6 +415,7 @@ error_available:
 	return ERR_PTR(err);
 }
 
+#define VIRTIO_MMIO_F_IRQFD        (1 << 7)
 static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
 		       struct virtqueue *vqs[],
 		       vq_callback_t *callbacks[],
@@ -400,8 +425,13 @@ static int vm_find_vqs(struct virtio_device *vdev, unsigned
nvqs,
 	unsigned int irq = platform_get_irq(vm_dev->pdev, 0);
 	int i, err;
 
-	err = request_irq(irq, vm_interrupt, IRQF_SHARED,
-			dev_name(&vdev->dev), vm_dev);
+	if (*vm_dev->isr_mem & VIRTIO_MMIO_F_IRQFD) {
+		err = request_irq(irq, vm_interrupt_irqfd, IRQF_SHARED,
+				  dev_name(&vdev->dev), vm_dev);
+	} else {
+		err = request_irq(irq, vm_interrupt, IRQF_SHARED,
+				  dev_name(&vdev->dev), vm_dev);
+	}
 	if (err)
 		return err;
 
-- 
1.7.9.5

On 2014/10/26 19:56, Michael S. Tsirkin wrote:
> On Sat, Oct 25, 2014 at 04:24:54PM +0800, john.liuli wrote:
>> From: Li Liu <john.liuli at huawei.com>
>>
>> This irq handler will get the interrupt reason from a
>> shared memory. And will be assigned only while irqfd
>> enabled.
>>
>> Signed-off-by: Li Liu <john.liuli at huawei.com>
>> ---
>>  drivers/virtio/virtio_mmio.c |   34 ++++++++++++++++++++++++++++++++--
>>  1 file changed, 32 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/virtio/virtio_mmio.c
b/drivers/virtio/virtio_mmio.c
>> index 28ddb55..7229605 100644
>> --- a/drivers/virtio/virtio_mmio.c
>> +++ b/drivers/virtio/virtio_mmio.c
>> @@ -259,7 +259,31 @@ static irqreturn_t vm_interrupt(int irq, void
*opaque)
>>  	return ret;
>>  }
>>  
>> +/* Notify all virtqueues on an interrupt. */
>> +static irqreturn_t vm_interrupt_irqfd(int irq, void *opaque)
>> +{
>> +	struct virtio_mmio_device *vm_dev = opaque;
>> +	struct virtio_mmio_vq_info *info;
>> +	unsigned long status;
>> +	unsigned long flags;
>> +	irqreturn_t ret = IRQ_NONE;
>>  
>> +	/* Read the interrupt reason and reset it */
>> +	status = *vm_dev->isr_mem;
>> +	*vm_dev->isr_mem = 0x0;
> 
> you are reading and modifying shared memory
> without atomics and any memory barriers.
> Why is this safe?
> 
good catch, a stupid mistake.
>> +
>> +	if (unlikely(status & VIRTIO_MMIO_INT_CONFIG)) {
>> +		virtio_config_changed(&vm_dev->vdev);
>> +		ret = IRQ_HANDLED;
>> +	}
>> +
>> +	spin_lock_irqsave(&vm_dev->lock, flags);
>> +	list_for_each_entry(info, &vm_dev->virtqueues, node)
>> +		ret |= vring_interrupt(irq, info->vq);
>> +	spin_unlock_irqrestore(&vm_dev->lock, flags);
>> +
>> +	return ret;
>> +}
>>  
>>  static void vm_del_vq(struct virtqueue *vq)
>>  {
> 
> So you invoke callbacks for all VQs.
> This won't scale well as the number of VQs grows, will it?
> 
>> @@ -391,6 +415,7 @@ error_available:
>>  	return ERR_PTR(err);
>>  }
>>  
>> +#define VIRTIO_MMIO_F_IRQFD        (1 << 7)
>>  static int vm_find_vqs(struct virtio_device *vdev, unsigned nvqs,
>>  		       struct virtqueue *vqs[],
>>  		       vq_callback_t *callbacks[],
>> @@ -400,8 +425,13 @@ static int vm_find_vqs(struct virtio_device *vdev,
unsigned nvqs,
>>  	unsigned int irq = platform_get_irq(vm_dev->pdev, 0);
>>  	int i, err;
>>  
>> -	err = request_irq(irq, vm_interrupt, IRQF_SHARED,
>> -			dev_name(&vdev->dev), vm_dev);
>> +	if (*vm_dev->isr_mem & VIRTIO_MMIO_F_IRQFD) {
>> +		err = request_irq(irq, vm_interrupt_irqfd, IRQF_SHARED,
>> +				  dev_name(&vdev->dev), vm_dev);
>> +	} else {
>> +		err = request_irq(irq, vm_interrupt, IRQF_SHARED,
>> +				  dev_name(&vdev->dev), vm_dev);
>> +	}
>>  	if (err)
>>  		return err;
> 
> 
> So still a single interrupt for all VQs.
> Again this doesn't scale: a single CPU has to handle
> interrupts for all of them.
> I think you need to find a way to get per-VQ interrupts.
Yeah, AFAIK it's impossible to distribute works to different CPUs with
only one irq without MSI-X kind mechanism. Assign multiple gsis to one
device, obviously it's consumptive and not scalable. Any ideas? Thx.
> 
>> -- 
>> 1.7.9.5
>>
> 
> .
>