On Sat, May 07, 2022 at 03:19:53PM +0800, Jason Wang
wrote:> This is a rework on the previous IRQ hardening that is done for
> virtio-pci where several drawbacks were found and were reverted:
>
> 1) try to use IRQF_NO_AUTOEN which is not friendly to affinity managed IRQ
> that is used by some device such as virtio-blk
> 2) done only for PCI transport
>
> The vq->broken is re-used in this patch for implementing the IRQ
> hardening. The vq->broken is set to true during both initialization
> and reset. And the vq->broken is set to false in
> virtio_device_ready(). Then vring_interrupt can check and return when
> vq->broken is true. And in this case, switch to return IRQ_NONE to let
> the interrupt core aware of such invalid interrupt to prevent IRQ
> storm.
>
> The reason of using a per queue variable instead of a per device one
> is that we may need it for per queue reset hardening in the future.
>
> Note that the hardening is only done for vring interrupt since the
> config interrupt hardening is already done in commit 22b7050a024d7
> ("virtio: defer config changed notifications"). But the method
that is
> used by config interrupt can't be reused by the vring interrupt
> handler because it uses spinlock to do the synchronization which is
> expensive.
>
> Cc: Thomas Gleixner <tglx at linutronix.de>
> Cc: Peter Zijlstra <peterz at infradead.org>
> Cc: "Paul E. McKenney" <paulmck at kernel.org>
> Cc: Marc Zyngier <maz at kernel.org>
> Cc: Halil Pasic <pasic at linux.ibm.com>
> Cc: Cornelia Huck <cohuck at redhat.com>
> Signed-off-by: Jason Wang <jasowang at redhat.com>
> ---
> drivers/virtio/virtio.c | 15 ++++++++++++---
> drivers/virtio/virtio_ring.c | 11 +++++++----
> include/linux/virtio_config.h | 12 ++++++++++++
> 3 files changed, 31 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
> index 8dde44ea044a..696f5ba4f38e 100644
> --- a/drivers/virtio/virtio.c
> +++ b/drivers/virtio/virtio.c
> @@ -220,6 +220,15 @@ static int virtio_features_ok(struct virtio_device
*dev)
> * */
> void virtio_reset_device(struct virtio_device *dev)
> {
> + /*
> + * The below virtio_synchronize_cbs() guarantees that any
> + * interrupt for this line arriving after
> + * virtio_synchronize_vqs() has completed is guaranteed to see
> + * driver_ready == false.
> + */
> + virtio_break_device(dev);
> + virtio_synchronize_cbs(dev);
> +
> dev->config->reset(dev);
> }
> EXPORT_SYMBOL_GPL(virtio_reset_device);
> @@ -428,6 +437,9 @@ int register_virtio_device(struct virtio_device *dev)
> dev->config_enabled = false;
> dev->config_change_pending = false;
>
> + INIT_LIST_HEAD(&dev->vqs);
> + spin_lock_init(&dev->vqs_list_lock);
> +
> /* We always start by resetting the device, in case a previous
> * driver messed it up. This also tests that code path a little. */
> virtio_reset_device(dev);
> @@ -435,9 +447,6 @@ int register_virtio_device(struct virtio_device *dev)
> /* Acknowledge that we've seen the device. */
> virtio_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE);
>
> - INIT_LIST_HEAD(&dev->vqs);
> - spin_lock_init(&dev->vqs_list_lock);
> -
> /*
> * device_add() causes the bus infrastructure to look for a matching
> * driver.
> diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
> index 5b7df7c455f0..9dfad2890d7a 100644
> --- a/drivers/virtio/virtio_ring.c
> +++ b/drivers/virtio/virtio_ring.c
> @@ -1690,7 +1690,7 @@ static struct virtqueue
*vring_create_virtqueue_packed(
> vq->we_own_ring = true;
> vq->notify = notify;
> vq->weak_barriers = weak_barriers;
> - vq->broken = false;
> + vq->broken = true;
> vq->last_used_idx = 0;
> vq->event_triggered = false;
> vq->num_added = 0;
> @@ -2136,8 +2136,11 @@ irqreturn_t vring_interrupt(int irq, void *_vq)
> return IRQ_NONE;
> }
>
> - if (unlikely(vq->broken))
> - return IRQ_HANDLED;
> + if (unlikely(vq->broken)) {
> + dev_warn_once(&vq->vq.vdev->dev,
> + "virtio vring IRQ raised before DRIVER_OK");
> + return IRQ_NONE;
> + }
>
> /* Just a hint for performance: so it's ok that this can be racy! */
> if (vq->event)
> @@ -2179,7 +2182,7 @@ struct virtqueue *__vring_new_virtqueue(unsigned int
index,
> vq->we_own_ring = false;
> vq->notify = notify;
> vq->weak_barriers = weak_barriers;
> - vq->broken = false;
> + vq->broken = true;
> vq->last_used_idx = 0;
> vq->event_triggered = false;
> vq->num_added = 0;
> diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
> index d8a2340f928e..23f1694cdbd5 100644
> --- a/include/linux/virtio_config.h
> +++ b/include/linux/virtio_config.h
> @@ -256,6 +256,18 @@ void virtio_device_ready(struct virtio_device *dev)
> unsigned status = dev->config->get_status(dev);
>
> BUG_ON(status & VIRTIO_CONFIG_S_DRIVER_OK);
> +
> + /*
> + * The virtio_synchronize_cbs() makes sure vring_interrupt()
> + * will see the driver specific setup if it sees vq->broken
> + * as false.
> + */
> + virtio_synchronize_cbs(dev);
since you mention vq->broken above, maybe add
"set vq->broken to false"
> + __virtio_unbreak_device(dev);
> + /*
> + * The transport is expected ensure the visibility of
to ensure
> + * vq->broken
let's add: "visibility by vq callbacks"
> before setting VIRTIO_CONFIG_S_DRIVER_OK.
> + */
Can I see some analysis of existing transports showing
this is actually the case for them?
And maybe add a comment near set_status to document the
requirement.
> dev->config->set_status(dev, status | VIRTIO_CONFIG_S_DRIVER_OK);
> }
>
> --
> 2.25.1