[V9fs-developer] [PATCH v3] Fix a hard lockup case in the virtio transport

[V9fs-developer] [PATCH v3] Fix a hard lockup case in the virtio transport

[jiangyiwen]

When client has multiple threads that issue io requests
all the time, and the server has a very good performance,
it may cause cpu is running in the irq context for a long
time because it can check virtqueue has buf in the *while*
loop.

So we should keep chan->lock in the whole loop.

Signed-off-by: Yiwen Jiang <jiangyiwen@huawei.com>
---
 net/9p/trans_virtio.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 05006cb..3589864 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -144,24 +144,25 @@ static void req_done(struct virtqueue *vq)
 	struct virtio_chan *chan = vq->vdev->priv;
 	unsigned int len;
 	struct p9_req_t *req;
+	bool need_wakeup = false;
 	unsigned long flags;

 	p9_debug(P9_DEBUG_TRANS, ": request done\n");

-	while (1) {
-		spin_lock_irqsave(&chan->lock, flags);
-		req = virtqueue_get_buf(chan->vq, &len);
-		if (req == NULL) {
-			spin_unlock_irqrestore(&chan->lock, flags);
-			break;
+	spin_lock_irqsave(&chan->lock, flags);
+	while ((req = virtqueue_get_buf(chan->vq, &len)) != NULL) {
+		if (!chan->ring_bufs_avail) {
+			chan->ring_bufs_avail = 1;
+			need_wakeup = true;
 		}
-		chan->ring_bufs_avail = 1;
-		spin_unlock_irqrestore(&chan->lock, flags);
-		/* Wakeup if anyone waiting for VirtIO ring space. */
-		wake_up(chan->vc_wq);
+
 		if (len)
 			p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
 	}
+	spin_unlock_irqrestore(&chan->lock, flags);
+	/* Wakeup if anyone waiting for VirtIO ring space. */
+	if (need_wakeup)
+		wake_up(chan->vc_wq);
 }

 /**
-- 
1.8.3.1

Re: [V9fs-developer] [PATCH v3] Fix a hard lockup case in the virtio transport

[piaojun]

LGTM

On 2018/7/19 15:17, jiangyiwen wrote:
> When client has multiple threads that issue io requests
> all the time, and the server has a very good performance,
> it may cause cpu is running in the irq context for a long
> time because it can check virtqueue has buf in the *while*
> loop.
> 
> So we should keep chan->lock in the whole loop.
> 
> Signed-off-by: Yiwen Jiang <jiangyiwen@huawei.com>
Reviewed-by: Jun Piao <piaojun@huawei.com>
> ---
>  net/9p/trans_virtio.c | 21 +++++++++++----------
>  1 file changed, 11 insertions(+), 10 deletions(-)
> 
> diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
> index 05006cb..3589864 100644
> --- a/net/9p/trans_virtio.c
> +++ b/net/9p/trans_virtio.c
> @@ -144,24 +144,25 @@ static void req_done(struct virtqueue *vq)
>  	struct virtio_chan *chan = vq->vdev->priv;
>  	unsigned int len;
>  	struct p9_req_t *req;
> +	bool need_wakeup = false;
>  	unsigned long flags;
> 
>  	p9_debug(P9_DEBUG_TRANS, ": request done\n");
> 
> -	while (1) {
> -		spin_lock_irqsave(&chan->lock, flags);
> -		req = virtqueue_get_buf(chan->vq, &len);
> -		if (req == NULL) {
> -			spin_unlock_irqrestore(&chan->lock, flags);
> -			break;
> +	spin_lock_irqsave(&chan->lock, flags);
> +	while ((req = virtqueue_get_buf(chan->vq, &len)) != NULL) {
> +		if (!chan->ring_bufs_avail) {
> +			chan->ring_bufs_avail = 1;
> +			need_wakeup = true;
>  		}
> -		chan->ring_bufs_avail = 1;
> -		spin_unlock_irqrestore(&chan->lock, flags);
> -		/* Wakeup if anyone waiting for VirtIO ring space. */
> -		wake_up(chan->vc_wq);
> +
>  		if (len)
>  			p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
>  	}
> +	spin_unlock_irqrestore(&chan->lock, flags);
> +	/* Wakeup if anyone waiting for VirtIO ring space. */
> +	if (need_wakeup)
> +		wake_up(chan->vc_wq);
>  }
> 
>  /**
>