Re: [PATCH 3/3] virtio-blk: Add bio-based IO path for virtio-blk
From: Stefan Hajnoczi <hidden>
Date: 2012-06-18 09:37:11
Also in:
kvm, lkml
On Mon, Jun 18, 2012 at 7:53 AM, Asias He [off-list ref] wrote:
quoted hunk ↗ jump to hunk
+static void virtblk_add_buf_wait(struct virtio_blk *vblk, + struct virtblk_req *vbr, + unsigned long out, + unsigned long in) +{ + DEFINE_WAIT(wait); + + for (;;) { + prepare_to_wait_exclusive(&vblk->queue_wait, &wait, + TASK_UNINTERRUPTIBLE); + + spin_lock_irq(vblk->disk->queue->queue_lock); + if (virtqueue_add_buf(vblk->vq, vbr->sg, out, in, vbr, + GFP_ATOMIC) < 0) { + spin_unlock_irq(vblk->disk->queue->queue_lock); + io_schedule(); + } else { + virtqueue_kick(vblk->vq); + spin_unlock_irq(vblk->disk->queue->queue_lock); + break; + } + + }
Is there a meaningful condition where we would cancel this request (e.g. signal)? If the vring fills up for some reason and we get stuck here the user might wish to kill hung processes. Stefan