Separate virtqueue_kick_prepare from virtqueue_notify, so that the expensive vmexit is done without holding the lock. Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx> --- drivers/scsi/virtio_scsi.c | 4 +++- 1 files changed, 3 insertions(+), 1 deletions(-) diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c index 1b38431..b0ad5aa 100644 --- a/drivers/scsi/virtio_scsi.c +++ b/drivers/scsi/virtio_scsi.c @@ -264,9 +264,11 @@ static int virtscsi_kick_cmd(struct virtio_scsi *vscsi, struct virtqueue *vq, ret = virtqueue_add_buf(vq, vscsi->sg, out_num, in_num, cmd, gfp); if (ret >= 0) - virtqueue_kick(vq); + ret = virtqueue_kick_prepare(vq); spin_unlock_irqrestore(&vscsi->vq_lock, flags); + if (ret > 0) + virtqueue_notify(vq); return ret; } -- 1.7.1 -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
