| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20101028052021.GD5599@redhat.com>
Date: Thu, 28 Oct 2010 07:20:21 +0200
From: "Michael S. Tsirkin" <mst@...hat.com>
To: Shirley Ma <mashirle@...ibm.com>
Cc: David Miller <davem@...emloft.net>, netdev@...r.kernel.org,
kvm@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [RFC PATCH 1/1] vhost: TX used buffer guest signal accumulation
On Wed, Oct 27, 2010 at 09:40:04PM -0700, Shirley Ma wrote:
> Resubmit this patch for fixing some minor error (white space, typo).
>
> Signed-off-by: Shirley Ma <xma@...ibm.com>
My concern is this can delay signalling for unlimited time.
Could you pls test this with guests that do not have
2b5bbe3b8bee8b38bdc27dd9c0270829b6eb7eeb
b0c39dbdc204006ef3558a66716ff09797619778
that is 2.6.31 and older?
This seems to be slighltly out of spec, even though
for TX, signals are less important.
Two ideas:
1. How about writing out used, just delaying the signal?
This way we don't have to queue separately.
2. How about flushing out queued stuff before we exit
the handle_tx loop? That would address most of
the spec issue.
> ---
> drivers/vhost/net.c | 20 +++++++++++++++++++-
> drivers/vhost/vhost.c | 32 ++++++++++++++++++++++++++++++++
> drivers/vhost/vhost.h | 3 +++
> 3 files changed, 54 insertions(+), 1 deletions(-)
>
> diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
> index 4b4da5b..3eb8016 100644
> --- a/drivers/vhost/net.c
> +++ b/drivers/vhost/net.c
> @@ -128,6 +128,7 @@ static void handle_tx(struct vhost_net *net)
> int err, wmem;
> size_t hdr_size;
> struct socket *sock;
> + int max_pend = vq->num - (vq->num >> 2);
>
> sock = rcu_dereference_check(vq->private_data,
> lockdep_is_held(&vq->mutex));
> @@ -198,7 +199,24 @@ static void handle_tx(struct vhost_net *net)
> if (err != len)
> pr_debug("Truncated TX packet: "
> " len %d != %zd\n", err, len);
> - vhost_add_used_and_signal(&net->dev, vq, head, 0);
> + /*
> + * if no pending buffer size allocate, signal used buffer
> + * one by one, otherwise, signal used buffer when reaching
> + * 3/4 ring size to reduce CPU utilization.
> + */
> + if (unlikely(vq->pend))
> + vhost_add_used_and_signal(&net->dev, vq, head, 0);
> + else {
> + vq->pend[vq->num_pend].id = head;
> + vq->pend[vq->num_pend].len = 0;
> + ++vq->num_pend;
> + if (vq->num_pend == max_pend) {
> + vhost_add_used_and_signal_n(&net->dev, vq,
> + vq->pend,
> + vq->num_pend);
> + vq->num_pend = 0;
> + }
> + }
> total_len += len;
> if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
> vhost_poll_queue(&vq->poll);
> diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
> index 94701ff..f2f3288 100644
> --- a/drivers/vhost/vhost.c
> +++ b/drivers/vhost/vhost.c
> @@ -170,6 +170,16 @@ static void vhost_vq_reset(struct vhost_dev *dev,
> vq->call_ctx = NULL;
> vq->call = NULL;
> vq->log_ctx = NULL;
> + /* signal pending used buffers */
> + if (vq->pend) {
> + if (vq->num_pend != 0) {
> + vhost_add_used_and_signal_n(dev, vq, vq->pend,
> + vq->num_pend);
> + vq->num_pend = 0;
> + }
> + kfree(vq->pend);
> + }
> + vq->pend = NULL;
> }
>
> static int vhost_worker(void *data)
> @@ -273,7 +283,14 @@ long vhost_dev_init(struct vhost_dev *dev,
> dev->vqs[i].heads = NULL;
> dev->vqs[i].dev = dev;
> mutex_init(&dev->vqs[i].mutex);
> + dev->vqs[i].num_pend = 0;
> + dev->vqs[i].pend = NULL;
> vhost_vq_reset(dev, dev->vqs + i);
> + /* signal 3/4 of ring size used buffers */
> + dev->vqs[i].pend = kmalloc((dev->vqs[i].num -
> + (dev->vqs[i].num >> 2)) *
> + sizeof *dev->vqs[i].pend,
> + GFP_KERNEL);
> if (dev->vqs[i].handle_kick)
> vhost_poll_init(&dev->vqs[i].poll,
> dev->vqs[i].handle_kick, POLLIN, dev);
> @@ -599,6 +616,21 @@ static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
> r = -EINVAL;
> break;
> }
> + if (vq->num != s.num) {
> + /* signal used buffers first */
> + if (vq->pend) {
> + if (vq->num_pend != 0) {
> + vhost_add_used_and_signal_n(vq->dev, vq,
> + vq->pend,
> + vq->num_pend);
> + vq->num_pend = 0;
> + }
> + kfree(vq->pend);
> + }
> + /* realloc pending used buffers size */
> + vq->pend = kmalloc((s.num - (s.num >> 2)) *
> + sizeof *vq->pend, GFP_KERNEL);
> + }
> vq->num = s.num;
> break;
> case VHOST_SET_VRING_BASE:
> diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
> index 073d06a..78949c0 100644
> --- a/drivers/vhost/vhost.h
> +++ b/drivers/vhost/vhost.h
> @@ -108,6 +108,9 @@ struct vhost_virtqueue {
> /* Log write descriptors */
> void __user *log_base;
> struct vhost_log *log;
> + /* delay multiple used buffers to signal once */
> + int num_pend;
> + struct vring_used_elem *pend;
> };
>
> struct vhost_dev {
>
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists