From: Tomasz Kulasek <tomaszx.kulasek@intel.com>
To: yliu@fridaylinux.org
Cc: daniel.verkamp@intel.com, james.r.harris@intel.com,
pawelx.wodkowski@intel.com, dev@dpdk.org,
Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Subject: [dpdk-dev] [PATCH] vhost: stop device before updating public vring data
Date: Mon, 5 Mar 2018 17:11:08 +0100 [thread overview]
Message-ID: <20180305161108.8232-1-tomaszx.kulasek@intel.com> (raw)
For now DPDK assumes that callfd, kickfd and last_idx are being set just
once during vring initialization and device cannot be running while DPDK
receives SET_VRING_KICK, SET_VRING_CALL and SET_VRING_BASE messages.
However, that assumption is wrong. For Vhost SCSI messages might arrive
at any point of time, possibly multiple times, one after another.
QEMU issues SET_VRING_CALL once during device initialization, then again
during device start. The second message will close previous callfd,
which is still being used by the user-implementation of vhost device.
This results in writing to invalid (closed) callfd.
Other messages like SET_FEATURES, SET_VRING_ADDR etc also will change
internal state of VQ or device. To prevent race condition device should
also be stopped before updateing vring data.
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
---
lib/librte_vhost/vhost_user.c | 40 ++++++++++++++++++++++++++++++++++++++++
1 file changed, 40 insertions(+)
diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
index 65ee33919..3895e6edd 100644
--- a/lib/librte_vhost/vhost_user.c
+++ b/lib/librte_vhost/vhost_user.c
@@ -172,6 +172,10 @@ vhost_user_set_features(struct virtio_net *dev, uint64_t features)
if (dev->notify_ops->features_changed)
dev->notify_ops->features_changed(dev->vid, features);
+ else {
+ dev->flags &= ~VIRTIO_DEV_RUNNING;
+ dev->notify_ops->destroy_device(dev->vid);
+ }
}
dev->features = features;
@@ -487,6 +491,12 @@ vhost_user_set_vring_addr(struct virtio_net **pdev, VhostUserMsg *msg)
if (dev->mem == NULL)
return -1;
+ /* Remove from the data plane. */
+ if (dev->flags & VIRTIO_DEV_RUNNING) {
+ dev->flags &= ~VIRTIO_DEV_RUNNING;
+ dev->notify_ops->destroy_device(dev->vid);
+ }
+
/* addr->index refers to the queue index. The txq 1, rxq is 0. */
vq = dev->virtqueue[msg->payload.addr.index];
@@ -517,6 +527,12 @@ static int
vhost_user_set_vring_base(struct virtio_net *dev,
VhostUserMsg *msg)
{
+ /* Remove from the data plane. */
+ if (dev->flags & VIRTIO_DEV_RUNNING) {
+ dev->flags &= ~VIRTIO_DEV_RUNNING;
+ dev->notify_ops->destroy_device(dev->vid);
+ }
+
dev->virtqueue[msg->payload.state.index]->last_used_idx =
msg->payload.state.num;
dev->virtqueue[msg->payload.state.index]->last_avail_idx =
@@ -796,6 +812,12 @@ vhost_user_set_vring_call(struct virtio_net *dev, struct VhostUserMsg *pmsg)
struct vhost_vring_file file;
struct vhost_virtqueue *vq;
+ /* Remove from the data plane. */
+ if (dev->flags & VIRTIO_DEV_RUNNING) {
+ dev->flags &= ~VIRTIO_DEV_RUNNING;
+ dev->notify_ops->destroy_device(dev->vid);
+ }
+
file.index = pmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
if (pmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK)
file.fd = VIRTIO_INVALID_EVENTFD;
@@ -818,6 +840,12 @@ vhost_user_set_vring_kick(struct virtio_net **pdev, struct VhostUserMsg *pmsg)
struct vhost_virtqueue *vq;
struct virtio_net *dev = *pdev;
+ /* Remove from the data plane. */
+ if (dev->flags & VIRTIO_DEV_RUNNING) {
+ dev->flags &= ~VIRTIO_DEV_RUNNING;
+ dev->notify_ops->destroy_device(dev->vid);
+ }
+
file.index = pmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
if (pmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK)
file.fd = VIRTIO_INVALID_EVENTFD;
@@ -959,6 +987,12 @@ vhost_user_set_protocol_features(struct virtio_net *dev,
if (protocol_features & ~VHOST_USER_PROTOCOL_FEATURES)
return;
+ /* Remove from the data plane. */
+ if (dev->flags & VIRTIO_DEV_RUNNING) {
+ dev->flags &= ~VIRTIO_DEV_RUNNING;
+ dev->notify_ops->destroy_device(dev->vid);
+ }
+
dev->protocol_features = protocol_features;
}
@@ -981,6 +1015,12 @@ vhost_user_set_log_base(struct virtio_net *dev, struct VhostUserMsg *msg)
return -1;
}
+ /* Remove from the data plane. */
+ if (dev->flags & VIRTIO_DEV_RUNNING) {
+ dev->flags &= ~VIRTIO_DEV_RUNNING;
+ dev->notify_ops->destroy_device(dev->vid);
+ }
+
size = msg->payload.log.mmap_size;
off = msg->payload.log.mmap_offset;
RTE_LOG(INFO, VHOST_CONFIG,
--
2.14.1
next reply other threads:[~2018-03-05 16:11 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-05 16:11 Tomasz Kulasek [this message]
2018-03-06 16:26 ` Maxime Coquelin
2018-03-07 9:16 ` Wodkowski, PawelX
2018-03-07 10:09 ` Maxime Coquelin
2018-03-07 10:59 ` Wodkowski, PawelX
2018-03-07 11:29 ` Maxime Coquelin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20180305161108.8232-1-tomaszx.kulasek@intel.com \
--to=tomaszx.kulasek@intel.com \
--cc=daniel.verkamp@intel.com \
--cc=dariuszx.stojaczyk@intel.com \
--cc=dev@dpdk.org \
--cc=james.r.harris@intel.com \
--cc=pawelx.wodkowski@intel.com \
--cc=yliu@fridaylinux.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).