We try using cancel_delayed_work_sync() to prevent the work from
enabling NAPI. This is insufficient since we don't disable the source
of the refill work scheduling. This means an NAPI poll callback after
cancel_delayed_work_sync() can schedule the refill work then can
re-enable the NAPI that leads to use-after-free [1].
Since the work can enable NAPI, we can't simply disable NAPI before
calling cancel_delayed_work_sync(). So fix this by introducing a
dedicated boolean to control whether or not the work could be
scheduled from NAPI.
[1]
==================================================================
BUG: KASAN: use-after-free in refill_work+0x43/0xd4
Read of size 2 at addr ffff88810562c92e by task kworker/2:1/42
CPU: 2 PID: 42 Comm: kworker/2:1 Not tainted 5.19.0-rc1+ #480
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
Workqueue: events refill_work
Call Trace:
<TASK>
dump_stack_lvl+0x34/0x44
print_report.cold+0xbb/0x6ac
? _printk+0xad/0xde
? refill_work+0x43/0xd4
kasan_report+0xa8/0x130
? refill_work+0x43/0xd4
refill_work+0x43/0xd4
process_one_work+0x43d/0x780
worker_thread+0x2a0/0x6f0
? process_one_work+0x780/0x780
kthread+0x167/0x1a0
? kthread_exit+0x50/0x50
ret_from_fork+0x22/0x30
</TASK>
...
Fixes: b2baed69e605c ("virtio_net: set/cancel work on ndo_open/ndo_stop")
Signed-off-by: Jason Wang <[email protected]>
---
drivers/net/virtio_net.c | 38 ++++++++++++++++++++++++++++++++++++--
1 file changed, 36 insertions(+), 2 deletions(-)
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index db05b5e930be..21bf1e5c81ef 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -251,6 +251,12 @@ struct virtnet_info {
/* Does the affinity hint is set for virtqueues? */
bool affinity_hint_set;
+ /* Is refill work enabled? */
+ bool refill_work_enabled;
+
+ /* The lock to synchronize the access to refill_work_enabled */
+ spinlock_t refill_lock;
+
/* CPU hotplug instances for online & dead */
struct hlist_node node;
struct hlist_node node_dead;
@@ -348,6 +354,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
return p;
}
+static void enable_refill_work(struct virtnet_info *vi)
+{
+ spin_lock(&vi->refill_lock);
+ vi->refill_work_enabled = true;
+ spin_unlock(&vi->refill_lock);
+}
+
+static void disable_refill_work(struct virtnet_info *vi)
+{
+ spin_lock(&vi->refill_lock);
+ vi->refill_work_enabled = false;
+ spin_unlock(&vi->refill_lock);
+}
+
static void virtqueue_napi_schedule(struct napi_struct *napi,
struct virtqueue *vq)
{
@@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
}
if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
- if (!try_fill_recv(vi, rq, GFP_ATOMIC))
- schedule_delayed_work(&vi->refill, 0);
+ if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
+ spin_lock(&vi->refill_lock);
+ if (vi->refill_work_enabled)
+ schedule_delayed_work(&vi->refill, 0);
+ spin_unlock(&vi->refill_lock);
+ }
}
u64_stats_update_begin(&rq->stats.syncp);
@@ -1651,6 +1675,8 @@ static int virtnet_open(struct net_device *dev)
struct virtnet_info *vi = netdev_priv(dev);
int i, err;
+ enable_refill_work(vi);
+
for (i = 0; i < vi->max_queue_pairs; i++) {
if (i < vi->curr_queue_pairs)
/* Make sure we have some buffers: if oom use wq. */
@@ -2033,6 +2059,8 @@ static int virtnet_close(struct net_device *dev)
struct virtnet_info *vi = netdev_priv(dev);
int i;
+ /* Make sure NAPI doesn't schedule refill work */
+ disable_refill_work(vi);
/* Make sure refill_work doesn't re-enable napi! */
cancel_delayed_work_sync(&vi->refill);
@@ -2776,6 +2804,9 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
netif_tx_lock_bh(vi->dev);
netif_device_detach(vi->dev);
netif_tx_unlock_bh(vi->dev);
+ /* Make sure NAPI doesn't schedule refill work */
+ disable_refill_work(vi);
+ /* Make sure refill_work doesn't re-enable napi! */
cancel_delayed_work_sync(&vi->refill);
if (netif_running(vi->dev)) {
@@ -2799,6 +2830,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)
virtio_device_ready(vdev);
+ enable_refill_work(vi);
+
if (netif_running(vi->dev)) {
for (i = 0; i < vi->curr_queue_pairs; i++)
if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
@@ -3548,6 +3581,7 @@ static int virtnet_probe(struct virtio_device *vdev)
vdev->priv = vi;
INIT_WORK(&vi->config_work, virtnet_config_changed_work);
+ spin_lock_init(&vi->refill_lock);
/* If we can receive ANY GSO packets, we must allocate large ones. */
if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
--
2.25.1
On Thu, 30 Jun 2022 10:08:04 +0800 Jason Wang wrote:
> +static void enable_refill_work(struct virtnet_info *vi)
> +{
> + spin_lock(&vi->refill_lock);
> + vi->refill_work_enabled = true;
> + spin_unlock(&vi->refill_lock);
> +}
> +
> +static void disable_refill_work(struct virtnet_info *vi)
> +{
> + spin_lock(&vi->refill_lock);
> + vi->refill_work_enabled = false;
> + spin_unlock(&vi->refill_lock);
> +}
> +
> static void virtqueue_napi_schedule(struct napi_struct *napi,
> struct virtqueue *vq)
> {
> @@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
> }
>
> if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
> - if (!try_fill_recv(vi, rq, GFP_ATOMIC))
> - schedule_delayed_work(&vi->refill, 0);
> + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
> + spin_lock(&vi->refill_lock);
> + if (vi->refill_work_enabled)
> + schedule_delayed_work(&vi->refill, 0);
> + spin_unlock(&vi->refill_lock);
Are you sure you can use the basic spin_lock() flavor in all cases?
Isn't the disable/enable called from a different context than this
thing here?
The entire delayed work construct seems a little risky because the work
may go to sleep after disabling napi, causing large latency spikes.
I guess you must have a good reason no to simply reschedule the NAPI
and keep retrying with GFP_ATOMIC...
Please add the target tree name to the subject.
On Thu, 30 Jun 2022 10:08:04 +0800, Jason Wang <[email protected]> wrote:
> We try using cancel_delayed_work_sync() to prevent the work from
> enabling NAPI. This is insufficient since we don't disable the source
> of the refill work scheduling. This means an NAPI poll callback after
> cancel_delayed_work_sync() can schedule the refill work then can
> re-enable the NAPI that leads to use-after-free [1].
Can you explain in more detail how this happened?
napi_disable() is normally called after cancel_delayed_work_sync(). This ensures
that all napi callbacks will end, and the new napi_disable() will wait.
There will be no re-enable napi.
So I guess the use-after-free is caused by refill_work being called after
dev/vi/napi is released. In this way, we can just call
cancel_delayed_work_sync() after napi_disalbe().
Thanks.
>
> Since the work can enable NAPI, we can't simply disable NAPI before
> calling cancel_delayed_work_sync(). So fix this by introducing a
> dedicated boolean to control whether or not the work could be
> scheduled from NAPI.
>
> [1]
> ==================================================================
> BUG: KASAN: use-after-free in refill_work+0x43/0xd4
> Read of size 2 at addr ffff88810562c92e by task kworker/2:1/42
>
> CPU: 2 PID: 42 Comm: kworker/2:1 Not tainted 5.19.0-rc1+ #480
> Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
> Workqueue: events refill_work
> Call Trace:
> <TASK>
> dump_stack_lvl+0x34/0x44
> print_report.cold+0xbb/0x6ac
> ? _printk+0xad/0xde
> ? refill_work+0x43/0xd4
> kasan_report+0xa8/0x130
> ? refill_work+0x43/0xd4
> refill_work+0x43/0xd4
> process_one_work+0x43d/0x780
> worker_thread+0x2a0/0x6f0
> ? process_one_work+0x780/0x780
> kthread+0x167/0x1a0
> ? kthread_exit+0x50/0x50
> ret_from_fork+0x22/0x30
> </TASK>
> ...
>
> Fixes: b2baed69e605c ("virtio_net: set/cancel work on ndo_open/ndo_stop")
> Signed-off-by: Jason Wang <[email protected]>
> ---
> drivers/net/virtio_net.c | 38 ++++++++++++++++++++++++++++++++++++--
> 1 file changed, 36 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> index db05b5e930be..21bf1e5c81ef 100644
> --- a/drivers/net/virtio_net.c
> +++ b/drivers/net/virtio_net.c
> @@ -251,6 +251,12 @@ struct virtnet_info {
> /* Does the affinity hint is set for virtqueues? */
> bool affinity_hint_set;
>
> + /* Is refill work enabled? */
> + bool refill_work_enabled;
> +
> + /* The lock to synchronize the access to refill_work_enabled */
> + spinlock_t refill_lock;
> +
> /* CPU hotplug instances for online & dead */
> struct hlist_node node;
> struct hlist_node node_dead;
> @@ -348,6 +354,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
> return p;
> }
>
> +static void enable_refill_work(struct virtnet_info *vi)
> +{
> + spin_lock(&vi->refill_lock);
> + vi->refill_work_enabled = true;
> + spin_unlock(&vi->refill_lock);
> +}
> +
> +static void disable_refill_work(struct virtnet_info *vi)
> +{
> + spin_lock(&vi->refill_lock);
> + vi->refill_work_enabled = false;
> + spin_unlock(&vi->refill_lock);
> +}
> +
> static void virtqueue_napi_schedule(struct napi_struct *napi,
> struct virtqueue *vq)
> {
> @@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
> }
>
> if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
> - if (!try_fill_recv(vi, rq, GFP_ATOMIC))
> - schedule_delayed_work(&vi->refill, 0);
> + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
> + spin_lock(&vi->refill_lock);
> + if (vi->refill_work_enabled)
> + schedule_delayed_work(&vi->refill, 0);
> + spin_unlock(&vi->refill_lock);
> + }
> }
>
> u64_stats_update_begin(&rq->stats.syncp);
> @@ -1651,6 +1675,8 @@ static int virtnet_open(struct net_device *dev)
> struct virtnet_info *vi = netdev_priv(dev);
> int i, err;
>
> + enable_refill_work(vi);
> +
> for (i = 0; i < vi->max_queue_pairs; i++) {
> if (i < vi->curr_queue_pairs)
> /* Make sure we have some buffers: if oom use wq. */
> @@ -2033,6 +2059,8 @@ static int virtnet_close(struct net_device *dev)
> struct virtnet_info *vi = netdev_priv(dev);
> int i;
>
> + /* Make sure NAPI doesn't schedule refill work */
> + disable_refill_work(vi);
> /* Make sure refill_work doesn't re-enable napi! */
> cancel_delayed_work_sync(&vi->refill);
>
> @@ -2776,6 +2804,9 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
> netif_tx_lock_bh(vi->dev);
> netif_device_detach(vi->dev);
> netif_tx_unlock_bh(vi->dev);
> + /* Make sure NAPI doesn't schedule refill work */
> + disable_refill_work(vi);
> + /* Make sure refill_work doesn't re-enable napi! */
> cancel_delayed_work_sync(&vi->refill);
>
> if (netif_running(vi->dev)) {
> @@ -2799,6 +2830,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)
>
> virtio_device_ready(vdev);
>
> + enable_refill_work(vi);
> +
> if (netif_running(vi->dev)) {
> for (i = 0; i < vi->curr_queue_pairs; i++)
> if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
> @@ -3548,6 +3581,7 @@ static int virtnet_probe(struct virtio_device *vdev)
> vdev->priv = vi;
>
> INIT_WORK(&vi->config_work, virtnet_config_changed_work);
> + spin_lock_init(&vi->refill_lock);
>
> /* If we can receive ANY GSO packets, we must allocate large ones. */
> if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
> --
> 2.25.1
>
On Thu, Jun 30, 2022 at 2:07 PM Jason Wang <[email protected]> wrote:
>
> On Thu, Jun 30, 2022 at 10:51 AM Jakub Kicinski <[email protected]> wrote:
> >
> > On Thu, 30 Jun 2022 10:08:04 +0800 Jason Wang wrote:
> > > +static void enable_refill_work(struct virtnet_info *vi)
> > > +{
> > > + spin_lock(&vi->refill_lock);
> > > + vi->refill_work_enabled = true;
> > > + spin_unlock(&vi->refill_lock);
> > > +}
> > > +
> > > +static void disable_refill_work(struct virtnet_info *vi)
> > > +{
> > > + spin_lock(&vi->refill_lock);
> > > + vi->refill_work_enabled = false;
> > > + spin_unlock(&vi->refill_lock);
> > > +}
> > > +
> > > static void virtqueue_napi_schedule(struct napi_struct *napi,
> > > struct virtqueue *vq)
> > > {
> > > @@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
> > > }
> > >
> > > if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
> > > - if (!try_fill_recv(vi, rq, GFP_ATOMIC))
> > > - schedule_delayed_work(&vi->refill, 0);
> > > + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
> > > + spin_lock(&vi->refill_lock);
> > > + if (vi->refill_work_enabled)
> > > + schedule_delayed_work(&vi->refill, 0);
> > > + spin_unlock(&vi->refill_lock);
> >
> > Are you sure you can use the basic spin_lock() flavor in all cases?
> > Isn't the disable/enable called from a different context than this
> > thing here?
>
> This function will only be called in bh so it's safe.
Ok, so it looks like we should use the bh variant in close. Otherwise
we may have a deadlock. Will fix it.
Thanks
>
> >
> > The entire delayed work construct seems a little risky because the work
> > may go to sleep after disabling napi, causing large latency spikes.
>
> Yes, but it only happens on OOM.
>
> > I guess you must have a good reason no to simply reschedule the NAPI
> > and keep retrying with GFP_ATOMIC...
>
> Less pressure on the memory allocator on OOM probably, but it looks
> like an independent issue that might be optimized in the future.
>
> >
> > Please add the target tree name to the subject.
>
> Ok
>
> Thanks
>
> >
On Thu, Jun 30, 2022 at 10:51 AM Jakub Kicinski <[email protected]> wrote:
>
> On Thu, 30 Jun 2022 10:08:04 +0800 Jason Wang wrote:
> > +static void enable_refill_work(struct virtnet_info *vi)
> > +{
> > + spin_lock(&vi->refill_lock);
> > + vi->refill_work_enabled = true;
> > + spin_unlock(&vi->refill_lock);
> > +}
> > +
> > +static void disable_refill_work(struct virtnet_info *vi)
> > +{
> > + spin_lock(&vi->refill_lock);
> > + vi->refill_work_enabled = false;
> > + spin_unlock(&vi->refill_lock);
> > +}
> > +
> > static void virtqueue_napi_schedule(struct napi_struct *napi,
> > struct virtqueue *vq)
> > {
> > @@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
> > }
> >
> > if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
> > - if (!try_fill_recv(vi, rq, GFP_ATOMIC))
> > - schedule_delayed_work(&vi->refill, 0);
> > + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
> > + spin_lock(&vi->refill_lock);
> > + if (vi->refill_work_enabled)
> > + schedule_delayed_work(&vi->refill, 0);
> > + spin_unlock(&vi->refill_lock);
>
> Are you sure you can use the basic spin_lock() flavor in all cases?
> Isn't the disable/enable called from a different context than this
> thing here?
This function will only be called in bh so it's safe.
>
> The entire delayed work construct seems a little risky because the work
> may go to sleep after disabling napi, causing large latency spikes.
Yes, but it only happens on OOM.
> I guess you must have a good reason no to simply reschedule the NAPI
> and keep retrying with GFP_ATOMIC...
Less pressure on the memory allocator on OOM probably, but it looks
like an independent issue that might be optimized in the future.
>
> Please add the target tree name to the subject.
Ok
Thanks
>
On Thu, Jun 30, 2022 at 10:22 AM Xuan Zhuo <[email protected]> wrote:
>
> On Thu, 30 Jun 2022 10:08:04 +0800, Jason Wang <[email protected]> wrote:
> > We try using cancel_delayed_work_sync() to prevent the work from
> > enabling NAPI. This is insufficient since we don't disable the source
> > of the refill work scheduling. This means an NAPI poll callback after
> > cancel_delayed_work_sync() can schedule the refill work then can
> > re-enable the NAPI that leads to use-after-free [1].
>
>
> Can you explain in more detail how this happened?
>
> napi_disable() is normally called after cancel_delayed_work_sync(). This ensures
> that all napi callbacks will end, and the new napi_disable() will wait.
> There will be no re-enable napi.
An rx interrupt that may come between after the cancel_delayed_work()
but before the napi_disable(). It schedules a refill_work that may run
after the napi_disable() in virtnet_close().
>
> So I guess the use-after-free is caused by refill_work being called after
> dev/vi/napi is released. In this way, we can just call
> cancel_delayed_work_sync() after napi_disalbe().
So the refill_work can re-enable the NAPI when it is run after
napi_disable() in this case.
Thanks
>
> Thanks.
>
> >
> > Since the work can enable NAPI, we can't simply disable NAPI before
> > calling cancel_delayed_work_sync(). So fix this by introducing a
> > dedicated boolean to control whether or not the work could be
> > scheduled from NAPI.
> >
> > [1]
> > ==================================================================
> > BUG: KASAN: use-after-free in refill_work+0x43/0xd4
> > Read of size 2 at addr ffff88810562c92e by task kworker/2:1/42
> >
> > CPU: 2 PID: 42 Comm: kworker/2:1 Not tainted 5.19.0-rc1+ #480
> > Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
> > Workqueue: events refill_work
> > Call Trace:
> > <TASK>
> > dump_stack_lvl+0x34/0x44
> > print_report.cold+0xbb/0x6ac
> > ? _printk+0xad/0xde
> > ? refill_work+0x43/0xd4
> > kasan_report+0xa8/0x130
> > ? refill_work+0x43/0xd4
> > refill_work+0x43/0xd4
> > process_one_work+0x43d/0x780
> > worker_thread+0x2a0/0x6f0
> > ? process_one_work+0x780/0x780
> > kthread+0x167/0x1a0
> > ? kthread_exit+0x50/0x50
> > ret_from_fork+0x22/0x30
> > </TASK>
> > ...
> >
> > Fixes: b2baed69e605c ("virtio_net: set/cancel work on ndo_open/ndo_stop")
> > Signed-off-by: Jason Wang <[email protected]>
> > ---
> > drivers/net/virtio_net.c | 38 ++++++++++++++++++++++++++++++++++++--
> > 1 file changed, 36 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > index db05b5e930be..21bf1e5c81ef 100644
> > --- a/drivers/net/virtio_net.c
> > +++ b/drivers/net/virtio_net.c
> > @@ -251,6 +251,12 @@ struct virtnet_info {
> > /* Does the affinity hint is set for virtqueues? */
> > bool affinity_hint_set;
> >
> > + /* Is refill work enabled? */
> > + bool refill_work_enabled;
> > +
> > + /* The lock to synchronize the access to refill_work_enabled */
> > + spinlock_t refill_lock;
> > +
> > /* CPU hotplug instances for online & dead */
> > struct hlist_node node;
> > struct hlist_node node_dead;
> > @@ -348,6 +354,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
> > return p;
> > }
> >
> > +static void enable_refill_work(struct virtnet_info *vi)
> > +{
> > + spin_lock(&vi->refill_lock);
> > + vi->refill_work_enabled = true;
> > + spin_unlock(&vi->refill_lock);
> > +}
> > +
> > +static void disable_refill_work(struct virtnet_info *vi)
> > +{
> > + spin_lock(&vi->refill_lock);
> > + vi->refill_work_enabled = false;
> > + spin_unlock(&vi->refill_lock);
> > +}
> > +
> > static void virtqueue_napi_schedule(struct napi_struct *napi,
> > struct virtqueue *vq)
> > {
> > @@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
> > }
> >
> > if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
> > - if (!try_fill_recv(vi, rq, GFP_ATOMIC))
> > - schedule_delayed_work(&vi->refill, 0);
> > + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
> > + spin_lock(&vi->refill_lock);
> > + if (vi->refill_work_enabled)
> > + schedule_delayed_work(&vi->refill, 0);
> > + spin_unlock(&vi->refill_lock);
> > + }
> > }
> >
> > u64_stats_update_begin(&rq->stats.syncp);
> > @@ -1651,6 +1675,8 @@ static int virtnet_open(struct net_device *dev)
> > struct virtnet_info *vi = netdev_priv(dev);
> > int i, err;
> >
> > + enable_refill_work(vi);
> > +
> > for (i = 0; i < vi->max_queue_pairs; i++) {
> > if (i < vi->curr_queue_pairs)
> > /* Make sure we have some buffers: if oom use wq. */
> > @@ -2033,6 +2059,8 @@ static int virtnet_close(struct net_device *dev)
> > struct virtnet_info *vi = netdev_priv(dev);
> > int i;
> >
> > + /* Make sure NAPI doesn't schedule refill work */
> > + disable_refill_work(vi);
> > /* Make sure refill_work doesn't re-enable napi! */
> > cancel_delayed_work_sync(&vi->refill);
> >
> > @@ -2776,6 +2804,9 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
> > netif_tx_lock_bh(vi->dev);
> > netif_device_detach(vi->dev);
> > netif_tx_unlock_bh(vi->dev);
> > + /* Make sure NAPI doesn't schedule refill work */
> > + disable_refill_work(vi);
> > + /* Make sure refill_work doesn't re-enable napi! */
> > cancel_delayed_work_sync(&vi->refill);
> >
> > if (netif_running(vi->dev)) {
> > @@ -2799,6 +2830,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)
> >
> > virtio_device_ready(vdev);
> >
> > + enable_refill_work(vi);
> > +
> > if (netif_running(vi->dev)) {
> > for (i = 0; i < vi->curr_queue_pairs; i++)
> > if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
> > @@ -3548,6 +3581,7 @@ static int virtnet_probe(struct virtio_device *vdev)
> > vdev->priv = vi;
> >
> > INIT_WORK(&vi->config_work, virtnet_config_changed_work);
> > + spin_lock_init(&vi->refill_lock);
> >
> > /* If we can receive ANY GSO packets, we must allocate large ones. */
> > if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
> > --
> > 2.25.1
> >
>
On Thu, Jun 30, 2022 at 2:26 PM Xuan Zhuo <[email protected]> wrote:
>
> On Thu, 30 Jun 2022 14:07:52 +0800, Jason Wang <[email protected]> wrote:
> > On Thu, Jun 30, 2022 at 10:22 AM Xuan Zhuo <[email protected]> wrote:
> > >
> > > On Thu, 30 Jun 2022 10:08:04 +0800, Jason Wang <[email protected]> wrote:
> > > > We try using cancel_delayed_work_sync() to prevent the work from
> > > > enabling NAPI. This is insufficient since we don't disable the source
> > > > of the refill work scheduling. This means an NAPI poll callback after
> > > > cancel_delayed_work_sync() can schedule the refill work then can
> > > > re-enable the NAPI that leads to use-after-free [1].
> > >
> > >
> > > Can you explain in more detail how this happened?
> > >
> > > napi_disable() is normally called after cancel_delayed_work_sync(). This ensures
> > > that all napi callbacks will end, and the new napi_disable() will wait.
> > > There will be no re-enable napi.
> >
> > An rx interrupt that may come between after the cancel_delayed_work()
> > but before the napi_disable(). It schedules a refill_work that may run
> > after the napi_disable() in virtnet_close().
>
> Yes
>
>
> >
> > >
> > > So I guess the use-after-free is caused by refill_work being called after
> > > dev/vi/napi is released. In this way, we can just call
> > > cancel_delayed_work_sync() after napi_disalbe().
> >
> > So the refill_work can re-enable the NAPI when it is run after
> > napi_disable() in this case.
>
>
> Since napi_disable() has been called in virtnet_close(), it will get stuck when
> napi_disable() in refill_work().
Right because e.g NAPIF_STATE_SCHED has been set by napi_disable() before.
> I think use-after-free is because vi/napi etc.
> have been released, refill_work() going to access again causes an exception.
Yes, this is the use-after-free I mentioned above.
>
> napi will not be re-enable.
>
> I would like to call cancel_delayed_work_sync() after napi_disable()
> to solve this problem. But this also has a problem, refill_work() can get stuck
> on napi_disable() and cannot exit. In this way, we want napi_disable() to check
> that the current state is disabled and exit directly.
Not sure this is a good design and it doesn't fit for -stable.
I think the design of NAPI is to pair napi_enable() and napi_disable()
instead of allowing napi_disable() to be called twice.
Thanks
>
> Thanks.
>
>
> >
> > Thanks
> >
> >
> > >
> > > Thanks.
> > >
> > > >
> > > > Since the work can enable NAPI, we can't simply disable NAPI before
> > > > calling cancel_delayed_work_sync(). So fix this by introducing a
> > > > dedicated boolean to control whether or not the work could be
> > > > scheduled from NAPI.
> > > >
> > > > [1]
> > > > ==================================================================
> > > > BUG: KASAN: use-after-free in refill_work+0x43/0xd4
> > > > Read of size 2 at addr ffff88810562c92e by task kworker/2:1/42
> > > >
> > > > CPU: 2 PID: 42 Comm: kworker/2:1 Not tainted 5.19.0-rc1+ #480
> > > > Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
> > > > Workqueue: events refill_work
> > > > Call Trace:
> > > > <TASK>
> > > > dump_stack_lvl+0x34/0x44
> > > > print_report.cold+0xbb/0x6ac
> > > > ? _printk+0xad/0xde
> > > > ? refill_work+0x43/0xd4
> > > > kasan_report+0xa8/0x130
> > > > ? refill_work+0x43/0xd4
> > > > refill_work+0x43/0xd4
> > > > process_one_work+0x43d/0x780
> > > > worker_thread+0x2a0/0x6f0
> > > > ? process_one_work+0x780/0x780
> > > > kthread+0x167/0x1a0
> > > > ? kthread_exit+0x50/0x50
> > > > ret_from_fork+0x22/0x30
> > > > </TASK>
> > > > ...
> > > >
> > > > Fixes: b2baed69e605c ("virtio_net: set/cancel work on ndo_open/ndo_stop")
> > > > Signed-off-by: Jason Wang <[email protected]>
> > > > ---
> > > > drivers/net/virtio_net.c | 38 ++++++++++++++++++++++++++++++++++++--
> > > > 1 file changed, 36 insertions(+), 2 deletions(-)
> > > >
> > > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > > index db05b5e930be..21bf1e5c81ef 100644
> > > > --- a/drivers/net/virtio_net.c
> > > > +++ b/drivers/net/virtio_net.c
> > > > @@ -251,6 +251,12 @@ struct virtnet_info {
> > > > /* Does the affinity hint is set for virtqueues? */
> > > > bool affinity_hint_set;
> > > >
> > > > + /* Is refill work enabled? */
> > > > + bool refill_work_enabled;
> > > > +
> > > > + /* The lock to synchronize the access to refill_work_enabled */
> > > > + spinlock_t refill_lock;
> > > > +
> > > > /* CPU hotplug instances for online & dead */
> > > > struct hlist_node node;
> > > > struct hlist_node node_dead;
> > > > @@ -348,6 +354,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
> > > > return p;
> > > > }
> > > >
> > > > +static void enable_refill_work(struct virtnet_info *vi)
> > > > +{
> > > > + spin_lock(&vi->refill_lock);
> > > > + vi->refill_work_enabled = true;
> > > > + spin_unlock(&vi->refill_lock);
> > > > +}
> > > > +
> > > > +static void disable_refill_work(struct virtnet_info *vi)
> > > > +{
> > > > + spin_lock(&vi->refill_lock);
> > > > + vi->refill_work_enabled = false;
> > > > + spin_unlock(&vi->refill_lock);
> > > > +}
> > > > +
> > > > static void virtqueue_napi_schedule(struct napi_struct *napi,
> > > > struct virtqueue *vq)
> > > > {
> > > > @@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
> > > > }
> > > >
> > > > if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
> > > > - if (!try_fill_recv(vi, rq, GFP_ATOMIC))
> > > > - schedule_delayed_work(&vi->refill, 0);
> > > > + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
> > > > + spin_lock(&vi->refill_lock);
> > > > + if (vi->refill_work_enabled)
> > > > + schedule_delayed_work(&vi->refill, 0);
> > > > + spin_unlock(&vi->refill_lock);
> > > > + }
> > > > }
> > > >
> > > > u64_stats_update_begin(&rq->stats.syncp);
> > > > @@ -1651,6 +1675,8 @@ static int virtnet_open(struct net_device *dev)
> > > > struct virtnet_info *vi = netdev_priv(dev);
> > > > int i, err;
> > > >
> > > > + enable_refill_work(vi);
> > > > +
> > > > for (i = 0; i < vi->max_queue_pairs; i++) {
> > > > if (i < vi->curr_queue_pairs)
> > > > /* Make sure we have some buffers: if oom use wq. */
> > > > @@ -2033,6 +2059,8 @@ static int virtnet_close(struct net_device *dev)
> > > > struct virtnet_info *vi = netdev_priv(dev);
> > > > int i;
> > > >
> > > > + /* Make sure NAPI doesn't schedule refill work */
> > > > + disable_refill_work(vi);
> > > > /* Make sure refill_work doesn't re-enable napi! */
> > > > cancel_delayed_work_sync(&vi->refill);
> > > >
> > > > @@ -2776,6 +2804,9 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
> > > > netif_tx_lock_bh(vi->dev);
> > > > netif_device_detach(vi->dev);
> > > > netif_tx_unlock_bh(vi->dev);
> > > > + /* Make sure NAPI doesn't schedule refill work */
> > > > + disable_refill_work(vi);
> > > > + /* Make sure refill_work doesn't re-enable napi! */
> > > > cancel_delayed_work_sync(&vi->refill);
> > > >
> > > > if (netif_running(vi->dev)) {
> > > > @@ -2799,6 +2830,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)
> > > >
> > > > virtio_device_ready(vdev);
> > > >
> > > > + enable_refill_work(vi);
> > > > +
> > > > if (netif_running(vi->dev)) {
> > > > for (i = 0; i < vi->curr_queue_pairs; i++)
> > > > if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
> > > > @@ -3548,6 +3581,7 @@ static int virtnet_probe(struct virtio_device *vdev)
> > > > vdev->priv = vi;
> > > >
> > > > INIT_WORK(&vi->config_work, virtnet_config_changed_work);
> > > > + spin_lock_init(&vi->refill_lock);
> > > >
> > > > /* If we can receive ANY GSO packets, we must allocate large ones. */
> > > > if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
> > > > --
> > > > 2.25.1
> > > >
> > >
> >
>
On Thu, 30 Jun 2022 14:07:52 +0800, Jason Wang <[email protected]> wrote:
> On Thu, Jun 30, 2022 at 10:22 AM Xuan Zhuo <[email protected]> wrote:
> >
> > On Thu, 30 Jun 2022 10:08:04 +0800, Jason Wang <[email protected]> wrote:
> > > We try using cancel_delayed_work_sync() to prevent the work from
> > > enabling NAPI. This is insufficient since we don't disable the source
> > > of the refill work scheduling. This means an NAPI poll callback after
> > > cancel_delayed_work_sync() can schedule the refill work then can
> > > re-enable the NAPI that leads to use-after-free [1].
> >
> >
> > Can you explain in more detail how this happened?
> >
> > napi_disable() is normally called after cancel_delayed_work_sync(). This ensures
> > that all napi callbacks will end, and the new napi_disable() will wait.
> > There will be no re-enable napi.
>
> An rx interrupt that may come between after the cancel_delayed_work()
> but before the napi_disable(). It schedules a refill_work that may run
> after the napi_disable() in virtnet_close().
Yes
>
> >
> > So I guess the use-after-free is caused by refill_work being called after
> > dev/vi/napi is released. In this way, we can just call
> > cancel_delayed_work_sync() after napi_disalbe().
>
> So the refill_work can re-enable the NAPI when it is run after
> napi_disable() in this case.
Since napi_disable() has been called in virtnet_close(), it will get stuck when
napi_disable() in refill_work(). I think use-after-free is because vi/napi etc.
have been released, refill_work() going to access again causes an exception.
napi will not be re-enable.
I would like to call cancel_delayed_work_sync() after napi_disable()
to solve this problem. But this also has a problem, refill_work() can get stuck
on napi_disable() and cannot exit. In this way, we want napi_disable() to check
that the current state is disabled and exit directly.
Thanks.
>
> Thanks
>
>
> >
> > Thanks.
> >
> > >
> > > Since the work can enable NAPI, we can't simply disable NAPI before
> > > calling cancel_delayed_work_sync(). So fix this by introducing a
> > > dedicated boolean to control whether or not the work could be
> > > scheduled from NAPI.
> > >
> > > [1]
> > > ==================================================================
> > > BUG: KASAN: use-after-free in refill_work+0x43/0xd4
> > > Read of size 2 at addr ffff88810562c92e by task kworker/2:1/42
> > >
> > > CPU: 2 PID: 42 Comm: kworker/2:1 Not tainted 5.19.0-rc1+ #480
> > > Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014
> > > Workqueue: events refill_work
> > > Call Trace:
> > > <TASK>
> > > dump_stack_lvl+0x34/0x44
> > > print_report.cold+0xbb/0x6ac
> > > ? _printk+0xad/0xde
> > > ? refill_work+0x43/0xd4
> > > kasan_report+0xa8/0x130
> > > ? refill_work+0x43/0xd4
> > > refill_work+0x43/0xd4
> > > process_one_work+0x43d/0x780
> > > worker_thread+0x2a0/0x6f0
> > > ? process_one_work+0x780/0x780
> > > kthread+0x167/0x1a0
> > > ? kthread_exit+0x50/0x50
> > > ret_from_fork+0x22/0x30
> > > </TASK>
> > > ...
> > >
> > > Fixes: b2baed69e605c ("virtio_net: set/cancel work on ndo_open/ndo_stop")
> > > Signed-off-by: Jason Wang <[email protected]>
> > > ---
> > > drivers/net/virtio_net.c | 38 ++++++++++++++++++++++++++++++++++++--
> > > 1 file changed, 36 insertions(+), 2 deletions(-)
> > >
> > > diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
> > > index db05b5e930be..21bf1e5c81ef 100644
> > > --- a/drivers/net/virtio_net.c
> > > +++ b/drivers/net/virtio_net.c
> > > @@ -251,6 +251,12 @@ struct virtnet_info {
> > > /* Does the affinity hint is set for virtqueues? */
> > > bool affinity_hint_set;
> > >
> > > + /* Is refill work enabled? */
> > > + bool refill_work_enabled;
> > > +
> > > + /* The lock to synchronize the access to refill_work_enabled */
> > > + spinlock_t refill_lock;
> > > +
> > > /* CPU hotplug instances for online & dead */
> > > struct hlist_node node;
> > > struct hlist_node node_dead;
> > > @@ -348,6 +354,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask)
> > > return p;
> > > }
> > >
> > > +static void enable_refill_work(struct virtnet_info *vi)
> > > +{
> > > + spin_lock(&vi->refill_lock);
> > > + vi->refill_work_enabled = true;
> > > + spin_unlock(&vi->refill_lock);
> > > +}
> > > +
> > > +static void disable_refill_work(struct virtnet_info *vi)
> > > +{
> > > + spin_lock(&vi->refill_lock);
> > > + vi->refill_work_enabled = false;
> > > + spin_unlock(&vi->refill_lock);
> > > +}
> > > +
> > > static void virtqueue_napi_schedule(struct napi_struct *napi,
> > > struct virtqueue *vq)
> > > {
> > > @@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
> > > }
> > >
> > > if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) {
> > > - if (!try_fill_recv(vi, rq, GFP_ATOMIC))
> > > - schedule_delayed_work(&vi->refill, 0);
> > > + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) {
> > > + spin_lock(&vi->refill_lock);
> > > + if (vi->refill_work_enabled)
> > > + schedule_delayed_work(&vi->refill, 0);
> > > + spin_unlock(&vi->refill_lock);
> > > + }
> > > }
> > >
> > > u64_stats_update_begin(&rq->stats.syncp);
> > > @@ -1651,6 +1675,8 @@ static int virtnet_open(struct net_device *dev)
> > > struct virtnet_info *vi = netdev_priv(dev);
> > > int i, err;
> > >
> > > + enable_refill_work(vi);
> > > +
> > > for (i = 0; i < vi->max_queue_pairs; i++) {
> > > if (i < vi->curr_queue_pairs)
> > > /* Make sure we have some buffers: if oom use wq. */
> > > @@ -2033,6 +2059,8 @@ static int virtnet_close(struct net_device *dev)
> > > struct virtnet_info *vi = netdev_priv(dev);
> > > int i;
> > >
> > > + /* Make sure NAPI doesn't schedule refill work */
> > > + disable_refill_work(vi);
> > > /* Make sure refill_work doesn't re-enable napi! */
> > > cancel_delayed_work_sync(&vi->refill);
> > >
> > > @@ -2776,6 +2804,9 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
> > > netif_tx_lock_bh(vi->dev);
> > > netif_device_detach(vi->dev);
> > > netif_tx_unlock_bh(vi->dev);
> > > + /* Make sure NAPI doesn't schedule refill work */
> > > + disable_refill_work(vi);
> > > + /* Make sure refill_work doesn't re-enable napi! */
> > > cancel_delayed_work_sync(&vi->refill);
> > >
> > > if (netif_running(vi->dev)) {
> > > @@ -2799,6 +2830,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)
> > >
> > > virtio_device_ready(vdev);
> > >
> > > + enable_refill_work(vi);
> > > +
> > > if (netif_running(vi->dev)) {
> > > for (i = 0; i < vi->curr_queue_pairs; i++)
> > > if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL))
> > > @@ -3548,6 +3581,7 @@ static int virtnet_probe(struct virtio_device *vdev)
> > > vdev->priv = vi;
> > >
> > > INIT_WORK(&vi->config_work, virtnet_config_changed_work);
> > > + spin_lock_init(&vi->refill_lock);
> > >
> > > /* If we can receive ANY GSO packets, we must allocate large ones. */
> > > if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
> > > --
> > > 2.25.1
> > >
> >
>