On 09/07/2017 03:44 PM, Yuanhan Liu wrote:
On Thu, Aug 31, 2017 at 11:50:05AM +0200, Maxime Coquelin wrote:
virtio_net device might be accessed while being reallocated
in case of NUMA awareness.
From data path? data path won't be enabled until all are ready, which is
at a stage after numa_r
On Thu, Aug 31, 2017 at 11:50:05AM +0200, Maxime Coquelin wrote:
> virtio_net device might be accessed while being reallocated
> in case of NUMA awareness.
>From data path? data path won't be enabled until all are ready, which is
at a stage after numa_realloc(). Or, am I miss something?
-
On Wed, Sep 06, 2017 at 10:02:29PM +0200, Maxime Coquelin wrote:
> On 09/06/2017 09:30 AM, Tiwei Bie wrote:
> > On Wed, Sep 06, 2017 at 09:15:47AM +0200, Maxime Coquelin wrote:
> > > Hi Tiwei,
> > >
> > > On 09/06/2017 03:15 AM, Tiwei Bie wrote:
> > > > On Tue, Sep 05, 2017 at 01:00:42PM +0200, Ma
On 09/06/2017 09:30 AM, Tiwei Bie wrote:
On Wed, Sep 06, 2017 at 09:15:47AM +0200, Maxime Coquelin wrote:
Hi Tiwei,
On 09/06/2017 03:15 AM, Tiwei Bie wrote:
On Tue, Sep 05, 2017 at 01:00:42PM +0200, Maxime Coquelin wrote:
On 09/05/2017 12:07 PM, Tiwei Bie wrote:
On Tue, Sep 05, 2017 at 11:
Hi Stephen,
On 09/06/2017 04:59 AM, Stephen Hemminger wrote:
This lock has currently two purposes:
1. Prevent referencing freed virtio_dev struct in case of numa_realloc.
2. Protect vring pages against invalidation.
For 2., it can be fixed by using the per-vq IOTLB lock (it was not the
case in
On Wed, Sep 06, 2017 at 09:15:47AM +0200, Maxime Coquelin wrote:
> Hi Tiwei,
>
> On 09/06/2017 03:15 AM, Tiwei Bie wrote:
> > On Tue, Sep 05, 2017 at 01:00:42PM +0200, Maxime Coquelin wrote:
> > > On 09/05/2017 12:07 PM, Tiwei Bie wrote:
> > > > On Tue, Sep 05, 2017 at 11:24:14AM +0200, Maxime Coq
Hi Tiwei,
On 09/06/2017 03:15 AM, Tiwei Bie wrote:
On Tue, Sep 05, 2017 at 01:00:42PM +0200, Maxime Coquelin wrote:
On 09/05/2017 12:07 PM, Tiwei Bie wrote:
On Tue, Sep 05, 2017 at 11:24:14AM +0200, Maxime Coquelin wrote:
On 09/05/2017 06:45 AM, Tiwei Bie wrote:
On Thu, Aug 31, 2017 at 11:50
> > > This lock has currently two purposes:
> > > 1. Prevent referencing freed virtio_dev struct in case of numa_realloc.
> > > 2. Protect vring pages against invalidation.
> > >
> > > For 2., it can be fixed by using the per-vq IOTLB lock (it was not the
> > > case in my early prototypes that had
On Tue, Sep 05, 2017 at 01:00:42PM +0200, Maxime Coquelin wrote:
> On 09/05/2017 12:07 PM, Tiwei Bie wrote:
> > On Tue, Sep 05, 2017 at 11:24:14AM +0200, Maxime Coquelin wrote:
> > > On 09/05/2017 06:45 AM, Tiwei Bie wrote:
> > > > On Thu, Aug 31, 2017 at 11:50:05AM +0200, Maxime Coquelin wrote:
>
On 09/05/2017 12:07 PM, Tiwei Bie wrote:
On Tue, Sep 05, 2017 at 11:24:14AM +0200, Maxime Coquelin wrote:
On 09/05/2017 06:45 AM, Tiwei Bie wrote:
On Thu, Aug 31, 2017 at 11:50:05AM +0200, Maxime Coquelin wrote:
virtio_net device might be accessed while being reallocated
in case of NUMA awar
On Tue, Sep 05, 2017 at 11:24:14AM +0200, Maxime Coquelin wrote:
> On 09/05/2017 06:45 AM, Tiwei Bie wrote:
> > On Thu, Aug 31, 2017 at 11:50:05AM +0200, Maxime Coquelin wrote:
> > > virtio_net device might be accessed while being reallocated
> > > in case of NUMA awareness. This case might be theo
On 09/05/2017 06:45 AM, Tiwei Bie wrote:
On Thu, Aug 31, 2017 at 11:50:05AM +0200, Maxime Coquelin wrote:
virtio_net device might be accessed while being reallocated
in case of NUMA awareness. This case might be theoretical,
but it will be needed anyway to protect vrings pages against
invalida
On Thu, Aug 31, 2017 at 11:50:05AM +0200, Maxime Coquelin wrote:
> virtio_net device might be accessed while being reallocated
> in case of NUMA awareness. This case might be theoretical,
> but it will be needed anyway to protect vrings pages against
> invalidation.
>
> The virtio_net devs are now
virtio_net device might be accessed while being reallocated
in case of NUMA awareness. This case might be theoretical,
but it will be needed anyway to protect vrings pages against
invalidation.
The virtio_net devs are now protected with a readers/writers
lock, so that before reallocating the devic
14 matches
Mail list logo