Hi Stefano,
On 20/12/16 19:38, Stefano Stabellini wrote:
On Tue, 20 Dec 2016, Julien Grall wrote:
On 20/12/2016 00:22, Stefano Stabellini wrote:
On Mon, 19 Dec 2016, Julien Grall wrote:
On 19/12/2016 23:30, Stefano Stabellini wrote:
On Mon, 19 Dec 2016, Julien Grall wrote:
2) We run
On Tue, 20 Dec 2016, Stefano Stabellini wrote:
> On Tue, 20 Dec 2016, Julien Grall wrote:
> > Hi Stefano,
> >
> > On 20/12/2016 00:22, Stefano Stabellini wrote:
> > > On Mon, 19 Dec 2016, Julien Grall wrote:
> > > > Hi Stefano,
> > > >
> > > > On 19/12/2016 23:30, Stefano Stabellini wrote:
> > >
On Tue, 20 Dec 2016, Julien Grall wrote:
> Hi Stefano,
>
> On 20/12/2016 00:22, Stefano Stabellini wrote:
> > On Mon, 19 Dec 2016, Julien Grall wrote:
> > > Hi Stefano,
> > >
> > > On 19/12/2016 23:30, Stefano Stabellini wrote:
> > > > On Mon, 19 Dec 2016, Julien Grall wrote:
> > > > > > > 2) We
Hi Stefano,
On 20/12/2016 00:22, Stefano Stabellini wrote:
On Mon, 19 Dec 2016, Julien Grall wrote:
Hi Stefano,
On 19/12/2016 23:30, Stefano Stabellini wrote:
On Mon, 19 Dec 2016, Julien Grall wrote:
2) We run gic_update_one_lr and vgic_store_itargetsr in parallel
safely
and locklessly.
On Mon, 19 Dec 2016, Julien Grall wrote:
> Hi Stefano,
>
> On 19/12/2016 23:30, Stefano Stabellini wrote:
> > On Mon, 19 Dec 2016, Julien Grall wrote:
> > > > > 2) We run gic_update_one_lr and vgic_store_itargetsr in parallel
> > > > > safely
> > > > > and locklessly. There might be a way to do
Hi Stefano,
On 19/12/2016 23:30, Stefano Stabellini wrote:
On Mon, 19 Dec 2016, Julien Grall wrote:
2) We run gic_update_one_lr and vgic_store_itargetsr in parallel safely
and locklessly. There might be a way to do it, but it is not easy I
haven't found it yet.
Correct me if I am wrong.
On Mon, 19 Dec 2016, Julien Grall wrote:
> Hi Stefano,
>
> On 17/12/2016 02:13, Stefano Stabellini wrote:
> > On Fri, 16 Dec 2016, Stefano Stabellini wrote:
> > > On Fri, 16 Dec 2016, Julien Grall wrote:
> > > > Hi Stefano,
> > > >
> > > > On 16/12/16 00:08, Stefano Stabellini wrote:
> > > > >
Hi Stefano,
On 17/12/2016 02:13, Stefano Stabellini wrote:
On Fri, 16 Dec 2016, Stefano Stabellini wrote:
On Fri, 16 Dec 2016, Julien Grall wrote:
Hi Stefano,
On 16/12/16 00:08, Stefano Stabellini wrote:
On Thu, 15 Dec 2016, Julien Grall wrote:
On 15/12/2016 01:04, Stefano Stabellini
On Fri, 16 Dec 2016, Stefano Stabellini wrote:
> On Fri, 16 Dec 2016, Julien Grall wrote:
> > Hi Stefano,
> >
> > On 16/12/16 00:08, Stefano Stabellini wrote:
> > > On Thu, 15 Dec 2016, Julien Grall wrote:
> > > > On 15/12/2016 01:04, Stefano Stabellini wrote:
> > > > > The locking order is:
On Fri, 16 Dec 2016, Julien Grall wrote:
> Hi Stefano,
>
> On 16/12/16 00:08, Stefano Stabellini wrote:
> > On Thu, 15 Dec 2016, Julien Grall wrote:
> > > On 15/12/2016 01:04, Stefano Stabellini wrote:
> > > > The locking order is: first rank lock, then vgic lock. The order is
> > > > respected
Hi Stefano,
On 16/12/16 00:08, Stefano Stabellini wrote:
On Thu, 15 Dec 2016, Julien Grall wrote:
On 15/12/2016 01:04, Stefano Stabellini wrote:
The locking order is: first rank lock, then vgic lock. The order is
respected everywhere, except for gic_update_one_lr.
gic_update_one_lr is called
On Thu, 15 Dec 2016, Julien Grall wrote:
> Hi Stefano,
>
> On 15/12/2016 01:04, Stefano Stabellini wrote:
> > The locking order is: first rank lock, then vgic lock. The order is
> > respected everywhere, except for gic_update_one_lr.
> >
> > gic_update_one_lr is called with the vgic lock held,
Hi Stefano,
On 15/12/2016 01:04, Stefano Stabellini wrote:
The locking order is: first rank lock, then vgic lock. The order is
respected everywhere, except for gic_update_one_lr.
gic_update_one_lr is called with the vgic lock held, but it calls
vgic_get_target_vcpu, which tries to obtain the
The locking order is: first rank lock, then vgic lock. The order is
respected everywhere, except for gic_update_one_lr.
gic_update_one_lr is called with the vgic lock held, but it calls
vgic_get_target_vcpu, which tries to obtain the rank lock. This can
cause deadlocks.
We already have a version
14 matches
Mail list logo