From: Jason Wang
Date: Tue, 5 Sep 2017 09:22:05 +0800
> We check tx avail through vhost_enable_notify() in the past which is
> wrong since it only checks whether or not guest has filled more
> available buffer since last avail idx synchronization which was just
> done by
On 05/09/17 16:31, Waiman Long wrote:
> On 09/05/2017 10:24 AM, Waiman Long wrote:
>> On 09/05/2017 10:18 AM, Juergen Gross wrote:
>>> On 05/09/17 16:10, Waiman Long wrote:
On 09/05/2017 09:24 AM, Juergen Gross wrote:
> There are cases where a guest tries to switch spinlocks to bare metal
Jeremy Fitzhardinge is stepping down as a paravirt maintainer. I'll
replace him.
While at it, update the file list to the actual pattern.
Signed-off-by: Juergen Gross
---
MAINTAINERS | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/MAINTAINERS
On 09/05/2017 10:24 AM, Waiman Long wrote:
> On 09/05/2017 10:18 AM, Juergen Gross wrote:
>> On 05/09/17 16:10, Waiman Long wrote:
>>> On 09/05/2017 09:24 AM, Juergen Gross wrote:
There are cases where a guest tries to switch spinlocks to bare metal
behavior (e.g. by setting
On 09/05/2017 10:18 AM, Juergen Gross wrote:
> On 05/09/17 16:10, Waiman Long wrote:
>> On 09/05/2017 09:24 AM, Juergen Gross wrote:
>>> There are cases where a guest tries to switch spinlocks to bare metal
>>> behavior (e.g. by setting "xen_nopvspin" boot parameter). Today this
>>> has the
On 09/05/2017 10:08 AM, Peter Zijlstra wrote:
> On Tue, Sep 05, 2017 at 10:02:57AM -0400, Waiman Long wrote:
>> On 09/05/2017 09:24 AM, Juergen Gross wrote:
>>> +static inline bool native_virt_spin_lock(struct qspinlock *lock)
>>> +{
>>> + if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
>>> +
On 09/05/2017 09:24 AM, Juergen Gross wrote:
> There are cases where a guest tries to switch spinlocks to bare metal
> behavior (e.g. by setting "xen_nopvspin" boot parameter). Today this
> has the downside of falling back to unfair test and set scheme for
> qspinlocks due to virt_spin_lock()
On Mon, Sep 4, 2017 at 5:03 AM, Jason Wang wrote:
>
>
> On 2017年09月02日 00:17, Willem de Bruijn wrote:
>
> This is not a 50/50 split, which impliesTw that some packets from the
> large
> packet flow are still converted to copying. Without the change the rate
On Tue, Sep 05, 2017 at 10:02:57AM -0400, Waiman Long wrote:
> On 09/05/2017 09:24 AM, Juergen Gross wrote:
> > +static inline bool native_virt_spin_lock(struct qspinlock *lock)
> > +{
> > + if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
> > + return false;
> > +
>
> I think you can
On 09/05/2017 09:24 AM, Juergen Gross wrote:
> There are cases where a guest tries to switch spinlocks to bare metal
> behavior (e.g. by setting "xen_nopvspin" boot parameter). Today this
> has the downside of falling back to unfair test and set scheme for
> qspinlocks due to virt_spin_lock()
On 05/09/17 15:55, Peter Zijlstra wrote:
> On Tue, Sep 05, 2017 at 03:24:43PM +0200, Juergen Gross wrote:
>> diff --git a/arch/x86/include/asm/qspinlock.h
>> b/arch/x86/include/asm/qspinlock.h
>> index 48a706f641f2..fbd98896385c 100644
>> --- a/arch/x86/include/asm/qspinlock.h
>> +++
With the boot parameter "xen_nopvspin" specified a Xen guest should not
make use of paravirt spinlocks, but behave as if running on bare
metal. This is not true, however, as the qspinlock code will fall back
to a test-and-set scheme when it is detecting a hypervisor.
In order to avoid this set
Instead of special casing pv_lock_ops.vcpu_is_preempted when patching
use _paravirt_false() on bare metal.
Signed-off-by: Juergen Gross
---
arch/x86/kernel/paravirt-spinlocks.c | 14 +-
arch/x86/kernel/paravirt_patch_32.c | 10 --
Add a _paravirt_false() default function returning always false which
can be used for cases where a boolean pvops replacement should just
say "no".
Signed-off-by: Juergen Gross
---
arch/x86/include/asm/paravirt_types.h | 2 ++
arch/x86/kernel/paravirt.c| 7 +++
There are cases where a guest tries to switch spinlocks to bare metal
behavior (e.g. by setting "xen_nopvspin" boot parameter). Today this
has the downside of falling back to unfair test and set scheme for
qspinlocks due to virt_spin_lock() detecting the virtualized
environment.
Make
With virt_spin_lock() being a pvops function the bare metal case can be
optimized by patching the call away completely. In case a kernel running
as a guest it can decide whether to use paravitualized spinlocks, the
current fallback to the unfair test-and-set scheme, or to mimic the
bare metal
Ping for comments if possible. Thanks.
On Monday, August 28, 2017 6:09 PM, Wang, Wei W wrote:
> [PATCH v15 5/5] virtio-balloon: VIRTIO_BALLOON_F_CTRL_VQ
>
> Add a new vq, ctrl_vq, to handle commands between the host and guest.
> With this feature, we will be able to have the control plane and
17 matches
Mail list logo