Re: [PATCH net V2] vhost_net: correctly check tx avail during rx busy polling

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

Re: [PATCH 3/4] paravirt: add virt_spin_lock pvops function

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

[PATCH] paravirt: switch maintainer

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

Re: [PATCH 3/4] paravirt: add virt_spin_lock pvops function

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

Re: [PATCH 3/4] paravirt: add virt_spin_lock pvops function

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

Re: [PATCH 3/4] paravirt: add virt_spin_lock pvops function

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)) >>> +

Re: [PATCH 3/4] paravirt: add virt_spin_lock pvops function

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()

Re: [PATCH net-next] virtio-net: invoke zerocopy callback on xmit path if no tx napi

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

Re: [PATCH 3/4] paravirt: add virt_spin_lock pvops function

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

Re: [PATCH 3/4] paravirt: add virt_spin_lock pvops function

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()

Re: [PATCH 3/4] paravirt: add virt_spin_lock pvops function

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 >> +++

[PATCH 4/4] paravirt,xen: correct xen_nopvspin case

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

[PATCH 2/4] paravirt: switch vcpu_is_preempted to use _paravirt_false() on bare metal

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 --

[PATCH 1/4] paravirt: add generic _paravirt_false() function

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 +++

[PATCH 3/4] paravirt: add virt_spin_lock pvops function

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

[PATCH 0/4] make virt_spin_lock() a pvops function

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

RE: [PATCH v15 5/5] virtio-balloon: VIRTIO_BALLOON_F_CTRL_VQ

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