similar to: [PATCH 1/8] vhost vdpa: fix vhost_vdpa_open error handling

On Thu, Sep 24, 2020 at 11:21:03AM +0800, Jason Wang wrote: > We need to free vqs during the err path after it has been allocated > since vhost won't do that for us. > > Signed-off-by: Jason Wang <jasowang at redhat.com> This is a bugfix too right? I don't see it posted separately ... > --- > drivers/vhost/vdpa.c | 11 ++++++++--- > 1 file changed, 8

On 2020/9/24 ??3:48, Eli Cohen wrote: > On Thu, Sep 24, 2020 at 11:21:03AM +0800, Jason Wang wrote: >> We need to free vqs during the err path after it has been allocated >> since vhost won't do that for us. >> >> Signed-off-by: Jason Wang <jasowang at redhat.com> >> --- >> drivers/vhost/vdpa.c | 11 ++++++++--- >> 1 file changed, 8

We need to free vqs during the err path after it has been allocated since vhost won't do that for us. Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vhost/vdpa.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 796fe979f997..9c641274b9f3 100644 --- a/drivers/vhost/vdpa.c +++

On Wed, Feb 15, 2023 at 01:15:55PM +0800, Longpeng (Mike, Cloud Infrastructure Service Product Dept.) wrote: > > > ? 2023/2/15 10:56, Jason Wang ??: > > On Wed, Feb 15, 2023 at 10:49 AM Longpeng (Mike, Cloud Infrastructure > > Service Product Dept.) <longpeng2 at huawei.com> wrote: > > > > > > > > > > > > ? 2023/2/15 10:00, Jason

On Tue, Feb 04, 2020 at 11:30:11AM +0800, Jason Wang wrote: > On 2020/1/31 ??11:36, Tiwei Bie wrote: > > This patch introduces a vDPA based vhost backend. This > > backend is built on top of the same interface defined > > in virtio-vDPA and provides a generic vhost interface > > for userspace to accelerate the virtio devices in guest. > > > > This backend is

On 2020/7/31 ??2:55, Zhu Lingshan wrote: > This patch introduce a set of functions for setup/unsetup > and update irq offloading respectively by register/unregister > and re-register the irq_bypass_producer. > > With these functions, this commit can setup/unsetup > irq offloading through setting DRIVER_OK/!DRIVER_OK, and > update irq offloading through SET_VRING_CALL. >

On 2020/7/28 ??12:24, Zhu Lingshan wrote: > This patch introduce a set of functions for setup/unsetup > and update irq offloading respectively by register/unregister > and re-register the irq_bypass_producer. > > With these functions, this commit can setup/unsetup > irq offloading through setting DRIVER_OK/!DRIVER_OK, and > update irq offloading through SET_VRING_CALL. >

On Tue, Aug 04, 2020 at 05:31:38PM +0800, Zhu, Lingshan wrote: > > On 8/4/2020 4:51 PM, Jason Wang wrote: > > > On 2020/7/31 ??2:55, Zhu Lingshan wrote: > > This patch introduce a set of functions for setup/unsetup > and update irq offloading respectively by register/unregister > and re-register the irq_bypass_producer. > >

On 2020/8/4 ??5:31, Zhu, Lingshan wrote: > > > On 8/4/2020 4:51 PM, Jason Wang wrote: >> >> On 2020/7/31 ??2:55, Zhu Lingshan wrote: >>> This patch introduce a set of functions for setup/unsetup >>> and update irq offloading respectively by register/unregister >>> and re-register the irq_bypass_producer. >>> >>> With these

On 2020/8/5 ??1:45, Zhu, Lingshan wrote: > > > On 8/5/2020 10:36 AM, Jason Wang wrote: >> >> On 2020/8/4 ??5:31, Zhu, Lingshan wrote: >>> >>> >>> On 8/4/2020 4:51 PM, Jason Wang wrote: >>>> >>>> On 2020/7/31 ??2:55, Zhu Lingshan wrote: >>>>> This patch introduce a set of functions for setup/unsetup

On 2020/5/26 ??1:32, Zhu Lingshan wrote: > Standard vhost devices rely on waking up a vhost_worker to kick > a virtquque. However vdpa devices have hardware backends, so it > does not need this waking up routin. In this commit, vdpa device > will kick a virtqueue directly, reduce the performance overhead > caused by waking up a vhost_woker. Thanks for the patch. It would be

Currently the doorbell is relayed via eventfd which may have significant overhead because of the cost of vmexits or syscall. This patch introduces mmap() based doorbell mapping which can eliminate the overhead caused by vmexit or syscall. To ease the userspace modeling of the doorbell layout (usually virtio-pci), this patch starts from a doorbell per page model. Vhost-vdpa only support the

On 2020/5/29 ??5:16, Mika Penttil? wrote: > Hi, > > On 29.5.2020 11.03, Jason Wang wrote: >> Currently the doorbell is relayed via eventfd which may have >> significant overhead because of the cost of vmexits or syscall. This >> patch introduces mmap() based doorbell mapping which can eliminate the >> overhead caused by vmexit or syscall. > > Just wondering.

On 2020/4/26 ??4:42, Zhu Lingshan wrote: > This commit implements config interrupt support in > vhost_vdpa layer. > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> > --- > drivers/vhost/vdpa.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++ > drivers/vhost/vhost.c | 2 +- > include/uapi/linux/vhost.h | 4 ++++ > 3 files changed, 52

On 2020/1/31 ??11:36, Tiwei Bie wrote: > This patch introduces a vDPA based vhost backend. This > backend is built on top of the same interface defined > in virtio-vDPA and provides a generic vhost interface > for userspace to accelerate the virtio devices in guest. > > This backend is implemented as a vDPA device driver on > top of the same ops used in virtio-vDPA. It will

On 2020/1/31 ??11:36, Tiwei Bie wrote: > This patch introduces a vDPA based vhost backend. This > backend is built on top of the same interface defined > in virtio-vDPA and provides a generic vhost interface > for userspace to accelerate the virtio devices in guest. > > This backend is implemented as a vDPA device driver on > top of the same ops used in virtio-vDPA. It will

Given the need for 4K doorbell such that QEMU can easily map, ect, and assuming that I have a HW device which exposes 2 VQ's, with a notification area off of BAR3, offset=whatever, notifier_multiplier=4, we don't need to have 2 x 4K pages mapped into the VM for both doorbells do we? The guest driver would ring DB0 at BAR4+offset, and DB1 at BAR4+offset+(4*1). The 4K per DB is useful how?

On 2020/4/24 ??6:04, Zhu Lingshan wrote: > This commit implements config interrupt support in > vhost_vdpa layer. > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> One should be sufficient. > --- > drivers/vhost/vdpa.c | 53 ++++++++++++++++++++++++++++++++++++++++ >

On 2020/4/26 ??2:09, Zhu Lingshan wrote: > This commit implements config interrupt support in > vhost_vdpa layer. > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> > --- > drivers/vhost/vdpa.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++ > drivers/vhost/vhost.c | 2 +- > drivers/vhost/vhost.h | 2 ++ >

On 2020/4/26 ??2:09, Zhu Lingshan wrote: > This commit implements config interrupt support in > vhost_vdpa layer. > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> > --- > drivers/vhost/vdpa.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++ > drivers/vhost/vhost.c | 2 +- > drivers/vhost/vhost.h | 2 ++ >