similar to: [PATCH RFC 1/5] vringfd syscall

On 2020/4/24 ??6:04, Zhu Lingshan wrote: > This commit implements config interrupt support > in IFC VF > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> > --- > drivers/vdpa/ifcvf/ifcvf_base.c | 3 +++ > drivers/vdpa/ifcvf/ifcvf_base.h | 2 ++ > drivers/vdpa/ifcvf/ifcvf_main.c | 22 +++++++++++++++++++++- > 3 files changed, 26 insertions(+), 1

Details about this can be found here: https://lwn.net/Articles/750770/ What's new in this version ========================== A new VFIO device type is introduced - vfio-vhost. This addressed some comments from here: https://patchwork.ozlabs.org/cover/984763/ Below is the updated device interface: Currently, there are two regions of this device: 1) CONFIG_REGION

Details about this can be found here: https://lwn.net/Articles/750770/ What's new in this version ========================== A new VFIO device type is introduced - vfio-vhost. This addressed some comments from here: https://patchwork.ozlabs.org/cover/984763/ Below is the updated device interface: Currently, there are two regions of this device: 1) CONFIG_REGION

This patch introduces a mdev (mediated device) based hardware vhost backend. This backend is an abstraction of the various hardware vhost accelerators (potentially any device that uses virtio ring can be used as a vhost accelerator). Some generic mdev parent ops are provided for accelerator drivers to support generating mdev instances. What's this =========== The idea is that we can setup a

This patch introduces a mdev (mediated device) based hardware vhost backend. This backend is an abstraction of the various hardware vhost accelerators (potentially any device that uses virtio ring can be used as a vhost accelerator). Some generic mdev parent ops are provided for accelerator drivers to support generating mdev instances. What's this =========== The idea is that we can setup a

Hello Rusty, while playing with your virtio descriptor code, I realized that the desc_pages data structure is not 64 bit safe. struct lguest_desc desc[NUM_DESCS] can be smaller than a page, as struct lguest_desc is 24 bytes on 64bit systems. Lets add a char padding to make the next page really page aligned. Btw. the new_io_desc.patch does not apply on current git. What base should I use?

Hello Rusty, while playing with your virtio descriptor code, I realized that the desc_pages data structure is not 64 bit safe. struct lguest_desc desc[NUM_DESCS] can be smaller than a page, as struct lguest_desc is 24 bytes on 64bit systems. Lets add a char padding to make the next page really page aligned. Btw. the new_io_desc.patch does not apply on current git. What base should I use?

On Thu, 2007-08-16 at 19:13 -0400, Gregory Haskins wrote: > Here is the v3 release of the patch series for a generalized PV-IO > infrastructure. It has v2 plus the following changes: Hi Gregory, This is a lot of code. I'm having trouble taking it all in, TBH. It might help me if we could to go back to the basic transport implementation questions. Transport has several parts. What

On Thu, 2007-08-16 at 19:13 -0400, Gregory Haskins wrote: > Here is the v3 release of the patch series for a generalized PV-IO > infrastructure. It has v2 plus the following changes: Hi Gregory, This is a lot of code. I'm having trouble taking it all in, TBH. It might help me if we could to go back to the basic transport implementation questions. Transport has several parts. What

On 2020/4/26 ??4:42, Zhu Lingshan wrote: > This commit implements config interrupt support > in IFC VF > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> > --- > drivers/vdpa/ifcvf/ifcvf_base.c | 3 +++ > drivers/vdpa/ifcvf/ifcvf_base.h | 3 +++ > drivers/vdpa/ifcvf/ifcvf_main.c | 22 +++++++++++++++++++++- > 3 files changed, 27 insertions(+), 1

In this commit, virtqueue operations including: set_vq_num(), set_vq_address(), set_vq_ready() and get_vq_ready() access PCI registers directly to take immediate actions. Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> --- drivers/vdpa/ifcvf/ifcvf_base.c | 58 ++++++++++++++++++++------------- drivers/vdpa/ifcvf/ifcvf_base.h | 10 +++--- drivers/vdpa/ifcvf/ifcvf_main.c | 16

On 2019/7/3 ??5:13, Tiwei Bie wrote: > Details about this can be found here: > > https://lwn.net/Articles/750770/ > > What's new in this version > ========================== > > A new VFIO device type is introduced - vfio-vhost. This addressed > some comments from here: https://patchwork.ozlabs.org/cover/984763/ > > Below is the updated device interface: >

On 2019/11/5 ??5:37, Zhu Lingshan wrote: > This commit introduced ifcvf_base layer, which handles hardware > operations and configurations. It looks like the PCI layout is pretty similar to virtio. Can we reuse e.g virtio_pci_modern_probe() (or helpers in virtio_pci_modern.c) to do the probing? > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> > --- >

On 2018?04?02? 23:23, Tiwei Bie wrote: > This patch introduces a mdev (mediated device) based hardware > vhost backend. This backend is an abstraction of the various > hardware vhost accelerators (potentially any device that uses > virtio ring can be used as a vhost accelerator). Some generic > mdev parent ops are provided for accelerator drivers to support > generating mdev

On Tue, Nov 05, 2019 at 05:37:39PM +0800, Zhu Lingshan wrote: > This commit introduced ifcvf_base layer, which handles hardware > operations and configurations. > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> > --- > drivers/vhost/ifcvf/ifcvf_base.c | 344 +++++++++++++++++++++++++++++++++++++++ > drivers/vhost/ifcvf/ifcvf_base.h | 132 +++++++++++++++ >

On Tue, Nov 05, 2019 at 05:37:39PM +0800, Zhu Lingshan wrote: > This commit introduced ifcvf_base layer, which handles hardware > operations and configurations. > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> > --- > drivers/vhost/ifcvf/ifcvf_base.c | 344 +++++++++++++++++++++++++++++++++++++++ > drivers/vhost/ifcvf/ifcvf_base.h | 132 +++++++++++++++ >

On Tue, Nov 05, 2019 at 05:37:39PM +0800, Zhu Lingshan wrote: > This commit introduced ifcvf_base layer, which handles hardware > operations and configurations. > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> > --- > drivers/vhost/ifcvf/ifcvf_base.c | 344 +++++++++++++++++++++++++++++++++++++++ > drivers/vhost/ifcvf/ifcvf_base.h | 132 +++++++++++++++ >

On 2019/10/16 ??9:30, Zhu Lingshan wrote: > This commit introduced ifcvf_base layer, which handles IFC VF NIC > hardware operations and configurations. It's better to describe the difference between ifc vf and virtio in the commit log or is there a open doc for this? > > Signed-off-by: Zhu Lingshan <lingshan.zhu at intel.com> > --- >

On 2019/10/21 ??6:00, Zhu, Lingshan wrote: > > On 10/16/2019 4:40 PM, Jason Wang wrote: >> >> On 2019/10/16 ??9:30, Zhu Lingshan wrote: >>> This commit introduced ifcvf_base layer, which handles IFC VF NIC >>> hardware operations and configurations. >> >> >> It's better to describe the difference between ifc vf and virtio in >> the

virtio allows drivers to suppress callbacks (ie. interrupts) for efficiency (no locking, it's just an optimization). There's a similar mechanism for the host to suppress notifications coming from the guest: in that case, we ignore the suppression if the ring is completely full. It turns out that life is simpler if the host similarly ignores callback suppression when the ring is