From: Jason Wang <jasowang@redhat.com> To: Eli Cohen <elic@nvidia.com> Cc: mst@redhat.com, eperezma@redhat.com, kvm@vger.kernel.org, virtualization@lists.linux-foundation.org, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, lulu@redhat.com, eli@mellanox.com, lingshan.zhu@intel.com, rob.miller@broadcom.com, stefanha@redhat.com, sgarzare@redhat.com Subject: Re: [PATCH 21/21] vdpasim: control virtqueue support Date: Tue, 12 Jan 2021 11:11:53 +0800 [thread overview] Message-ID: <da50981b-6bbc-ee61-b5b1-a57a09da8e93@redhat.com> (raw) In-Reply-To: <20210111122601.GA172492@mtl-vdi-166.wap.labs.mlnx> On 2021/1/11 下午8:26, Eli Cohen wrote: > On Wed, Dec 16, 2020 at 02:48:18PM +0800, Jason Wang wrote: >> This patch introduces the control virtqueue support for vDPA >> simulator. This is a requirement for supporting advanced features like >> multiqueue. >> >> A requirement for control virtqueue is to isolate its memory access >> from the rx/tx virtqueues. This is because when using vDPA device >> for VM, the control virqueue is not directly assigned to VM. Userspace >> (Qemu) will present a shadow control virtqueue to control for >> recording the device states. >> >> The isolation is done via the virtqueue groups and ASID support in >> vDPA through vhost-vdpa. The simulator is extended to have: >> >> 1) three virtqueues: RXVQ, TXVQ and CVQ (control virtqueue) >> 2) two virtqueue groups: group 0 contains RXVQ and TXVQ; group 1 >> contains CVQ >> 3) two address spaces and the simulator simply implements the address >> spaces by mapping it 1:1 to IOTLB. >> >> For the VM use cases, userspace(Qemu) may set AS 0 to group 0 and AS 1 >> to group 1. So we have: >> >> 1) The IOTLB for virtqueue group 0 contains the mappings of guest, so >> RX and TX can be assigned to guest directly. >> 2) The IOTLB for virtqueue group 1 contains the mappings of CVQ which >> is the buffers that allocated and managed by VMM only. So CVQ of >> vhost-vdpa is visible to VMM only. And Guest can not access the CVQ >> of vhost-vdpa. >> >> For the other use cases, since AS 0 is associated to all virtqueue >> groups by default. All virtqueues share the same mapping by default. >> >> To demonstrate the function, VIRITO_NET_F_CTRL_MACADDR is >> implemented in the simulator for the driver to set mac address. >> > Hi Jason, > > is there any version of qemu/libvirt available that I can see the > control virtqueue working in action? Not yet, the qemu part depends on the shadow virtqueue work of Eugenio. But it will work as: 1) qemu will use a separated address space for the control virtqueue (shadow) exposed through vhost-vDPA 2) the commands sent through control virtqueue by guest driver will intercept by qemu 3) Qemu will send those commands to the shadow control virtqueue Eugenio, any ETA for the new version of shadow virtqueue support in Qemu? Thanks >
WARNING: multiple messages have this Message-ID (diff)
From: Jason Wang <jasowang@redhat.com> To: Eli Cohen <elic@nvidia.com> Cc: lulu@redhat.com, kvm@vger.kernel.org, mst@redhat.com, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org, eperezma@redhat.com, stefanha@redhat.com, eli@mellanox.com, lingshan.zhu@intel.com, rob.miller@broadcom.com Subject: Re: [PATCH 21/21] vdpasim: control virtqueue support Date: Tue, 12 Jan 2021 11:11:53 +0800 [thread overview] Message-ID: <da50981b-6bbc-ee61-b5b1-a57a09da8e93@redhat.com> (raw) In-Reply-To: <20210111122601.GA172492@mtl-vdi-166.wap.labs.mlnx> On 2021/1/11 下午8:26, Eli Cohen wrote: > On Wed, Dec 16, 2020 at 02:48:18PM +0800, Jason Wang wrote: >> This patch introduces the control virtqueue support for vDPA >> simulator. This is a requirement for supporting advanced features like >> multiqueue. >> >> A requirement for control virtqueue is to isolate its memory access >> from the rx/tx virtqueues. This is because when using vDPA device >> for VM, the control virqueue is not directly assigned to VM. Userspace >> (Qemu) will present a shadow control virtqueue to control for >> recording the device states. >> >> The isolation is done via the virtqueue groups and ASID support in >> vDPA through vhost-vdpa. The simulator is extended to have: >> >> 1) three virtqueues: RXVQ, TXVQ and CVQ (control virtqueue) >> 2) two virtqueue groups: group 0 contains RXVQ and TXVQ; group 1 >> contains CVQ >> 3) two address spaces and the simulator simply implements the address >> spaces by mapping it 1:1 to IOTLB. >> >> For the VM use cases, userspace(Qemu) may set AS 0 to group 0 and AS 1 >> to group 1. So we have: >> >> 1) The IOTLB for virtqueue group 0 contains the mappings of guest, so >> RX and TX can be assigned to guest directly. >> 2) The IOTLB for virtqueue group 1 contains the mappings of CVQ which >> is the buffers that allocated and managed by VMM only. So CVQ of >> vhost-vdpa is visible to VMM only. And Guest can not access the CVQ >> of vhost-vdpa. >> >> For the other use cases, since AS 0 is associated to all virtqueue >> groups by default. All virtqueues share the same mapping by default. >> >> To demonstrate the function, VIRITO_NET_F_CTRL_MACADDR is >> implemented in the simulator for the driver to set mac address. >> > Hi Jason, > > is there any version of qemu/libvirt available that I can see the > control virtqueue working in action? Not yet, the qemu part depends on the shadow virtqueue work of Eugenio. But it will work as: 1) qemu will use a separated address space for the control virtqueue (shadow) exposed through vhost-vDPA 2) the commands sent through control virtqueue by guest driver will intercept by qemu 3) Qemu will send those commands to the shadow control virtqueue Eugenio, any ETA for the new version of shadow virtqueue support in Qemu? Thanks > _______________________________________________ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
next prev parent reply other threads:[~2021-01-12 3:14 UTC|newest] Thread overview: 136+ messages / expand[flat|nested] mbox.gz Atom feed top 2020-12-16 6:47 [PATCH 00/21] Control VQ support in vDPA Jason Wang 2020-12-16 6:47 ` Jason Wang 2020-12-16 6:47 ` [PATCH 01/21] vhost: move the backend feature bits to vhost_types.h Jason Wang 2020-12-16 6:47 ` Jason Wang 2020-12-16 6:47 ` [PATCH 02/21] virtio-vdpa: don't set callback if virtio doesn't need it Jason Wang 2020-12-16 6:47 ` Jason Wang 2020-12-16 6:48 ` [PATCH 03/21] vhost-vdpa: passing iotlb to IOMMU mapping helpers Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 04/21] vhost-vdpa: switch to use vhost-vdpa specific IOTLB Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 05/21] vdpa: add the missing comment for nvqs in struct vdpa_device Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 06/21] vdpa: introduce virtqueue groups Jason Wang 2020-12-16 6:48 ` Jason Wang 2021-01-04 10:04 ` Stefan Hajnoczi 2021-01-04 10:04 ` Stefan Hajnoczi 2021-01-05 4:13 ` Jason Wang 2021-01-05 4:13 ` Jason Wang 2020-12-16 6:48 ` [PATCH 07/21] vdpa: multiple address spaces support Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-29 7:28 ` Eli Cohen 2020-12-30 4:00 ` Jason Wang 2020-12-30 4:00 ` Jason Wang 2020-12-30 4:04 ` Jason Wang 2020-12-30 4:04 ` Jason Wang 2020-12-30 9:44 ` Eli Cohen 2020-12-16 6:48 ` [PATCH 08/21] vdpa: introduce config operations for associating ASID to a virtqueue group Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 09/21] vhost_iotlb: split out IOTLB initialization Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 10/21] vhost: support ASID in IOTLB API Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-29 10:20 ` Eli Cohen 2020-12-30 4:27 ` Jason Wang 2020-12-30 4:27 ` Jason Wang 2020-12-16 6:48 ` [PATCH 11/21] vhost-vdpa: introduce asid based IOTLB Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-29 11:41 ` Eli Cohen 2020-12-30 6:23 ` Jason Wang 2020-12-30 6:23 ` Jason Wang 2020-12-29 11:53 ` Eli Cohen 2020-12-30 6:34 ` Jason Wang 2020-12-30 6:34 ` Jason Wang 2020-12-29 12:05 ` Eli Cohen 2020-12-30 6:33 ` Jason Wang 2020-12-30 6:33 ` Jason Wang 2020-12-16 6:48 ` [PATCH 12/21] vhost-vdpa: introduce uAPI to get the number of virtqueue groups Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-29 12:24 ` Eli Cohen 2020-12-30 6:49 ` Jason Wang 2020-12-30 6:49 ` Jason Wang 2020-12-30 10:05 ` Eli Cohen 2020-12-31 2:36 ` Jason Wang 2020-12-31 2:36 ` Jason Wang 2020-12-16 6:48 ` [PATCH 13/21] vhost-vdpa: introduce uAPI to get the number of address spaces Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 14/21] vhost-vdpa: uAPI to get virtqueue group id Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 15/21] vhost-vdpa: introduce uAPI to set group ASID Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 16/21] vhost-vdpa: support ASID based IOTLB API Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 17/21] vdpa_sim: split vdpasim_virtqueue's iov field in out_iov and in_iov Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 18/21] vdpa_sim: advertise VIRTIO_NET_F_MTU Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 19/21] vdpa_sim: factor out buffer completion logic Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 20/21] vdpa_sim: filter destination mac address Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-16 6:48 ` [PATCH 21/21] vdpasim: control virtqueue support Jason Wang 2020-12-16 6:48 ` Jason Wang 2020-12-17 20:19 ` kernel test robot 2020-12-17 20:19 ` kernel test robot 2020-12-17 20:19 ` kernel test robot 2021-01-11 12:26 ` Eli Cohen 2021-01-12 3:11 ` Jason Wang [this message] 2021-01-12 3:11 ` Jason Wang 2021-01-22 19:43 ` Eugenio Perez Martin 2021-01-25 3:16 ` Jason Wang 2021-01-25 3:16 ` Jason Wang 2020-12-16 9:47 ` [PATCH 00/21] Control VQ support in vDPA Michael S. Tsirkin 2020-12-16 9:47 ` Michael S. Tsirkin 2020-12-17 3:30 ` Jason Wang 2020-12-17 3:30 ` Jason Wang 2020-12-17 7:58 ` Michael S. Tsirkin 2020-12-17 7:58 ` Michael S. Tsirkin 2020-12-17 9:02 ` Jason Wang 2020-12-17 9:02 ` Jason Wang 2020-12-17 22:28 ` Michael S. Tsirkin 2020-12-17 22:28 ` Michael S. Tsirkin 2020-12-18 2:56 ` Jason Wang 2020-12-18 2:56 ` Jason Wang 2020-12-17 7:26 ` Eli Cohen 2022-02-24 21:22 ` [RFC PATCH v2 00/19] " Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 01/19] vhost: move the backend feature bits to vhost_types.h Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 02/19] virtio-vdpa: don't set callback if virtio doesn't need it Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 03/19] vhost-vdpa: passing iotlb to IOMMU mapping helpers Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 04/19] vhost-vdpa: switch to use vhost-vdpa specific IOTLB Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 05/19] vdpa: introduce virtqueue groups Gautam Dawar 2022-02-28 8:07 ` Jason Wang 2022-02-28 8:07 ` Jason Wang 2022-02-28 10:57 ` Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 06/19] vdpa: multiple address spaces support Gautam Dawar 2022-03-03 19:39 ` Eugenio Perez Martin 2022-03-04 6:30 ` Gautam Dawar 2022-03-04 17:45 ` Eugenio Perez Martin 2022-02-24 21:22 ` [RFC PATCH v2 07/19] vdpa: introduce config operations for associating ASID to a virtqueue group Gautam Dawar 2022-03-04 9:54 ` Eugenio Perez Martin 2022-03-04 17:48 ` Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 08/19] vhost_iotlb: split out IOTLB initialization Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 09/19] vhost: support ASID in IOTLB API Gautam Dawar 2022-03-04 10:25 ` Eugenio Perez Martin 2022-03-04 17:52 ` Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 10/19] vhost-vdpa: introduce asid based IOTLB Gautam Dawar 2022-03-04 17:56 ` Eugenio Perez Martin 2022-03-07 10:07 ` Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 11/19] vhost-vdpa: introduce uAPI to get the number of virtqueue groups Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 12/19] vhost-vdpa: introduce uAPI to get the number of address spaces Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 13/19] vhost-vdpa: uAPI to get virtqueue group id Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 14/19] vhost-vdpa: introduce uAPI to set group ASID Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 15/19] vhost-vdpa: support ASID based IOTLB API Gautam Dawar 2022-03-04 18:04 ` Eugenio Perez Martin 2022-03-07 10:23 ` Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 16/19] vdpa_sim: advertise VIRTIO_NET_F_MTU Gautam Dawar 2022-03-10 17:55 ` Eugenio Perez Martin 2022-02-24 21:22 ` [RFC PATCH v2 17/19] vdpa_sim: factor out buffer completion logic Gautam Dawar 2022-02-24 21:22 ` [RFC PATCH v2 18/19] vdpa_sim: filter destination mac address Gautam Dawar 2022-03-10 18:22 ` Eugenio Perez Martin 2022-02-24 21:22 ` [RFC PATCH v2 19/19] vdpasim: control virtqueue support Gautam Dawar 2022-03-10 18:20 ` Eugenio Perez Martin 2022-03-18 7:35 ` Eugenio Perez Martin 2022-03-22 8:46 ` Gautam Dawar 2022-02-28 8:17 ` [RFC PATCH v2 00/19] Control VQ support in vDPA Jason Wang 2022-02-28 8:17 ` Jason Wang 2022-02-28 10:56 ` Gautam Dawar
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=da50981b-6bbc-ee61-b5b1-a57a09da8e93@redhat.com \ --to=jasowang@redhat.com \ --cc=eli@mellanox.com \ --cc=elic@nvidia.com \ --cc=eperezma@redhat.com \ --cc=kvm@vger.kernel.org \ --cc=lingshan.zhu@intel.com \ --cc=linux-kernel@vger.kernel.org \ --cc=lulu@redhat.com \ --cc=mst@redhat.com \ --cc=netdev@vger.kernel.org \ --cc=rob.miller@broadcom.com \ --cc=sgarzare@redhat.com \ --cc=stefanha@redhat.com \ --cc=virtualization@lists.linux-foundation.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.