From: Jason Wang <jasowang@redhat.com>
To: Eli Cohen <elic@nvidia.com>
Cc: mst@redhat.com, lulu@redhat.com, kvm@vger.kernel.org,
virtualization@lists.linux-foundation.org,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
rob.miller@broadcom.com, lingshan.zhu@intel.com,
eperezma@redhat.com, hanand@xilinx.com, mhabets@solarflare.com,
amorenoz@redhat.com, maxime.coquelin@redhat.com,
stefanha@redhat.com, sgarzare@redhat.com
Subject: Re: [RFC PATCH 09/24] vdpa: multiple address spaces support
Date: Fri, 9 Oct 2020 11:51:44 +0800 [thread overview]
Message-ID: <028ebad8-2106-0ea9-4092-4c14f1e2fdfe@redhat.com> (raw)
In-Reply-To: <20201001132124.GA32363@mtl-vdi-166.wap.labs.mlnx>
On 2020/10/1 下午9:21, Eli Cohen wrote:
> On Thu, Sep 24, 2020 at 11:21:10AM +0800, Jason Wang wrote:
>> This patches introduces the multiple address spaces support for vDPA
>> device. This idea is to identify a specific address space via an
>> dedicated identifier - ASID.
>>
>> During vDPA device allocation, vDPA device driver needs to report the
>> number of address spaces supported by the device then the DMA mapping
>> ops of the vDPA device needs to be extended to support ASID.
>>
>> This helps to isolate the DMA among the virtqueues. E.g in the case of
>> virtio-net, the control virtqueue will not be assigned directly to
>> guest.
>>
>> This RFC patch only converts for the device that wants its own
>> IOMMU/DMA translation logic. So it will rejects the device with more
>> that 1 address space that depends on platform IOMMU. The plan to
> This is not apparent from the code. Instead you enforce number of groups
> to 1.
Yes, will fix.
>
>> moving all the DMA mapping logic to the vDPA device driver instead of
>> doing it in vhost-vDPA (otherwise it could result a very complicated
>> APIs and actually vhost-vDPA doesn't care about how the actual
>> composition/emulation were done in the device driver).
>>
>> Signed-off-by: Jason Wang <jasowang@redhat.com>
>> ---
>> drivers/vdpa/ifcvf/ifcvf_main.c | 2 +-
>> drivers/vdpa/mlx5/net/mlx5_vnet.c | 5 +++--
>> drivers/vdpa/vdpa.c | 4 +++-
>> drivers/vdpa/vdpa_sim/vdpa_sim.c | 10 ++++++----
>> drivers/vhost/vdpa.c | 14 +++++++++-----
>> include/linux/vdpa.h | 23 ++++++++++++++++-------
>> 6 files changed, 38 insertions(+), 20 deletions(-)
>>
>> diff --git a/drivers/vdpa/ifcvf/ifcvf_main.c b/drivers/vdpa/ifcvf/ifcvf_main.c
>> index e6a0be374e51..86cdf5f8bcae 100644
>> --- a/drivers/vdpa/ifcvf/ifcvf_main.c
>> +++ b/drivers/vdpa/ifcvf/ifcvf_main.c
>> @@ -440,7 +440,7 @@ static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
>>
>> adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
>> dev, &ifc_vdpa_ops,
>> - IFCVF_MAX_QUEUE_PAIRS * 2, 1);
>> + IFCVF_MAX_QUEUE_PAIRS * 2, 1, 1);
>>
>> if (adapter == NULL) {
>> IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
>> diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c
>> index 4e480f4f754e..db7404e121bf 100644
>> --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
>> +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
>> @@ -1788,7 +1788,8 @@ static u32 mlx5_vdpa_get_generation(struct vdpa_device *vdev)
>> return mvdev->generation;
>> }
>>
>> -static int mlx5_vdpa_set_map(struct vdpa_device *vdev, struct vhost_iotlb *iotlb)
>> +static int mlx5_vdpa_set_map(struct vdpa_device *vdev, unsigned int asid,
>> + struct vhost_iotlb *iotlb)
>> {
>> struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
>> struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
>> @@ -1931,7 +1932,7 @@ void *mlx5_vdpa_add_dev(struct mlx5_core_dev *mdev)
>> max_vqs = min_t(u32, max_vqs, MLX5_MAX_SUPPORTED_VQS);
>>
>> ndev = vdpa_alloc_device(struct mlx5_vdpa_net, mvdev.vdev, mdev->device, &mlx5_vdpa_ops,
>> - 2 * mlx5_vdpa_max_qps(max_vqs), 1);
>> + 2 * mlx5_vdpa_max_qps(max_vqs), 1, 1);
>> if (IS_ERR(ndev))
>> return ndev;
>>
>> diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
>> index 46399746ec7c..05195fa7865d 100644
>> --- a/drivers/vdpa/vdpa.c
>> +++ b/drivers/vdpa/vdpa.c
>> @@ -63,6 +63,7 @@ static void vdpa_release_dev(struct device *d)
>> * @config: the bus operations that is supported by this device
>> * @nvqs: number of virtqueues supported by this device
>> * @ngroups: number of groups supported by this device
>> + * @nas: number of address spaces supported by this device
>> * @size: size of the parent structure that contains private data
>> *
>> * Driver should use vdpa_alloc_device() wrapper macro instead of
>> @@ -74,7 +75,7 @@ static void vdpa_release_dev(struct device *d)
>> struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>> const struct vdpa_config_ops *config,
>> int nvqs, unsigned int ngroups,
>> - size_t size)
>> + unsigned int nas, size_t size)
>> {
>> struct vdpa_device *vdev;
>> int err = -EINVAL;
>> @@ -102,6 +103,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>> vdev->features_valid = false;
>> vdev->nvqs = nvqs;
>> vdev->ngroups = ngroups;
>> + vdev->nas = nas;
>>
>> err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index);
>> if (err)
>> diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
>> index 6669c561bc6e..5dc04ec271bb 100644
>> --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
>> +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
>> @@ -354,7 +354,7 @@ static struct vdpasim *vdpasim_create(void)
>> ops = &vdpasim_net_config_ops;
>>
>> vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops,
>> - VDPASIM_VQ_NUM, 1);
>> + VDPASIM_VQ_NUM, 1, 1);
>> if (!vdpasim)
>> goto err_alloc;
>>
>> @@ -581,7 +581,7 @@ static u32 vdpasim_get_generation(struct vdpa_device *vdpa)
>> return vdpasim->generation;
>> }
>>
>> -static int vdpasim_set_map(struct vdpa_device *vdpa,
>> +static int vdpasim_set_map(struct vdpa_device *vdpa, unsigned int asid,
>> struct vhost_iotlb *iotlb)
>> {
>> struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
>> @@ -608,7 +608,8 @@ static int vdpasim_set_map(struct vdpa_device *vdpa,
>> return ret;
>> }
>>
>> -static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,
>> +static int vdpasim_dma_map(struct vdpa_device *vdpa, unsigned int asid,
>> + u64 iova, u64 size,
>> u64 pa, u32 perm)
>> {
>> struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
>> @@ -622,7 +623,8 @@ static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,
>> return ret;
>> }
>>
>> -static int vdpasim_dma_unmap(struct vdpa_device *vdpa, u64 iova, u64 size)
>> +static int vdpasim_dma_unmap(struct vdpa_device *vdpa, unsigned int asid,
>> + u64 iova, u64 size)
>> {
>> struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
>>
>> diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
>> index ec3c94f706c1..eeefcd971e3f 100644
>> --- a/drivers/vhost/vdpa.c
>> +++ b/drivers/vhost/vdpa.c
>> @@ -557,10 +557,10 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
>> return r;
>>
>> if (ops->dma_map) {
>> - r = ops->dma_map(vdpa, iova, size, pa, perm);
>> + r = ops->dma_map(vdpa, 0, iova, size, pa, perm);
>> } else if (ops->set_map) {
>> if (!v->in_batch)
>> - r = ops->set_map(vdpa, iotlb);
>> + r = ops->set_map(vdpa, 0, iotlb);
>> } else {
>> r = iommu_map(v->domain, iova, pa, size,
>> perm_to_iommu_flags(perm));
>> @@ -579,10 +579,10 @@ static void vhost_vdpa_unmap(struct vhost_vdpa *v,
>> vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1);
>>
>> if (ops->dma_map) {
>> - ops->dma_unmap(vdpa, iova, size);
>> + ops->dma_unmap(vdpa, 0, iova, size);
>> } else if (ops->set_map) {
>> if (!v->in_batch)
>> - ops->set_map(vdpa, iotlb);
>> + ops->set_map(vdpa, 0, iotlb);
>> } else {
>> iommu_unmap(v->domain, iova, size);
>> }
>> @@ -700,7 +700,7 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,
>> break;
>> case VHOST_IOTLB_BATCH_END:
>> if (v->in_batch && ops->set_map)
>> - ops->set_map(vdpa, iotlb);
>> + ops->set_map(vdpa, 0, iotlb);
>> v->in_batch = false;
>> break;
>> default:
>> @@ -949,6 +949,10 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
>> int minor;
>> int r;
>>
>> + /* Only support 1 address space */
>> + if (vdpa->ngroups != 1)
>> + return -ENOTSUPP;
>> +
> Did you mean to check agains vdpa->nas?
I think we should check both.
Thanks
>
>> /* Currently, we only accept the network devices. */
>> if (ops->get_device_id(vdpa) != VIRTIO_ID_NET)
>> return -ENOTSUPP;
>> diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
>> index d829512efd27..1e1163daa352 100644
>> --- a/include/linux/vdpa.h
>> +++ b/include/linux/vdpa.h
>> @@ -43,6 +43,8 @@ struct vdpa_vq_state {
>> * @index: device index
>> * @features_valid: were features initialized? for legacy guests
>> * @nvqs: the number of virtqueues
>> + * @ngroups: the number of virtqueue groups
>> + * @nas: the number of address spaces
>> */
>> struct vdpa_device {
>> struct device dev;
>> @@ -52,6 +54,7 @@ struct vdpa_device {
>> bool features_valid;
>> int nvqs;
>> unsigned int ngroups;
>> + unsigned int nas;
>> };
>>
>> /**
>> @@ -161,6 +164,7 @@ struct vdpa_device {
>> * Needed for device that using device
>> * specific DMA translation (on-chip IOMMU)
>> * @vdev: vdpa device
>> + * @asid: address space identifier
>> * @iotlb: vhost memory mapping to be
>> * used by the vDPA
>> * Returns integer: success (0) or error (< 0)
>> @@ -169,6 +173,7 @@ struct vdpa_device {
>> * specific DMA translation (on-chip IOMMU)
>> * and preferring incremental map.
>> * @vdev: vdpa device
>> + * @asid: address space identifier
>> * @iova: iova to be mapped
>> * @size: size of the area
>> * @pa: physical address for the map
>> @@ -180,6 +185,7 @@ struct vdpa_device {
>> * specific DMA translation (on-chip IOMMU)
>> * and preferring incremental unmap.
>> * @vdev: vdpa device
>> + * @asid: address space identifier
>> * @iova: iova to be unmapped
>> * @size: size of the area
>> * Returns integer: success (0) or error (< 0)
>> @@ -225,10 +231,12 @@ struct vdpa_config_ops {
>> u32 (*get_generation)(struct vdpa_device *vdev);
>>
>> /* DMA ops */
>> - int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb);
>> - int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size,
>> - u64 pa, u32 perm);
>> - int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size);
>> + int (*set_map)(struct vdpa_device *vdev, unsigned int asid,
>> + struct vhost_iotlb *iotlb);
>> + int (*dma_map)(struct vdpa_device *vdev, unsigned int asid,
>> + u64 iova, u64 size, u64 pa, u32 perm);
>> + int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid,
>> + u64 iova, u64 size);
>>
>> /* Free device resources */
>> void (*free)(struct vdpa_device *vdev);
>> @@ -237,11 +245,12 @@ struct vdpa_config_ops {
>> struct vdpa_device *__vdpa_alloc_device(struct device *parent,
>> const struct vdpa_config_ops *config,
>> int nvqs, unsigned int ngroups,
>> - size_t size);
>> + unsigned int nas, size_t size);
>>
>> -#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs, ngroups) \
>> +#define vdpa_alloc_device(dev_struct, member, parent, config, nvqs, \
>> + ngroups, nas) \
>> container_of(__vdpa_alloc_device( \
>> - parent, config, nvqs, ngroups, \
>> + parent, config, nvqs, ngroups, nas, \
>> sizeof(dev_struct) + \
>> BUILD_BUG_ON_ZERO(offsetof( \
>> dev_struct, member))), \
>> --
>> 2.20.1
>>
next prev parent reply other threads:[~2020-10-09 3:52 UTC|newest]
Thread overview: 55+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-24 3:21 [RFC PATCH 00/24] Control VQ support in vDPA Jason Wang
2020-09-24 3:21 ` [RFC PATCH 01/24] vhost-vdpa: fix backend feature ioctls Jason Wang
2020-09-24 7:16 ` Eli Cohen
2020-09-24 7:26 ` Jason Wang
2020-09-24 7:38 ` Eli Cohen
2020-09-24 7:50 ` Michael S. Tsirkin
2020-09-24 8:28 ` Jason Wang
2020-09-24 3:21 ` [RFC PATCH 02/24] vhost-vdpa: fix vqs leak in vhost_vdpa_open() Jason Wang
2020-09-24 7:48 ` Eli Cohen
2020-09-25 11:41 ` Jason Wang
2020-09-24 9:31 ` Michael S. Tsirkin
2020-09-25 11:27 ` Jason Wang
2020-09-24 3:21 ` [RFC PATCH 03/24] vhost: move the backend feature bits to vhost_types.h Jason Wang
2020-09-24 3:21 ` [RFC PATCH 04/24] virtio-vdpa: don't set callback if virtio doesn't need it Jason Wang
2020-09-24 3:21 ` [RFC PATCH 05/24] vhost-vdpa: passing iotlb to IOMMU mapping helpers Jason Wang
2020-09-30 11:26 ` Eli Cohen
2020-10-09 2:01 ` Jason Wang
2020-09-24 3:21 ` [RFC PATCH 06/24] vhost-vdpa: switch to use vhost-vdpa specific IOTLB Jason Wang
2020-09-30 12:02 ` Eli Cohen
2020-10-09 3:46 ` Jason Wang
2020-09-24 3:21 ` [RFC PATCH 07/24] vdpa: add the missing comment for nvqs in struct vdpa_device Jason Wang
2020-09-24 3:21 ` [RFC PATCH 08/24] vdpa: introduce virtqueue groups Jason Wang
2020-09-28 15:44 ` Eugenio Perez Martin
2020-10-09 3:49 ` Jason Wang
2020-09-24 3:21 ` [RFC PATCH 09/24] vdpa: multiple address spaces support Jason Wang
2020-10-01 13:21 ` Eli Cohen
2020-10-09 3:51 ` Jason Wang [this message]
2020-10-01 13:23 ` Eli Cohen
2020-10-09 3:52 ` Jason Wang
2020-09-24 3:21 ` [RFC PATCH 10/24] vdpa: introduce config operations for associating ASID to a virtqueue group Jason Wang
2020-10-01 13:29 ` Eli Cohen
2020-10-09 3:56 ` Jason Wang
2020-10-12 6:59 ` Eli Cohen
2020-10-12 7:45 ` Jason Wang
2020-10-12 8:17 ` Eli Cohen
2020-10-13 5:40 ` Jason Wang
2020-09-24 3:21 ` [RFC PATCH 11/24] vhost_iotlb: split out IOTLB initialization Jason Wang
2020-09-24 3:21 ` [RFC PATCH 12/24] vhost: support ASID in IOTLB API Jason Wang
2020-09-24 3:21 ` [RFC PATCH 13/24] vhost-vdpa: introduce ASID based IOTLB Jason Wang
2020-09-29 14:40 ` Eugenio Perez Martin
2020-09-24 3:21 ` [RFC PATCH 14/24] vhost-vdpa: introduce uAPI to get the number of virtqueue groups Jason Wang
2020-09-24 3:21 ` [RFC PATCH 15/24] vhost-vdpa: introduce uAPI to get the number of address spaces Jason Wang
2020-09-24 3:21 ` [RFC PATCH 16/24] vhost-vdpa: uAPI to get virtqueue group id Jason Wang
2020-09-24 3:21 ` [RFC PATCH 17/24] vhost-vdpa: introduce uAPI to set group ASID Jason Wang
2020-09-24 3:21 ` [RFC PATCH 18/24] vhost-vdpa: support ASID based IOTLB API Jason Wang
2020-09-28 15:44 ` Eugenio Perez Martin
2020-10-09 3:59 ` Jason Wang
2020-09-24 3:21 ` [RFC PATCH 19/24] vdpa_sim: use separated iov for reading and writing Jason Wang
2020-09-24 3:21 ` [RFC PATCH 20/24] vdpa_sim: advertise VIRTIO_NET_F_MTU Jason Wang
2020-09-24 3:21 ` [RFC PATCH 21/24] vdpa_sim: advertise VIRTIO_NET_F_MAC Jason Wang
2020-09-24 3:21 ` [RFC PATCH 22/24] vdpa_sim: factor out buffer completion logic Jason Wang
2020-09-24 3:21 ` [RFC PATCH 23/24] vdpa_sim: filter destination mac address Jason Wang
2020-09-24 3:21 ` [RFC PATCH 24/24] vdpasim: control virtqueue support Jason Wang
2020-09-24 10:17 ` [RFC PATCH 00/24] Control VQ support in vDPA Stefan Hajnoczi
2020-09-25 11:36 ` Jason Wang
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=028ebad8-2106-0ea9-4092-4c14f1e2fdfe@redhat.com \
--to=jasowang@redhat.com \
--cc=amorenoz@redhat.com \
--cc=elic@nvidia.com \
--cc=eperezma@redhat.com \
--cc=hanand@xilinx.com \
--cc=kvm@vger.kernel.org \
--cc=lingshan.zhu@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lulu@redhat.com \
--cc=maxime.coquelin@redhat.com \
--cc=mhabets@solarflare.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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).