Hi Gautam,
On Wed, Mar 30, 2022 at 8:21 PM Gautam Dawar <gautam.dawar@xxxxxxxxxx> 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.
>
> Signed-off-by: Jason Wang <jasowang@xxxxxxxxxx>
> Signed-off-by: Gautam Dawar <gdawar@xxxxxxxxxx>
> ---
> drivers/vdpa/vdpa_sim/vdpa_sim.c | 91 ++++++++++++++++++++++------
> drivers/vdpa/vdpa_sim/vdpa_sim.h | 2 +
> drivers/vdpa/vdpa_sim/vdpa_sim_net.c | 88 ++++++++++++++++++++++++++-
> 3 files changed, 161 insertions(+), 20 deletions(-)
>
> diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
> index 659e2e2e4b0c..51bd0bafce06 100644
> --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
> +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
> @@ -96,11 +96,17 @@ static void vdpasim_do_reset(struct vdpasim *vdpasim)
> {
> int i;
>
> - for (i = 0; i < vdpasim->dev_attr.nvqs; i++)
> + spin_lock(&vdpasim->iommu_lock);
> +
> + for (i = 0; i < vdpasim->dev_attr.nvqs; i++) {
> vdpasim_vq_reset(vdpasim, &vdpasim->vqs[i]);
> + vringh_set_iotlb(&vdpasim->vqs[i].vring, &vdpasim->iommu[0],
> + &vdpasim->iommu_lock);
> + }
> +
> + for (i = 0; i < vdpasim->dev_attr.nas; i++)
> + vhost_iotlb_reset(&vdpasim->iommu[i]);
>
> - spin_lock(&vdpasim->iommu_lock);
> - vhost_iotlb_reset(vdpasim->iommu);
> spin_unlock(&vdpasim->iommu_lock);
>
> vdpasim->features = 0;
> @@ -145,7 +151,7 @@ static dma_addr_t vdpasim_map_range(struct vdpasim *vdpasim, phys_addr_t paddr,
> dma_addr = iova_dma_addr(&vdpasim->iova, iova);
>
> spin_lock(&vdpasim->iommu_lock);
> - ret = vhost_iotlb_add_range(vdpasim->iommu, (u64)dma_addr,
> + ret = vhost_iotlb_add_range(&vdpasim->iommu[0], (u64)dma_addr,
> (u64)dma_addr + size - 1, (u64)paddr, perm);
> spin_unlock(&vdpasim->iommu_lock);
>
> @@ -161,7 +167,7 @@ static void vdpasim_unmap_range(struct vdpasim *vdpasim, dma_addr_t dma_addr,
> size_t size)
> {
> spin_lock(&vdpasim->iommu_lock);
> - vhost_iotlb_del_range(vdpasim->iommu, (u64)dma_addr,
> + vhost_iotlb_del_range(&vdpasim->iommu[0], (u64)dma_addr,
> (u64)dma_addr + size - 1);
> spin_unlock(&vdpasim->iommu_lock);
>
> @@ -250,8 +256,9 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)
> else
> ops = &vdpasim_config_ops;
>
> - vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops, 1,
> - 1, dev_attr->name, false);
> + vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops,
> + dev_attr->ngroups, dev_attr->nas,
> + dev_attr->name, false);
> if (IS_ERR(vdpasim)) {
> ret = PTR_ERR(vdpasim);
> goto err_alloc;
> @@ -278,16 +285,20 @@ struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)
> if (!vdpasim->vqs)
> goto err_iommu;
>
> - vdpasim->iommu = vhost_iotlb_alloc(max_iotlb_entries, 0);
> + vdpasim->iommu = kmalloc_array(vdpasim->dev_attr.nas,
> + sizeof(*vdpasim->iommu), GFP_KERNEL);
> if (!vdpasim->iommu)
> goto err_iommu;
>
> + for (i = 0; i < vdpasim->dev_attr.nas; i++)
> + vhost_iotlb_init(&vdpasim->iommu[i], 0, 0);
> +
> vdpasim->buffer = kvmalloc(dev_attr->buffer_size, GFP_KERNEL);
> if (!vdpasim->buffer)
> goto err_iommu;
>
> for (i = 0; i < dev_attr->nvqs; i++)
> - vringh_set_iotlb(&vdpasim->vqs[i].vring, vdpasim->iommu,
> + vringh_set_iotlb(&vdpasim->vqs[i].vring, &vdpasim->iommu[0],
> &vdpasim->iommu_lock);
>
> ret = iova_cache_get();
> @@ -401,7 +412,11 @@ static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)
>
> static u32 vdpasim_get_vq_group(struct vdpa_device *vdpa, u16 idx)
> {
> - return 0;
> + /* RX and TX belongs to group 0, CVQ belongs to group 1 */
> + if (idx == 2)
> + return 1;
> + else
> + return 0;
This code only works for the vDPA-net simulator, since
vdpasim_get_vq_group() is also shared with other simulators (e.g.
vdpa_sim_blk), should we move this net-specific code into
vdpa_sim_net.c, maybe adding a callback implemented by the different
simulators?
Thanks,
Stefano
