On Thu, Aug 7, 2025 at 7:58 PM Eugenio Pérez <eperezma@xxxxxxxxxx> wrote:
>
> This allows sepparate the different virtqueues in groups that shares the
> same address space. Asking the VDUSE device for the groups of the vq at
> the beginning as they're needed for the DMA API.
>
> Allocating 3 vq groups as net is the device that need the most groups:
> * Dataplane (guest passthrough)
> * CVQ
> * Shadowed vrings.
>
> Future versions of the series can include dynamic allocation of the
> groups array so VDUSE can declare more groups.
>
> Signed-off-by: Eugenio Pérez <eperezma@xxxxxxxxxx>
> ---
> v2:
> * Cache group information in kernel, as we need to provide the vq map
> tokens properly.
> * Add descs vq group to optimize SVQ forwarding and support indirect
> descriptors out of the box.
> ---
> drivers/vdpa/vdpa_user/vduse_dev.c | 71 +++++++++++++++++++++++++++++-
> include/uapi/linux/vduse.h | 19 +++++++-
> 2 files changed, 88 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
> index d858c4389cc1..d1f6d00a9c71 100644
> --- a/drivers/vdpa/vdpa_user/vduse_dev.c
> +++ b/drivers/vdpa/vdpa_user/vduse_dev.c
> @@ -46,6 +46,11 @@
> #define VDUSE_IOVA_SIZE (VDUSE_MAX_BOUNCE_SIZE + 128 * 1024 * 1024)
> #define VDUSE_MSG_DEFAULT_TIMEOUT 30
>
> +/*
> + * Let's make it 3 for simplicity.
> + */
> +#define VDUSE_MAX_VQ_GROUPS 3
I think we can release this to something like 64. Otherwise we might
bump the version again just to increase the limitation? Or having a
sysfs entry like bounce_size?
> +
> #define IRQ_UNBOUND -1
>
> struct vduse_virtqueue {
> @@ -58,6 +63,8 @@ struct vduse_virtqueue {
> struct vdpa_vq_state state;
> bool ready;
> bool kicked;
> + u32 vq_group;
> + u32 vq_desc_group;
> spinlock_t kick_lock;
> spinlock_t irq_lock;
> struct eventfd_ctx *kickfd;
> @@ -114,6 +121,7 @@ struct vduse_dev {
> u8 status;
> u32 vq_num;
> u32 vq_align;
> + u32 ngroups;
> struct vduse_umem *umem;
> struct mutex mem_lock;
> unsigned int bounce_size;
> @@ -592,6 +600,20 @@ static int vduse_vdpa_set_vq_state(struct vdpa_device *vdpa, u16 idx,
> return 0;
> }
>
> +static u32 vduse_get_vq_group(struct vdpa_device *vdpa, u16 idx)
> +{
> + struct vduse_dev *dev = vdpa_to_vduse(vdpa);
> +
> + return dev->vqs[idx]->vq_group;
> +}
> +
> +static u32 vduse_get_vq_desc_group(struct vdpa_device *vdpa, u16 idx)
> +{
> + struct vduse_dev *dev = vdpa_to_vduse(vdpa);
> +
> + return dev->vqs[idx]->vq_desc_group;
> +}
> +
> static int vduse_vdpa_get_vq_state(struct vdpa_device *vdpa, u16 idx,
> struct vdpa_vq_state *state)
> {
> @@ -678,13 +700,48 @@ static u8 vduse_vdpa_get_status(struct vdpa_device *vdpa)
> return dev->status;
> }
>
> +static int vduse_fill_vq_groups(struct vduse_dev *dev)
> +{
> + if (dev->api_version < VDUSE_API_VERSION_1)
> + return 0;
> +
> + for (int i = 0; i < dev->vdev->vdpa.nvqs; ++i) {
> + struct vduse_dev_msg msg = { 0 };
> + int ret;
> +
> + msg.req.type = VDUSE_GET_VQ_GROUP;
> + msg.req.vq_group.index = i;
> + ret = vduse_dev_msg_sync(dev, &msg);
I fail to understand why the default group mapping is not done during
device creation.
> + if (ret)
> + return ret;
> +
> + dev->vqs[i]->vq_group = msg.resp.vq_group.num;
> +
> + msg.req.type = VDUSE_GET_VRING_DESC_GROUP;
> + ret = vduse_dev_msg_sync(dev, &msg);
> + if (ret)
> + return ret;
> +
> + dev->vqs[i]->vq_desc_group = msg.resp.vq_group.num;
> + }
> +
> + return 0;
> +}
> +
> static void vduse_vdpa_set_status(struct vdpa_device *vdpa, u8 status)
> {
> struct vduse_dev *dev = vdpa_to_vduse(vdpa);
> + u8 previous_status = dev->status;
>
> if (vduse_dev_set_status(dev, status))
> return;
>
> + if ((dev->status ^ previous_status) &
> + BIT_ULL(VIRTIO_CONFIG_S_FEATURES_OK) &&
> + status & (1ULL << VIRTIO_CONFIG_S_FEATURES_OK))
> + if (vduse_fill_vq_groups(dev))
Can we merge the two messages into a single one? Or can we use a
shared memory for storing such mapping?
For example, if we have 256 queues it would be very slow.
Thanks
