On Fri, Sep 26, 2025 at 4:16 PM Eugenio Perez Martin <[email protected]> wrote: > > On Fri, Sep 26, 2025 at 9:42 AM Jason Wang <[email protected]> wrote: > > > > On Thu, Sep 25, 2025 at 5:14 PM Eugenio Pérez <[email protected]> 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 <[email protected]> > > > --- > > > v4: > > > * Revert the "invalid vq group" concept and assume 0 if not set (Jason). > > > * Make config->ngroups == 0 invalid (Jason). > > > > > > v3: > > > * Make the default group an invalid group as long as VDUSE device does > > > not set it to some valid u32 value. Modify the vdpa core to take that > > > into account (Jason). > > > * Create the VDUSE_DEV_MAX_GROUPS instead of using a magic number > > > > > > v2: > > > * Now the vq group is in vduse_vq_config struct instead of issuing one > > > VDUSE message per vq. > > > > > > v1: > > > * Fix: Remove BIT_ULL(VIRTIO_S_*), as _S_ is already the bit (Maxime) > > > > > > RFC v3: > > > * Increase VDUSE_MAX_VQ_GROUPS to 0xffff (Jason). It was set to a lower > > > value to reduce memory consumption, but vqs are already limited to > > > that value and userspace VDUSE is able to allocate that many vqs. > > > * Remove the descs vq group capability as it will not be used and we can > > > add it on top. > > > * Do not ask for vq groups in number of vq groups < 2. > > > * Move the valid vq groups range check to vduse_validate_config. > > > > > > RFC 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 | 46 ++++++++++++++++++++++++++---- > > > drivers/vhost/vdpa.c | 11 +++++-- > > > include/uapi/linux/vduse.h | 12 ++++++-- > > > 3 files changed, 58 insertions(+), 11 deletions(-) > > > > > > diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c > > > b/drivers/vdpa/vdpa_user/vduse_dev.c > > > index 2b6a8958ffe0..3415217cb3a9 100644 > > > --- a/drivers/vdpa/vdpa_user/vduse_dev.c > > > +++ b/drivers/vdpa/vdpa_user/vduse_dev.c > > > @@ -40,6 +40,7 @@ > > > #define DRV_LICENSE "GPL v2" > > > > > > #define VDUSE_DEV_MAX (1U << MINORBITS) > > > +#define VDUSE_DEV_MAX_GROUPS 0xffff > > > #define VDUSE_MAX_BOUNCE_SIZE (1024 * 1024 * 1024) > > > #define VDUSE_MIN_BOUNCE_SIZE (1024 * 1024) > > > #define VDUSE_BOUNCE_SIZE (64 * 1024 * 1024) > > > @@ -59,6 +60,7 @@ struct vduse_virtqueue { > > > struct vdpa_vq_state state; > > > bool ready; > > > bool kicked; > > > + u32 vq_group; > > > spinlock_t kick_lock; > > > spinlock_t irq_lock; > > > struct eventfd_ctx *kickfd; > > > @@ -115,6 +117,7 @@ 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; > > > @@ -456,6 +459,7 @@ static void vduse_dev_reset(struct vduse_dev *dev) > > > vq->driver_addr = 0; > > > vq->device_addr = 0; > > > vq->num = 0; > > > + vq->vq_group = 0; > > > memset(&vq->state, 0, sizeof(vq->state)); > > > > > > spin_lock(&vq->kick_lock); > > > @@ -593,6 +597,16 @@ 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); > > > + > > > + if (dev->api_version < VDUSE_API_VERSION_1) > > > + return 0; > > > + > > > + return dev->vqs[idx]->vq_group; > > > +} > > > + > > > static int vduse_vdpa_get_vq_state(struct vdpa_device *vdpa, u16 idx, > > > struct vdpa_vq_state *state) > > > { > > > @@ -790,6 +804,7 @@ static const struct vdpa_config_ops > > > vduse_vdpa_config_ops = { > > > .set_vq_cb = vduse_vdpa_set_vq_cb, > > > .set_vq_num = vduse_vdpa_set_vq_num, > > > .get_vq_size = vduse_vdpa_get_vq_size, > > > + .get_vq_group = vduse_get_vq_group, > > > .set_vq_ready = vduse_vdpa_set_vq_ready, > > > .get_vq_ready = vduse_vdpa_get_vq_ready, > > > .set_vq_state = vduse_vdpa_set_vq_state, > > > @@ -1253,12 +1268,24 @@ static long vduse_dev_ioctl(struct file *file, > > > unsigned int cmd, > > > if (config.index >= dev->vq_num) > > > break; > > > > > > - if (!is_mem_zero((const char *)config.reserved, > > > - sizeof(config.reserved))) > > > + if (dev->api_version < VDUSE_API_VERSION_1 && > > > config.group) > > > + break; > > > + > > > + if (dev->api_version >= VDUSE_API_VERSION_1) { > > > + if (config.group > dev->ngroups) > > > + break; > > > > This should be ">=". > > > > Right, good catch! > > > > + if (dev->status & VIRTIO_CONFIG_S_DRIVER_OK) > > > + break; > > > + } > > > + > > > + if (config.reserved1 || > > > + !is_mem_zero((const char *)config.reserved2, > > > + sizeof(config.reserved2))) > > > break; > > > > > > index = array_index_nospec(config.index, dev->vq_num); > > > dev->vqs[index]->num_max = config.max_size; > > > + dev->vqs[index]->vq_group = config.group; > > > ret = 0; > > > break; > > > } > > > @@ -1738,12 +1765,20 @@ static bool features_is_valid(struct > > > vduse_dev_config *config) > > > return true; > > > } > > > > > > -static bool vduse_validate_config(struct vduse_dev_config *config) > > > +static bool vduse_validate_config(struct vduse_dev_config *config, > > > + u64 api_version) > > > { > > > if (!is_mem_zero((const char *)config->reserved, > > > sizeof(config->reserved))) > > > return false; > > > > > > + if (api_version < VDUSE_API_VERSION_1 && config->ngroups) > > > + return false; > > > + > > > + if (api_version >= VDUSE_API_VERSION_1 && > > > + (!config->ngroups || config->ngroups > VDUSE_DEV_MAX_GROUPS)) > > > + return false; > > > + > > > if (config->vq_align > PAGE_SIZE) > > > return false; > > > > > > @@ -1859,6 +1894,7 @@ static int vduse_create_dev(struct vduse_dev_config > > > *config, > > > dev->device_features = config->features; > > > dev->device_id = config->device_id; > > > dev->vendor_id = config->vendor_id; > > > + dev->ngroups = (dev->api_version < 1) ? 1 : config->ngroups; > > > dev->name = kstrdup(config->name, GFP_KERNEL); > > > if (!dev->name) > > > goto err_str; > > > @@ -1937,7 +1973,7 @@ static long vduse_ioctl(struct file *file, unsigned > > > int cmd, > > > break; > > > > > > ret = -EINVAL; > > > - if (vduse_validate_config(&config) == false) > > > + if (!vduse_validate_config(&config, control->api_version)) > > > break; > > > > > > buf = vmemdup_user(argp + size, config.config_size); > > > @@ -2018,7 +2054,7 @@ static int vduse_dev_init_vdpa(struct vduse_dev > > > *dev, const char *name) > > > > > > vdev = vdpa_alloc_device(struct vduse_vdpa, vdpa, dev->dev, > > > &vduse_vdpa_config_ops, &vduse_map_ops, > > > - 1, 1, name, true); > > > + dev->ngroups, 1, name, true); > > > if (IS_ERR(vdev)) > > > return PTR_ERR(vdev); > > > > > > diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c > > > index 05a481e4c385..6305382eacbb 100644 > > > --- a/drivers/vhost/vdpa.c > > > +++ b/drivers/vhost/vdpa.c > > > @@ -22,6 +22,7 @@ > > > #include <linux/vdpa.h> > > > #include <linux/nospec.h> > > > #include <linux/vhost.h> > > > +#include <linux/types.h> > > > > > > #include "vhost.h" > > > > > > @@ -657,16 +658,20 @@ static long vhost_vdpa_vring_ioctl(struct > > > vhost_vdpa *v, unsigned int cmd, > > > return -EFAULT; > > > ops->set_vq_ready(vdpa, idx, s.num); > > > return 0; > > > - case VHOST_VDPA_GET_VRING_GROUP: > > > + case VHOST_VDPA_GET_VRING_GROUP: { > > > + u64 group; > > > + > > > if (!ops->get_vq_group) > > > return -EOPNOTSUPP; > > > s.index = idx; > > > - s.num = ops->get_vq_group(vdpa, idx); > > > - if (s.num >= vdpa->ngroups) > > > + group = ops->get_vq_group(vdpa, idx); > > > + if (group >= vdpa->ngroups || group > U32_MAX || group < > > > 0) > > > return -EIO; > > > else if (copy_to_user(argp, &s, sizeof(s))) > > > return -EFAULT; > > > + s.num = group; > > > > I guess this won't work. > > > > Right, and it has a lot of dead code from the s64 conversion. Fixing it. > > Should I send the whole series again or a patch on top?
I think a new version might be better. Thanks
