search for: vdpa_alloc_device

...g->mac); > + > + INIT_WORK(&vdpasim->work, vdpasim_work); > + spin_lock_init(&vdpasim->lock); > + > + vdpa = &vdpasim->vdpa; > + vdpa->dev.release = vdpasim_release_dev; The driver should not provide the release function. Again the safest model is 'vdpa_alloc_device' which combines the kzalloc and the vdpa_init_device() and returns something that is error unwound with put_device() The subsystem owns the release and does the kfree and other cleanup like releasing the IDA. > + vringh_set_iotlb(&vdpasim->vqs[0].vring, vdpasim->iommu); > + vr...

On Thu, Mar 23, 2023 at 11:42:07AM +0800, Jason Wang wrote: >On Tue, Mar 21, 2023 at 11:48?PM Stefano Garzarella <sgarzare at redhat.com> wrote: >> >> The new "use_va" module parameter (default: true) is used in >> vdpa_alloc_device() to inform the vDPA framework that the device >> supports VA. >> >> vringh is initialized to use VA only when "use_va" is true and the >> user's mm has been bound. So, only when the bus supports user VA >> (e.g. vhost-vdpa). >> >> vdpasim_mm_...

On Wed, Feb 26, 2020 at 02:04:54PM +0800, Jason Wang wrote: > +struct vdpa_device *vdpa_alloc_device(struct device *parent, > + struct device *dma_dev, > + const struct vdpa_config_ops *config) > +{ > + struct vdpa_device *vdev; > + int err = -ENOMEM; > + > + if (!parent || !dma_dev || !config) > + goto err; > + > + vdev = kzalloc(sizeof(*vdev), GFP...

The function should be called only after a success calling for vdpa_alloc_device(). Reported-by: Eli Cohen <eli at mellanox.com> Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vdpa/vdpa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index e9ed6a2b635b..ff6562f602e0 100644 --- a/driver...

...t; >> On Thu, Mar 23, 2023 at 11:42:07AM +0800, Jason Wang wrote: >> >On Tue, Mar 21, 2023 at 11:48?PM Stefano Garzarella <sgarzare at redhat.com> wrote: >> >> >> >> The new "use_va" module parameter (default: true) is used in >> >> vdpa_alloc_device() to inform the vDPA framework that the device >> >> supports VA. >> >> >> >> vringh is initialized to use VA only when "use_va" is true and the >> >> user's mm has been bound. So, only when the bus supports user VA >> >> (e....

...t bus_type vdpa_bus = { + .name = "vdpa", + .probe = vdpa_dev_probe, + .remove = vdpa_dev_remove, +}; + +static void vdpa_release_dev(struct device *d) +{ + struct vdpa_device *vdev = dev_to_vdpa(d); + + ida_simple_remove(&vdpa_index_ida, vdev->index); + kfree(vdev); +} + +/** + * vdpa_alloc_device - allocate and initilaize a vDPA device + * This allows driver to some prepartion after device is + * initialized but before registered. + * @parent: the parent device + * @dma_dev: the actual device that is performing DMA + * @config: the bus operations that is supported by this device + * + * Ret...

Hi All: This series tries to add the support for control virtqueue in vDPA. Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations. When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is

Hi All: This series tries to add the support for control virtqueue in vDPA. Control virtqueue is used by networking device for accepting various commands from the driver. It's a must to support multiqueue and other configurations. When used by vhost-vDPA bus driver for VM, the control virtqueue should be shadowed via userspace VMM (Qemu) instead of being assigned directly to Guest. This is

On Tue, Mar 21, 2023 at 11:48?PM Stefano Garzarella <sgarzare at redhat.com> wrote: > > The new "use_va" module parameter (default: true) is used in > vdpa_alloc_device() to inform the vDPA framework that the device > supports VA. > > vringh is initialized to use VA only when "use_va" is true and the > user's mm has been bound. So, only when the bus supports user VA > (e.g. vhost-vdpa). > > vdpasim_mm_work_fn work is used to seri...

On Thu, Mar 2, 2023 at 7:35?PM Stefano Garzarella <sgarzare at redhat.com> wrote: > > The new "use_va" module parameter (default: false) is used in > vdpa_alloc_device() to inform the vDPA framework that the device > supports VA. > > vringh is initialized to use VA only when "use_va" is true and the > user's mm has been bound. So, only when the bus supports user VA > (e.g. vhost-vdpa). > > vdpasim_mm_work_fn work is used to atta...

? 2023/3/21 23:48, Stefano Garzarella ??: > The new "use_va" module parameter (default: true) is used in > vdpa_alloc_device() to inform the vDPA framework that the device > supports VA. > > vringh is initialized to use VA only when "use_va" is true and the > user's mm has been bound. So, only when the bus supports user VA > (e.g. vhost-vdpa). > > vdpasim_mm_work_fn work is used to seri...

Fix two typos in the comments for __vdpa_alloc_device(). Signed-off-by: Jason Wang <jasowang at redhat.com> --- drivers/vdpa/vdpa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index ff6562f602e0..de211ef3738c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -63,7 +6...

...char *name, > > > struct device *dev = &pdev->dev; > > > struct vp_vdpa *vp_vdpa = NULL; > > > u64 device_features; > > > - int ret, i; > > > + int ret, i, queues; > > > > > > vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa, > > > dev, &vp_vdpa_ops, 1, 1, name, > > false); > > > @@ -491,7 +491,14 @@ static int vp_vdpa_dev_add(struct vdpa_mgmt_dev > > *v_mdev, const char *name, > > > vp_vdpa_mgtdev->vp_vdpa =...

Hi all: This series tries to support batched IOTLB updating vhost-vdpa. Currently vhost-vdpa accepts userspace mapping via IOTLB API, and it can only forward one mapping to IOMMU or device through IOMMU API or dma_map(). Though set_map() is designed to have the capability to pass an rbtree based mapping to vDPA device, it's still be called at least once for each VHOST_IOTLB_UPDATE or

Hi all: This series tries to support batched IOTLB updating vhost-vdpa. Currently vhost-vdpa accepts userspace mapping via IOTLB API, and it can only forward one mapping to IOMMU or device through IOMMU API or dma_map(). Though set_map() is deisgend to have the capability to pass an rbtree based mapping to vDPA device, it's still be called at least once for each VHOST_IOTLB_UPDATE or

...truct device *dev; 2c53d0f64c06f4 drivers/virtio/vdpa/vdpa_sim/vdpa_sim.c Jason Wang 2020-03-26 312 int ret = -ENOMEM; 2c53d0f64c06f4 drivers/virtio/vdpa/vdpa_sim/vdpa_sim.c Jason Wang 2020-03-26 313 2c53d0f64c06f4 drivers/virtio/vdpa/vdpa_sim/vdpa_sim.c Jason Wang 2020-03-26 314 vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, 2c53d0f64c06f4 drivers/virtio/vdpa/vdpa_sim/vdpa_sim.c Jason Wang 2020-03-26 315 &vdpasim_net_config_ops); 2c53d0f64c06f4 drivers/virtio/vdpa/vdpa_sim/vdpa_sim.c Jason Wang 2020-03-26 316 if (!vdpasim) 2c53d0f64c06f4 drivers/virtio/vdpa/vdpa_sim/vdpa_sim...

...0x1040; >> + } >> + virtio_id.vendor = pdev->subsystem_vendor; >> + >> + ret = pcim_enable_device(pdev); >> + if (ret) { >> + dev_err(dev, "vp_vdpa: Fail to enable PCI device\n"); >> + return ret; >> + } >> + >> + vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa, >> + dev, &vp_vdpa_ops); >> + if (vp_vdpa == NULL) { >> + dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n"); >> + return -ENOMEM; >> + } >> + >> + pci_set_master(pdev); >> + pci_set_drvdata(pdev,...

...0x1040; >> + } >> + virtio_id.vendor = pdev->subsystem_vendor; >> + >> + ret = pcim_enable_device(pdev); >> + if (ret) { >> + dev_err(dev, "vp_vdpa: Fail to enable PCI device\n"); >> + return ret; >> + } >> + >> + vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa, >> + dev, &vp_vdpa_ops); >> + if (vp_vdpa == NULL) { >> + dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n"); >> + return -ENOMEM; >> + } >> + >> + pci_set_master(pdev); >> + pci_set_drvdata(pdev,...

...PCI device id, + * but start from 0x1040. + */ + virtio_id.device = pdev->device - 0x1040; + } + virtio_id.vendor = pdev->subsystem_vendor; + + ret = pcim_enable_device(pdev); + if (ret) { + dev_err(dev, "vp_vdpa: Fail to enable PCI device\n"); + return ret; + } + + vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa, + dev, &vp_vdpa_ops); + if (vp_vdpa == NULL) { + dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n"); + return -ENOMEM; + } + + pci_set_master(pdev); + pci_set_drvdata(pdev, vp_vdpa); + + vp_vdpa->pdev = pdev; + vp_vdpa->vdpa.dma_dev = &am...

...PCI device id, + * but start from 0x1040. + */ + virtio_id.device = pdev->device - 0x1040; + } + virtio_id.vendor = pdev->subsystem_vendor; + + ret = pcim_enable_device(pdev); + if (ret) { + dev_err(dev, "vp_vdpa: Fail to enable PCI device\n"); + return ret; + } + + vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa, + dev, &vp_vdpa_ops); + if (vp_vdpa == NULL) { + dev_err(dev, "vp_vdpa: Failed to allocate vDPA structure\n"); + return -ENOMEM; + } + + pci_set_master(pdev); + pci_set_drvdata(pdev, vp_vdpa); + + vp_vdpa->pdev = pdev; + vp_vdpa->vdpa.dma_dev = &am...