| Message ID | 20201222145221.711-9-xieyongji@bytedance.com (mailing list archive) |
|---|---|
| State | RFC |
| Headers | show |
| Series | Introduce VDUSE - vDPA Device in Userspace | expand |
| Context | Check | Description |
|---|---|---|
| netdev/tree_selection | success | Not a local patch |
On 2020/12/22 下午10:52, Xie Yongji wrote: > This patch introduces a new method in the vdpa_config_ops to > support processing the raw vhost memory mapping message in the > vDPA device driver. > > Signed-off-by: Xie Yongji <xieyongji@bytedance.com> > --- > drivers/vhost/vdpa.c | 5 ++++- > include/linux/vdpa.h | 7 +++++++ > 2 files changed, 11 insertions(+), 1 deletion(-) > > diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c > index 448be7875b6d..ccbb391e38be 100644 > --- a/drivers/vhost/vdpa.c > +++ b/drivers/vhost/vdpa.c > @@ -728,6 +728,9 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, > if (r) > return r; > > + if (ops->process_iotlb_msg) > + return ops->process_iotlb_msg(vdpa, msg); > + > switch (msg->type) { > case VHOST_IOTLB_UPDATE: > r = vhost_vdpa_process_iotlb_update(v, msg); > @@ -770,7 +773,7 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v) > int ret; > > /* Device want to do DMA by itself */ > - if (ops->set_map || ops->dma_map) > + if (ops->set_map || ops->dma_map || ops->process_iotlb_msg) > return 0; > > bus = dma_dev->bus; > diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h > index 656fe264234e..7bccedf22f4b 100644 > --- a/include/linux/vdpa.h > +++ b/include/linux/vdpa.h > @@ -5,6 +5,7 @@ > #include <linux/kernel.h> > #include <linux/device.h> > #include <linux/interrupt.h> > +#include <linux/vhost_types.h> > #include <linux/vhost_iotlb.h> > #include <net/genetlink.h> > > @@ -172,6 +173,10 @@ struct vdpa_iova_range { > * @vdev: vdpa device > * Returns the iova range supported by > * the device. > + * @process_iotlb_msg: Process vhost memory mapping message (optional) > + * Only used for VDUSE device now > + * @vdev: vdpa device > + * @msg: vhost memory mapping message > * @set_map: Set device memory mapping (optional) > * Needed for device that using device > * specific DMA translation (on-chip IOMMU) > @@ -240,6 +245,8 @@ struct vdpa_config_ops { > struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); > > /* DMA ops */ > + int (*process_iotlb_msg)(struct vdpa_device *vdev, > + struct vhost_iotlb_msg *msg); > 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); Is there any reason that it can't be done via dma_map/dma_unmap or set_map? Thanks
On Wed, Dec 23, 2020 at 4:37 PM Jason Wang <jasowang@redhat.com> wrote: > > > On 2020/12/22 下午10:52, Xie Yongji wrote: > > This patch introduces a new method in the vdpa_config_ops to > > support processing the raw vhost memory mapping message in the > > vDPA device driver. > > > > Signed-off-by: Xie Yongji <xieyongji@bytedance.com> > > --- > > drivers/vhost/vdpa.c | 5 ++++- > > include/linux/vdpa.h | 7 +++++++ > > 2 files changed, 11 insertions(+), 1 deletion(-) > > > > diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c > > index 448be7875b6d..ccbb391e38be 100644 > > --- a/drivers/vhost/vdpa.c > > +++ b/drivers/vhost/vdpa.c > > @@ -728,6 +728,9 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, > > if (r) > > return r; > > > > + if (ops->process_iotlb_msg) > > + return ops->process_iotlb_msg(vdpa, msg); > > + > > switch (msg->type) { > > case VHOST_IOTLB_UPDATE: > > r = vhost_vdpa_process_iotlb_update(v, msg); > > @@ -770,7 +773,7 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v) > > int ret; > > > > /* Device want to do DMA by itself */ > > - if (ops->set_map || ops->dma_map) > > + if (ops->set_map || ops->dma_map || ops->process_iotlb_msg) > > return 0; > > > > bus = dma_dev->bus; > > diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h > > index 656fe264234e..7bccedf22f4b 100644 > > --- a/include/linux/vdpa.h > > +++ b/include/linux/vdpa.h > > @@ -5,6 +5,7 @@ > > #include <linux/kernel.h> > > #include <linux/device.h> > > #include <linux/interrupt.h> > > +#include <linux/vhost_types.h> > > #include <linux/vhost_iotlb.h> > > #include <net/genetlink.h> > > > > @@ -172,6 +173,10 @@ struct vdpa_iova_range { > > * @vdev: vdpa device > > * Returns the iova range supported by > > * the device. > > + * @process_iotlb_msg: Process vhost memory mapping message (optional) > > + * Only used for VDUSE device now > > + * @vdev: vdpa device > > + * @msg: vhost memory mapping message > > * @set_map: Set device memory mapping (optional) > > * Needed for device that using device > > * specific DMA translation (on-chip IOMMU) > > @@ -240,6 +245,8 @@ struct vdpa_config_ops { > > struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); > > > > /* DMA ops */ > > + int (*process_iotlb_msg)(struct vdpa_device *vdev, > > + struct vhost_iotlb_msg *msg); > > 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); > > > Is there any reason that it can't be done via dma_map/dma_unmap or set_map? > To get the shmfd, we need the vma rather than physical address. And it's not necessary to pin the user pages in VDUSE case. Thanks, Yongji
On 2020/12/23 下午7:06, Yongji Xie wrote: > On Wed, Dec 23, 2020 at 4:37 PM Jason Wang <jasowang@redhat.com> wrote: >> >> On 2020/12/22 下午10:52, Xie Yongji wrote: >>> This patch introduces a new method in the vdpa_config_ops to >>> support processing the raw vhost memory mapping message in the >>> vDPA device driver. >>> >>> Signed-off-by: Xie Yongji <xieyongji@bytedance.com> >>> --- >>> drivers/vhost/vdpa.c | 5 ++++- >>> include/linux/vdpa.h | 7 +++++++ >>> 2 files changed, 11 insertions(+), 1 deletion(-) >>> >>> diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c >>> index 448be7875b6d..ccbb391e38be 100644 >>> --- a/drivers/vhost/vdpa.c >>> +++ b/drivers/vhost/vdpa.c >>> @@ -728,6 +728,9 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, >>> if (r) >>> return r; >>> >>> + if (ops->process_iotlb_msg) >>> + return ops->process_iotlb_msg(vdpa, msg); >>> + >>> switch (msg->type) { >>> case VHOST_IOTLB_UPDATE: >>> r = vhost_vdpa_process_iotlb_update(v, msg); >>> @@ -770,7 +773,7 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v) >>> int ret; >>> >>> /* Device want to do DMA by itself */ >>> - if (ops->set_map || ops->dma_map) >>> + if (ops->set_map || ops->dma_map || ops->process_iotlb_msg) >>> return 0; >>> >>> bus = dma_dev->bus; >>> diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h >>> index 656fe264234e..7bccedf22f4b 100644 >>> --- a/include/linux/vdpa.h >>> +++ b/include/linux/vdpa.h >>> @@ -5,6 +5,7 @@ >>> #include <linux/kernel.h> >>> #include <linux/device.h> >>> #include <linux/interrupt.h> >>> +#include <linux/vhost_types.h> >>> #include <linux/vhost_iotlb.h> >>> #include <net/genetlink.h> >>> >>> @@ -172,6 +173,10 @@ struct vdpa_iova_range { >>> * @vdev: vdpa device >>> * Returns the iova range supported by >>> * the device. >>> + * @process_iotlb_msg: Process vhost memory mapping message (optional) >>> + * Only used for VDUSE device now >>> + * @vdev: vdpa device >>> + * @msg: vhost memory mapping message >>> * @set_map: Set device memory mapping (optional) >>> * Needed for device that using device >>> * specific DMA translation (on-chip IOMMU) >>> @@ -240,6 +245,8 @@ struct vdpa_config_ops { >>> struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); >>> >>> /* DMA ops */ >>> + int (*process_iotlb_msg)(struct vdpa_device *vdev, >>> + struct vhost_iotlb_msg *msg); >>> 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); >> >> Is there any reason that it can't be done via dma_map/dma_unmap or set_map? >> > To get the shmfd, we need the vma rather than physical address. And > it's not necessary to pin the user pages in VDUSE case. Right, actually, vhost-vDPA is planning to support shared virtual address space. So let's try to reuse the existing config ops. How about just introduce an attribute to vdpa device that tells the bus tells the bus it can do shared virtual memory. Then when the device is probed by vhost-vDPA, use pages won't be pinned and we will do VA->VA mapping as IOVA->PA mapping in the vhost IOTLB and the config ops. vhost IOTLB needs to be extended to accept opaque pointer to store the file. And the file was pass via the config ops as well. Thanks > > Thanks, > Yongji >
On Thu, Dec 24, 2020 at 10:37 AM Jason Wang <jasowang@redhat.com> wrote: > > > On 2020/12/23 下午7:06, Yongji Xie wrote: > > On Wed, Dec 23, 2020 at 4:37 PM Jason Wang <jasowang@redhat.com> wrote: > >> > >> On 2020/12/22 下午10:52, Xie Yongji wrote: > >>> This patch introduces a new method in the vdpa_config_ops to > >>> support processing the raw vhost memory mapping message in the > >>> vDPA device driver. > >>> > >>> Signed-off-by: Xie Yongji <xieyongji@bytedance.com> > >>> --- > >>> drivers/vhost/vdpa.c | 5 ++++- > >>> include/linux/vdpa.h | 7 +++++++ > >>> 2 files changed, 11 insertions(+), 1 deletion(-) > >>> > >>> diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c > >>> index 448be7875b6d..ccbb391e38be 100644 > >>> --- a/drivers/vhost/vdpa.c > >>> +++ b/drivers/vhost/vdpa.c > >>> @@ -728,6 +728,9 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, > >>> if (r) > >>> return r; > >>> > >>> + if (ops->process_iotlb_msg) > >>> + return ops->process_iotlb_msg(vdpa, msg); > >>> + > >>> switch (msg->type) { > >>> case VHOST_IOTLB_UPDATE: > >>> r = vhost_vdpa_process_iotlb_update(v, msg); > >>> @@ -770,7 +773,7 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v) > >>> int ret; > >>> > >>> /* Device want to do DMA by itself */ > >>> - if (ops->set_map || ops->dma_map) > >>> + if (ops->set_map || ops->dma_map || ops->process_iotlb_msg) > >>> return 0; > >>> > >>> bus = dma_dev->bus; > >>> diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h > >>> index 656fe264234e..7bccedf22f4b 100644 > >>> --- a/include/linux/vdpa.h > >>> +++ b/include/linux/vdpa.h > >>> @@ -5,6 +5,7 @@ > >>> #include <linux/kernel.h> > >>> #include <linux/device.h> > >>> #include <linux/interrupt.h> > >>> +#include <linux/vhost_types.h> > >>> #include <linux/vhost_iotlb.h> > >>> #include <net/genetlink.h> > >>> > >>> @@ -172,6 +173,10 @@ struct vdpa_iova_range { > >>> * @vdev: vdpa device > >>> * Returns the iova range supported by > >>> * the device. > >>> + * @process_iotlb_msg: Process vhost memory mapping message (optional) > >>> + * Only used for VDUSE device now > >>> + * @vdev: vdpa device > >>> + * @msg: vhost memory mapping message > >>> * @set_map: Set device memory mapping (optional) > >>> * Needed for device that using device > >>> * specific DMA translation (on-chip IOMMU) > >>> @@ -240,6 +245,8 @@ struct vdpa_config_ops { > >>> struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); > >>> > >>> /* DMA ops */ > >>> + int (*process_iotlb_msg)(struct vdpa_device *vdev, > >>> + struct vhost_iotlb_msg *msg); > >>> 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); > >> > >> Is there any reason that it can't be done via dma_map/dma_unmap or set_map? > >> > > To get the shmfd, we need the vma rather than physical address. And > > it's not necessary to pin the user pages in VDUSE case. > > > Right, actually, vhost-vDPA is planning to support shared virtual > address space. > > So let's try to reuse the existing config ops. How about just introduce > an attribute to vdpa device that tells the bus tells the bus it can do > shared virtual memory. Then when the device is probed by vhost-vDPA, use > pages won't be pinned and we will do VA->VA mapping as IOVA->PA mapping > in the vhost IOTLB and the config ops. vhost IOTLB needs to be extended > to accept opaque pointer to store the file. And the file was pass via > the config ops as well. > OK, I see. Will try it in v3. Thanks, Yongji
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c index 448be7875b6d..ccbb391e38be 100644 --- a/drivers/vhost/vdpa.c +++ b/drivers/vhost/vdpa.c @@ -728,6 +728,9 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, if (r) return r; + if (ops->process_iotlb_msg) + return ops->process_iotlb_msg(vdpa, msg); + switch (msg->type) { case VHOST_IOTLB_UPDATE: r = vhost_vdpa_process_iotlb_update(v, msg); @@ -770,7 +773,7 @@ static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v) int ret; /* Device want to do DMA by itself */ - if (ops->set_map || ops->dma_map) + if (ops->set_map || ops->dma_map || ops->process_iotlb_msg) return 0; bus = dma_dev->bus; diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 656fe264234e..7bccedf22f4b 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -5,6 +5,7 @@ #include <linux/kernel.h> #include <linux/device.h> #include <linux/interrupt.h> +#include <linux/vhost_types.h> #include <linux/vhost_iotlb.h> #include <net/genetlink.h> @@ -172,6 +173,10 @@ struct vdpa_iova_range { * @vdev: vdpa device * Returns the iova range supported by * the device. + * @process_iotlb_msg: Process vhost memory mapping message (optional) + * Only used for VDUSE device now + * @vdev: vdpa device + * @msg: vhost memory mapping message * @set_map: Set device memory mapping (optional) * Needed for device that using device * specific DMA translation (on-chip IOMMU) @@ -240,6 +245,8 @@ struct vdpa_config_ops { struct vdpa_iova_range (*get_iova_range)(struct vdpa_device *vdev); /* DMA ops */ + int (*process_iotlb_msg)(struct vdpa_device *vdev, + struct vhost_iotlb_msg *msg); 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);
This patch introduces a new method in the vdpa_config_ops to support processing the raw vhost memory mapping message in the vDPA device driver. Signed-off-by: Xie Yongji <xieyongji@bytedance.com> --- drivers/vhost/vdpa.c | 5 ++++- include/linux/vdpa.h | 7 +++++++ 2 files changed, 11 insertions(+), 1 deletion(-)