On Thu, 5 Mar 2020 20:21:48 -0500 Yan Zhao <yan.y.zhao@xxxxxxxxx> wrote: > On Mon, Feb 24, 2020 at 04:47:15PM +0800, Zhao, Yan Y wrote: > > vfio_dma_rw will read/write a range of user space memory pointed to by > > IOVA into/from a kernel buffer without enforcing pinning the user space > > memory. > > > > TODO: mark the IOVAs to user space memory dirty if they are written in > > vfio_dma_rw(). > > > > Cc: Kevin Tian <kevin.tian@xxxxxxxxx> > > Signed-off-by: Yan Zhao <yan.y.zhao@xxxxxxxxx> > > --- > > drivers/vfio/vfio.c | 49 +++++++++++++++++++++ > > drivers/vfio/vfio_iommu_type1.c | 77 +++++++++++++++++++++++++++++++++ > > include/linux/vfio.h | 5 +++ > > 3 files changed, 131 insertions(+) > > > > diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c > > index 914bdf4b9d73..902867627cbf 100644 > > --- a/drivers/vfio/vfio.c > > +++ b/drivers/vfio/vfio.c > > @@ -1998,6 +1998,55 @@ int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage) > > } > > EXPORT_SYMBOL(vfio_unpin_pages); > > > > + > > +/* > > + * This interface allows the CPUs to perform some sort of virtual DMA on > > + * behalf of the device. > > + * > > + * CPUs read/write a range of IOVAs pointing to user space memory into/from > > + * a kernel buffer. > > + * > > + * As the read/write of user space memory is conducted via the CPUs and is > > + * not a real device DMA, it is not necessary to pin the user space memory. > > + * > > + * The caller needs to call vfio_group_get_external_user() or > > + * vfio_group_get_external_user_from_dev() prior to calling this interface, > > + * so as to prevent the VFIO group from disposal in the middle of the call. > > + * But it can keep the reference to the VFIO group for several calls into > > + * this interface. > > + * After finishing using of the VFIO group, the caller needs to release the > > + * VFIO group by calling vfio_group_put_external_user(). > > + * > > + * @group [in]: vfio group of a device > > + * @iova [in] : base IOVA of a user space buffer > > + * @data [in] : pointer to kernel buffer > > + * @len [in] : kernel buffer length > > + * @write : indicate read or write > > + * Return error code on failure or 0 on success. > > + */ > > +int vfio_dma_rw(struct vfio_group *group, dma_addr_t iova, > > + void *data, size_t len, bool write) > hi Alex > May I rename this interface to vfio_dma_rw_from_group() that takes > VFIO group as arg and add another interface vfio_dma_rw(struct device *dev...) ? > That might be easier for a driver to use the second one if it does not care about > performance much. Perhaps vfio_group_dma_rw() and vfio_dev_dma_rw()? I'd be reluctant to add the latter, if a caller doesn't care about performance then they won't mind making a couple calls to get and release the group reference. Thanks, Alex
