vfio/pci: Add vfio_pci_dma_buf_iommufd_map()

This function is used to establish the "private interconnect" between the
VFIO DMABUF exporter and the iommufd DMABUF importer. This is intended to
be a temporary API until the core DMABUF interface is improved to natively
support a private interconnect and revocable negotiation.

This function should only be called by iommufd when trying to map a
DMABUF. For now iommufd will only support VFIO DMABUFs.

The following improvements are needed in the DMABUF API to generically
support more exporters with iommufd/kvm type importers that cannot use the
DMA API:

 1) Revoke semantics. VFIO needs to be able to prevent access to the MMIO
    during FLR, and so it will use dma_buf_move_notify() to prevent
    access. iommmufd does not support fault handling so it cannot
    implement the full move_notify. Instead if revoke is negotiated the
    exporter promises not to use move_notify() unless the importer can
    experiance failures. iommufd will unmap the dmabuf from the iommu page
    tables while it is revoked.

 2) Private interconnect negotiation. iommufd will only be able to map
    a "private interconnect" that provides a phys_addr_t and a
    struct p2pdma_provider * to describe the memory. It cannot use a DMA
    mapped scatterlist since it is directly calling iommu_map().

 3) NULL device during dma_buf_dynamic_attach(). Since iommufd doesn't use
    the DMA API it doesn't have a DMAable struct device to pass here.

Link: https://patch.msgid.link/r/1-v2-b2c110338e3f+5c2-iommufd_dmabuf_jgg@nvidia.com
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Shuai Xue <xueshuai@linux.alibaba.com>
Acked-by: Alex Williamson <alex@shazbot.org>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
index 6698f540bdac875c3770ab1ca1841b3f4f78563d..d4d0f7d08c53e2b9b756f00b0bd41b2cd3d5370d 100644 (file)
--- a/drivers/vfio/pci/vfio_pci_dmabuf.c
+++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
@@ -82,6 +82,40 @@ static const struct dma_buf_ops vfio_pci_dmabuf_ops = {
        .release = vfio_pci_dma_buf_release,
 };
 
+/*
+ * This is a temporary "private interconnect" between VFIO DMABUF and iommufd.
+ * It allows the two co-operating drivers to exchange the physical address of
+ * the BAR. This is to be replaced with a formal DMABUF system for negotiated
+ * interconnect types.
+ *
+ * If this function succeeds the following are true:
+ *  - There is one physical range and it is pointing to MMIO
+ *  - When move_notify is called it means revoke, not move, vfio_dma_buf_map
+ *    will fail if it is currently revoked
+ */
+int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
+                                struct dma_buf_phys_vec *phys)
+{
+       struct vfio_pci_dma_buf *priv;
+
+       dma_resv_assert_held(attachment->dmabuf->resv);
+
+       if (attachment->dmabuf->ops != &vfio_pci_dmabuf_ops)
+               return -EOPNOTSUPP;
+
+       priv = attachment->dmabuf->priv;
+       if (priv->revoked)
+               return -ENODEV;
+
+       /* More than one range to iommufd will require proper DMABUF support */
+       if (priv->nr_ranges != 1)
+               return -EOPNOTSUPP;
+
+       *phys = priv->phys_vec[0];
+       return 0;
+}
+EXPORT_SYMBOL_FOR_MODULES(vfio_pci_dma_buf_iommufd_map, "iommufd");
+
 int vfio_pci_core_fill_phys_vec(struct dma_buf_phys_vec *phys_vec,
                                struct vfio_region_dma_range *dma_ranges,
                                size_t nr_ranges, phys_addr_t start,

diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index c9466ba323fa9c652c166810c5751e8abf1db072..6a3074f2cf1ceab88268173925bfeeafd533c660 100644 (file)
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -28,6 +28,7 @@ struct vfio_pci_core_device;
 struct vfio_pci_region;
 struct p2pdma_provider;
 struct dma_buf_phys_vec;
+struct dma_buf_attachment;
 
 struct vfio_pci_regops {
        ssize_t (*rw)(struct vfio_pci_core_device *vdev, char __user *buf,
@@ -203,4 +204,7 @@ VFIO_IOREAD_DECLARATION(32)
 VFIO_IOREAD_DECLARATION(64)
 #endif
 
+int vfio_pci_dma_buf_iommufd_map(struct dma_buf_attachment *attachment,
+                                struct dma_buf_phys_vec *phys);
+
 #endif /* VFIO_PCI_CORE_H */