From: Wei Lin Guay <wg...@meta.com>
Summary:
Support vfio to export dmabuf to importer such as RDMA NIC that does
not support move_notify callback, since not all RDMA driver support
on-demand-paging (ODP).
There are some use-cases such as bind accelerator that always pinned
the device memory via vfio and export it to RDMA NIC such as EFA, BNXT_RE
or IRDMA that does not support ODP.
Signed-off-by: Wei Lin Guay <wg...@meta.com>
Reviewed-by: Dag Moxnes <dagmox...@meta.com>
Reviewed-by: Keith Busch <kbu...@kernel.org>
Reviewed-by: Nic Viljoen <nvilj...@meta.com>
---
drivers/vfio/pci/dma_buf.c | 32 +++++++++++++++++++++++++++-----
drivers/vfio/pci/vfio_pci_core.c | 16 ++++++++++++++++
drivers/vfio/pci/vfio_pci_priv.h | 7 +++++++
3 files changed, 50 insertions(+), 5 deletions(-)
diff --git a/drivers/vfio/pci/dma_buf.c b/drivers/vfio/pci/dma_buf.c
index fd772b520cd7..8017f48296cb 100644
--- a/drivers/vfio/pci/dma_buf.c
+++ b/drivers/vfio/pci/dma_buf.c
@@ -17,6 +17,7 @@ struct vfio_pci_dma_buf {
unsigned int orig_nents;
size_t offset;
bool revoked;
+ bool pinned;
};
static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf,
@@ -32,17 +33,38 @@ static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf,
return 0;
}
+bool vfio_pci_dma_buf_pinned(struct vfio_pci_core_device *vdev)
+{
+ struct vfio_pci_dma_buf *priv;
+ struct vfio_pci_dma_buf *tmp;
+ bool pinned = false;
+
+ down_write(&vdev->memory_lock);
+ list_for_each_entry_safe(priv, tmp, &vdev->dmabufs, dmabufs_elm) {
+ if (!dma_buf_try_get(priv->dmabuf))
+ continue;
+ if (priv->pinned) {
+ pinned = true;
+ break;
+ }
+ }
+ up_write(&vdev->memory_lock);
+ return pinned;
+}
+
static void vfio_pci_dma_buf_unpin(struct dma_buf_attachment *attachment)
{
+ struct vfio_pci_dma_buf *priv = attachment->dmabuf->priv;
+
+ priv->pinned = false;
}
static int vfio_pci_dma_buf_pin(struct dma_buf_attachment *attachment)
{
- /*
- * Uses the dynamic interface but must always allow for
- * dma_buf_move_notify() to do revoke
- */
- return -EINVAL;
+ struct vfio_pci_dma_buf *priv = attachment->dmabuf->priv;
+
+ priv->pinned = true;
+ return 0;
}
static struct sg_table *
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index bb97b4d94eb7..db28fa2cc9a8 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1246,6 +1246,13 @@ static int vfio_pci_ioctl_reset(struct
vfio_pci_core_device *vdev,
*/
vfio_pci_set_power_state(vdev, PCI_D0);
+ /*
+ * prevent reset if dma_buf is pinned to avoid stale pinned
+ * expose to the dmabuf exporter.
+ */
+ if (vfio_pci_dma_buf_pinned(vdev))
+ return -EINVAL;
+
vfio_pci_dma_buf_move(vdev, true);
ret = pci_try_reset_function(vdev->pdev);
if (__vfio_pci_memory_enabled(vdev))
@@ -2444,6 +2451,15 @@ static int vfio_pci_dev_set_hot_reset(struct
vfio_device_set *dev_set,
break;
}
+ /*
+ * prevent reset if dma_buf is pinned to avoid stale pinned
+ * expose to the dmabuf exporter.
+ */
+ if (vfio_pci_dma_buf_pinned(vdev)) {
+ ret = -EINVAL;
+ break;
+ }
+
/*
* Take the memory write lock for each device and zap BAR
* mappings to prevent the user accessing the device while in
diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h
index 09d3c300918c..43c40dc4751c 100644
--- a/drivers/vfio/pci/vfio_pci_priv.h
+++ b/drivers/vfio/pci/vfio_pci_priv.h
@@ -107,6 +107,7 @@ int vfio_pci_core_feature_dma_buf(struct
vfio_pci_core_device *vdev, u32 flags,
size_t argsz);
void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev);
void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev, bool revoked);
+bool vfio_pci_dma_buf_pinned(struct vfio_pci_core_device *vdev);
#else
static int
vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
@@ -115,6 +116,12 @@ vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device
*vdev, u32 flags,
{
return -ENOTTY;
}
+
+static inline bool vfio_pci_dma_buf_pinned(struct vfio_pci_core_device *vdev)
+{
+ return false;
+}
+
static inline void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev)
{
}
--
2.43.5
