[PATCH v6 8/9] vfio/pci: Support mmap() of a VFIO DMABUF

[Matt Evans <matt@ozlabs.org>]

A VFIO DMABUF can export a subset of a BAR to userspace by fd; add
support for mmap() of this fd.  This provides another route for a
process to map BARs, in which the process can only map a specific
subset of a BAR represented by the exported DMABUF.

mmap() support enables userspace driver designs that safely delegate
access to BAR sub-ranges to other client processes by sharing a DMABUF
fd, without having to share the (omnipotent) VFIO device fd with them.

Since the main VFIO BAR mmap() is now DMABUF-aware, the new mmap() reuses
the existing vm_ops.

The lifecycle of an exported DMABUF remains decoupled from that of the
device fd it came from, i.e. the device fd could be closed with DMABUF
VMAs present, meaning a fault on a VMA could happen concurrently with
vfio_pci_dma_buf_cleanup().

To deal with this scenario, the fault handler now temporarily takes a
VFIO device registration to ensure the vdev remains valid, and then
vdev locks can be taken.

Signed-off-by: Matt Evans <matt@ozlabs.org>
---
 drivers/vfio/pci/vfio_pci_core.c   | 84 ++++++++++++++++++++++++++----
 drivers/vfio/pci/vfio_pci_dmabuf.c | 47 +++++++++++++++++
 drivers/vfio/pci/vfio_pci_priv.h   |  1 +
 3 files changed, 123 insertions(+), 9 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 760a816e6de0..711ef54fd91e 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -13,6 +13,8 @@
 #include <linux/aperture.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/dma-resv.h>
 #include <linux/eventfd.h>
 #include <linux/file.h>
 #include <linux/interrupt.h>
@@ -1802,21 +1804,79 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf,
 	vm_fault_t ret = VM_FAULT_SIGBUS;
 
 	/*
-	 * We can rely on the existence of both a DMABUF (priv) and
-	 * the VFIO device it was exported from (vdev).  This fault's
-	 * VMA was established using vfio_pci_core_mmap_prep_dmabuf()
-	 * which transfers ownership of the VFIO device fd to the
-	 * DMABUF, and so the VFIO device is held open because the
-	 * VMA's vm_file (DMABUF) is open.
+	 * The only thing this can rely on is that the DMABUF relating
+	 * to the VMA's vm_file exists (priv).
 	 *
-	 * Since vfio_pci_dma_buf_cleanup() cannot have happened,
-	 * vdev must be valid; we can take vdev locks.
+	 * A DMABUF for a VFIO device fd mmap() holds a reference to
+	 * the original VFIO device fd, but an explicitly-exported
+	 * DMABUF does not.  The original fd might have closed,
+	 * meaning this fault can race with
+	 * vfio_pci_dma_buf_cleanup(), meaning the buffer could have
+	 * been revoked (in which case priv->vdev might be NULL), and
+	 * the VFIO device registration might have been dropped.
+	 *
+	 * With the goal of taking vdev locks in a world where vdev
+	 * might not still exist:
+	 *
+	 * 1. Take the resv lock on the DMABUF:
+	 *  - If racing cleanup got in first, the buffer is revoked;
+	 *    stop/exit if so.
+	 *  - If we got in first, the buffer is not revoked so vdev is
+	 *    non-NULL, accessible, and cleanup _has not yet put the
+	 *    VFIO device registration_.  So, the device refcount must
+	 *    be >0.
+	 *
+	 * 2. Take vfio_device registration (refcount guaranteed >0
+	 *    hereafter).
+	 *
+	 * 3. Unlock the DMABUF's resv lock:
+	 *  - A racing cleanup can now complete.
+	 *  - But, the device refcount >0, meaning the vfio_device
+	 *    (and vfio_pcie_core device vdev) have not yet been
+	 *    freed.  vdev is accessible, even if the DMABUF has been
+	 *    revoked or cleanup has happened, because
+	 *    vfio_unregister_group_dev() can't complete.
+	 *
+	 * 4. Take the vdev->memory_lock then vdev->dmabuf_lock:
+	 *  - Either the DMABUF is usable, or has been cleaned up.
+	 *  - It's not necessary to also take the resv lock, because
+	 *    the status/vdev can't change while dmabuf_lock is held.
+	 *  - Test the DMABUF revocation status again: if it was
+	 *    revoked between 1 and 4, return a SIGBUS. Otherwise,
+	 *    return a PFN.
+	 *
+	 * 5. Unlock, done.
 	 */
+
+	dma_resv_lock(priv->dmabuf->resv, NULL);
+
+	if (priv->revoked) {
+		pr_debug_ratelimited("%s VA 0x%lx, pgoff 0x%lx: DMABUF revoked/cleaned up\n",
+				     __func__, vmf->address, vma->vm_pgoff);
+		dma_resv_unlock(priv->dmabuf->resv);
+		return VM_FAULT_SIGBUS;
+	}
+
+	/* If the buffer isn't revoked, vdev is valid */
 	vdev = priv->vdev;
 
+	if (!vfio_device_try_get_registration(&vdev->vdev)) {
+		/*
+		 * If vdev != NULL (above), the registration should
+		 * already be >0 and so this try_get should never
+		 * fail.
+		 */
+		dev_warn_ratelimited(&vdev->pdev->dev,
+				     "%s: Unexpected registration failure\n",
+				     __func__);
+		dma_resv_unlock(priv->dmabuf->resv);
+		return VM_FAULT_SIGBUS;
+	}
+	dma_resv_unlock(priv->dmabuf->resv);
+
 	/* memory_lock for vfio_pci_vmf_insert_pfn() */
 	down_read(&vdev->memory_lock);
-	/* Test revocation status under dmabuf_lock */
+	/* Re-test revocation status under dmabuf_lock */
 	down_read(&vdev->dmabuf_lock);
 	if (!priv->revoked) {
 		int pres = vfio_pci_dma_buf_find_pfn(vdev, priv, vma,
@@ -1837,6 +1897,7 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf,
 			    __func__, order, pfn, vmf->address,
 			    vma->vm_pgoff, (unsigned int)ret);
 
+	vfio_device_put_registration(&vdev->vdev);
 	return ret;
 }
 
@@ -1852,6 +1913,11 @@ static const struct vm_operations_struct vfio_pci_mmap_ops = {
 #endif
 };
 
+void vfio_pci_set_vma_ops(struct vm_area_struct *vma)
+{
+	vma->vm_ops = &vfio_pci_mmap_ops;
+}
+
 int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma)
 {
 	struct vfio_pci_core_device *vdev =
diff --git a/drivers/vfio/pci/vfio_pci_dmabuf.c b/drivers/vfio/pci/vfio_pci_dmabuf.c
index 0126a0582072..1c85c15290d4 100644
--- a/drivers/vfio/pci/vfio_pci_dmabuf.c
+++ b/drivers/vfio/pci/vfio_pci_dmabuf.c
@@ -27,6 +27,50 @@ static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf,
 
 	return 0;
 }
+
+static int vfio_pci_dma_buf_mmap(struct dma_buf *dmabuf, struct vm_area_struct *vma)
+{
+	struct vfio_pci_dma_buf *priv = dmabuf->priv;
+
+	/*
+	 * dma_buf_mmap_internal() has asserted that the VMA is
+	 * contained within the DMABUF size before calling this.
+	 *
+	 * Also, if we observe that the buffer is revoked now then
+	 * refuse the mmap().  This is a belt-and-braces early failure
+	 * to ease debugging a revoked buffer being used.  Userspace
+	 * might also race an mmap() against an explicit revocation,
+	 * or an action doing a temporary revoke; race scenarios are
+	 * still safe because the fault handler ultimately prevents
+	 * access to a revoked buffer if it isn't caught here.
+	 */
+	if (priv->revoked)
+		return -ENODEV;
+	/*
+	 * Make clear that anything with an offset adjustment is
+	 * explicitly unsupported, as vfio_pci_dma_buf_find_pfn()
+	 * maths would underflow; this doesn't happen through the
+	 * regular DMABUF export path used with this mmap().  A DMABUF
+	 * implicitly created for BAR mmap could have adjust > 0, but
+	 * these can't currently be re-opened and mmap()ed again.
+	 * Catch here in case that assumption ever changes.
+	 */
+	if (priv->vma_pgoff_adjust)
+		return -EINVAL;
+	if ((vma->vm_flags & VM_SHARED) == 0)
+		return -EINVAL;
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
+
+	/* See comments in vfio_pci_core_mmap() re VM_ALLOW_ANY_UNCACHED. */
+	vm_flags_set(vma, VM_ALLOW_ANY_UNCACHED | VM_IO | VM_PFNMAP |
+		     VM_DONTEXPAND | VM_DONTDUMP);
+	vma->vm_private_data = priv;
+	vfio_pci_set_vma_ops(vma);
+
+	return 0;
+}
 #else
 static int vfio_pci_dma_buf_attach(struct dma_buf *dmabuf,
 				   struct dma_buf_attachment *attachment)
@@ -104,6 +148,9 @@ static void vfio_pci_dma_buf_release(struct dma_buf *dmabuf)
 
 static const struct dma_buf_ops vfio_pci_dmabuf_ops = {
 	.attach = vfio_pci_dma_buf_attach,
+#ifdef CONFIG_VFIO_PCI_DMABUF
+	.mmap = vfio_pci_dma_buf_mmap,
+#endif
 	.map_dma_buf = vfio_pci_dma_buf_map,
 	.unmap_dma_buf = vfio_pci_dma_buf_unmap,
 	.release = vfio_pci_dma_buf_release,
diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h
index b0e0ac295db4..cd432f52c38f 100644
--- a/drivers/vfio/pci/vfio_pci_priv.h
+++ b/drivers/vfio/pci/vfio_pci_priv.h
@@ -142,6 +142,7 @@ int vfio_pci_core_mmap_prep_dmabuf(struct vfio_pci_core_device *vdev,
 				   unsigned int res_index);
 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);
+void vfio_pci_set_vma_ops(struct vm_area_struct *vma);
 
 #ifdef CONFIG_VFIO_PCI_DMABUF
 int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
-- 
2.50.1 (Apple Git-155)