Merge tag 'vfio-v7.1-rc4' of https://github.com/awilliam/linux-vfio

Pull VFIO fixes from Alex Williamson:

 - Convert vfio-pci BAR resource requests and iomaps initialization
   from a lazy, on-demand model to an eager pre-allocation model to
   avoid races while preserving legacy error behavior.  Fix unchecked
   barmap access in dma-buf export path (Matt Evans)

 - Introduce an implicit unsigned cast in converting vfio-pci device
   offsets to region indexes, closing a potential out-of-bounds
   access through the vfio_pci_ioeventfd() interface (Matt Evans)

 - Fix a dma-buf kref underflow and stuck wait_for_completion() when
   closing a previously revoked dma-buf (Alex Williamson)

* tag 'vfio-v7.1-rc4' of https://github.com/awilliam/linux-vfio:
  vfio/pci: Check BAR resources before exporting a DMABUF
  vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()
  vfio/pci: Make VFIO_PCI_OFFSET_TO_INDEX() return unsigned
  vfio/pci: fix dma-buf kref underflow after revoke

drivers/vfio/pci/vfio_pci_core.c

@@ -482,6 +482,40 @@ static int vfio_pci_core_runtime_resume(struct device *dev)
 }
 #endif /* CONFIG_PM */
 
+/*
+ * Eager-request BAR resources, and iomap them.  Soft failures are
+ * allowed, and consumers must check the barmap before use in order to
+ * give compatible user-visible behaviour with the previous on-demand
+ * allocation method.
+ */
+static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
+{
+	struct pci_dev *pdev = vdev->pdev;
+	int i;
+
+	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
+		int bar = i + PCI_STD_RESOURCES;
+
+		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
+
+		if (!pci_resource_len(pdev, i))
+			continue;
+
+		if (pci_request_selected_regions(pdev, 1 << bar, "vfio")) {
+			pci_dbg(pdev, "Failed to reserve region %d\n", bar);
+			vdev->barmap[bar] = IOMEM_ERR_PTR(-EBUSY);
+			continue;
+		}
+
+		vdev->barmap[bar] = pci_iomap(pdev, bar, 0);
+		if (!vdev->barmap[bar]) {
+			pci_dbg(pdev, "Failed to iomap region %d\n", bar);
+			pci_release_selected_regions(pdev, 1 << bar);
+			vdev->barmap[bar] = IOMEM_ERR_PTR(-ENOMEM);
+		}
+	}
+}
+
 /*
  * The pci-driver core runtime PM routines always save the device state
  * before going into suspended state. If the device is going into low power
@@ -568,6 +602,7 @@ int vfio_pci_core_enable(struct vfio_pci_core_device *vdev)
 	if (!vfio_vga_disabled() && vfio_pci_is_vga(pdev))
 		vdev->has_vga = true;
 
+	vfio_pci_core_map_bars(vdev);
 
 	return 0;
 
@@ -648,7 +683,7 @@ void vfio_pci_core_disable(struct vfio_pci_core_device *vdev)
 
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		bar = i + PCI_STD_RESOURCES;
-		if (!vdev->barmap[bar])
+		if (IS_ERR_OR_NULL(vdev->barmap[bar]))
 			continue;
 		pci_iounmap(pdev, vdev->barmap[bar]);
 		pci_release_selected_regions(pdev, 1 << bar);

drivers/vfio/pci/vfio_pci_dmabuf.c

@@ -244,9 +244,11 @@ int vfio_pci_core_feature_dma_buf(struct vfio_pci_core_device *vdev, u32 flags,
 		return -EINVAL;
 
 	/*
-	 * For PCI the region_index is the BAR number like everything else.
+	 * For PCI the region_index is the BAR number like everything
+	 * else.  Check that PCI resources have been claimed for it.
 	 */
-	if (get_dma_buf.region_index >= VFIO_PCI_ROM_REGION_INDEX)
+	if (get_dma_buf.region_index >= VFIO_PCI_ROM_REGION_INDEX ||
+	    vfio_pci_core_setup_barmap(vdev, get_dma_buf.region_index))
 		return -ENODEV;
 
 	dma_ranges = memdup_array_user(&arg->dma_ranges, get_dma_buf.nr_ranges,
@@ -354,19 +356,18 @@ void vfio_pci_dma_buf_move(struct vfio_pci_core_device *vdev, bool revoked)
 			if (revoked) {
 				kref_put(&priv->kref, vfio_pci_dma_buf_done);
 				wait_for_completion(&priv->comp);
-			} else {
 				/*
-				 * Kref is initialize again, because when revoke
-				 * was performed the reference counter was decreased
-				 * to zero to trigger completion.
+				 * Re-arm the registered kref reference and the
+				 * completion so the post-revoke state matches the
+				 * post-creation state.  An un-revoke followed by a
+				 * new mapping needs the kref to be non-zero before
+				 * kref_get(), and vfio_pci_dma_buf_cleanup()
+				 * delegates its drain back through this revoke
+				 * path on a possibly-already-revoked dma-buf.
 				 */
 				kref_init(&priv->kref);
-				/*
-				 * There is no need to wait as no mapping was
-				 * performed when the previous status was
-				 * priv->revoked == true.
-				 */
 				reinit_completion(&priv->comp);
+			} else {
 				dma_resv_lock(priv->dmabuf->resv, NULL);
 				priv->revoked = false;
 				dma_resv_unlock(priv->dmabuf->resv);
@@ -382,21 +383,22 @@ void vfio_pci_dma_buf_cleanup(struct vfio_pci_core_device *vdev)
 	struct vfio_pci_dma_buf *tmp;
 
 	down_write(&vdev->memory_lock);
+
+	/*
+	 * Drain any active mappings via the revoke path.  The move is
+	 * idempotent for dma-bufs already in the revoked state and
+	 * leaves every priv with the kref re-armed and the completion
+	 * ready, so cleanup itself does not need to participate in kref
+	 * bookkeeping.
+	 */
+	vfio_pci_dma_buf_move(vdev, true);
+
 	list_for_each_entry_safe(priv, tmp, &vdev->dmabufs, dmabufs_elm) {
 		if (!get_file_active(&priv->dmabuf->file))
 			continue;
 
-		dma_resv_lock(priv->dmabuf->resv, NULL);
 		list_del_init(&priv->dmabufs_elm);
 		priv->vdev = NULL;
-		priv->revoked = true;
-		dma_buf_invalidate_mappings(priv->dmabuf);
-		dma_resv_wait_timeout(priv->dmabuf->resv,
-				      DMA_RESV_USAGE_BOOKKEEP, false,
-				      MAX_SCHEDULE_TIMEOUT);
-		dma_resv_unlock(priv->dmabuf->resv);
-		kref_put(&priv->kref, vfio_pci_dma_buf_done);
-		wait_for_completion(&priv->comp);
 		vfio_device_put_registration(&vdev->vdev);
 		fput(priv->dmabuf->file);
 	}

drivers/vfio/pci/vfio_pci_rdwr.c

@@ -198,27 +198,15 @@ ssize_t vfio_pci_core_do_io_rw(struct vfio_pci_core_device *vdev, bool test_mem,
 }
 EXPORT_SYMBOL_GPL(vfio_pci_core_do_io_rw);
 
+/*
+ * The barmap is set up in vfio_pci_core_enable().  Callers use this
+ * function to check that the BAR resources are requested or that the
+ * pci_iomap() was done.
+ */
 int vfio_pci_core_setup_barmap(struct vfio_pci_core_device *vdev, int bar)
 {
-	struct pci_dev *pdev = vdev->pdev;
-	int ret;
-	void __iomem *io;
-
-	if (vdev->barmap[bar])
-		return 0;
-
-	ret = pci_request_selected_regions(pdev, 1 << bar, "vfio");
-	if (ret)
-		return ret;
-
-	io = pci_iomap(pdev, bar, 0);
-	if (!io) {
-		pci_release_selected_regions(pdev, 1 << bar);
-		return -ENOMEM;
-	}
-
-	vdev->barmap[bar] = io;
-
+	if (IS_ERR(vdev->barmap[bar]))
+		return PTR_ERR(vdev->barmap[bar]);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(vfio_pci_core_setup_barmap);

include/linux/vfio_pci_core.h

@@ -21,7 +21,7 @@
 #define VFIO_PCI_CORE_H
 
 #define VFIO_PCI_OFFSET_SHIFT   40
-#define VFIO_PCI_OFFSET_TO_INDEX(off)	(off >> VFIO_PCI_OFFSET_SHIFT)
+#define VFIO_PCI_OFFSET_TO_INDEX(off)	((u64)(off) >> VFIO_PCI_OFFSET_SHIFT)
 #define VFIO_PCI_INDEX_TO_OFFSET(index)	((u64)(index) << VFIO_PCI_OFFSET_SHIFT)
 #define VFIO_PCI_OFFSET_MASK	(((u64)(1) << VFIO_PCI_OFFSET_SHIFT) - 1)