vfio/pci: Set up BAR resources and maps in vfio_pci_core_enable()

Previously BAR resource requests and the corresponding pci_iomap()
were performed on-demand and without synchronisation, which was racy.
Rather than add synchronisation, it's simplest to address this by
doing both activities from vfio_pci_core_enable().

The resource allocation and/or pci_iomap() can still fail; their
status is tracked and existing calls to vfio_pci_core_setup_barmap()
will fail in a similar way to before.  This keeps the point of failure
as observed by userspace the same, i.e. failures to request/map unused
BARs are benign.

Fixes: 89e1f7d4c66d ("vfio: Add PCI device driver")
Signed-off-by: Matt Evans <mattev@meta.com>
Link: https://lore.kernel.org/r/20260511145829.2993601-2-mattev@meta.com
[ERR_PTR -> IOMEM_ERR_PTR per lkp report]
Signed-off-by: Alex Williamson <alex@shazbot.org>

2 files changed, 43 insertions, 20 deletions

diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 3f8d093aacf8..050e7542952e 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -483,6 +483,40 @@ 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
  * state with only with runtime PM ops, then no explicit handling is needed
@@ -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);
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 4251ee03e146..3bfbb879a005 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/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);