vfio-pci: Allow to mmap sub-page MMIO BARs if the mmio page is exclusive
Current vfio-pci implementation disallows to mmap
sub-page(size < PAGE_SIZE) MMIO BARs because these BARs' mmio
page may be shared with other BARs. This will cause some
performance issues when we passthrough a PCI device with
this kind of BARs. Guest will be not able to handle the mmio
accesses to the BARs which leads to mmio emulations in host.
However, not all sub-page BARs will share page with other BARs.
We should allow to mmap the sub-page MMIO BARs which we can
make sure will not share page with other BARs.
This patch adds support for this case. And we try to add a
dummy resource to reserve the remainder of the page which
hot-add device's BAR might be assigned into. But it's not
necessary to handle the case when the BAR is not page aligned.
Because we can't expect the BAR will be assigned into the same
location in a page in guest when we passthrough the BAR. And
it's hard to access this BAR in userspace because we have
no way to get the BAR's location in a page.
Signed-off-by: Yongji Xie <xyjxie@linux.vnet.ibm.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 188b1ff..d624a52 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -110,6 +110,74 @@
return (pdev->class >> 8) == PCI_CLASS_DISPLAY_VGA;
}
+static void vfio_pci_probe_mmaps(struct vfio_pci_device *vdev)
+{
+ struct resource *res;
+ int bar;
+ struct vfio_pci_dummy_resource *dummy_res;
+
+ INIT_LIST_HEAD(&vdev->dummy_resources_list);
+
+ for (bar = PCI_STD_RESOURCES; bar <= PCI_STD_RESOURCE_END; bar++) {
+ res = vdev->pdev->resource + bar;
+
+ if (!IS_ENABLED(CONFIG_VFIO_PCI_MMAP))
+ goto no_mmap;
+
+ if (!(res->flags & IORESOURCE_MEM))
+ goto no_mmap;
+
+ /*
+ * The PCI core shouldn't set up a resource with a
+ * type but zero size. But there may be bugs that
+ * cause us to do that.
+ */
+ if (!resource_size(res))
+ goto no_mmap;
+
+ if (resource_size(res) >= PAGE_SIZE) {
+ vdev->bar_mmap_supported[bar] = true;
+ continue;
+ }
+
+ if (!(res->start & ~PAGE_MASK)) {
+ /*
+ * Add a dummy resource to reserve the remainder
+ * of the exclusive page in case that hot-add
+ * device's bar is assigned into it.
+ */
+ dummy_res = kzalloc(sizeof(*dummy_res), GFP_KERNEL);
+ if (dummy_res == NULL)
+ goto no_mmap;
+
+ dummy_res->resource.name = "vfio sub-page reserved";
+ dummy_res->resource.start = res->end + 1;
+ dummy_res->resource.end = res->start + PAGE_SIZE - 1;
+ dummy_res->resource.flags = res->flags;
+ if (request_resource(res->parent,
+ &dummy_res->resource)) {
+ kfree(dummy_res);
+ goto no_mmap;
+ }
+ dummy_res->index = bar;
+ list_add(&dummy_res->res_next,
+ &vdev->dummy_resources_list);
+ vdev->bar_mmap_supported[bar] = true;
+ continue;
+ }
+ /*
+ * Here we don't handle the case when the BAR is not page
+ * aligned because we can't expect the BAR will be
+ * assigned into the same location in a page in guest
+ * when we passthrough the BAR. And it's hard to access
+ * this BAR in userspace because we have no way to get
+ * the BAR's location in a page.
+ */
+no_mmap:
+ vdev->bar_mmap_supported[bar] = false;
+ }
+}
+
static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev);
static void vfio_pci_disable(struct vfio_pci_device *vdev);
@@ -218,12 +286,15 @@
}
}
+ vfio_pci_probe_mmaps(vdev);
+
return 0;
}
static void vfio_pci_disable(struct vfio_pci_device *vdev)
{
struct pci_dev *pdev = vdev->pdev;
+ struct vfio_pci_dummy_resource *dummy_res, *tmp;
int i, bar;
/* Stop the device from further DMA */
@@ -252,6 +323,13 @@
vdev->barmap[bar] = NULL;
}
+ list_for_each_entry_safe(dummy_res, tmp,
+ &vdev->dummy_resources_list, res_next) {
+ list_del(&dummy_res->res_next);
+ release_resource(&dummy_res->resource);
+ kfree(dummy_res);
+ }
+
vdev->needs_reset = true;
/*
@@ -623,9 +701,7 @@
info.flags = VFIO_REGION_INFO_FLAG_READ |
VFIO_REGION_INFO_FLAG_WRITE;
- if (IS_ENABLED(CONFIG_VFIO_PCI_MMAP) &&
- pci_resource_flags(pdev, info.index) &
- IORESOURCE_MEM && info.size >= PAGE_SIZE) {
+ if (vdev->bar_mmap_supported[info.index]) {
info.flags |= VFIO_REGION_INFO_FLAG_MMAP;
if (info.index == vdev->msix_bar) {
ret = msix_sparse_mmap_cap(vdev, &caps);
@@ -1049,16 +1125,16 @@
return -EINVAL;
if (index >= VFIO_PCI_ROM_REGION_INDEX)
return -EINVAL;
- if (!(pci_resource_flags(pdev, index) & IORESOURCE_MEM))
+ if (!vdev->bar_mmap_supported[index])
return -EINVAL;
- phys_len = pci_resource_len(pdev, index);
+ phys_len = PAGE_ALIGN(pci_resource_len(pdev, index));
req_len = vma->vm_end - vma->vm_start;
pgoff = vma->vm_pgoff &
((1U << (VFIO_PCI_OFFSET_SHIFT - PAGE_SHIFT)) - 1);
req_start = pgoff << PAGE_SHIFT;
- if (phys_len < PAGE_SIZE || req_start + req_len > phys_len)
+ if (req_start + req_len > phys_len)
return -EINVAL;
if (index == vdev->msix_bar) {