Skip to content
Snippets Groups Projects
Commit b5048a4c authored by Alex Williamson's avatar Alex Williamson :monkey:
Browse files

vfio/pci: Static Resizable BAR capability


The PCI Resizable BAR (ReBAR) capability is currently hidden from the
VM because the protocol for interacting with the capability does not
support a mechanism for the device to reject an advertised supported
BAR size.  However, when assigned to a VM, the act of resizing the
BAR requires adjustment of host resources for the device, which
absolutely can fail.  Linux does not currently allow us to reserve
resources for the device independent of the current usage.

The only writable field within the ReBAR capability is the BAR Size
register.  The PCIe spec indicates that when written, the device
should immediately begin to operate with the provided BAR size.  The
spec however also notes that software must only write values
corresponding to supported sizes as indicated in the capability and
control registers.  Writing unsupported sizes produces undefined
results.  Therefore, if the hypervisor were to virtualize the
capability and control registers such that the current size is the
only indicated available size, then a write of anything other than
the current size falls into the category of undefined behavior,
where we can essentially expose the modified ReBAR capability as
read-only.

This may seem pointless, but users have reported that virtualizing
the capability in this way not only allows guest software to expose
related features as available (even if only cosmetic), but in some
scenarios can resolve guest driver issues.  Additionally, no
regressions in behavior have been reported for this change.

A caveat here is that the PCIe spec requires for compatibility that
devices report support for a size in the range of 1MB to 512GB,
therefore if the current BAR size falls outside that range we revert
to hiding the capability.

Reviewed-by: Cédric Le Goater's avatarCédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/r/20230505232308.2869912-1-alex.williamson@redhat.com


Signed-off-by: Alex Williamson's avatarAlex Williamson <alex.williamson@redhat.com>
parent ff180c6b
No related branches found
No related tags found
No related merge requests found
......@@ -2066,6 +2066,54 @@ static int vfio_add_std_cap(VFIOPCIDevice *vdev, uint8_t pos, Error **errp)
return 0;
}
static int vfio_setup_rebar_ecap(VFIOPCIDevice *vdev, uint16_t pos)
{
uint32_t ctrl;
int i, nbar;
ctrl = pci_get_long(vdev->pdev.config + pos + PCI_REBAR_CTRL);
nbar = (ctrl & PCI_REBAR_CTRL_NBAR_MASK) >> PCI_REBAR_CTRL_NBAR_SHIFT;
for (i = 0; i < nbar; i++) {
uint32_t cap;
int size;
ctrl = pci_get_long(vdev->pdev.config + pos + PCI_REBAR_CTRL + (i * 8));
size = (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> PCI_REBAR_CTRL_BAR_SHIFT;
/* The cap register reports sizes 1MB to 128TB, with 4 reserved bits */
cap = size <= 27 ? 1U << (size + 4) : 0;
/*
* The PCIe spec (v6.0.1, 7.8.6) requires HW to support at least one
* size in the range 1MB to 512GB. We intend to mask all sizes except
* the one currently enabled in the size field, therefore if it's
* outside the range, hide the whole capability as this virtualization
* trick won't work. If >512GB resizable BARs start to appear, we
* might need an opt-in or reservation scheme in the kernel.
*/
if (!(cap & PCI_REBAR_CAP_SIZES)) {
return -EINVAL;
}
/* Hide all sizes reported in the ctrl reg per above requirement. */
ctrl &= (PCI_REBAR_CTRL_BAR_SIZE |
PCI_REBAR_CTRL_NBAR_MASK |
PCI_REBAR_CTRL_BAR_IDX);
/*
* The BAR size field is RW, however we've mangled the capability
* register such that we only report a single size, ie. the current
* BAR size. A write of an unsupported value is undefined, therefore
* the register field is essentially RO.
*/
vfio_add_emulated_long(vdev, pos + PCI_REBAR_CAP + (i * 8), cap, ~0);
vfio_add_emulated_long(vdev, pos + PCI_REBAR_CTRL + (i * 8), ctrl, ~0);
}
return 0;
}
static void vfio_add_ext_cap(VFIOPCIDevice *vdev)
{
PCIDevice *pdev = &vdev->pdev;
......@@ -2139,9 +2187,13 @@ static void vfio_add_ext_cap(VFIOPCIDevice *vdev)
case 0: /* kernel masked capability */
case PCI_EXT_CAP_ID_SRIOV: /* Read-only VF BARs confuse OVMF */
case PCI_EXT_CAP_ID_ARI: /* XXX Needs next function virtualization */
case PCI_EXT_CAP_ID_REBAR: /* Can't expose read-only */
trace_vfio_add_ext_cap_dropped(vdev->vbasedev.name, cap_id, next);
break;
case PCI_EXT_CAP_ID_REBAR:
if (!vfio_setup_rebar_ecap(vdev, next)) {
pcie_add_capability(pdev, cap_id, cap_ver, next, size);
}
break;
default:
pcie_add_capability(pdev, cap_id, cap_ver, next, size);
}
......
  • I'd just like to comment that this patch changes the behaviour of AMD RX 7000 series GPUs. While tools like GPU-Z report Resizeable BAR is enabled, and the windows resources report the full BAR is available, AMD's drivers rely on the rebar capability flag to correctly program the GPU. This can be confirmed through the AMD Adrenalin Software where without this patch, AMD SmartAccess Memory is reported as unsupported.

    It has been verified that this is not simply a cosmetic change, as the windows DirectX12 API ID3D12Device3::OpenExistingHeapFromAddress causes the GPU driver to internally fault with out of memory errors after it has been used if this is not properly advertised to the guest. It appears this is due to this API exhausting the address space of the BAR when the heap is mapped into its address space.

    The detailed error reported by DirectX12 when this fault occurs is:

    D3D12 ERROR: Kernel memory failure. There might be a memory leak. [ EXECUTION ERROR #834: MAP_OUTOFMEMORY_RETURN]
    D3D12 WARNING: Using ID3D12DebugDevice2::ReportLiveDeviceObjects with D3D12_RLDO_DETAIL will help drill into object lifetimes.
     [ STATE_CREATION WARNING #255: LIVE_OBJECT_SUMMARY]
    D3D12 WARNING: Live ID3D12Device at 0x0000023BF4429E80, Refcount: 16 [ STATE_CREATION WARNING #274: LIVE_DEVICE]
    D3D12 WARNING: Live       ID3D12ShaderCacheSession :      2 [ STATE_CREATION WARNING #255: LIVE_OBJECT_SUMMARY]
    D3D12 WARNING: Live            ID3D12RootSignature :      6 [ STATE_CREATION WARNING #255: LIVE_OBJECT_SUMMARY]
    D3D12 WARNING: Live            ID3D12PipelineState :      5 [ STATE_CREATION WARNING #255: LIVE_OBJECT_SUMMARY]
    D3D12 WARNING: Live                 ID3D12Resource :     31 [ STATE_CREATION WARNING #255: LIVE_OBJECT_SUMMARY]
    D3D12 WARNING: Live                     ID3D12Heap :     11 [ STATE_CREATION WARNING #255: LIVE_OBJECT_SUMMARY]
    D3D12 WARNING: Live             ID3D12CommandQueue :      4 [ STATE_CREATION WARNING #255: LIVE_OBJECT_SUMMARY]
    D3D12 WARNING: Live                    ID3D12Fence :     10 [ STATE_CREATION WARNING #255: LIVE_OBJECT_SUMMARY]
    D3D12 WARNING: Live         ID3D12CommandAllocator :     34 [ STATE_CREATION WARNING #255: LIVE_OBJECT_SUMMARY]
    D3D12 WARNING: Live      ID3D12GraphicsCommandList :      6 [ STATE_CREATION WARNING #255: LIVE_OBJECT_SUMMARY]
    D3D12: Removing Device.
    Edited by Geoffrey McRae
  • Cédric Le Goater @clegoate

    mentioned in issue #703

    ·

    mentioned in issue #703

    Toggle commit list
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment