vfio/pci: Add option to disable GeForce quirks

These quirks are necessary for GeForce, but not for Quadro/GRID/Tesla
assignment.  Leaving them enabled is fully functional and provides the
most compatibility, but due to the unique NVIDIA MSI ACK behavior[1],
it also introduces latency in re-triggering the MSI interrupt.  This
overhead is typically negligible, but has been shown to adversely
affect some (very) high interrupt rate applications.  This adds the
vfio-pci device option "x-no-geforce-quirks=" which can be set to
"on" to disable this additional overhead.

A follow-on optimization for GeForce might be to make use of an
ioeventfd to allow KVM to trigger an irqfd in the kernel vfio-pci
driver, avoiding the bounce through userspace to handle this device
write.

[1] Background: the NVIDIA driver has been observed to issue a write
to the MMIO mirror of PCI config space in BAR0 in order to allow the
MSI interrupt for the device to retrigger.  Older reports indicated a
write of 0xff to the (read-only) MSI capability ID register, while
more recently a write of 0x0 is observed at config space offset 0x704,
non-architected, extended config space of the device (BAR0 offset
0x88704).  Virtualization of this range is only required for GeForce.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

3 files changed, 9 insertions, 3 deletions

diff --git a/hw/vfio/pci-quirks.c b/hw/vfio/pci-quirks.c
index 60ad5fb91a..e5779a7ad3 100644
--- a/hw/vfio/pci-quirks.c
+++ b/hw/vfio/pci-quirks.c
@@ -542,7 +542,8 @@ static void vfio_vga_probe_nvidia_3d0_quirk(VFIOPCIDevice *vdev)
     VFIOQuirk *quirk;
     VFIONvidia3d0Quirk *data;
 
-    if (!vfio_pci_is(vdev, PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID) ||
+    if (vdev->no_geforce_quirks ||
+        !vfio_pci_is(vdev, PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID) ||
         !vdev->bars[1].region.size) {
         return;
     }
@@ -660,7 +661,8 @@ static void vfio_probe_nvidia_bar5_quirk(VFIOPCIDevice *vdev, int nr)
     VFIONvidiaBAR5Quirk *bar5;
     VFIOConfigWindowQuirk *window;
 
-    if (!vfio_pci_is(vdev, PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID) ||
+    if (vdev->no_geforce_quirks ||
+        !vfio_pci_is(vdev, PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID) ||
         !vdev->vga || nr != 5 || !vdev->bars[5].ioport) {
         return;
     }
@@ -754,7 +756,8 @@ static void vfio_probe_nvidia_bar0_quirk(VFIOPCIDevice *vdev, int nr)
     VFIOQuirk *quirk;
     VFIOConfigMirrorQuirk *mirror;
 
-    if (!vfio_pci_is(vdev, PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID) ||
+    if (vdev->no_geforce_quirks ||
+        !vfio_pci_is(vdev, PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID) ||
         !vfio_is_vga(vdev) || nr != 0) {
         return;
     }
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index cab2aecb80..879510c046 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -3130,6 +3130,8 @@ static Property vfio_pci_dev_properties[] = {
     DEFINE_PROP_BOOL("x-no-kvm-intx", VFIOPCIDevice, no_kvm_intx, false),
     DEFINE_PROP_BOOL("x-no-kvm-msi", VFIOPCIDevice, no_kvm_msi, false),
     DEFINE_PROP_BOOL("x-no-kvm-msix", VFIOPCIDevice, no_kvm_msix, false),
+    DEFINE_PROP_BOOL("x-no-geforce-quirks", VFIOPCIDevice,
+                     no_geforce_quirks, false),
     DEFINE_PROP_UINT32("x-pci-vendor-id", VFIOPCIDevice, vendor_id, PCI_ANY_ID),
     DEFINE_PROP_UINT32("x-pci-device-id", VFIOPCIDevice, device_id, PCI_ANY_ID),
     DEFINE_PROP_UINT32("x-pci-sub-vendor-id", VFIOPCIDevice,
diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h
index 588381f201..f4aa13e021 100644
--- a/hw/vfio/pci.h
+++ b/hw/vfio/pci.h
@@ -146,6 +146,7 @@ typedef struct VFIOPCIDevice {
     bool no_kvm_intx;
     bool no_kvm_msi;
     bool no_kvm_msix;
+    bool no_geforce_quirks;
 } VFIOPCIDevice;
 
 uint32_t vfio_pci_read_config(PCIDevice *pdev, uint32_t addr, int len);