xen/pt: reserve PCI slot 2 for Intel igd-passthru

Intel specifies that the Intel IGD must occupy slot 2 on the PCI bus,
as noted in docs/igd-assign.txt in the Qemu source code.

Currently, when the xl toolstack is used to configure a Xen HVM guest with
Intel IGD passthrough to the guest with the Qemu upstream device model,
a Qemu emulated PCI device will occupy slot 2 and the Intel IGD will occupy
a different slot. This problem often prevents the guest from booting.

The only available workarounds are not good: Configure Xen HVM guests to
use the old and no longer maintained Qemu traditional device model
available from xenbits.xen.org which does reserve slot 2 for the Intel
IGD or use the "pc" machine type instead of the "xenfv" machine type and
add the xen platform device at slot 3 using a command line option
instead of patching qemu to fix the "xenfv" machine type directly. The
second workaround causes some degredation in startup performance such as
a longer boot time and reduced resolution of the grub menu that is
displayed on the monitor. This patch avoids that reduced startup
performance when using the Qemu upstream device model for Xen HVM guests
configured with the igd-passthru=on option.

To implement this feature in the Qemu upstream device model for Xen HVM
guests, introduce the following new functions, types, and macros:

* XEN_PT_DEVICE_CLASS declaration, based on the existing TYPE_XEN_PT_DEVICE
* XEN_PT_DEVICE_GET_CLASS macro helper function for XEN_PT_DEVICE_CLASS
* typedef XenPTQdevRealize function pointer
* XEN_PCI_IGD_SLOT_MASK, the value of slot_reserved_mask to reserve slot 2
* xen_igd_reserve_slot and xen_igd_clear_slot functions

Michael Tsirkin:
* Introduce XEN_PCI_IGD_DOMAIN, XEN_PCI_IGD_BUS, XEN_PCI_IGD_DEV, and
  XEN_PCI_IGD_FN - use them to compute the value of XEN_PCI_IGD_SLOT_MASK

The new xen_igd_reserve_slot function uses the existing slot_reserved_mask
member of PCIBus to reserve PCI slot 2 for Xen HVM guests configured using
the xl toolstack with the gfx_passthru option enabled, which sets the
igd-passthru=on option to Qemu for the Xen HVM machine type.

The new xen_igd_reserve_slot function also needs to be implemented in
hw/xen/xen_pt_stub.c to prevent FTBFS during the link stage for the case
when Qemu is configured with --enable-xen and --disable-xen-pci-passthrough,
in which case it does nothing.

The new xen_igd_clear_slot function overrides qdev->realize of the parent
PCI device class to enable the Intel IGD to occupy slot 2 on the PCI bus
since slot 2 was reserved by xen_igd_reserve_slot when the PCI bus was
created in hw/i386/pc_piix.c for the case when igd-passthru=on.

Move the call to xen_host_pci_device_get, and the associated error
handling, from xen_pt_realize to the new xen_igd_clear_slot function to
initialize the device class and vendor values which enables the checks for
the Intel IGD to succeed. The verification that the host device is an
Intel IGD to be passed through is done by checking the domain, bus, slot,
and function values as well as by checking that gfx_passthru is enabled,
the device class is VGA, and the device vendor in Intel.

Signed-off-by: Chuck Zmudzinski <brchuckz@aol.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Message-Id: <b1b4a21fe9a600b1322742dda55a40e9961daa57.1674346505.git.brchuckz@aol.com>
Signed-off-by: Anthony PERARD <anthony.perard@citrix.com>

hw/i386/pc_piix.c

@@ -422,6 +422,7 @@ static void pc_xen_hvm_init(MachineState *machine)
     }
 
     pc_xen_hvm_init_pci(machine);
+    xen_igd_reserve_slot(pcms->bus);
     pci_create_simple(pcms->bus, -1, "xen-platform");
 }
 #endif

hw/xen/xen_pt.c

@@ -57,6 +57,7 @@
 #include <sys/ioctl.h>
 
 #include "hw/pci/pci.h"
+#include "hw/pci/pci_bus.h"
 #include "hw/qdev-properties.h"
 #include "hw/qdev-properties-system.h"
 #include "hw/xen/xen.h"
@@ -780,15 +781,6 @@ static void xen_pt_realize(PCIDevice *d, Error **errp)
                s->hostaddr.bus, s->hostaddr.slot, s->hostaddr.function,
                s->dev.devfn);
 
-    xen_host_pci_device_get(&s->real_device,
-                            s->hostaddr.domain, s->hostaddr.bus,
-                            s->hostaddr.slot, s->hostaddr.function,
-                            errp);
-    if (*errp) {
-        error_append_hint(errp, "Failed to \"open\" the real pci device");
-        return;
-    }
-
     s->is_virtfn = s->real_device.is_virtfn;
     if (s->is_virtfn) {
         XEN_PT_LOG(d, "%04x:%02x:%02x.%d is a SR-IOV Virtual Function\n",
@@ -803,8 +795,10 @@ static void xen_pt_realize(PCIDevice *d, Error **errp)
     s->io_listener = xen_pt_io_listener;
 
     /* Setup VGA bios for passthrough GFX */
-    if ((s->real_device.domain == 0) && (s->real_device.bus == 0) &&
-        (s->real_device.dev == 2) && (s->real_device.func == 0)) {
+    if ((s->real_device.domain == XEN_PCI_IGD_DOMAIN) &&
+        (s->real_device.bus == XEN_PCI_IGD_BUS) &&
+        (s->real_device.dev == XEN_PCI_IGD_DEV) &&
+        (s->real_device.func == XEN_PCI_IGD_FN)) {
         if (!is_igd_vga_passthrough(&s->real_device)) {
             error_setg(errp, "Need to enable igd-passthru if you're trying"
                     " to passthrough IGD GFX");
@@ -950,11 +944,58 @@ static void xen_pci_passthrough_instance_init(Object *obj)
     PCI_DEVICE(obj)->cap_present |= QEMU_PCI_CAP_EXPRESS;
 }
 
+void xen_igd_reserve_slot(PCIBus *pci_bus)
+{
+    if (!xen_igd_gfx_pt_enabled()) {
+        return;
+    }
+
+    XEN_PT_LOG(0, "Reserving PCI slot 2 for IGD\n");
+    pci_bus->slot_reserved_mask |= XEN_PCI_IGD_SLOT_MASK;
+}
+
+static void xen_igd_clear_slot(DeviceState *qdev, Error **errp)
+{
+    ERRP_GUARD();
+    PCIDevice *pci_dev = (PCIDevice *)qdev;
+    XenPCIPassthroughState *s = XEN_PT_DEVICE(pci_dev);
+    XenPTDeviceClass *xpdc = XEN_PT_DEVICE_GET_CLASS(s);
+    PCIBus *pci_bus = pci_get_bus(pci_dev);
+
+    xen_host_pci_device_get(&s->real_device,
+                            s->hostaddr.domain, s->hostaddr.bus,
+                            s->hostaddr.slot, s->hostaddr.function,
+                            errp);
+    if (*errp) {
+        error_append_hint(errp, "Failed to \"open\" the real pci device");
+        return;
+    }
+
+    if (!(pci_bus->slot_reserved_mask & XEN_PCI_IGD_SLOT_MASK)) {
+        xpdc->pci_qdev_realize(qdev, errp);
+        return;
+    }
+
+    if (is_igd_vga_passthrough(&s->real_device) &&
+        s->real_device.domain == XEN_PCI_IGD_DOMAIN &&
+        s->real_device.bus == XEN_PCI_IGD_BUS &&
+        s->real_device.dev == XEN_PCI_IGD_DEV &&
+        s->real_device.func == XEN_PCI_IGD_FN &&
+        s->real_device.vendor_id == PCI_VENDOR_ID_INTEL) {
+        pci_bus->slot_reserved_mask &= ~XEN_PCI_IGD_SLOT_MASK;
+        XEN_PT_LOG(pci_dev, "Intel IGD found, using slot 2\n");
+    }
+    xpdc->pci_qdev_realize(qdev, errp);
+}
+
 static void xen_pci_passthrough_class_init(ObjectClass *klass, void *data)
 {
     DeviceClass *dc = DEVICE_CLASS(klass);
     PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
 
+    XenPTDeviceClass *xpdc = XEN_PT_DEVICE_CLASS(klass);
+    xpdc->pci_qdev_realize = dc->realize;
+    dc->realize = xen_igd_clear_slot;
     k->realize = xen_pt_realize;
     k->exit = xen_pt_unregister_device;
     k->config_read = xen_pt_pci_read_config;
@@ -977,6 +1018,7 @@ static const TypeInfo xen_pci_passthrough_info = {
     .instance_size = sizeof(XenPCIPassthroughState),
     .instance_finalize = xen_pci_passthrough_finalize,
     .class_init = xen_pci_passthrough_class_init,
+    .class_size = sizeof(XenPTDeviceClass),
     .instance_init = xen_pci_passthrough_instance_init,
     .interfaces = (InterfaceInfo[]) {
         { INTERFACE_CONVENTIONAL_PCI_DEVICE },

hw/xen/xen_pt.h

@@ -40,7 +40,20 @@ typedef struct XenPTReg XenPTReg;
 #define TYPE_XEN_PT_DEVICE "xen-pci-passthrough"
 OBJECT_DECLARE_SIMPLE_TYPE(XenPCIPassthroughState, XEN_PT_DEVICE)
 
+#define XEN_PT_DEVICE_CLASS(klass) \
+    OBJECT_CLASS_CHECK(XenPTDeviceClass, klass, TYPE_XEN_PT_DEVICE)
+#define XEN_PT_DEVICE_GET_CLASS(obj) \
+    OBJECT_GET_CLASS(XenPTDeviceClass, obj, TYPE_XEN_PT_DEVICE)
+
+typedef void (*XenPTQdevRealize)(DeviceState *qdev, Error **errp);
+
+typedef struct XenPTDeviceClass {
+    PCIDeviceClass parent_class;
+    XenPTQdevRealize pci_qdev_realize;
+} XenPTDeviceClass;
+
 uint32_t igd_read_opregion(XenPCIPassthroughState *s);
+void xen_igd_reserve_slot(PCIBus *pci_bus);
 void igd_write_opregion(XenPCIPassthroughState *s, uint32_t val);
 void xen_igd_passthrough_isa_bridge_create(XenPCIPassthroughState *s,
                                            XenHostPCIDevice *dev);
@@ -75,6 +88,13 @@ typedef int (*xen_pt_conf_byte_read)
 
 #define XEN_PCI_INTEL_OPREGION 0xfc
 
+#define XEN_PCI_IGD_DOMAIN 0
+#define XEN_PCI_IGD_BUS 0
+#define XEN_PCI_IGD_DEV 2
+#define XEN_PCI_IGD_FN 0
+#define XEN_PCI_IGD_SLOT_MASK \
+    (1UL << PCI_SLOT(PCI_DEVFN(XEN_PCI_IGD_DEV, XEN_PCI_IGD_FN)))
+
 typedef enum {
     XEN_PT_GRP_TYPE_HARDWIRED = 0,  /* 0 Hardwired reg group */
     XEN_PT_GRP_TYPE_EMU,            /* emul reg group */

hw/xen/xen_pt_stub.c

@@ -20,3 +20,7 @@ void xen_igd_gfx_pt_set(bool value, Error **errp)
         error_setg(errp, "Xen PCI passthrough support not built in");
     }
 }
+
+void xen_igd_reserve_slot(PCIBus *pci_bus)
+{
+}