Merge remote-tracking branch 'remotes/sstabellini/tags/xen-2015-09-10-tag' into staging

xen-2015-09-10

# gpg: Signature made Thu 10 Sep 2015 17:52:08 BST using RSA key ID 70E1AE90
# gpg: Good signature from "Stefano Stabellini <stefano.stabellini@eu.citrix.com>"

* remotes/sstabellini/tags/xen-2015-09-10-tag: (29 commits)
  xen/pt: Don't slurp wholesale the PCI configuration registers
  xen/pt: Check for return values for xen_host_pci_[get|set] in init
  xen/pt: Move bulk of xen_pt_unregister_device in its own routine.
  xen/pt: Make xen_pt_unregister_device idempotent
  xen/pt: Log xen_host_pci_get/set errors in MSI code.
  xen/pt: Log xen_host_pci_get in two init functions
  xen/pt: Remove XenPTReg->data field.
  xen/pt: Check if reg->init function sets the 'data' past the reg->size
  xen/pt: Sync up the dev.config and data values.
  xen/pt: Use xen_host_pci_get_[byte|word] instead of dev.config
  xen/pt: Use XEN_PT_LOG properly to guard against compiler warnings.
  xen/pt/msi: Add the register value when printing logging and error messages
  xen: use errno instead of rc for xc_domain_add_to_physmap
  xen/pt: xen_host_pci_config_read returns -errno, not -1 on failure
  xen/pt: Make xen_pt_msi_set_enable static
  xen/pt: Update comments with proper function name.
  xen/HVM: atomically access pointers in bufioreq handling
  xen-hvm: When using xc_domain_add_to_physmap also include errno when reporting
  xen, gfx passthrough: add opregion mapping
  xen, gfx passthrough: register host bridge specific to passthrough
  ...
Signed-off-by: NPeter Maydell <peter.maydell@linaro.org>

configure

@@ -1881,6 +1881,34 @@ EOF
 #if !defined(HVM_MAX_VCPUS)
 # error HVM_MAX_VCPUS not defined
 #endif
+int main(void) {
+  xc_interface *xc;
+  xs_daemon_open();
+  xc = xc_interface_open(0, 0, 0);
+  xc_hvm_set_mem_type(0, 0, HVMMEM_ram_ro, 0, 0);
+  xc_gnttab_open(NULL, 0);
+  xc_domain_add_to_physmap(0, 0, XENMAPSPACE_gmfn, 0, 0);
+  xc_hvm_inject_msi(xc, 0, 0xf0000000, 0x00000000);
+  xc_hvm_create_ioreq_server(xc, 0, HVM_IOREQSRV_BUFIOREQ_ATOMIC, NULL);
+  xc_reserved_device_memory_map(xc, 0, 0, 0, 0, NULL, 0);
+  return 0;
+}
+EOF
+      compile_prog "" "$xen_libs"
+    then
+    xen_ctrl_version=460
+    xen=yes
+
+  # Xen 4.5
+  elif
+      cat > $TMPC <<EOF &&
+#include <xenctrl.h>
+#include <xenstore.h>
+#include <stdint.h>
+#include <xen/hvm/hvm_info_table.h>
+#if !defined(HVM_MAX_VCPUS)
+# error HVM_MAX_VCPUS not defined
+#endif
 int main(void) {
   xc_interface *xc;
   xs_daemon_open();

hw/core/machine.c

@@ -226,6 +226,20 @@ static void machine_set_usb(Object *obj, bool value, Error **errp)
     ms->usb_disabled = !value;
 }
 
+static bool machine_get_igd_gfx_passthru(Object *obj, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    return ms->igd_gfx_passthru;
+}
+
+static void machine_set_igd_gfx_passthru(Object *obj, bool value, Error **errp)
+{
+    MachineState *ms = MACHINE(obj);
+
+    ms->igd_gfx_passthru = value;
+}
+
 static char *machine_get_firmware(Object *obj, Error **errp)
 {
     MachineState *ms = MACHINE(obj);
@@ -388,6 +402,12 @@ static void machine_initfn(Object *obj)
     object_property_set_description(obj, "usb",
                                     "Set on/off to enable/disable usb",
                                     NULL);
+    object_property_add_bool(obj, "igd-passthru",
+                             machine_get_igd_gfx_passthru,
+                             machine_set_igd_gfx_passthru, NULL);
+    object_property_set_description(obj, "igd-passthru",
+                                    "Set on/off to enable/disable igd passthrou",
+                                    NULL);
     object_property_add_str(obj, "firmware",
                             machine_get_firmware,
                             machine_set_firmware, NULL);

hw/i386/Makefile.objs

@@ -7,6 +7,7 @@ obj-$(CONFIG_XEN) += ../xenpv/ xen/
 
 obj-y += kvmvapic.o
 obj-y += acpi-build.o
+obj-y += pci-assign-load-rom.o
 
 gen-hex-y += hw/i386/acpi-dsdt.hex
 gen-hex-y += hw/i386/q35-acpi-dsdt.hex

hw/i386/kvm/pci-assign.c

@@ -37,6 +37,7 @@
 #include "hw/pci/pci.h"
 #include "hw/pci/msi.h"
 #include "kvm_i386.h"
+#include "hw/pci/pci-assign.h"
 
 #define MSIX_PAGE_SIZE 0x1000
 
@@ -48,17 +49,6 @@
 #define IORESOURCE_PREFETCH 0x00002000  /* No side effects */
 #define IORESOURCE_MEM_64   0x00100000
 
-//#define DEVICE_ASSIGNMENT_DEBUG
-
-#ifdef DEVICE_ASSIGNMENT_DEBUG
-#define DEBUG(fmt, ...)                                       \
-    do {                                                      \
-        fprintf(stderr, "%s: " fmt, __func__ , __VA_ARGS__);  \
-    } while (0)
-#else
-#define DEBUG(fmt, ...)
-#endif
-
 typedef struct PCIRegion {
     int type;           /* Memory or port I/O */
     int valid;
@@ -1896,73 +1886,15 @@ static void assign_register_types(void)
 
 type_init(assign_register_types)
 
-/*
- * Scan the assigned devices for the devices that have an option ROM, and then
- * load the corresponding ROM data to RAM. If an error occurs while loading an
- * option ROM, we just ignore that option ROM and continue with the next one.
- */
 static void assigned_dev_load_option_rom(AssignedDevice *dev)
 {
-    char name[32], rom_file[64];
-    FILE *fp;
-    uint8_t val;
-    struct stat st;
-    void *ptr;
-
-    /* If loading ROM from file, pci handles it */
-    if (dev->dev.romfile || !dev->dev.rom_bar) {
-        return;
-    }
+    int size = 0;
 
-    snprintf(rom_file, sizeof(rom_file),
-             "/sys/bus/pci/devices/%04x:%02x:%02x.%01x/rom",
-             dev->host.domain, dev->host.bus, dev->host.slot,
-             dev->host.function);
+    pci_assign_dev_load_option_rom(&dev->dev, OBJECT(dev), &size,
+                                   dev->host.domain, dev->host.bus,
+                                   dev->host.slot, dev->host.function);
 
-    if (stat(rom_file, &st)) {
-        return;
-    }
-
-    if (access(rom_file, F_OK)) {
-        error_report("pci-assign: Insufficient privileges for %s", rom_file);
-        return;
-    }
-
-    /* Write "1" to the ROM file to enable it */
-    fp = fopen(rom_file, "r+");
-    if (fp == NULL) {
-        return;
+    if (!size) {
+        error_report("pci-assign: Invalid ROM.");
     }
-    val = 1;
-    if (fwrite(&val, 1, 1, fp) != 1) {
-        goto close_rom;
-    }
-    fseek(fp, 0, SEEK_SET);
-
-    snprintf(name, sizeof(name), "%s.rom",
-            object_get_typename(OBJECT(dev)));
-    memory_region_init_ram(&dev->dev.rom, OBJECT(dev), name, st.st_size,
-                           &error_abort);
-    vmstate_register_ram(&dev->dev.rom, &dev->dev.qdev);
-    ptr = memory_region_get_ram_ptr(&dev->dev.rom);
-    memset(ptr, 0xff, st.st_size);
-
-    if (!fread(ptr, 1, st.st_size, fp)) {
-        error_report("pci-assign: Cannot read from host %s", rom_file);
-        error_printf("Device option ROM contents are probably invalid "
-                     "(check dmesg).\nSkip option ROM probe with rombar=0, "
-                     "or load from file with romfile=\n");
-        goto close_rom;
-    }
-
-    pci_register_bar(&dev->dev, PCI_ROM_SLOT, 0, &dev->dev.rom);
-    dev->dev.has_rom = true;
-close_rom:
-    /* Write "0" to disable ROM */
-    fseek(fp, 0, SEEK_SET);
-    val = 0;
-    if (!fwrite(&val, 1, 1, fp)) {
-        DEBUG("%s\n", "Failed to disable pci-sysfs rom file");
-    }
-    fclose(fp);
 }

hw/i386/pc_piix.c

@@ -50,7 +50,8 @@
 #include "cpu.h"
 #include "qemu/error-report.h"
 #ifdef CONFIG_XEN
-#  include <xen/hvm/hvm_info_table.h>
+#include <xen/hvm/hvm_info_table.h>
+#include "hw/xen/xen_pt.h"
 #endif
 #include "migration/migration.h"
 
@@ -76,7 +77,8 @@ static bool has_reserved_memory = true;
 static bool kvmclock_enabled = true;
 
 /* PC hardware initialisation */
-static void pc_init1(MachineState *machine)
+static void pc_init1(MachineState *machine,
+                     const char *host_type, const char *pci_type)
 {
     PCMachineState *pcms = PC_MACHINE(machine);
     MemoryRegion *system_memory = get_system_memory();
@@ -194,7 +196,9 @@ static void pc_init1(MachineState *machine)
     }
 
     if (pci_enabled) {
-        pci_bus = i440fx_init(&i440fx_state, &piix3_devfn, &isa_bus, gsi,
+        pci_bus = i440fx_init(host_type,
+                              pci_type,
+                              &i440fx_state, &piix3_devfn, &isa_bus, gsi,
                               system_memory, system_io, machine->ram_size,
                               pcms->below_4g_mem_size,
                               pcms->above_4g_mem_size,
@@ -412,15 +416,25 @@ static void pc_init_isa(MachineState *machine)
     }
     x86_cpu_compat_kvm_no_autoenable(FEAT_KVM, 1 << KVM_FEATURE_PV_EOI);
     enable_compat_apic_id_mode();
-    pc_init1(machine);
+    pc_init1(machine, TYPE_I440FX_PCI_HOST_BRIDGE, TYPE_I440FX_PCI_DEVICE);
 }
 
 #ifdef CONFIG_XEN
+static void pc_xen_hvm_init_pci(MachineState *machine)
+{
+    const char *pci_type = has_igd_gfx_passthru ?
+                TYPE_IGD_PASSTHROUGH_I440FX_PCI_DEVICE : TYPE_I440FX_PCI_DEVICE;
+
+    pc_init1(machine,
+             TYPE_I440FX_PCI_HOST_BRIDGE,
+             pci_type);
+}
+
 static void pc_xen_hvm_init(MachineState *machine)
 {
     PCIBus *bus;
 
-    pc_init1(machine);
+    pc_xen_hvm_init_pci(machine);
 
     bus = pci_find_primary_bus();
     if (bus != NULL) {
@@ -436,7 +450,8 @@ static void pc_xen_hvm_init(MachineState *machine)
         if (compat) { \
             compat(machine); \
         } \
-        pc_init1(machine); \
+        pc_init1(machine, TYPE_I440FX_PCI_HOST_BRIDGE, \
+                 TYPE_I440FX_PCI_DEVICE); \
     } \
     DEFINE_PC_MACHINE(suffix, name, pc_init_##suffix, optionfn)
 
@@ -878,6 +893,118 @@ static void pc_i440fx_0_10_machine_options(MachineClass *m)
 DEFINE_I440FX_MACHINE(v0_10, "pc-0.10", pc_compat_0_13,
                       pc_i440fx_0_10_machine_options);
 
+typedef struct {
+    uint16_t gpu_device_id;
+    uint16_t pch_device_id;
+    uint8_t pch_revision_id;
+} IGDDeviceIDInfo;
+
+/* In real world different GPU should have different PCH. But actually
+ * the different PCH DIDs likely map to different PCH SKUs. We do the
+ * same thing for the GPU. For PCH, the different SKUs are going to be
+ * all the same silicon design and implementation, just different
+ * features turn on and off with fuses. The SW interfaces should be
+ * consistent across all SKUs in a given family (eg LPT). But just same
+ * features may not be supported.
+ *
+ * Most of these different PCH features probably don't matter to the
+ * Gfx driver, but obviously any difference in display port connections
+ * will so it should be fine with any PCH in case of passthrough.
+ *
+ * So currently use one PCH version, 0x8c4e, to cover all HSW(Haswell)
+ * scenarios, 0x9cc3 for BDW(Broadwell).
+ */
+static const IGDDeviceIDInfo igd_combo_id_infos[] = {
+    /* HSW Classic */
+    {0x0402, 0x8c4e, 0x04}, /* HSWGT1D, HSWD_w7 */
+    {0x0406, 0x8c4e, 0x04}, /* HSWGT1M, HSWM_w7 */
+    {0x0412, 0x8c4e, 0x04}, /* HSWGT2D, HSWD_w7 */
+    {0x0416, 0x8c4e, 0x04}, /* HSWGT2M, HSWM_w7 */
+    {0x041E, 0x8c4e, 0x04}, /* HSWGT15D, HSWD_w7 */
+    /* HSW ULT */
+    {0x0A06, 0x8c4e, 0x04}, /* HSWGT1UT, HSWM_w7 */
+    {0x0A16, 0x8c4e, 0x04}, /* HSWGT2UT, HSWM_w7 */
+    {0x0A26, 0x8c4e, 0x06}, /* HSWGT3UT, HSWM_w7 */
+    {0x0A2E, 0x8c4e, 0x04}, /* HSWGT3UT28W, HSWM_w7 */
+    {0x0A1E, 0x8c4e, 0x04}, /* HSWGT2UX, HSWM_w7 */
+    {0x0A0E, 0x8c4e, 0x04}, /* HSWGT1ULX, HSWM_w7 */
+    /* HSW CRW */
+    {0x0D26, 0x8c4e, 0x04}, /* HSWGT3CW, HSWM_w7 */
+    {0x0D22, 0x8c4e, 0x04}, /* HSWGT3CWDT, HSWD_w7 */
+    /* HSW Server */
+    {0x041A, 0x8c4e, 0x04}, /* HSWSVGT2, HSWD_w7 */
+    /* HSW SRVR */
+    {0x040A, 0x8c4e, 0x04}, /* HSWSVGT1, HSWD_w7 */
+    /* BSW */
+    {0x1606, 0x9cc3, 0x03}, /* BDWULTGT1, BDWM_w7 */
+    {0x1616, 0x9cc3, 0x03}, /* BDWULTGT2, BDWM_w7 */
+    {0x1626, 0x9cc3, 0x03}, /* BDWULTGT3, BDWM_w7 */
+    {0x160E, 0x9cc3, 0x03}, /* BDWULXGT1, BDWM_w7 */
+    {0x161E, 0x9cc3, 0x03}, /* BDWULXGT2, BDWM_w7 */
+    {0x1602, 0x9cc3, 0x03}, /* BDWHALOGT1, BDWM_w7 */
+    {0x1612, 0x9cc3, 0x03}, /* BDWHALOGT2, BDWM_w7 */
+    {0x1622, 0x9cc3, 0x03}, /* BDWHALOGT3, BDWM_w7 */
+    {0x162B, 0x9cc3, 0x03}, /* BDWHALO28W, BDWM_w7 */
+    {0x162A, 0x9cc3, 0x03}, /* BDWGT3WRKS, BDWM_w7 */
+    {0x162D, 0x9cc3, 0x03}, /* BDWGT3SRVR, BDWM_w7 */
+};
+
+static void isa_bridge_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+
+    dc->desc        = "ISA bridge faked to support IGD PT";
+    k->vendor_id    = PCI_VENDOR_ID_INTEL;
+    k->class_id     = PCI_CLASS_BRIDGE_ISA;
+};
+
+static TypeInfo isa_bridge_info = {
+    .name          = "igd-passthrough-isa-bridge",
+    .parent        = TYPE_PCI_DEVICE,
+    .instance_size = sizeof(PCIDevice),
+    .class_init = isa_bridge_class_init,
+};
+
+static void pt_graphics_register_types(void)
+{
+    type_register_static(&isa_bridge_info);
+}
+type_init(pt_graphics_register_types)
+
+void igd_passthrough_isa_bridge_create(PCIBus *bus, uint16_t gpu_dev_id)
+{
+    struct PCIDevice *bridge_dev;
+    int i, num;
+    uint16_t pch_dev_id = 0xffff;
+    uint8_t pch_rev_id;
+
+    num = ARRAY_SIZE(igd_combo_id_infos);
+    for (i = 0; i < num; i++) {
+        if (gpu_dev_id == igd_combo_id_infos[i].gpu_device_id) {
+            pch_dev_id = igd_combo_id_infos[i].pch_device_id;
+            pch_rev_id = igd_combo_id_infos[i].pch_revision_id;
+        }
+    }
+
+    if (pch_dev_id == 0xffff) {
+        return;
+    }
+
+    /* Currently IGD drivers always need to access PCH by 1f.0. */
+    bridge_dev = pci_create_simple(bus, PCI_DEVFN(0x1f, 0),
+                                   "igd-passthrough-isa-bridge");
+
+    /*
+     * Note that vendor id is always PCI_VENDOR_ID_INTEL.
+     */
+    if (!bridge_dev) {
+        fprintf(stderr, "set igd-passthrough-isa-bridge failed!\n");
+        return;
+    }
+    pci_config_set_device_id(bridge_dev->config, pch_dev_id);
+    pci_config_set_revision(bridge_dev->config, pch_rev_id);
+}
 
 static void isapc_machine_options(MachineClass *m)
 {

hw/i386/pci-assign-load-rom.c

+/*
+ * This is splited from hw/i386/kvm/pci-assign.c
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include "hw/hw.h"
+#include "hw/i386/pc.h"
+#include "qemu/error-report.h"
+#include "ui/console.h"
+#include "hw/loader.h"
+#include "monitor/monitor.h"
+#include "qemu/range.h"
+#include "sysemu/sysemu.h"
+#include "hw/pci/pci.h"
+#include "hw/pci/pci-assign.h"
+
+/*
+ * Scan the assigned devices for the devices that have an option ROM, and then
+ * load the corresponding ROM data to RAM. If an error occurs while loading an
+ * option ROM, we just ignore that option ROM and continue with the next one.
+ */
+void *pci_assign_dev_load_option_rom(PCIDevice *dev, struct Object *owner,
+                                     int *size, unsigned int domain,
+                                     unsigned int bus, unsigned int slot,
+                                     unsigned int function)
+{
+    char name[32], rom_file[64];
+    FILE *fp;
+    uint8_t val;
+    struct stat st;
+    void *ptr = NULL;
+
+    /* If loading ROM from file, pci handles it */
+    if (dev->romfile || !dev->rom_bar) {
+        return NULL;
+    }
+
+    snprintf(rom_file, sizeof(rom_file),
+             "/sys/bus/pci/devices/%04x:%02x:%02x.%01x/rom",
+             domain, bus, slot, function);
+
+    if (stat(rom_file, &st)) {
+        return NULL;
+    }
+
+    if (access(rom_file, F_OK)) {
+        error_report("pci-assign: Insufficient privileges for %s", rom_file);
+        return NULL;
+    }
+
+    /* Write "1" to the ROM file to enable it */
+    fp = fopen(rom_file, "r+");
+    if (fp == NULL) {
+        return NULL;
+    }
+    val = 1;
+    if (fwrite(&val, 1, 1, fp) != 1) {
+        goto close_rom;
+    }
+    fseek(fp, 0, SEEK_SET);
+
+    snprintf(name, sizeof(name), "%s.rom", object_get_typename(owner));
+    memory_region_init_ram(&dev->rom, owner, name, st.st_size, &error_abort);
+    vmstate_register_ram(&dev->rom, &dev->qdev);
+    ptr = memory_region_get_ram_ptr(&dev->rom);
+    memset(ptr, 0xff, st.st_size);
+
+    if (!fread(ptr, 1, st.st_size, fp)) {
+        error_report("pci-assign: Cannot read from host %s", rom_file);
+        error_printf("Device option ROM contents are probably invalid "
+                     "(check dmesg).\nSkip option ROM probe with rombar=0, "
+                     "or load from file with romfile=\n");
+        goto close_rom;
+    }
+
+    pci_register_bar(dev, PCI_ROM_SLOT, 0, &dev->rom);
+    dev->has_rom = true;
+    *size = st.st_size;
+close_rom:
+    /* Write "0" to disable ROM */
+    fseek(fp, 0, SEEK_SET);
+    val = 0;
+    if (!fwrite(&val, 1, 1, fp)) {
+        DEBUG("%s\n", "Failed to disable pci-sysfs rom file");
+    }
+    fclose(fp);
+
+    return ptr;
+}

hw/pci-host/piix.c

@@ -40,7 +40,6 @@
  * http://download.intel.com/design/chipsets/datashts/29054901.pdf
  */
 
-#define TYPE_I440FX_PCI_HOST_BRIDGE "i440FX-pcihost"
 #define I440FX_PCI_HOST_BRIDGE(obj) \
     OBJECT_CHECK(I440FXState, (obj), TYPE_I440FX_PCI_HOST_BRIDGE)
 
@@ -95,7 +94,6 @@ typedef struct PIIX3State {
 #define PIIX3_PCI_DEVICE(obj) \
     OBJECT_CHECK(PIIX3State, (obj), TYPE_PIIX3_PCI_DEVICE)
 
-#define TYPE_I440FX_PCI_DEVICE "i440FX"
 #define I440FX_PCI_DEVICE(obj) \
     OBJECT_CHECK(PCII440FXState, (obj), TYPE_I440FX_PCI_DEVICE)
 
@@ -305,7 +303,8 @@ static void i440fx_realize(PCIDevice *dev, Error **errp)
     dev->config[I440FX_SMRAM] = 0x02;
 }
 
-PCIBus *i440fx_init(PCII440FXState **pi440fx_state,
+PCIBus *i440fx_init(const char *host_type, const char *pci_type,
+                    PCII440FXState **pi440fx_state,
                     int *piix3_devfn,
                     ISABus **isa_bus, qemu_irq *pic,
                     MemoryRegion *address_space_mem,
@@ -325,7 +324,7 @@ PCIBus *i440fx_init(PCII440FXState **pi440fx_state,
     unsigned i;
     I440FXState *i440fx;
 
-    dev = qdev_create(NULL, TYPE_I440FX_PCI_HOST_BRIDGE);
+    dev = qdev_create(NULL, host_type);
     s = PCI_HOST_BRIDGE(dev);
     b = pci_bus_new(dev, NULL, pci_address_space,
                     address_space_io, 0, TYPE_PCI_BUS);
@@ -333,7 +332,7 @@ PCIBus *i440fx_init(PCII440FXState **pi440fx_state,
     object_property_add_child(qdev_get_machine(), "i440fx", OBJECT(dev), NULL);
     qdev_init_nofail(dev);
 
-    d = pci_create_simple(b, 0, TYPE_I440FX_PCI_DEVICE);
+    d = pci_create_simple(b, 0, pci_type);
     *pi440fx_state = I440FX_PCI_DEVICE(d);
     f = *pi440fx_state;
     f->system_memory = address_space_mem;
@@ -740,6 +739,90 @@ static const TypeInfo i440fx_info = {
     .class_init    = i440fx_class_init,
 };
 
+/* IGD Passthrough Host Bridge. */
+typedef struct {
+    uint8_t offset;
+    uint8_t len;
+} IGDHostInfo;
+
+/* Here we just expose minimal host bridge offset subset. */
+static const IGDHostInfo igd_host_bridge_infos[] = {
+    {0x08, 2},  /* revision id */
+    {0x2c, 2},  /* sybsystem vendor id */
+    {0x2e, 2},  /* sybsystem id */
+    {0x50, 2},  /* SNB: processor graphics control register */
+    {0x52, 2},  /* processor graphics control register */
+    {0xa4, 4},  /* SNB: graphics base of stolen memory */
+    {0xa8, 4},  /* SNB: base of GTT stolen memory */
+};
+
+static int host_pci_config_read(int pos, int len, uint32_t val)
+{
+    char path[PATH_MAX];
+    int config_fd;
+    ssize_t size = sizeof(path);
+    /* Access real host bridge. */
+    int rc = snprintf(path, size, "/sys/bus/pci/devices/%04x:%02x:%02x.%d/%s",
+                      0, 0, 0, 0, "config");
+
+    if (rc >= size || rc < 0) {
+        return -ENODEV;
+    }
+
+    config_fd = open(path, O_RDWR);
+    if (config_fd < 0) {
+        return -ENODEV;
+    }
+
+    if (lseek(config_fd, pos, SEEK_SET) != pos) {
+        return -errno;
+    }
+    do {
+        rc = read(config_fd, (uint8_t *)&val, len);
+    } while (rc < 0 && (errno == EINTR || errno == EAGAIN));
+    if (rc != len) {
+        return -errno;
+    }
+
+    return 0;
+}
+
+static int igd_pt_i440fx_initfn(struct PCIDevice *pci_dev)
+{
+    uint32_t val = 0;
+    int rc, i, num;
+    int pos, len;
+
+    num = ARRAY_SIZE(igd_host_bridge_infos);
+    for (i = 0; i < num; i++) {
+        pos = igd_host_bridge_infos[i].offset;
+        len = igd_host_bridge_infos[i].len;
+        rc = host_pci_config_read(pos, len, val);
+        if (rc) {
+            return -ENODEV;
+        }
+        pci_default_write_config(pci_dev, pos, val, len);
+    }
+
+    return 0;
+}
+
+static void igd_passthrough_i440fx_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+
+    k->init = igd_pt_i440fx_initfn;
+    dc->desc = "IGD Passthrough Host bridge";
+}
+
+static const TypeInfo igd_passthrough_i440fx_info = {
+    .name          = TYPE_IGD_PASSTHROUGH_I440FX_PCI_DEVICE,
+    .parent        = TYPE_I440FX_PCI_DEVICE,
+    .instance_size = sizeof(PCII440FXState),
+    .class_init    = igd_passthrough_i440fx_class_init,
+};
+
 static const char *i440fx_pcihost_root_bus_path(PCIHostState *host_bridge,
                                                 PCIBus *rootbus)
 {
@@ -781,6 +864,7 @@ static const TypeInfo i440fx_pcihost_info = {
 static void i440fx_register_types(void)
 {
     type_register_static(&i440fx_info);
+    type_register_static(&igd_passthrough_i440fx_info);
     type_register_static(&piix3_pci_type_info);
     type_register_static(&piix3_info);
     type_register_static(&piix3_xen_info);

hw/xen/Makefile.objs

@@ -3,3 +3,4 @@ common-obj-$(CONFIG_XEN_BACKEND) += xen_backend.o xen_devconfig.o
 
 obj-$(CONFIG_XEN_PCI_PASSTHROUGH) += xen-host-pci-device.o
 obj-$(CONFIG_XEN_PCI_PASSTHROUGH) += xen_pt.o xen_pt_config_init.o xen_pt_msi.o
+obj-$(CONFIG_XEN_PCI_PASSTHROUGH) += xen_pt.o xen_pt_config_init.o xen_pt_msi.o xen_pt_graphics.o

hw/xen/xen-host-pci-device.c

@@ -376,6 +376,11 @@ int xen_host_pci_device_get(XenHostPCIDevice *d, uint16_t domain,
         goto error;
     }
     d->irq = v;
+    rc = xen_host_pci_get_hex_value(d, "class", &v);
+    if (rc) {
+        goto error;
+    }
+    d->class_code = v;
     d->is_virtfn = xen_host_pci_dev_is_virtfn(d);
 
     return 0;
@@ -387,6 +392,11 @@ error:
     return rc;
 }
 
+bool xen_host_pci_device_closed(XenHostPCIDevice *d)
+{
+    return d->config_fd == -1;
+}
+
 void xen_host_pci_device_put(XenHostPCIDevice *d)
 {
     if (d->config_fd >= 0) {

hw/xen/xen-host-pci-device.h

@@ -25,6 +25,7 @@ typedef struct XenHostPCIDevice {
 
     uint16_t vendor_id;
     uint16_t device_id;
+    uint32_t class_code;
     int irq;
 
     XenHostPCIIORegion io_regions[PCI_NUM_REGIONS - 1];
@@ -38,6 +39,7 @@ typedef struct XenHostPCIDevice {
 int xen_host_pci_device_get(XenHostPCIDevice *d, uint16_t domain,
                             uint8_t bus, uint8_t dev, uint8_t func);
 void xen_host_pci_device_put(XenHostPCIDevice *pci_dev);
+bool xen_host_pci_device_closed(XenHostPCIDevice *d);
 
 int xen_host_pci_get_byte(XenHostPCIDevice *d, int pos, uint8_t *p);
 int xen_host_pci_get_word(XenHostPCIDevice *d, int pos, uint16_t *p);

hw/xen/xen_pt.c

@@ -56,6 +56,7 @@
 
 #include "hw/pci/pci.h"
 #include "hw/xen/xen.h"
+#include "hw/i386/pc.h"
 #include "hw/xen/xen_backend.h"
 #include "xen_pt.h"
 #include "qemu/range.h"
@@ -378,7 +379,7 @@ static void xen_pt_pci_write_config(PCIDevice *d, uint32_t addr,
         }
     }
 
-    /* need to shift back before passing them to xen_host_pci_device */
+    /* need to shift back before passing them to xen_host_pci_set_block. */
     val >>= (addr & 3) << 3;
 
     memory_region_transaction_commit();
@@ -406,7 +407,7 @@ out:
                                     (uint8_t *)&val + index, len);
 
         if (rc < 0) {
-            XEN_PT_ERR(d, "pci_write_block failed. return value: %d.\n", rc);
+            XEN_PT_ERR(d, "xen_host_pci_set_block failed. return value: %d.\n", rc);
         }
     }
 }
@@ -502,6 +503,7 @@ static int xen_pt_register_regions(XenPCIPassthroughState *s, uint16_t *cmd)
                    d->rom.size, d->rom.base_addr);
     }
 
+    xen_pt_register_vga_regions(d);
     return 0;
 }
 
@@ -683,13 +685,86 @@ static const MemoryListener xen_pt_io_listener = {
     .priority = 10,
 };
 
+static void
+xen_igd_passthrough_isa_bridge_create(XenPCIPassthroughState *s,
+                                      XenHostPCIDevice *dev)
+{
+    uint16_t gpu_dev_id;
+    PCIDevice *d = &s->dev;
+
+    gpu_dev_id = dev->device_id;
+    igd_passthrough_isa_bridge_create(d->bus, gpu_dev_id);
+}
+
+/* destroy. */
+static void xen_pt_destroy(PCIDevice *d) {
+
+    XenPCIPassthroughState *s = XEN_PT_DEVICE(d);
+    XenHostPCIDevice *host_dev = &s->real_device;
+    uint8_t machine_irq = s->machine_irq;
+    uint8_t intx;
+    int rc;
+
+    if (machine_irq && !xen_host_pci_device_closed(&s->real_device)) {
+        intx = xen_pt_pci_intx(s);
+        rc = xc_domain_unbind_pt_irq(xen_xc, xen_domid, machine_irq,
+                                     PT_IRQ_TYPE_PCI,
+                                     pci_bus_num(d->bus),
+                                     PCI_SLOT(s->dev.devfn),
+                                     intx,
+                                     0 /* isa_irq */);
+        if (rc < 0) {
+            XEN_PT_ERR(d, "unbinding of interrupt INT%c failed."
+                       " (machine irq: %i, err: %d)"
+                       " But bravely continuing on..\n",
+                       'a' + intx, machine_irq, errno);
+        }
+    }
+
+    /* N.B. xen_pt_config_delete takes care of freeing them. */
+    if (s->msi) {
+        xen_pt_msi_disable(s);
+    }
+    if (s->msix) {
+        xen_pt_msix_disable(s);
+    }
+
+    if (machine_irq) {
+        xen_pt_mapped_machine_irq[machine_irq]--;
+
+        if (xen_pt_mapped_machine_irq[machine_irq] == 0) {
+            rc = xc_physdev_unmap_pirq(xen_xc, xen_domid, machine_irq);
+
+            if (rc < 0) {
+                XEN_PT_ERR(d, "unmapping of interrupt %i failed. (err: %d)"
+                           " But bravely continuing on..\n",
+                           machine_irq, errno);
+            }
+        }
+        s->machine_irq = 0;
+    }
+
+    /* delete all emulated config registers */
+    xen_pt_config_delete(s);
+
+    xen_pt_unregister_vga_regions(host_dev);
+
+    if (s->listener_set) {
+        memory_listener_unregister(&s->memory_listener);
+        memory_listener_unregister(&s->io_listener);
+        s->listener_set = false;
+    }
+    if (!xen_host_pci_device_closed(&s->real_device)) {
+        xen_host_pci_device_put(&s->real_device);
+    }
+}
 /* init */
 
 static int xen_pt_initfn(PCIDevice *d)
 {
     XenPCIPassthroughState *s = XEN_PT_DEVICE(d);
     int rc = 0;
-    uint8_t machine_irq = 0;
+    uint8_t machine_irq = 0, scratch;
     uint16_t cmd = 0;
     int pirq = XEN_PT_UNASSIGNED_PIRQ;
 
@@ -715,27 +790,48 @@ static int xen_pt_initfn(PCIDevice *d)
     }
 
     /* Initialize virtualized PCI configuration (Extended 256 Bytes) */
-    if (xen_host_pci_get_block(&s->real_device, 0, d->config,
-                               PCI_CONFIG_SPACE_SIZE) == -1) {
-        xen_host_pci_device_put(&s->real_device);
-        return -1;
-    }
+    memset(d->config, 0, PCI_CONFIG_SPACE_SIZE);
 
     s->memory_listener = xen_pt_memory_listener;
     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 (!is_igd_vga_passthrough(&s->real_device)) {
+            XEN_PT_ERR(d, "Need to enable igd-passthru if you're trying"
+                       " to passthrough IGD GFX.\n");
+            xen_host_pci_device_put(&s->real_device);
+            return -1;
+        }
+
+        if (xen_pt_setup_vga(s, &s->real_device) < 0) {
+            XEN_PT_ERR(d, "Setup VGA BIOS of passthrough GFX failed!\n");
+            xen_host_pci_device_put(&s->real_device);
+            return -1;
+        }
+
+        /* Register ISA bridge for passthrough GFX. */
+        xen_igd_passthrough_isa_bridge_create(s, &s->real_device);
+    }
+
     /* Handle real device's MMIO/PIO BARs */
     xen_pt_register_regions(s, &cmd);
 
     /* reinitialize each config register to be emulated */
-    if (xen_pt_config_init(s)) {
+    rc = xen_pt_config_init(s);
+    if (rc) {
         XEN_PT_ERR(d, "PCI Config space initialisation failed.\n");
-        xen_host_pci_device_put(&s->real_device);
-        return -1;
+        goto err_out;
     }
 
     /* Bind interrupt */
-    if (!s->dev.config[PCI_INTERRUPT_PIN]) {
+    rc = xen_host_pci_get_byte(&s->real_device, PCI_INTERRUPT_PIN, &scratch);
+    if (rc) {
+        XEN_PT_ERR(d, "Failed to read PCI_INTERRUPT_PIN! (rc:%d)\n", rc);
+        goto err_out;
+    }
+    if (!scratch) {
         XEN_PT_LOG(d, "no pin interrupt\n");
         goto out;
     }
@@ -785,69 +881,41 @@ static int xen_pt_initfn(PCIDevice *d)
 
 out:
     if (cmd) {
-        xen_host_pci_set_word(&s->real_device, PCI_COMMAND,
-                              pci_get_word(d->config + PCI_COMMAND) | cmd);
+        uint16_t val;
+
+        rc = xen_host_pci_get_word(&s->real_device, PCI_COMMAND, &val);
+        if (rc) {
+            XEN_PT_ERR(d, "Failed to read PCI_COMMAND! (rc: %d)\n", rc);
+            goto err_out;
+        } else {
+            val |= cmd;
+            rc = xen_host_pci_set_word(&s->real_device, PCI_COMMAND, val);
+            if (rc) {
+                XEN_PT_ERR(d, "Failed to write PCI_COMMAND val=0x%x!(rc: %d)\n",
+                           val, rc);
+                goto err_out;
+            }
+        }
     }
 
     memory_listener_register(&s->memory_listener, &s->dev.bus_master_as);
     memory_listener_register(&s->io_listener, &address_space_io);
+    s->listener_set = true;
     XEN_PT_LOG(d,
                "Real physical device %02x:%02x.%d registered successfully!\n",
                s->hostaddr.bus, s->hostaddr.slot, s->hostaddr.function);
 
     return 0;
+
+err_out:
+    xen_pt_destroy(d);
+    assert(rc);
+    return rc;
 }
 
 static void xen_pt_unregister_device(PCIDevice *d)
 {
-    XenPCIPassthroughState *s = XEN_PT_DEVICE(d);
-    uint8_t machine_irq = s->machine_irq;
-    uint8_t intx = xen_pt_pci_intx(s);
-    int rc;
-
-    if (machine_irq) {
-        rc = xc_domain_unbind_pt_irq(xen_xc, xen_domid, machine_irq,
-                                     PT_IRQ_TYPE_PCI,
-                                     pci_bus_num(d->bus),
-                                     PCI_SLOT(s->dev.devfn),
-                                     intx,
-                                     0 /* isa_irq */);
-        if (rc < 0) {
-            XEN_PT_ERR(d, "unbinding of interrupt INT%c failed."
-                       " (machine irq: %i, err: %d)"
-                       " But bravely continuing on..\n",
-                       'a' + intx, machine_irq, errno);
-        }
-    }
-
-    if (s->msi) {
-        xen_pt_msi_disable(s);
-    }
-    if (s->msix) {
-        xen_pt_msix_disable(s);
-    }
-
-    if (machine_irq) {
-        xen_pt_mapped_machine_irq[machine_irq]--;
-
-        if (xen_pt_mapped_machine_irq[machine_irq] == 0) {
-            rc = xc_physdev_unmap_pirq(xen_xc, xen_domid, machine_irq);
-
-            if (rc < 0) {
-                XEN_PT_ERR(d, "unmapping of interrupt %i failed. (err: %d)"
-                           " But bravely continuing on..\n",
-                           machine_irq, errno);
-            }
-        }
-    }
-
-    /* delete all emulated config registers */
-    xen_pt_config_delete(s);
-
-    memory_listener_unregister(&s->memory_listener);
-    memory_listener_unregister(&s->io_listener);
-
-    xen_host_pci_device_put(&s->real_device);
+    xen_pt_destroy(d);
 }
 
 static Property xen_pci_passthrough_properties[] = {

hw/xen/xen_pt.h

@@ -40,6 +40,9 @@ typedef struct XenPCIPassthroughState XenPCIPassthroughState;
 #define XEN_PT_DEVICE(obj) \
     OBJECT_CHECK(XenPCIPassthroughState, (obj), TYPE_XEN_PT_DEVICE)
 
+uint32_t igd_read_opregion(XenPCIPassthroughState *s);
+void igd_write_opregion(XenPCIPassthroughState *s, uint32_t val);
+
 /* function type for config reg */
 typedef int (*xen_pt_conf_reg_init)
     (XenPCIPassthroughState *, XenPTRegInfo *, uint32_t real_offset,
@@ -66,8 +69,9 @@ typedef int (*xen_pt_conf_byte_read)
 #define XEN_PT_BAR_ALLF 0xFFFFFFFF
 #define XEN_PT_BAR_UNMAPPED (-1)
 
-#define PCI_CAP_MAX 48
+#define XEN_PCI_CAP_MAX 48
 
+#define XEN_PCI_INTEL_OPREGION 0xfc
 
 typedef enum {
     XEN_PT_GRP_TYPE_HARDWIRED = 0,  /* 0 Hardwired reg group */
@@ -134,7 +138,11 @@ struct XenPTRegInfo {
 struct XenPTReg {
     QLIST_ENTRY(XenPTReg) entries;
     XenPTRegInfo *reg;
-    uint32_t data; /* emulated value */
+    union {
+        uint8_t *byte;
+        uint16_t *half_word;
+        uint32_t *word;
+    } ptr; /* pointer to dev.config. */
 };
 
 typedef const struct XenPTRegGroupInfo XenPTRegGroupInfo;
@@ -217,6 +225,7 @@ struct XenPCIPassthroughState {
 
     MemoryListener memory_listener;
     MemoryListener io_listener;
+    bool listener_set;
 };
 
 int xen_pt_config_init(XenPCIPassthroughState *s);
@@ -282,6 +291,7 @@ static inline uint8_t xen_pt_pci_intx(XenPCIPassthroughState *s)
                    " value=%i, acceptable range is 1 - 4\n", r_val);
         r_val = 0;
     } else {
+        /* Note that if s.real_device.config_fd is closed we make 0xff. */
         r_val -= 1;
     }
 
@@ -289,7 +299,6 @@ static inline uint8_t xen_pt_pci_intx(XenPCIPassthroughState *s)
 }
 
 /* MSI/MSI-X */
-int xen_pt_msi_set_enable(XenPCIPassthroughState *s, bool en);
 int xen_pt_msi_setup(XenPCIPassthroughState *s);
 int xen_pt_msi_update(XenPCIPassthroughState *d);
 void xen_pt_msi_disable(XenPCIPassthroughState *s);
@@ -305,5 +314,18 @@ static inline bool xen_pt_has_msix_mapping(XenPCIPassthroughState *s, int bar)
     return s->msix && s->msix->bar_index == bar;
 }
 
-
+extern void *pci_assign_dev_load_option_rom(PCIDevice *dev,
+                                            struct Object *owner, int *size,
+                                            unsigned int domain,
+                                            unsigned int bus, unsigned int slot,
+                                            unsigned int function);
+extern bool has_igd_gfx_passthru;
+static inline bool is_igd_vga_passthrough(XenHostPCIDevice *dev)
+{
+    return (has_igd_gfx_passthru
+            && ((dev->class_code >> 0x8) == PCI_CLASS_DISPLAY_VGA));
+}
+int xen_pt_register_vga_regions(XenHostPCIDevice *dev);
+int xen_pt_unregister_vga_regions(XenHostPCIDevice *dev);
+int xen_pt_setup_vga(XenPCIPassthroughState *s, XenHostPCIDevice *dev);
 #endif /* !XEN_PT_H */

hw/xen/xen_pt_graphics.c

+/*
+ * graphics passthrough
+ */
+#include "xen_pt.h"
+#include "xen-host-pci-device.h"
+#include "hw/xen/xen_backend.h"
+
+static unsigned long igd_guest_opregion;
+static unsigned long igd_host_opregion;
+
+#define XEN_PCI_INTEL_OPREGION_MASK 0xfff
+
+typedef struct VGARegion {
+    int type;           /* Memory or port I/O */
+    uint64_t guest_base_addr;
+    uint64_t machine_base_addr;
+    uint64_t size;    /* size of the region */
+    int rc;
+} VGARegion;
+
+#define IORESOURCE_IO           0x00000100
+#define IORESOURCE_MEM          0x00000200
+
+static struct VGARegion vga_args[] = {
+    {
+        .type = IORESOURCE_IO,
+        .guest_base_addr = 0x3B0,
+        .machine_base_addr = 0x3B0,
+        .size = 0xC,
+        .rc = -1,
+    },
+    {
+        .type = IORESOURCE_IO,
+        .guest_base_addr = 0x3C0,
+        .machine_base_addr = 0x3C0,
+        .size = 0x20,
+        .rc = -1,
+    },
+    {
+        .type = IORESOURCE_MEM,
+        .guest_base_addr = 0xa0000 >> XC_PAGE_SHIFT,
+        .machine_base_addr = 0xa0000 >> XC_PAGE_SHIFT,
+        .size = 0x20,
+        .rc = -1,
+    },
+};
+
+/*
+ * register VGA resources for the domain with assigned gfx
+ */
+int xen_pt_register_vga_regions(XenHostPCIDevice *dev)
+{
+    int i = 0;
+
+    if (!is_igd_vga_passthrough(dev)) {
+        return 0;
+    }
+
+    for (i = 0 ; i < ARRAY_SIZE(vga_args); i++) {
+        if (vga_args[i].type == IORESOURCE_IO) {
+            vga_args[i].rc = xc_domain_ioport_mapping(xen_xc, xen_domid,
+                            vga_args[i].guest_base_addr,
+                            vga_args[i].machine_base_addr,
+                            vga_args[i].size, DPCI_ADD_MAPPING);
+        } else {
+            vga_args[i].rc = xc_domain_memory_mapping(xen_xc, xen_domid,
+                            vga_args[i].guest_base_addr,
+                            vga_args[i].machine_base_addr,
+                            vga_args[i].size, DPCI_ADD_MAPPING);
+        }
+
+        if (vga_args[i].rc) {
+            XEN_PT_ERR(NULL, "VGA %s mapping failed! (rc: %i)\n",
+                    vga_args[i].type == IORESOURCE_IO ? "ioport" : "memory",
+                    vga_args[i].rc);
+            return vga_args[i].rc;
+        }
+    }
+
+    return 0;
+}
+
+/*
+ * unregister VGA resources for the domain with assigned gfx
+ */
+int xen_pt_unregister_vga_regions(XenHostPCIDevice *dev)
+{
+    int i = 0;
+    int ret = 0;
+
+    if (!is_igd_vga_passthrough(dev)) {
+        return 0;
+    }
+
+    for (i = 0 ; i < ARRAY_SIZE(vga_args); i++) {
+        if (vga_args[i].type == IORESOURCE_IO) {
+            vga_args[i].rc = xc_domain_ioport_mapping(xen_xc, xen_domid,
+                            vga_args[i].guest_base_addr,
+                            vga_args[i].machine_base_addr,
+                            vga_args[i].size, DPCI_REMOVE_MAPPING);
+        } else {
+            vga_args[i].rc = xc_domain_memory_mapping(xen_xc, xen_domid,
+                            vga_args[i].guest_base_addr,
+                            vga_args[i].machine_base_addr,
+                            vga_args[i].size, DPCI_REMOVE_MAPPING);
+        }
+
+        if (vga_args[i].rc) {
+            XEN_PT_ERR(NULL, "VGA %s unmapping failed! (rc: %i)\n",
+                    vga_args[i].type == IORESOURCE_IO ? "ioport" : "memory",
+                    vga_args[i].rc);
+            return vga_args[i].rc;
+        }
+    }
+
+    if (igd_guest_opregion) {
+        ret = xc_domain_memory_mapping(xen_xc, xen_domid,
+                (unsigned long)(igd_guest_opregion >> XC_PAGE_SHIFT),
+                (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT),
+                3,
+                DPCI_REMOVE_MAPPING);
+        if (ret) {
+            return ret;
+        }
+    }
+
+    return 0;
+}
+
+static void *get_vgabios(XenPCIPassthroughState *s, int *size,
+                       XenHostPCIDevice *dev)
+{
+    return pci_assign_dev_load_option_rom(&s->dev, OBJECT(&s->dev), size,
+                                          dev->domain, dev->bus,
+                                          dev->dev, dev->func);
+}
+
+/* Refer to Seabios. */
+struct rom_header {
+    uint16_t signature;
+    uint8_t size;
+    uint8_t initVector[4];
+    uint8_t reserved[17];
+    uint16_t pcioffset;
+    uint16_t pnpoffset;
+} __attribute__((packed));
+
+struct pci_data {
+    uint32_t signature;
+    uint16_t vendor;
+    uint16_t device;
+    uint16_t vitaldata;
+    uint16_t dlen;
+    uint8_t drevision;
+    uint8_t class_lo;
+    uint16_t class_hi;
+    uint16_t ilen;
+    uint16_t irevision;
+    uint8_t type;
+    uint8_t indicator;
+    uint16_t reserved;
+} __attribute__((packed));
+
+int xen_pt_setup_vga(XenPCIPassthroughState *s, XenHostPCIDevice *dev)
+{
+    unsigned char *bios = NULL;
+    struct rom_header *rom;
+    int bios_size;
+    char *c = NULL;
+    char checksum = 0;
+    uint32_t len = 0;
+    struct pci_data *pd = NULL;
+
+    if (!is_igd_vga_passthrough(dev)) {
+        return -1;
+    }
+
+    bios = get_vgabios(s, &bios_size, dev);
+    if (!bios) {
+        XEN_PT_ERR(&s->dev, "VGA: Can't getting VBIOS!\n");
+        return -1;
+    }
+
+    /* Currently we fixed this address as a primary. */
+    rom = (struct rom_header *)bios;
+    pd = (void *)(bios + (unsigned char)rom->pcioffset);
+
+    /* We may need to fixup Device Identification. */
+    if (pd->device != s->real_device.device_id) {
+        pd->device = s->real_device.device_id;
+
+        len = rom->size * 512;
+        /* Then adjust the bios checksum */
+        for (c = (char *)bios; c < ((char *)bios + len); c++) {
+            checksum += *c;
+        }
+        if (checksum) {
+            bios[len - 1] -= checksum;
+            XEN_PT_LOG(&s->dev, "vga bios checksum is adjusted %x!\n",
+                       checksum);
+        }
+    }
+
+    /* Currently we fixed this address as a primary for legacy BIOS. */
+    cpu_physical_memory_rw(0xc0000, bios, bios_size, 1);
+    return 0;
+}
+
+uint32_t igd_read_opregion(XenPCIPassthroughState *s)
+{
+    uint32_t val = 0;
+
+    if (!igd_guest_opregion) {
+        return val;
+    }
+
+    val = igd_guest_opregion;
+
+    XEN_PT_LOG(&s->dev, "Read opregion val=%x\n", val);
+    return val;
+}
+
+#define XEN_PCI_INTEL_OPREGION_PAGES 0x3
+#define XEN_PCI_INTEL_OPREGION_ENABLE_ACCESSED 0x1
+void igd_write_opregion(XenPCIPassthroughState *s, uint32_t val)
+{
+    int ret;
+
+    if (igd_guest_opregion) {
+        XEN_PT_LOG(&s->dev, "opregion register already been set, ignoring %x\n",
+                   val);
+        return;
+    }
+
+    /* We just work with LE. */
+    xen_host_pci_get_block(&s->real_device, XEN_PCI_INTEL_OPREGION,
+            (uint8_t *)&igd_host_opregion, 4);
+    igd_guest_opregion = (unsigned long)(val & ~XEN_PCI_INTEL_OPREGION_MASK)
+                            | (igd_host_opregion & XEN_PCI_INTEL_OPREGION_MASK);
+
+    ret = xc_domain_iomem_permission(xen_xc, xen_domid,
+            (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT),
+            XEN_PCI_INTEL_OPREGION_PAGES,
+            XEN_PCI_INTEL_OPREGION_ENABLE_ACCESSED);
+
+    if (ret) {
+        XEN_PT_ERR(&s->dev, "[%d]:Can't enable to access IGD host opregion:"
+                    " 0x%lx.\n", ret,
+                    (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT)),
+        igd_guest_opregion = 0;
+        return;
+    }
+
+    ret = xc_domain_memory_mapping(xen_xc, xen_domid,
+            (unsigned long)(igd_guest_opregion >> XC_PAGE_SHIFT),
+            (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT),
+            XEN_PCI_INTEL_OPREGION_PAGES,
+            DPCI_ADD_MAPPING);
+
+    if (ret) {
+        XEN_PT_ERR(&s->dev, "[%d]:Can't map IGD host opregion:0x%lx to"
+                    " guest opregion:0x%lx.\n", ret,
+                    (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT),
+                    (unsigned long)(igd_guest_opregion >> XC_PAGE_SHIFT));
+        igd_guest_opregion = 0;
+        return;
+    }
+
+    XEN_PT_LOG(&s->dev, "Map OpRegion: 0x%lx -> 0x%lx\n",
+                    (unsigned long)(igd_host_opregion >> XC_PAGE_SHIFT),
+                    (unsigned long)(igd_guest_opregion >> XC_PAGE_SHIFT));
+}

hw/xen/xen_pt_msi.c

@@ -75,19 +75,29 @@ static int msi_msix_enable(XenPCIPassthroughState *s,
                            bool enable)
 {
     uint16_t val = 0;
+    int rc;
 
     if (!address) {
         return -1;
     }
 
-    xen_host_pci_get_word(&s->real_device, address, &val);
+    rc = xen_host_pci_get_word(&s->real_device, address, &val);
+    if (rc) {
+        XEN_PT_ERR(&s->dev, "Failed to read MSI/MSI-X register (0x%x), rc:%d\n",
+                   address, rc);
+        return rc;
+    }
     if (enable) {
         val |= flag;
     } else {
         val &= ~flag;
     }
-    xen_host_pci_set_word(&s->real_device, address, val);
-    return 0;
+    rc = xen_host_pci_set_word(&s->real_device, address, val);
+    if (rc) {
+        XEN_PT_ERR(&s->dev, "Failed to write MSI/MSI-X register (0x%x), rc:%d\n",
+                   address, rc);
+    }
+    return rc;
 }
 
 static int msi_msix_setup(XenPCIPassthroughState *s,
@@ -220,7 +230,7 @@ static int msi_msix_disable(XenPCIPassthroughState *s,
  * MSI virtualization functions
  */
 
-int xen_pt_msi_set_enable(XenPCIPassthroughState *s, bool enable)
+static int xen_pt_msi_set_enable(XenPCIPassthroughState *s, bool enable)
 {
     XEN_PT_LOG(&s->dev, "%s MSI.\n", enable ? "enabling" : "disabling");
 
@@ -276,7 +286,7 @@ void xen_pt_msi_disable(XenPCIPassthroughState *s)
         return;
     }
 
-    xen_pt_msi_set_enable(s, false);
+    (void)xen_pt_msi_set_enable(s, false);
 
     msi_msix_disable(s, msi_addr64(msi), msi->data, msi->pirq, false,
                      msi->initialized);

include/hw/boards.h

@@ -137,6 +137,7 @@ struct MachineState {
     bool mem_merge;
     bool usb;
     bool usb_disabled;
+    bool igd_gfx_passthru;
     char *firmware;
     bool iommu;
     bool suppress_vmdesc;

include/hw/i386/pc.h

@@ -220,7 +220,13 @@ extern int no_hpet;
 struct PCII440FXState;
 typedef struct PCII440FXState PCII440FXState;
 
-PCIBus *i440fx_init(PCII440FXState **pi440fx_state, int *piix_devfn,
+#define TYPE_I440FX_PCI_HOST_BRIDGE "i440FX-pcihost"
+#define TYPE_I440FX_PCI_DEVICE "i440FX"
+
+#define TYPE_IGD_PASSTHROUGH_I440FX_PCI_DEVICE "igd-passthrough-i440FX"
+
+PCIBus *i440fx_init(const char *host_type, const char *pci_type,
+                    PCII440FXState **pi440fx_state, int *piix_devfn,
                     ISABus **isa_bus, qemu_irq *pic,
                     MemoryRegion *address_space_mem,
                     MemoryRegion *address_space_io,
@@ -721,4 +727,5 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *);
     (m)->compat_props = props; \
 } while (0)
 
+extern void igd_passthrough_isa_bridge_create(PCIBus *bus, uint16_t gpu_dev_id);
 #endif

include/hw/pci/pci-assign.h

+/*
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Just split from hw/i386/kvm/pci-assign.c.
+ */
+#ifndef PCI_ASSIGN_H
+#define PCI_ASSIGN_H
+
+#include "hw/pci/pci.h"
+
+//#define DEVICE_ASSIGNMENT_DEBUG
+
+#ifdef DEVICE_ASSIGNMENT_DEBUG
+#define DEBUG(fmt, ...)                                       \
+    do {                                                      \
+        fprintf(stderr, "%s: " fmt, __func__ , __VA_ARGS__);  \
+    } while (0)
+#else
+#define DEBUG(fmt, ...)
+#endif
+
+void *pci_assign_dev_load_option_rom(PCIDevice *dev, struct Object *owner,
+                                     int *size, unsigned int domain,
+                                     unsigned int bus, unsigned int slot,
+                                     unsigned int function);
+#endif /* PCI_ASSIGN_H */

include/hw/xen/xen_common.h

@@ -186,6 +186,15 @@ static inline int xen_get_vmport_regs_pfn(XenXC xc, domid_t dom,
 }
 #endif
 
+/* Xen before 4.6 */
+#if CONFIG_XEN_CTRL_INTERFACE_VERSION < 460
+
+#ifndef HVM_IOREQSRV_BUFIOREQ_ATOMIC
+#define HVM_IOREQSRV_BUFIOREQ_ATOMIC 2
+#endif
+
+#endif
+
 /* Xen before 4.5 */
 #if CONFIG_XEN_CTRL_INTERFACE_VERSION < 450
 
@@ -370,7 +379,8 @@ static inline void xen_unmap_pcidev(XenXC xc, domid_t dom,
 static inline int xen_create_ioreq_server(XenXC xc, domid_t dom,
                                           ioservid_t *ioservid)
 {
-    int rc = xc_hvm_create_ioreq_server(xc, dom, 1, ioservid);
+    int rc = xc_hvm_create_ioreq_server(xc, dom, HVM_IOREQSRV_BUFIOREQ_ATOMIC,
+                                        ioservid);
 
     if (rc == 0) {
         trace_xen_ioreq_server_create(*ioservid);
@@ -407,4 +417,26 @@ static inline int xen_set_ioreq_server_state(XenXC xc, domid_t dom,
 
 #endif
 
+#if CONFIG_XEN_CTRL_INTERFACE_VERSION < 460
+static inline int xen_xc_domain_add_to_physmap(XenXC xch, uint32_t domid,
+                                               unsigned int space,
+                                               unsigned long idx,
+                                               xen_pfn_t gpfn)
+{
+    return xc_domain_add_to_physmap(xch, domid, space, idx, gpfn);
+}
+#else
+static inline int xen_xc_domain_add_to_physmap(XenXC xch, uint32_t domid,
+                                               unsigned int space,
+                                               unsigned long idx,
+                                               xen_pfn_t gpfn)
+{
+    /* In Xen 4.6 rc is -1 and errno contains the error value. */
+    int rc = xc_domain_add_to_physmap(xch, domid, space, idx, gpfn);
+    if (rc == -1)
+        return errno;
+    return rc;
+}
+#endif
+
 #endif /* QEMU_HW_XEN_COMMON_H */

qemu-options.hx

@@ -38,6 +38,7 @@ DEF("machine", HAS_ARG, QEMU_OPTION_machine, \
     "                dump-guest-core=on|off include guest memory in a core dump (default=on)\n"
     "                mem-merge=on|off controls memory merge support (default: on)\n"
     "                iommu=on|off controls emulated Intel IOMMU (VT-d) support (default=off)\n"
+    "                igd-passthru=on|off controls IGD GFX passthrough support (default=off)\n"
     "                aes-key-wrap=on|off controls support for AES key wrapping (default=on)\n"
     "                dea-key-wrap=on|off controls support for DEA key wrapping (default=on)\n"
     "                suppress-vmdesc=on|off disables self-describing migration (default=off)\n",
@@ -55,6 +56,8 @@ than one accelerator specified, the next one is used if the previous one fails
 to initialize.
 @item kernel_irqchip=on|off
 Enables in-kernel irqchip support for the chosen accelerator when available.
+@item gfx_passthru=on|off
+Enables IGD GFX passthrough support for the chosen machine when available.
 @item vmport=on|off|auto
 Enables emulation of VMWare IO port, for vmmouse etc. auto says to select the
 value based on accel. For accel=xen the default is off otherwise the default

trace-events

@@ -936,6 +936,13 @@ xen_map_portio_range(uint32_t id, uint64_t start_addr, uint64_t end_addr) "id: %
 xen_unmap_portio_range(uint32_t id, uint64_t start_addr, uint64_t end_addr) "id: %u start: %#"PRIx64" end: %#"PRIx64
 xen_map_pcidev(uint32_t id, uint8_t bus, uint8_t dev, uint8_t func) "id: %u bdf: %02x.%02x.%02x"
 xen_unmap_pcidev(uint32_t id, uint8_t bus, uint8_t dev, uint8_t func) "id: %u bdf: %02x.%02x.%02x"
+handle_ioreq(void *req, uint32_t type, uint32_t dir, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p type=%d dir=%d df=%d ptr=%d port=%#"PRIx64" data=%#"PRIx64" count=%d size=%d"
+handle_ioreq_read(void *req, uint32_t type, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p read type=%d df=%d ptr=%d port=%#"PRIx64" data=%#"PRIx64" count=%d size=%d"
+handle_ioreq_write(void *req, uint32_t type, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p write type=%d df=%d ptr=%d port=%#"PRIx64" data=%#"PRIx64" count=%d size=%d"
+cpu_ioreq_pio(void *req, uint32_t dir, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p pio dir=%d df=%d ptr=%d port=%#"PRIx64" data=%#"PRIx64" count=%d size=%d"
+cpu_ioreq_pio_read_reg(void *req, uint64_t data, uint64_t addr, uint32_t size) "I/O=%p pio read reg data=%#"PRIx64" port=%#"PRIx64" size=%d"
+cpu_ioreq_pio_write_reg(void *req, uint64_t data, uint64_t addr, uint32_t size) "I/O=%p pio write reg data=%#"PRIx64" port=%#"PRIx64" size=%d"
+cpu_ioreq_move(void *req, uint32_t dir, uint32_t df, uint32_t data_is_ptr, uint64_t addr, uint64_t data, uint32_t count, uint32_t size) "I/O=%p copy dir=%d df=%d ptr=%d port=%#"PRIx64" data=%#"PRIx64" count=%d size=%d"
 
 # xen-mapcache.c
 xen_map_cache(uint64_t phys_addr) "want %#"PRIx64

vl.c

@@ -1338,6 +1338,13 @@ static inline void semihosting_arg_fallback(const char *file, const char *cmd)
     }
 }
 
+/* Now we still need this for compatibility with XEN. */
+bool has_igd_gfx_passthru;
+static void igd_gfx_passthru(void)
+{
+    has_igd_gfx_passthru = current_machine->igd_gfx_passthru;
+}
+
 /***********************************************************/
 /* USB devices */
 
@@ -4528,6 +4535,9 @@ int main(int argc, char **argv, char **envp)
             exit(1);
     }
 
+    /* Check if IGD GFX passthrough. */
+    igd_gfx_passthru();
+
     /* init generic devices */
     if (qemu_opts_foreach(qemu_find_opts("device"),
                           device_init_func, NULL, NULL)) {

xen-hvm.c

@@ -344,10 +344,10 @@ go_physmap:
         unsigned long idx = pfn + i;
         xen_pfn_t gpfn = start_gpfn + i;
 
-        rc = xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn);
+        rc = xen_xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn);
         if (rc) {
             DPRINTF("add_to_physmap MFN %"PRI_xen_pfn" to PFN %"
-                    PRI_xen_pfn" failed: %d\n", idx, gpfn, rc);
+                    PRI_xen_pfn" failed: %d (errno: %d)\n", idx, gpfn, rc, errno);
             return -rc;
         }
     }
@@ -421,10 +421,10 @@ static int xen_remove_from_physmap(XenIOState *state,
         xen_pfn_t idx = start_addr + i;
         xen_pfn_t gpfn = phys_offset + i;
 
-        rc = xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn);
+        rc = xen_xc_domain_add_to_physmap(xen_xc, xen_domid, XENMAPSPACE_gmfn, idx, gpfn);
         if (rc) {
             fprintf(stderr, "add_to_physmap MFN %"PRI_xen_pfn" to PFN %"
-                    PRI_xen_pfn" failed: %d\n", idx, gpfn, rc);
+                    PRI_xen_pfn" failed: %d (errno: %d)\n", idx, gpfn, rc, errno);
             return -rc;
         }
     }
@@ -813,9 +813,14 @@ static void cpu_ioreq_pio(ioreq_t *req)
 {
     uint32_t i;
 
+    trace_cpu_ioreq_pio(req, req->dir, req->df, req->data_is_ptr, req->addr,
+                         req->data, req->count, req->size);
+
     if (req->dir == IOREQ_READ) {
         if (!req->data_is_ptr) {
             req->data = do_inp(req->addr, req->size);
+            trace_cpu_ioreq_pio_read_reg(req, req->data, req->addr,
+                                         req->size);
         } else {
             uint32_t tmp;
 
@@ -826,6 +831,8 @@ static void cpu_ioreq_pio(ioreq_t *req)
         }
     } else if (req->dir == IOREQ_WRITE) {
         if (!req->data_is_ptr) {
+            trace_cpu_ioreq_pio_write_reg(req, req->data, req->addr,
+                                          req->size);
             do_outp(req->addr, req->size, req->data);
         } else {
             for (i = 0; i < req->count; i++) {
@@ -842,6 +849,9 @@ static void cpu_ioreq_move(ioreq_t *req)
 {
     uint32_t i;
 
+    trace_cpu_ioreq_move(req, req->dir, req->df, req->data_is_ptr, req->addr,
+                         req->data, req->count, req->size);
+
     if (!req->data_is_ptr) {
         if (req->dir == IOREQ_READ) {
             for (i = 0; i < req->count; i++) {
@@ -914,11 +924,18 @@ static void handle_vmport_ioreq(XenIOState *state, ioreq_t *req)
 
 static void handle_ioreq(XenIOState *state, ioreq_t *req)
 {
+    trace_handle_ioreq(req, req->type, req->dir, req->df, req->data_is_ptr,
+                       req->addr, req->data, req->count, req->size);
+
     if (!req->data_is_ptr && (req->dir == IOREQ_WRITE) &&
             (req->size < sizeof (target_ulong))) {
         req->data &= ((target_ulong) 1 << (8 * req->size)) - 1;
     }
 
+    if (req->dir == IOREQ_WRITE)
+        trace_handle_ioreq_write(req, req->type, req->df, req->data_is_ptr,
+                                 req->addr, req->data, req->count, req->size);
+
     switch (req->type) {
         case IOREQ_TYPE_PIO:
             cpu_ioreq_pio(req);
@@ -958,23 +975,38 @@ static void handle_ioreq(XenIOState *state, ioreq_t *req)
         default:
             hw_error("Invalid ioreq type 0x%x\n", req->type);
     }
+    if (req->dir == IOREQ_READ) {
+        trace_handle_ioreq_read(req, req->type, req->df, req->data_is_ptr,
+                                req->addr, req->data, req->count, req->size);
+    }
 }
 
 static int handle_buffered_iopage(XenIOState *state)
 {
+    buffered_iopage_t *buf_page = state->buffered_io_page;
     buf_ioreq_t *buf_req = NULL;
     ioreq_t req;
     int qw;
 
-    if (!state->buffered_io_page) {
+    if (!buf_page) {
         return 0;
     }
 
     memset(&req, 0x00, sizeof(req));
 
-    while (state->buffered_io_page->read_pointer != state->buffered_io_page->write_pointer) {
-        buf_req = &state->buffered_io_page->buf_ioreq[
-            state->buffered_io_page->read_pointer % IOREQ_BUFFER_SLOT_NUM];
+    for (;;) {
+        uint32_t rdptr = buf_page->read_pointer, wrptr;
+
+        xen_rmb();
+        wrptr = buf_page->write_pointer;
+        xen_rmb();
+        if (rdptr != buf_page->read_pointer) {
+            continue;
+        }
+        if (rdptr == wrptr) {
+            break;
+        }
+        buf_req = &buf_page->buf_ioreq[rdptr % IOREQ_BUFFER_SLOT_NUM];
         req.size = 1UL << buf_req->size;
         req.count = 1;
         req.addr = buf_req->addr;
@@ -986,15 +1018,14 @@ static int handle_buffered_iopage(XenIOState *state)
         req.data_is_ptr = 0;
         qw = (req.size == 8);
         if (qw) {
-            buf_req = &state->buffered_io_page->buf_ioreq[
-                (state->buffered_io_page->read_pointer + 1) % IOREQ_BUFFER_SLOT_NUM];
+            buf_req = &buf_page->buf_ioreq[(rdptr + 1) %
+                                           IOREQ_BUFFER_SLOT_NUM];
             req.data |= ((uint64_t)buf_req->data) << 32;
         }
 
         handle_ioreq(state, &req);
 
-        xen_mb();
-        state->buffered_io_page->read_pointer += qw ? 2 : 1;
+        atomic_add(&buf_page->read_pointer, qw + 1);
     }
 
     return req.count;