Merge remote-tracking branch 'sstabellini/xen-pt' into staging

* sstabellini/xen-pt:
  Introduce Xen PCI Passthrough, MSI
  Introduce apic-msidef.h
  Introduce Xen PCI Passthrough, PCI config space helpers
  Introduce Xen PCI Passthrough, qdevice
  qdev-properties: Introduce pci-host-devaddr.
  pci.c: Add opaque argument to pci_for_each_device.
  Introduce XenHostPCIDevice to access a pci device on the host.
  configure: Introduce --enable-xen-pci-passthrough.
  pci_ids: Add INTEL_82599_SFP_VF id.

configure

@@ -137,6 +137,7 @@ vnc_png=""
 vnc_thread="no"
 xen=""
 xen_ctrl_version=""
+xen_pci_passthrough=""
 linux_aio=""
 cap_ng=""
 attr=""
@@ -684,6 +685,10 @@ for opt do
   ;;
   --enable-xen) xen="yes"
   ;;
+  --disable-xen-pci-passthrough) xen_pci_passthrough="no"
+  ;;
+  --enable-xen-pci-passthrough) xen_pci_passthrough="yes"
+  ;;
   --disable-brlapi) brlapi="no"
   ;;
   --enable-brlapi) brlapi="yes"
@@ -1031,6 +1036,8 @@ echo "                           (affects only QEMU, not qemu-img)"
 echo "  --enable-mixemu          enable mixer emulation"
 echo "  --disable-xen            disable xen backend driver support"
 echo "  --enable-xen             enable xen backend driver support"
+echo "  --disable-xen-pci-passthrough"
+echo "  --enable-xen-pci-passthrough"
 echo "  --disable-brlapi         disable BrlAPI"
 echo "  --enable-brlapi          enable BrlAPI"
 echo "  --disable-vnc-tls        disable TLS encryption for VNC server"
@@ -1507,6 +1514,25 @@ EOF
   fi
 fi
 
+if test "$xen_pci_passthrough" != "no"; then
+  if test "$xen" = "yes" && test "$linux" = "yes" &&
+    test "$xen_ctrl_version" -ge 340; then
+    xen_pci_passthrough=yes
+  else
+    if test "$xen_pci_passthrough" = "yes"; then
+      echo "ERROR"
+      echo "ERROR: User requested feature Xen PCI Passthrough"
+      echo "ERROR: but this feature require /sys from Linux"
+      if test "$xen_ctrl_version" -lt 340; then
+        echo "ERROR: This feature does not work with Xen 3.3"
+      fi
+      echo "ERROR"
+      exit 1;
+    fi
+    xen_pci_passthrough=no
+  fi
+fi
+
 ##########################################
 # pkg-config probe
 
@@ -3702,6 +3728,9 @@ case "$target_arch2" in
     if test "$xen" = "yes" -a "$target_softmmu" = "yes" ; then
       target_phys_bits=64
       echo "CONFIG_XEN=y" >> $config_target_mak
+      if test "$xen_pci_passthrough" = yes; then
+        echo "CONFIG_XEN_PCI_PASSTHROUGH=y" >> "$config_target_mak"
+      fi
     else
       echo "CONFIG_NO_XEN=y" >> $config_target_mak
     fi

hw/apic-msidef.h

+#ifndef HW_APIC_MSIDEF_H
+#define HW_APIC_MSIDEF_H
+
+/*
+ * Intel APIC constants: from include/asm/msidef.h
+ */
+
+/*
+ * Shifts for MSI data
+ */
+
+#define MSI_DATA_VECTOR_SHIFT           0
+#define  MSI_DATA_VECTOR_MASK           0x000000ff
+
+#define MSI_DATA_DELIVERY_MODE_SHIFT    8
+#define MSI_DATA_LEVEL_SHIFT            14
+#define MSI_DATA_TRIGGER_SHIFT          15
+
+/*
+ * Shift/mask fields for msi address
+ */
+
+#define MSI_ADDR_DEST_MODE_SHIFT        2
+
+#define MSI_ADDR_REDIRECTION_SHIFT      3
+
+#define MSI_ADDR_DEST_ID_SHIFT          12
+#define  MSI_ADDR_DEST_ID_MASK          0x00ffff0
+
+#endif /* HW_APIC_MSIDEF_H */

hw/apic.c

@@ -23,19 +23,10 @@
 #include "host-utils.h"
 #include "trace.h"
 #include "pc.h"
+#include "apic-msidef.h"
 
 #define MAX_APIC_WORDS 8
 
-/* Intel APIC constants: from include/asm/msidef.h */
-#define MSI_DATA_VECTOR_SHIFT		0
-#define MSI_DATA_VECTOR_MASK		0x000000ff
-#define MSI_DATA_DELIVERY_MODE_SHIFT	8
-#define MSI_DATA_TRIGGER_SHIFT		15
-#define MSI_DATA_LEVEL_SHIFT		14
-#define MSI_ADDR_DEST_MODE_SHIFT	2
-#define MSI_ADDR_DEST_ID_SHIFT		12
-#define	MSI_ADDR_DEST_ID_MASK		0x00ffff0
-
 #define SYNC_FROM_VAPIC                 0x1
 #define SYNC_TO_VAPIC                   0x2
 #define SYNC_ISR_IRR_TO_VAPIC           0x4

hw/i386/Makefile.objs

@@ -7,6 +7,8 @@ obj-y += debugcon.o multiboot.o
 obj-y += pc_piix.o
 obj-y += pc_sysfw.o
 obj-$(CONFIG_XEN) += xen_platform.o xen_apic.o
+obj-$(CONFIG_XEN_PCI_PASSTHROUGH) += xen-host-pci-device.o
+obj-$(CONFIG_XEN_PCI_PASSTHROUGH) += xen_pt.o xen_pt_config_init.o xen_pt_msi.o
 obj-y += kvm/
 obj-$(CONFIG_SPICE) += qxl.o qxl-logger.o qxl-render.o
 

hw/pci.c

@@ -1144,7 +1144,9 @@ static const pci_class_desc pci_class_descriptions[] =
 };
 
 static void pci_for_each_device_under_bus(PCIBus *bus,
-                                          void (*fn)(PCIBus *b, PCIDevice *d))
+                                          void (*fn)(PCIBus *b, PCIDevice *d,
+                                                     void *opaque),
+                                          void *opaque)
 {
     PCIDevice *d;
     int devfn;
@@ -1152,18 +1154,19 @@ static void pci_for_each_device_under_bus(PCIBus *bus,
     for(devfn = 0; devfn < ARRAY_SIZE(bus->devices); devfn++) {
         d = bus->devices[devfn];
         if (d) {
-            fn(bus, d);
+            fn(bus, d, opaque);
         }
     }
 }
 
 void pci_for_each_device(PCIBus *bus, int bus_num,
-                         void (*fn)(PCIBus *b, PCIDevice *d))
+                         void (*fn)(PCIBus *b, PCIDevice *d, void *opaque),
+                         void *opaque)
 {
     bus = pci_find_bus_nr(bus, bus_num);
 
     if (bus) {
-        pci_for_each_device_under_bus(bus, fn);
+        pci_for_each_device_under_bus(bus, fn, opaque);
     }
 }
 

hw/pci.h

@@ -312,7 +312,9 @@ PCIDevice *pci_nic_init(NICInfo *nd, const char *default_model,
 PCIDevice *pci_nic_init_nofail(NICInfo *nd, const char *default_model,
                                const char *default_devaddr);
 int pci_bus_num(PCIBus *s);
-void pci_for_each_device(PCIBus *bus, int bus_num, void (*fn)(PCIBus *bus, PCIDevice *d));
+void pci_for_each_device(PCIBus *bus, int bus_num,
+                         void (*fn)(PCIBus *bus, PCIDevice *d, void *opaque),
+                         void *opaque);
 PCIBus *pci_find_root_bus(int domain);
 int pci_find_domain(const PCIBus *bus);
 PCIDevice *pci_find_device(PCIBus *bus, int bus_num, uint8_t devfn);

hw/pci_ids.h

@@ -118,6 +118,7 @@
 #define PCI_DEVICE_ID_INTEL_82801I_UHCI6 0x2939
 #define PCI_DEVICE_ID_INTEL_82801I_EHCI1 0x293a
 #define PCI_DEVICE_ID_INTEL_82801I_EHCI2 0x293c
+#define PCI_DEVICE_ID_INTEL_82599_SFP_VF 0x10ed
 
 #define PCI_VENDOR_ID_XEN               0x5853
 #define PCI_DEVICE_ID_XEN_PLATFORM      0x0001

hw/qdev-properties.c

@@ -899,6 +899,113 @@ PropertyInfo qdev_prop_blocksize = {
     .set   = set_blocksize,
 };
 
+/* --- pci host address --- */
+
+static void get_pci_host_devaddr(Object *obj, Visitor *v, void *opaque,
+                                 const char *name, Error **errp)
+{
+    DeviceState *dev = DEVICE(obj);
+    Property *prop = opaque;
+    PCIHostDeviceAddress *addr = qdev_get_prop_ptr(dev, prop);
+    char buffer[] = "xxxx:xx:xx.x";
+    char *p = buffer;
+    int rc = 0;
+
+    rc = snprintf(buffer, sizeof(buffer), "%04x:%02x:%02x.%d",
+                  addr->domain, addr->bus, addr->slot, addr->function);
+    assert(rc == sizeof(buffer) - 1);
+
+    visit_type_str(v, &p, name, errp);
+}
+
+/*
+ * Parse [<domain>:]<bus>:<slot>.<func>
+ *   if <domain> is not supplied, it's assumed to be 0.
+ */
+static void set_pci_host_devaddr(Object *obj, Visitor *v, void *opaque,
+                                 const char *name, Error **errp)
+{
+    DeviceState *dev = DEVICE(obj);
+    Property *prop = opaque;
+    PCIHostDeviceAddress *addr = qdev_get_prop_ptr(dev, prop);
+    Error *local_err = NULL;
+    char *str, *p;
+    char *e;
+    unsigned long val;
+    unsigned long dom = 0, bus = 0;
+    unsigned int slot = 0, func = 0;
+
+    if (dev->state != DEV_STATE_CREATED) {
+        error_set(errp, QERR_PERMISSION_DENIED);
+        return;
+    }
+
+    visit_type_str(v, &str, name, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    p = str;
+    val = strtoul(p, &e, 16);
+    if (e == p || *e != ':') {
+        goto inval;
+    }
+    bus = val;
+
+    p = e + 1;
+    val = strtoul(p, &e, 16);
+    if (e == p) {
+        goto inval;
+    }
+    if (*e == ':') {
+        dom = bus;
+        bus = val;
+        p = e + 1;
+        val = strtoul(p, &e, 16);
+        if (e == p) {
+            goto inval;
+        }
+    }
+    slot = val;
+
+    if (*e != '.') {
+        goto inval;
+    }
+    p = e + 1;
+    val = strtoul(p, &e, 10);
+    if (e == p) {
+        goto inval;
+    }
+    func = val;
+
+    if (dom > 0xffff || bus > 0xff || slot > 0x1f || func > 7) {
+        goto inval;
+    }
+
+    if (*e) {
+        goto inval;
+    }
+
+    addr->domain = dom;
+    addr->bus = bus;
+    addr->slot = slot;
+    addr->function = func;
+
+    g_free(str);
+    return;
+
+inval:
+    error_set_from_qdev_prop_error(errp, EINVAL, dev, prop, str);
+    g_free(str);
+}
+
+PropertyInfo qdev_prop_pci_host_devaddr = {
+    .name = "pci-host-devaddr",
+    .get = get_pci_host_devaddr,
+    .set = set_pci_host_devaddr,
+};
+
 /* --- public helpers --- */
 
 static Property *qdev_prop_walk(Property *props, const char *name)

hw/qdev.h

@@ -237,6 +237,7 @@ extern PropertyInfo qdev_prop_netdev;
 extern PropertyInfo qdev_prop_vlan;
 extern PropertyInfo qdev_prop_pci_devfn;
 extern PropertyInfo qdev_prop_blocksize;
+extern PropertyInfo qdev_prop_pci_host_devaddr;
 
 #define DEFINE_PROP(_name, _state, _field, _prop, _type) { \
         .name      = (_name),                                    \
@@ -300,6 +301,8 @@ extern PropertyInfo qdev_prop_blocksize;
                         LostTickPolicy)
 #define DEFINE_PROP_BLOCKSIZE(_n, _s, _f, _d) \
     DEFINE_PROP_DEFAULT(_n, _s, _f, _d, qdev_prop_blocksize, uint16_t)
+#define DEFINE_PROP_PCI_HOST_DEVADDR(_n, _s, _f) \
+    DEFINE_PROP(_n, _s, _f, qdev_prop_pci_host_devaddr, PCIHostDeviceAddress)
 
 #define DEFINE_PROP_END_OF_LIST()               \
     {}

hw/xen-host-pci-device.c

+/*
+ * Copyright (C) 2011       Citrix Ltd.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu-common.h"
+#include "xen-host-pci-device.h"
+
+#define XEN_HOST_PCI_MAX_EXT_CAP \
+    ((PCIE_CONFIG_SPACE_SIZE - PCI_CONFIG_SPACE_SIZE) / (PCI_CAP_SIZEOF + 4))
+
+#ifdef XEN_HOST_PCI_DEVICE_DEBUG
+#  define XEN_HOST_PCI_LOG(f, a...) fprintf(stderr, "%s: " f, __func__, ##a)
+#else
+#  define XEN_HOST_PCI_LOG(f, a...) (void)0
+#endif
+
+/*
+ * from linux/ioport.h
+ * IO resources have these defined flags.
+ */
+#define IORESOURCE_BITS         0x000000ff      /* Bus-specific bits */
+
+#define IORESOURCE_TYPE_BITS    0x00000f00      /* Resource type */
+#define IORESOURCE_IO           0x00000100
+#define IORESOURCE_MEM          0x00000200
+
+#define IORESOURCE_PREFETCH     0x00001000      /* No side effects */
+#define IORESOURCE_MEM_64       0x00100000
+
+static int xen_host_pci_sysfs_path(const XenHostPCIDevice *d,
+                                   const char *name, char *buf, ssize_t size)
+{
+    int rc;
+
+    rc = snprintf(buf, size, "/sys/bus/pci/devices/%04x:%02x:%02x.%d/%s",
+                  d->domain, d->bus, d->dev, d->func, name);
+
+    if (rc >= size || rc < 0) {
+        /* The ouput is truncated or an other error is encountered */
+        return -ENODEV;
+    }
+    return 0;
+}
+
+
+/* This size should be enough to read the first 7 lines of a ressource file */
+#define XEN_HOST_PCI_RESSOURCE_BUFFER_SIZE 400
+static int xen_host_pci_get_resource(XenHostPCIDevice *d)
+{
+    int i, rc, fd;
+    char path[PATH_MAX];
+    char buf[XEN_HOST_PCI_RESSOURCE_BUFFER_SIZE];
+    unsigned long long start, end, flags, size;
+    char *endptr, *s;
+    uint8_t type;
+
+    rc = xen_host_pci_sysfs_path(d, "resource", path, sizeof (path));
+    if (rc) {
+        return rc;
+    }
+    fd = open(path, O_RDONLY);
+    if (fd == -1) {
+        XEN_HOST_PCI_LOG("Error: Can't open %s: %s\n", path, strerror(errno));
+        return -errno;
+    }
+
+    do {
+        rc = read(fd, &buf, sizeof (buf) - 1);
+        if (rc < 0 && errno != EINTR) {
+            rc = -errno;
+            goto out;
+        }
+    } while (rc < 0);
+    buf[rc] = 0;
+    rc = 0;
+
+    s = buf;
+    for (i = 0; i < PCI_NUM_REGIONS; i++) {
+        type = 0;
+
+        start = strtoll(s, &endptr, 16);
+        if (*endptr != ' ' || s == endptr) {
+            break;
+        }
+        s = endptr + 1;
+        end = strtoll(s, &endptr, 16);
+        if (*endptr != ' ' || s == endptr) {
+            break;
+        }
+        s = endptr + 1;
+        flags = strtoll(s, &endptr, 16);
+        if (*endptr != '\n' || s == endptr) {
+            break;
+        }
+        s = endptr + 1;
+
+        if (start) {
+            size = end - start + 1;
+        } else {
+            size = 0;
+        }
+
+        if (flags & IORESOURCE_IO) {
+            type |= XEN_HOST_PCI_REGION_TYPE_IO;
+        }
+        if (flags & IORESOURCE_MEM) {
+            type |= XEN_HOST_PCI_REGION_TYPE_MEM;
+        }
+        if (flags & IORESOURCE_PREFETCH) {
+            type |= XEN_HOST_PCI_REGION_TYPE_PREFETCH;
+        }
+        if (flags & IORESOURCE_MEM_64) {
+            type |= XEN_HOST_PCI_REGION_TYPE_MEM_64;
+        }
+
+        if (i < PCI_ROM_SLOT) {
+            d->io_regions[i].base_addr = start;
+            d->io_regions[i].size = size;
+            d->io_regions[i].type = type;
+            d->io_regions[i].bus_flags = flags & IORESOURCE_BITS;
+        } else {
+            d->rom.base_addr = start;
+            d->rom.size = size;
+            d->rom.type = type;
+            d->rom.bus_flags = flags & IORESOURCE_BITS;
+        }
+    }
+    if (i != PCI_NUM_REGIONS) {
+        /* Invalid format or input to short */
+        rc = -ENODEV;
+    }
+
+out:
+    close(fd);
+    return rc;
+}
+
+/* This size should be enough to read a long from a file */
+#define XEN_HOST_PCI_GET_VALUE_BUFFER_SIZE 22
+static int xen_host_pci_get_value(XenHostPCIDevice *d, const char *name,
+                                  unsigned int *pvalue, int base)
+{
+    char path[PATH_MAX];
+    char buf[XEN_HOST_PCI_GET_VALUE_BUFFER_SIZE];
+    int fd, rc;
+    unsigned long value;
+    char *endptr;
+
+    rc = xen_host_pci_sysfs_path(d, name, path, sizeof (path));
+    if (rc) {
+        return rc;
+    }
+    fd = open(path, O_RDONLY);
+    if (fd == -1) {
+        XEN_HOST_PCI_LOG("Error: Can't open %s: %s\n", path, strerror(errno));
+        return -errno;
+    }
+    do {
+        rc = read(fd, &buf, sizeof (buf) - 1);
+        if (rc < 0 && errno != EINTR) {
+            rc = -errno;
+            goto out;
+        }
+    } while (rc < 0);
+    buf[rc] = 0;
+    value = strtol(buf, &endptr, base);
+    if (endptr == buf || *endptr != '\n') {
+        rc = -1;
+    } else if ((value == LONG_MIN || value == LONG_MAX) && errno == ERANGE) {
+        rc = -errno;
+    } else {
+        rc = 0;
+        *pvalue = value;
+    }
+out:
+    close(fd);
+    return rc;
+}
+
+static inline int xen_host_pci_get_hex_value(XenHostPCIDevice *d,
+                                             const char *name,
+                                             unsigned int *pvalue)
+{
+    return xen_host_pci_get_value(d, name, pvalue, 16);
+}
+
+static inline int xen_host_pci_get_dec_value(XenHostPCIDevice *d,
+                                             const char *name,
+                                             unsigned int *pvalue)
+{
+    return xen_host_pci_get_value(d, name, pvalue, 10);
+}
+
+static bool xen_host_pci_dev_is_virtfn(XenHostPCIDevice *d)
+{
+    char path[PATH_MAX];
+    struct stat buf;
+
+    if (xen_host_pci_sysfs_path(d, "physfn", path, sizeof (path))) {
+        return false;
+    }
+    return !stat(path, &buf);
+}
+
+static int xen_host_pci_config_open(XenHostPCIDevice *d)
+{
+    char path[PATH_MAX];
+    int rc;
+
+    rc = xen_host_pci_sysfs_path(d, "config", path, sizeof (path));
+    if (rc) {
+        return rc;
+    }
+    d->config_fd = open(path, O_RDWR);
+    if (d->config_fd < 0) {
+        return -errno;
+    }
+    return 0;
+}
+
+static int xen_host_pci_config_read(XenHostPCIDevice *d,
+                                    int pos, void *buf, int len)
+{
+    int rc;
+
+    do {
+        rc = pread(d->config_fd, buf, len, pos);
+    } while (rc < 0 && (errno == EINTR || errno == EAGAIN));
+    if (rc != len) {
+        return -errno;
+    }
+    return 0;
+}
+
+static int xen_host_pci_config_write(XenHostPCIDevice *d,
+                                     int pos, const void *buf, int len)
+{
+    int rc;
+
+    do {
+        rc = pwrite(d->config_fd, buf, len, pos);
+    } while (rc < 0 && (errno == EINTR || errno == EAGAIN));
+    if (rc != len) {
+        return -errno;
+    }
+    return 0;
+}
+
+
+int xen_host_pci_get_byte(XenHostPCIDevice *d, int pos, uint8_t *p)
+{
+    uint8_t buf;
+    int rc = xen_host_pci_config_read(d, pos, &buf, 1);
+    if (!rc) {
+        *p = buf;
+    }
+    return rc;
+}
+
+int xen_host_pci_get_word(XenHostPCIDevice *d, int pos, uint16_t *p)
+{
+    uint16_t buf;
+    int rc = xen_host_pci_config_read(d, pos, &buf, 2);
+    if (!rc) {
+        *p = le16_to_cpu(buf);
+    }
+    return rc;
+}
+
+int xen_host_pci_get_long(XenHostPCIDevice *d, int pos, uint32_t *p)
+{
+    uint32_t buf;
+    int rc = xen_host_pci_config_read(d, pos, &buf, 4);
+    if (!rc) {
+        *p = le32_to_cpu(buf);
+    }
+    return rc;
+}
+
+int xen_host_pci_get_block(XenHostPCIDevice *d, int pos, uint8_t *buf, int len)
+{
+    return xen_host_pci_config_read(d, pos, buf, len);
+}
+
+int xen_host_pci_set_byte(XenHostPCIDevice *d, int pos, uint8_t data)
+{
+    return xen_host_pci_config_write(d, pos, &data, 1);
+}
+
+int xen_host_pci_set_word(XenHostPCIDevice *d, int pos, uint16_t data)
+{
+    data = cpu_to_le16(data);
+    return xen_host_pci_config_write(d, pos, &data, 2);
+}
+
+int xen_host_pci_set_long(XenHostPCIDevice *d, int pos, uint32_t data)
+{
+    data = cpu_to_le32(data);
+    return xen_host_pci_config_write(d, pos, &data, 4);
+}
+
+int xen_host_pci_set_block(XenHostPCIDevice *d, int pos, uint8_t *buf, int len)
+{
+    return xen_host_pci_config_write(d, pos, buf, len);
+}
+
+int xen_host_pci_find_ext_cap_offset(XenHostPCIDevice *d, uint32_t cap)
+{
+    uint32_t header = 0;
+    int max_cap = XEN_HOST_PCI_MAX_EXT_CAP;
+    int pos = PCI_CONFIG_SPACE_SIZE;
+
+    do {
+        if (xen_host_pci_get_long(d, pos, &header)) {
+            break;
+        }
+        /*
+         * If we have no capabilities, this is indicated by cap ID,
+         * cap version and next pointer all being 0.
+         */
+        if (header == 0) {
+            break;
+        }
+
+        if (PCI_EXT_CAP_ID(header) == cap) {
+            return pos;
+        }
+
+        pos = PCI_EXT_CAP_NEXT(header);
+        if (pos < PCI_CONFIG_SPACE_SIZE) {
+            break;
+        }
+
+        max_cap--;
+    } while (max_cap > 0);
+
+    return -1;
+}
+
+int xen_host_pci_device_get(XenHostPCIDevice *d, uint16_t domain,
+                            uint8_t bus, uint8_t dev, uint8_t func)
+{
+    unsigned int v;
+    int rc = 0;
+
+    d->config_fd = -1;
+    d->domain = domain;
+    d->bus = bus;
+    d->dev = dev;
+    d->func = func;
+
+    rc = xen_host_pci_config_open(d);
+    if (rc) {
+        goto error;
+    }
+    rc = xen_host_pci_get_resource(d);
+    if (rc) {
+        goto error;
+    }
+    rc = xen_host_pci_get_hex_value(d, "vendor", &v);
+    if (rc) {
+        goto error;
+    }
+    d->vendor_id = v;
+    rc = xen_host_pci_get_hex_value(d, "device", &v);
+    if (rc) {
+        goto error;
+    }
+    d->device_id = v;
+    rc = xen_host_pci_get_dec_value(d, "irq", &v);
+    if (rc) {
+        goto error;
+    }
+    d->irq = v;
+    d->is_virtfn = xen_host_pci_dev_is_virtfn(d);
+
+    return 0;
+error:
+    if (d->config_fd >= 0) {
+        close(d->config_fd);
+        d->config_fd = -1;
+    }
+    return rc;
+}
+
+void xen_host_pci_device_put(XenHostPCIDevice *d)
+{
+    if (d->config_fd >= 0) {
+        close(d->config_fd);
+        d->config_fd = -1;
+    }
+}

hw/xen-host-pci-device.h

+#ifndef XEN_HOST_PCI_DEVICE_H
+#define XEN_HOST_PCI_DEVICE_H
+
+#include "pci.h"
+
+enum {
+    XEN_HOST_PCI_REGION_TYPE_IO = 1 << 1,
+    XEN_HOST_PCI_REGION_TYPE_MEM = 1 << 2,
+    XEN_HOST_PCI_REGION_TYPE_PREFETCH = 1 << 3,
+    XEN_HOST_PCI_REGION_TYPE_MEM_64 = 1 << 4,
+};
+
+typedef struct XenHostPCIIORegion {
+    pcibus_t base_addr;
+    pcibus_t size;
+    uint8_t type;
+    uint8_t bus_flags; /* Bus-specific bits */
+} XenHostPCIIORegion;
+
+typedef struct XenHostPCIDevice {
+    uint16_t domain;
+    uint8_t bus;
+    uint8_t dev;
+    uint8_t func;
+
+    uint16_t vendor_id;
+    uint16_t device_id;
+    int irq;
+
+    XenHostPCIIORegion io_regions[PCI_NUM_REGIONS - 1];
+    XenHostPCIIORegion rom;
+
+    bool is_virtfn;
+
+    int config_fd;
+} 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);
+
+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);
+int xen_host_pci_get_long(XenHostPCIDevice *d, int pos, uint32_t *p);
+int xen_host_pci_get_block(XenHostPCIDevice *d, int pos, uint8_t *buf,
+                           int len);
+int xen_host_pci_set_byte(XenHostPCIDevice *d, int pos, uint8_t data);
+int xen_host_pci_set_word(XenHostPCIDevice *d, int pos, uint16_t data);
+int xen_host_pci_set_long(XenHostPCIDevice *d, int pos, uint32_t data);
+int xen_host_pci_set_block(XenHostPCIDevice *d, int pos, uint8_t *buf,
+                           int len);
+
+int xen_host_pci_find_ext_cap_offset(XenHostPCIDevice *s, uint32_t cap);
+
+#endif /* !XEN_HOST_PCI_DEVICE_H_ */

hw/xen_common.h

@@ -150,4 +150,7 @@ static inline int xen_xc_hvm_inject_msi(XenXC xen_xc, domid_t dom,
 
 void destroy_hvm_domain(bool reboot);
 
+/* shutdown/destroy current domain because of an error */
+void xen_shutdown_fatal_error(const char *fmt, ...) GCC_FMT_ATTR(1, 2);
+
 #endif /* QEMU_HW_XEN_COMMON_H */

hw/xen_platform.c

@@ -83,7 +83,7 @@ static void log_writeb(PCIXenPlatformState *s, char val)
 #define UNPLUG_ALL_NICS 2
 #define UNPLUG_AUX_IDE_DISKS 4
 
-static void unplug_nic(PCIBus *b, PCIDevice *d)
+static void unplug_nic(PCIBus *b, PCIDevice *d, void *o)
 {
     if (pci_get_word(d->config + PCI_CLASS_DEVICE) ==
             PCI_CLASS_NETWORK_ETHERNET) {
@@ -96,10 +96,10 @@ static void unplug_nic(PCIBus *b, PCIDevice *d)
 
 static void pci_unplug_nics(PCIBus *bus)
 {
-    pci_for_each_device(bus, 0, unplug_nic);
+    pci_for_each_device(bus, 0, unplug_nic, NULL);
 }
 
-static void unplug_disks(PCIBus *b, PCIDevice *d)
+static void unplug_disks(PCIBus *b, PCIDevice *d, void *o)
 {
     if (pci_get_word(d->config + PCI_CLASS_DEVICE) ==
             PCI_CLASS_STORAGE_IDE) {
@@ -109,7 +109,7 @@ static void unplug_disks(PCIBus *b, PCIDevice *d)
 
 static void pci_unplug_disks(PCIBus *bus)
 {
-    pci_for_each_device(bus, 0, unplug_disks);
+    pci_for_each_device(bus, 0, unplug_disks, NULL);
 }
 
 static void platform_fixed_ioport_writew(void *opaque, uint32_t addr, uint32_t val)

hw/xen_pt.c

+/*
+ * Copyright (c) 2007, Neocleus Corporation.
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Alex Novik <alex@neocleus.com>
+ * Allen Kay <allen.m.kay@intel.com>
+ * Guy Zana <guy@neocleus.com>
+ *
+ * This file implements direct PCI assignment to a HVM guest
+ */
+
+/*
+ * Interrupt Disable policy:
+ *
+ * INTx interrupt:
+ *   Initialize(register_real_device)
+ *     Map INTx(xc_physdev_map_pirq):
+ *       <fail>
+ *         - Set real Interrupt Disable bit to '1'.
+ *         - Set machine_irq and assigned_device->machine_irq to '0'.
+ *         * Don't bind INTx.
+ *
+ *     Bind INTx(xc_domain_bind_pt_pci_irq):
+ *       <fail>
+ *         - Set real Interrupt Disable bit to '1'.
+ *         - Unmap INTx.
+ *         - Decrement xen_pt_mapped_machine_irq[machine_irq]
+ *         - Set assigned_device->machine_irq to '0'.
+ *
+ *   Write to Interrupt Disable bit by guest software(xen_pt_cmd_reg_write)
+ *     Write '0'
+ *       - Set real bit to '0' if assigned_device->machine_irq isn't '0'.
+ *
+ *     Write '1'
+ *       - Set real bit to '1'.
+ *
+ * MSI interrupt:
+ *   Initialize MSI register(xen_pt_msi_setup, xen_pt_msi_update)
+ *     Bind MSI(xc_domain_update_msi_irq)
+ *       <fail>
+ *         - Unmap MSI.
+ *         - Set dev->msi->pirq to '-1'.
+ *
+ * MSI-X interrupt:
+ *   Initialize MSI-X register(xen_pt_msix_update_one)
+ *     Bind MSI-X(xc_domain_update_msi_irq)
+ *       <fail>
+ *         - Unmap MSI-X.
+ *         - Set entry->pirq to '-1'.
+ */
+
+#include <sys/ioctl.h>
+
+#include "pci.h"
+#include "xen.h"
+#include "xen_backend.h"
+#include "xen_pt.h"
+#include "range.h"
+
+#define XEN_PT_NR_IRQS (256)
+static uint8_t xen_pt_mapped_machine_irq[XEN_PT_NR_IRQS] = {0};
+
+void xen_pt_log(const PCIDevice *d, const char *f, ...)
+{
+    va_list ap;
+
+    va_start(ap, f);
+    if (d) {
+        fprintf(stderr, "[%02x:%02x.%d] ", pci_bus_num(d->bus),
+                PCI_SLOT(d->devfn), PCI_FUNC(d->devfn));
+    }
+    vfprintf(stderr, f, ap);
+    va_end(ap);
+}
+
+/* Config Space */
+
+static int xen_pt_pci_config_access_check(PCIDevice *d, uint32_t addr, int len)
+{
+    /* check offset range */
+    if (addr >= 0xFF) {
+        XEN_PT_ERR(d, "Failed to access register with offset exceeding 0xFF. "
+                   "(addr: 0x%02x, len: %d)\n", addr, len);
+        return -1;
+    }
+
+    /* check read size */
+    if ((len != 1) && (len != 2) && (len != 4)) {
+        XEN_PT_ERR(d, "Failed to access register with invalid access length. "
+                   "(addr: 0x%02x, len: %d)\n", addr, len);
+        return -1;
+    }
+
+    /* check offset alignment */
+    if (addr & (len - 1)) {
+        XEN_PT_ERR(d, "Failed to access register with invalid access size "
+                   "alignment. (addr: 0x%02x, len: %d)\n", addr, len);
+        return -1;
+    }
+
+    return 0;
+}
+
+int xen_pt_bar_offset_to_index(uint32_t offset)
+{
+    int index = 0;
+
+    /* check Exp ROM BAR */
+    if (offset == PCI_ROM_ADDRESS) {
+        return PCI_ROM_SLOT;
+    }
+
+    /* calculate BAR index */
+    index = (offset - PCI_BASE_ADDRESS_0) >> 2;
+    if (index >= PCI_NUM_REGIONS) {
+        return -1;
+    }
+
+    return index;
+}
+
+static uint32_t xen_pt_pci_read_config(PCIDevice *d, uint32_t addr, int len)
+{
+    XenPCIPassthroughState *s = DO_UPCAST(XenPCIPassthroughState, dev, d);
+    uint32_t val = 0;
+    XenPTRegGroup *reg_grp_entry = NULL;
+    XenPTReg *reg_entry = NULL;
+    int rc = 0;
+    int emul_len = 0;
+    uint32_t find_addr = addr;
+
+    if (xen_pt_pci_config_access_check(d, addr, len)) {
+        goto exit;
+    }
+
+    /* find register group entry */
+    reg_grp_entry = xen_pt_find_reg_grp(s, addr);
+    if (reg_grp_entry) {
+        /* check 0-Hardwired register group */
+        if (reg_grp_entry->reg_grp->grp_type == XEN_PT_GRP_TYPE_HARDWIRED) {
+            /* no need to emulate, just return 0 */
+            val = 0;
+            goto exit;
+        }
+    }
+
+    /* read I/O device register value */
+    rc = xen_host_pci_get_block(&s->real_device, addr, (uint8_t *)&val, len);
+    if (rc < 0) {
+        XEN_PT_ERR(d, "pci_read_block failed. return value: %d.\n", rc);
+        memset(&val, 0xff, len);
+    }
+
+    /* just return the I/O device register value for
+     * passthrough type register group */
+    if (reg_grp_entry == NULL) {
+        goto exit;
+    }
+
+    /* adjust the read value to appropriate CFC-CFF window */
+    val <<= (addr & 3) << 3;
+    emul_len = len;
+
+    /* loop around the guest requested size */
+    while (emul_len > 0) {
+        /* find register entry to be emulated */
+        reg_entry = xen_pt_find_reg(reg_grp_entry, find_addr);
+        if (reg_entry) {
+            XenPTRegInfo *reg = reg_entry->reg;
+            uint32_t real_offset = reg_grp_entry->base_offset + reg->offset;
+            uint32_t valid_mask = 0xFFFFFFFF >> ((4 - emul_len) << 3);
+            uint8_t *ptr_val = NULL;
+
+            valid_mask <<= (find_addr - real_offset) << 3;
+            ptr_val = (uint8_t *)&val + (real_offset & 3);
+
+            /* do emulation based on register size */
+            switch (reg->size) {
+            case 1:
+                if (reg->u.b.read) {
+                    rc = reg->u.b.read(s, reg_entry, ptr_val, valid_mask);
+                }
+                break;
+            case 2:
+                if (reg->u.w.read) {
+                    rc = reg->u.w.read(s, reg_entry,
+                                       (uint16_t *)ptr_val, valid_mask);
+                }
+                break;
+            case 4:
+                if (reg->u.dw.read) {
+                    rc = reg->u.dw.read(s, reg_entry,
+                                        (uint32_t *)ptr_val, valid_mask);
+                }
+                break;
+            }
+
+            if (rc < 0) {
+                xen_shutdown_fatal_error("Internal error: Invalid read "
+                                         "emulation. (%s, rc: %d)\n",
+                                         __func__, rc);
+                return 0;
+            }
+
+            /* calculate next address to find */
+            emul_len -= reg->size;
+            if (emul_len > 0) {
+                find_addr = real_offset + reg->size;
+            }
+        } else {
+            /* nothing to do with passthrough type register,
+             * continue to find next byte */
+            emul_len--;
+            find_addr++;
+        }
+    }
+
+    /* need to shift back before returning them to pci bus emulator */
+    val >>= ((addr & 3) << 3);
+
+exit:
+    XEN_PT_LOG_CONFIG(d, addr, val, len);
+    return val;
+}
+
+static void xen_pt_pci_write_config(PCIDevice *d, uint32_t addr,
+                                    uint32_t val, int len)
+{
+    XenPCIPassthroughState *s = DO_UPCAST(XenPCIPassthroughState, dev, d);
+    int index = 0;
+    XenPTRegGroup *reg_grp_entry = NULL;
+    int rc = 0;
+    uint32_t read_val = 0;
+    int emul_len = 0;
+    XenPTReg *reg_entry = NULL;
+    uint32_t find_addr = addr;
+    XenPTRegInfo *reg = NULL;
+
+    if (xen_pt_pci_config_access_check(d, addr, len)) {
+        return;
+    }
+
+    XEN_PT_LOG_CONFIG(d, addr, val, len);
+
+    /* check unused BAR register */
+    index = xen_pt_bar_offset_to_index(addr);
+    if ((index >= 0) && (val > 0 && val < XEN_PT_BAR_ALLF) &&
+        (s->bases[index].bar_flag == XEN_PT_BAR_FLAG_UNUSED)) {
+        XEN_PT_WARN(d, "Guest attempt to set address to unused Base Address "
+                    "Register. (addr: 0x%02x, len: %d)\n", addr, len);
+    }
+
+    /* find register group entry */
+    reg_grp_entry = xen_pt_find_reg_grp(s, addr);
+    if (reg_grp_entry) {
+        /* check 0-Hardwired register group */
+        if (reg_grp_entry->reg_grp->grp_type == XEN_PT_GRP_TYPE_HARDWIRED) {
+            /* ignore silently */
+            XEN_PT_WARN(d, "Access to 0-Hardwired register. "
+                        "(addr: 0x%02x, len: %d)\n", addr, len);
+            return;
+        }
+    }
+
+    rc = xen_host_pci_get_block(&s->real_device, addr,
+                                (uint8_t *)&read_val, len);
+    if (rc < 0) {
+        XEN_PT_ERR(d, "pci_read_block failed. return value: %d.\n", rc);
+        memset(&read_val, 0xff, len);
+    }
+
+    /* pass directly to the real device for passthrough type register group */
+    if (reg_grp_entry == NULL) {
+        goto out;
+    }
+
+    memory_region_transaction_begin();
+    pci_default_write_config(d, addr, val, len);
+
+    /* adjust the read and write value to appropriate CFC-CFF window */
+    read_val <<= (addr & 3) << 3;
+    val <<= (addr & 3) << 3;
+    emul_len = len;
+
+    /* loop around the guest requested size */
+    while (emul_len > 0) {
+        /* find register entry to be emulated */
+        reg_entry = xen_pt_find_reg(reg_grp_entry, find_addr);
+        if (reg_entry) {
+            reg = reg_entry->reg;
+            uint32_t real_offset = reg_grp_entry->base_offset + reg->offset;
+            uint32_t valid_mask = 0xFFFFFFFF >> ((4 - emul_len) << 3);
+            uint8_t *ptr_val = NULL;
+
+            valid_mask <<= (find_addr - real_offset) << 3;
+            ptr_val = (uint8_t *)&val + (real_offset & 3);
+
+            /* do emulation based on register size */
+            switch (reg->size) {
+            case 1:
+                if (reg->u.b.write) {
+                    rc = reg->u.b.write(s, reg_entry, ptr_val,
+                                        read_val >> ((real_offset & 3) << 3),
+                                        valid_mask);
+                }
+                break;
+            case 2:
+                if (reg->u.w.write) {
+                    rc = reg->u.w.write(s, reg_entry, (uint16_t *)ptr_val,
+                                        (read_val >> ((real_offset & 3) << 3)),
+                                        valid_mask);
+                }
+                break;
+            case 4:
+                if (reg->u.dw.write) {
+                    rc = reg->u.dw.write(s, reg_entry, (uint32_t *)ptr_val,
+                                         (read_val >> ((real_offset & 3) << 3)),
+                                         valid_mask);
+                }
+                break;
+            }
+
+            if (rc < 0) {
+                xen_shutdown_fatal_error("Internal error: Invalid write"
+                                         " emulation. (%s, rc: %d)\n",
+                                         __func__, rc);
+                return;
+            }
+
+            /* calculate next address to find */
+            emul_len -= reg->size;
+            if (emul_len > 0) {
+                find_addr = real_offset + reg->size;
+            }
+        } else {
+            /* nothing to do with passthrough type register,
+             * continue to find next byte */
+            emul_len--;
+            find_addr++;
+        }
+    }
+
+    /* need to shift back before passing them to xen_host_pci_device */
+    val >>= (addr & 3) << 3;
+
+    memory_region_transaction_commit();
+
+out:
+    if (!(reg && reg->no_wb)) {
+        /* unknown regs are passed through */
+        rc = xen_host_pci_set_block(&s->real_device, addr,
+                                    (uint8_t *)&val, len);
+
+        if (rc < 0) {
+            XEN_PT_ERR(d, "pci_write_block failed. return value: %d.\n", rc);
+        }
+    }
+}
+
+/* register regions */
+
+static uint64_t xen_pt_bar_read(void *o, target_phys_addr_t addr,
+                                unsigned size)
+{
+    PCIDevice *d = o;
+    /* if this function is called, that probably means that there is a
+     * misconfiguration of the IOMMU. */
+    XEN_PT_ERR(d, "Should not read BAR through QEMU. @0x"TARGET_FMT_plx"\n",
+               addr);
+    return 0;
+}
+static void xen_pt_bar_write(void *o, target_phys_addr_t addr, uint64_t val,
+                             unsigned size)
+{
+    PCIDevice *d = o;
+    /* Same comment as xen_pt_bar_read function */
+    XEN_PT_ERR(d, "Should not write BAR through QEMU. @0x"TARGET_FMT_plx"\n",
+               addr);
+}
+
+static const MemoryRegionOps ops = {
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .read = xen_pt_bar_read,
+    .write = xen_pt_bar_write,
+};
+
+static int xen_pt_register_regions(XenPCIPassthroughState *s)
+{
+    int i = 0;
+    XenHostPCIDevice *d = &s->real_device;
+
+    /* Register PIO/MMIO BARs */
+    for (i = 0; i < PCI_ROM_SLOT; i++) {
+        XenHostPCIIORegion *r = &d->io_regions[i];
+        uint8_t type;
+
+        if (r->base_addr == 0 || r->size == 0) {
+            continue;
+        }
+
+        s->bases[i].access.u = r->base_addr;
+
+        if (r->type & XEN_HOST_PCI_REGION_TYPE_IO) {
+            type = PCI_BASE_ADDRESS_SPACE_IO;
+        } else {
+            type = PCI_BASE_ADDRESS_SPACE_MEMORY;
+            if (r->type & XEN_HOST_PCI_REGION_TYPE_PREFETCH) {
+                type |= PCI_BASE_ADDRESS_MEM_PREFETCH;
+            }
+        }
+
+        memory_region_init_io(&s->bar[i], &ops, &s->dev,
+                              "xen-pci-pt-bar", r->size);
+        pci_register_bar(&s->dev, i, type, &s->bar[i]);
+
+        XEN_PT_LOG(&s->dev, "IO region %i registered (size=0x%08"PRIx64
+                   " base_addr=0x%08"PRIx64" type: %#x)\n",
+                   i, r->size, r->base_addr, type);
+    }
+
+    /* Register expansion ROM address */
+    if (d->rom.base_addr && d->rom.size) {
+        uint32_t bar_data = 0;
+
+        /* Re-set BAR reported by OS, otherwise ROM can't be read. */
+        if (xen_host_pci_get_long(d, PCI_ROM_ADDRESS, &bar_data)) {
+            return 0;
+        }
+        if ((bar_data & PCI_ROM_ADDRESS_MASK) == 0) {
+            bar_data |= d->rom.base_addr & PCI_ROM_ADDRESS_MASK;
+            xen_host_pci_set_long(d, PCI_ROM_ADDRESS, bar_data);
+        }
+
+        s->bases[PCI_ROM_SLOT].access.maddr = d->rom.base_addr;
+
+        memory_region_init_rom_device(&s->rom, NULL, NULL,
+                                      "xen-pci-pt-rom", d->rom.size);
+        pci_register_bar(&s->dev, PCI_ROM_SLOT, PCI_BASE_ADDRESS_MEM_PREFETCH,
+                         &s->rom);
+
+        XEN_PT_LOG(&s->dev, "Expansion ROM registered (size=0x%08"PRIx64
+                   " base_addr=0x%08"PRIx64")\n",
+                   d->rom.size, d->rom.base_addr);
+    }
+
+    return 0;
+}
+
+static void xen_pt_unregister_regions(XenPCIPassthroughState *s)
+{
+    XenHostPCIDevice *d = &s->real_device;
+    int i;
+
+    for (i = 0; i < PCI_NUM_REGIONS - 1; i++) {
+        XenHostPCIIORegion *r = &d->io_regions[i];
+
+        if (r->base_addr == 0 || r->size == 0) {
+            continue;
+        }
+
+        memory_region_destroy(&s->bar[i]);
+    }
+    if (d->rom.base_addr && d->rom.size) {
+        memory_region_destroy(&s->rom);
+    }
+}
+
+/* region mapping */
+
+static int xen_pt_bar_from_region(XenPCIPassthroughState *s, MemoryRegion *mr)
+{
+    int i = 0;
+
+    for (i = 0; i < PCI_NUM_REGIONS - 1; i++) {
+        if (mr == &s->bar[i]) {
+            return i;
+        }
+    }
+    if (mr == &s->rom) {
+        return PCI_ROM_SLOT;
+    }
+    return -1;
+}
+
+/*
+ * This function checks if an io_region overlaps an io_region from another
+ * device.  The io_region to check is provided with (addr, size and type)
+ * A callback can be provided and will be called for every region that is
+ * overlapped.
+ * The return value indicates if the region is overlappsed */
+struct CheckBarArgs {
+    XenPCIPassthroughState *s;
+    pcibus_t addr;
+    pcibus_t size;
+    uint8_t type;
+    bool rc;
+};
+static void xen_pt_check_bar_overlap(PCIBus *bus, PCIDevice *d, void *opaque)
+{
+    struct CheckBarArgs *arg = opaque;
+    XenPCIPassthroughState *s = arg->s;
+    uint8_t type = arg->type;
+    int i;
+
+    if (d->devfn == s->dev.devfn) {
+        return;
+    }
+
+    /* xxx: This ignores bridges. */
+    for (i = 0; i < PCI_NUM_REGIONS; i++) {
+        const PCIIORegion *r = &d->io_regions[i];
+
+        if (!r->size) {
+            continue;
+        }
+        if ((type & PCI_BASE_ADDRESS_SPACE_IO)
+            != (r->type & PCI_BASE_ADDRESS_SPACE_IO)) {
+            continue;
+        }
+
+        if (ranges_overlap(arg->addr, arg->size, r->addr, r->size)) {
+            XEN_PT_WARN(&s->dev,
+                        "Overlapped to device [%02x:%02x.%d] Region: %i"
+                        " (addr: %#"FMT_PCIBUS", len: %#"FMT_PCIBUS")\n",
+                        pci_bus_num(bus), PCI_SLOT(d->devfn),
+                        PCI_FUNC(d->devfn), i, r->addr, r->size);
+            arg->rc = true;
+        }
+    }
+}
+
+static void xen_pt_region_update(XenPCIPassthroughState *s,
+                                 MemoryRegionSection *sec, bool adding)
+{
+    PCIDevice *d = &s->dev;
+    MemoryRegion *mr = sec->mr;
+    int bar = -1;
+    int rc;
+    int op = adding ? DPCI_ADD_MAPPING : DPCI_REMOVE_MAPPING;
+    struct CheckBarArgs args = {
+        .s = s,
+        .addr = sec->offset_within_address_space,
+        .size = sec->size,
+        .rc = false,
+    };
+
+    bar = xen_pt_bar_from_region(s, mr);
+    if (bar == -1 && (!s->msix || &s->msix->mmio != mr)) {
+        return;
+    }
+
+    if (s->msix && &s->msix->mmio == mr) {
+        if (adding) {
+            s->msix->mmio_base_addr = sec->offset_within_address_space;
+            rc = xen_pt_msix_update_remap(s, s->msix->bar_index);
+        }
+        return;
+    }
+
+    args.type = d->io_regions[bar].type;
+    pci_for_each_device(d->bus, pci_bus_num(d->bus),
+                        xen_pt_check_bar_overlap, &args);
+    if (args.rc) {
+        XEN_PT_WARN(d, "Region: %d (addr: %#"FMT_PCIBUS
+                    ", len: %#"FMT_PCIBUS") is overlapped.\n",
+                    bar, sec->offset_within_address_space, sec->size);
+    }
+
+    if (d->io_regions[bar].type & PCI_BASE_ADDRESS_SPACE_IO) {
+        uint32_t guest_port = sec->offset_within_address_space;
+        uint32_t machine_port = s->bases[bar].access.pio_base;
+        uint32_t size = sec->size;
+        rc = xc_domain_ioport_mapping(xen_xc, xen_domid,
+                                      guest_port, machine_port, size,
+                                      op);
+        if (rc) {
+            XEN_PT_ERR(d, "%s ioport mapping failed! (rc: %i)\n",
+                       adding ? "create new" : "remove old", rc);
+        }
+    } else {
+        pcibus_t guest_addr = sec->offset_within_address_space;
+        pcibus_t machine_addr = s->bases[bar].access.maddr
+            + sec->offset_within_region;
+        pcibus_t size = sec->size;
+        rc = xc_domain_memory_mapping(xen_xc, xen_domid,
+                                      XEN_PFN(guest_addr + XC_PAGE_SIZE - 1),
+                                      XEN_PFN(machine_addr + XC_PAGE_SIZE - 1),
+                                      XEN_PFN(size + XC_PAGE_SIZE - 1),
+                                      op);
+        if (rc) {
+            XEN_PT_ERR(d, "%s mem mapping failed! (rc: %i)\n",
+                       adding ? "create new" : "remove old", rc);
+        }
+    }
+}
+
+static void xen_pt_begin(MemoryListener *l)
+{
+}
+
+static void xen_pt_commit(MemoryListener *l)
+{
+}
+
+static void xen_pt_region_add(MemoryListener *l, MemoryRegionSection *sec)
+{
+    XenPCIPassthroughState *s = container_of(l, XenPCIPassthroughState,
+                                             memory_listener);
+
+    xen_pt_region_update(s, sec, true);
+}
+
+static void xen_pt_region_del(MemoryListener *l, MemoryRegionSection *sec)
+{
+    XenPCIPassthroughState *s = container_of(l, XenPCIPassthroughState,
+                                             memory_listener);
+
+    xen_pt_region_update(s, sec, false);
+}
+
+static void xen_pt_region_nop(MemoryListener *l, MemoryRegionSection *s)
+{
+}
+
+static void xen_pt_log_fns(MemoryListener *l, MemoryRegionSection *s)
+{
+}
+
+static void xen_pt_log_global_fns(MemoryListener *l)
+{
+}
+
+static void xen_pt_eventfd_fns(MemoryListener *l, MemoryRegionSection *s,
+                               bool match_data, uint64_t data, int fd)
+{
+}
+
+static const MemoryListener xen_pt_memory_listener = {
+    .begin = xen_pt_begin,
+    .commit = xen_pt_commit,
+    .region_add = xen_pt_region_add,
+    .region_nop = xen_pt_region_nop,
+    .region_del = xen_pt_region_del,
+    .log_start = xen_pt_log_fns,
+    .log_stop = xen_pt_log_fns,
+    .log_sync = xen_pt_log_fns,
+    .log_global_start = xen_pt_log_global_fns,
+    .log_global_stop = xen_pt_log_global_fns,
+    .eventfd_add = xen_pt_eventfd_fns,
+    .eventfd_del = xen_pt_eventfd_fns,
+    .priority = 10,
+};
+
+/* init */
+
+static int xen_pt_initfn(PCIDevice *d)
+{
+    XenPCIPassthroughState *s = DO_UPCAST(XenPCIPassthroughState, dev, d);
+    int rc = 0;
+    uint8_t machine_irq = 0;
+    int pirq = XEN_PT_UNASSIGNED_PIRQ;
+
+    /* register real device */
+    XEN_PT_LOG(d, "Assigning real physical device %02x:%02x.%d"
+               " to devfn %#x\n",
+               s->hostaddr.bus, s->hostaddr.slot, s->hostaddr.function,
+               s->dev.devfn);
+
+    rc = xen_host_pci_device_get(&s->real_device,
+                                 s->hostaddr.domain, s->hostaddr.bus,
+                                 s->hostaddr.slot, s->hostaddr.function);
+    if (rc) {
+        XEN_PT_ERR(d, "Failed to \"open\" the real pci device. rc: %i\n", rc);
+        return -1;
+    }
+
+    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",
+                   s->real_device.domain, bus, slot, func);
+    }
+
+    /* 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;
+    }
+
+    s->memory_listener = xen_pt_memory_listener;
+
+    /* Handle real device's MMIO/PIO BARs */
+    xen_pt_register_regions(s);
+
+    /* reinitialize each config register to be emulated */
+    if (xen_pt_config_init(s)) {
+        XEN_PT_ERR(d, "PCI Config space initialisation failed.\n");
+        xen_host_pci_device_put(&s->real_device);
+        return -1;
+    }
+
+    /* Bind interrupt */
+    if (!s->dev.config[PCI_INTERRUPT_PIN]) {
+        XEN_PT_LOG(d, "no pin interrupt\n");
+        goto out;
+    }
+
+    machine_irq = s->real_device.irq;
+    rc = xc_physdev_map_pirq(xen_xc, xen_domid, machine_irq, &pirq);
+
+    if (rc < 0) {
+        XEN_PT_ERR(d, "Mapping machine irq %u to pirq %i failed, (rc: %d)\n",
+                   machine_irq, pirq, rc);
+
+        /* Disable PCI intx assertion (turn on bit10 of devctl) */
+        xen_host_pci_set_word(&s->real_device,
+                              PCI_COMMAND,
+                              pci_get_word(s->dev.config + PCI_COMMAND)
+                              | PCI_COMMAND_INTX_DISABLE);
+        machine_irq = 0;
+        s->machine_irq = 0;
+    } else {
+        machine_irq = pirq;
+        s->machine_irq = pirq;
+        xen_pt_mapped_machine_irq[machine_irq]++;
+    }
+
+    /* bind machine_irq to device */
+    if (machine_irq != 0) {
+        uint8_t e_intx = xen_pt_pci_intx(s);
+
+        rc = xc_domain_bind_pt_pci_irq(xen_xc, xen_domid, machine_irq,
+                                       pci_bus_num(d->bus),
+                                       PCI_SLOT(d->devfn),
+                                       e_intx);
+        if (rc < 0) {
+            XEN_PT_ERR(d, "Binding of interrupt %i failed! (rc: %d)\n",
+                       e_intx, rc);
+
+            /* Disable PCI intx assertion (turn on bit10 of devctl) */
+            xen_host_pci_set_word(&s->real_device, PCI_COMMAND,
+                                  *(uint16_t *)(&s->dev.config[PCI_COMMAND])
+                                  | PCI_COMMAND_INTX_DISABLE);
+            xen_pt_mapped_machine_irq[machine_irq]--;
+
+            if (xen_pt_mapped_machine_irq[machine_irq] == 0) {
+                if (xc_physdev_unmap_pirq(xen_xc, xen_domid, machine_irq)) {
+                    XEN_PT_ERR(d, "Unmapping of machine interrupt %i failed!"
+                               " (rc: %d)\n", machine_irq, rc);
+                }
+            }
+            s->machine_irq = 0;
+        }
+    }
+
+out:
+    memory_listener_register(&s->memory_listener, NULL);
+    XEN_PT_LOG(d, "Real physical device %02x:%02x.%d registered successfuly!\n",
+               bus, slot, func);
+
+    return 0;
+}
+
+static int xen_pt_unregister_device(PCIDevice *d)
+{
+    XenPCIPassthroughState *s = DO_UPCAST(XenPCIPassthroughState, dev, 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, rc: %d)"
+                       " But bravely continuing on..\n",
+                       'a' + intx, machine_irq, rc);
+        }
+    }
+
+    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. (rc: %d)"
+                           " But bravely continuing on..\n",
+                           machine_irq, rc);
+            }
+        }
+    }
+
+    /* delete all emulated config registers */
+    xen_pt_config_delete(s);
+
+    xen_pt_unregister_regions(s);
+    memory_listener_unregister(&s->memory_listener);
+
+    xen_host_pci_device_put(&s->real_device);
+
+    return 0;
+}
+
+static Property xen_pci_passthrough_properties[] = {
+    DEFINE_PROP_PCI_HOST_DEVADDR("hostaddr", XenPCIPassthroughState, hostaddr),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void xen_pci_passthrough_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+
+    k->init = xen_pt_initfn;
+    k->exit = xen_pt_unregister_device;
+    k->config_read = xen_pt_pci_read_config;
+    k->config_write = xen_pt_pci_write_config;
+    dc->desc = "Assign an host PCI device with Xen";
+    dc->props = xen_pci_passthrough_properties;
+};
+
+static TypeInfo xen_pci_passthrough_info = {
+    .name = "xen-pci-passthrough",
+    .parent = TYPE_PCI_DEVICE,
+    .instance_size = sizeof(XenPCIPassthroughState),
+    .class_init = xen_pci_passthrough_class_init,
+};
+
+static void xen_pci_passthrough_register_types(void)
+{
+    type_register_static(&xen_pci_passthrough_info);
+}
+
+type_init(xen_pci_passthrough_register_types)

hw/xen_pt.h

+#ifndef XEN_PT_H
+#define XEN_PT_H
+
+#include "qemu-common.h"
+#include "xen_common.h"
+#include "pci.h"
+#include "xen-host-pci-device.h"
+
+void xen_pt_log(const PCIDevice *d, const char *f, ...) GCC_FMT_ATTR(2, 3);
+
+#define XEN_PT_ERR(d, _f, _a...) xen_pt_log(d, "%s: Error: "_f, __func__, ##_a)
+
+#ifdef XEN_PT_LOGGING_ENABLED
+#  define XEN_PT_LOG(d, _f, _a...)  xen_pt_log(d, "%s: " _f, __func__, ##_a)
+#  define XEN_PT_WARN(d, _f, _a...) \
+    xen_pt_log(d, "%s: Warning: "_f, __func__, ##_a)
+#else
+#  define XEN_PT_LOG(d, _f, _a...)
+#  define XEN_PT_WARN(d, _f, _a...)
+#endif
+
+#ifdef XEN_PT_DEBUG_PCI_CONFIG_ACCESS
+#  define XEN_PT_LOG_CONFIG(d, addr, val, len) \
+    xen_pt_log(d, "%s: address=0x%04x val=0x%08x len=%d\n", \
+               __func__, addr, val, len)
+#else
+#  define XEN_PT_LOG_CONFIG(d, addr, val, len)
+#endif
+
+
+/* Helper */
+#define XEN_PFN(x) ((x) >> XC_PAGE_SHIFT)
+
+typedef struct XenPTRegInfo XenPTRegInfo;
+typedef struct XenPTReg XenPTReg;
+
+typedef struct XenPCIPassthroughState XenPCIPassthroughState;
+
+/* function type for config reg */
+typedef int (*xen_pt_conf_reg_init)
+    (XenPCIPassthroughState *, XenPTRegInfo *, uint32_t real_offset,
+     uint32_t *data);
+typedef int (*xen_pt_conf_dword_write)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint32_t *val, uint32_t dev_value, uint32_t valid_mask);
+typedef int (*xen_pt_conf_word_write)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint16_t *val, uint16_t dev_value, uint16_t valid_mask);
+typedef int (*xen_pt_conf_byte_write)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint8_t *val, uint8_t dev_value, uint8_t valid_mask);
+typedef int (*xen_pt_conf_dword_read)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint32_t *val, uint32_t valid_mask);
+typedef int (*xen_pt_conf_word_read)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint16_t *val, uint16_t valid_mask);
+typedef int (*xen_pt_conf_byte_read)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint8_t *val, uint8_t valid_mask);
+
+#define XEN_PT_BAR_ALLF 0xFFFFFFFF
+#define XEN_PT_BAR_UNMAPPED (-1)
+
+#define PCI_CAP_MAX 48
+
+
+typedef enum {
+    XEN_PT_GRP_TYPE_HARDWIRED = 0,  /* 0 Hardwired reg group */
+    XEN_PT_GRP_TYPE_EMU,            /* emul reg group */
+} XenPTRegisterGroupType;
+
+typedef enum {
+    XEN_PT_BAR_FLAG_MEM = 0,        /* Memory type BAR */
+    XEN_PT_BAR_FLAG_IO,             /* I/O type BAR */
+    XEN_PT_BAR_FLAG_UPPER,          /* upper 64bit BAR */
+    XEN_PT_BAR_FLAG_UNUSED,         /* unused BAR */
+} XenPTBarFlag;
+
+
+typedef struct XenPTRegion {
+    /* BAR flag */
+    XenPTBarFlag bar_flag;
+    /* Translation of the emulated address */
+    union {
+        uint64_t maddr;
+        uint64_t pio_base;
+        uint64_t u;
+    } access;
+} XenPTRegion;
+
+/* XenPTRegInfo declaration
+ * - only for emulated register (either a part or whole bit).
+ * - for passthrough register that need special behavior (like interacting with
+ *   other component), set emu_mask to all 0 and specify r/w func properly.
+ * - do NOT use ALL F for init_val, otherwise the tbl will not be registered.
+ */
+
+/* emulated register infomation */
+struct XenPTRegInfo {
+    uint32_t offset;
+    uint32_t size;
+    uint32_t init_val;
+    /* reg read only field mask (ON:RO/ROS, OFF:other) */
+    uint32_t ro_mask;
+    /* reg emulate field mask (ON:emu, OFF:passthrough) */
+    uint32_t emu_mask;
+    /* no write back allowed */
+    uint32_t no_wb;
+    xen_pt_conf_reg_init init;
+    /* read/write function pointer
+     * for double_word/word/byte size */
+    union {
+        struct {
+            xen_pt_conf_dword_write write;
+            xen_pt_conf_dword_read read;
+        } dw;
+        struct {
+            xen_pt_conf_word_write write;
+            xen_pt_conf_word_read read;
+        } w;
+        struct {
+            xen_pt_conf_byte_write write;
+            xen_pt_conf_byte_read read;
+        } b;
+    } u;
+};
+
+/* emulated register management */
+struct XenPTReg {
+    QLIST_ENTRY(XenPTReg) entries;
+    XenPTRegInfo *reg;
+    uint32_t data; /* emulated value */
+};
+
+typedef struct XenPTRegGroupInfo XenPTRegGroupInfo;
+
+/* emul reg group size initialize method */
+typedef int (*xen_pt_reg_size_init_fn)
+    (XenPCIPassthroughState *, const XenPTRegGroupInfo *,
+     uint32_t base_offset, uint8_t *size);
+
+/* emulated register group infomation */
+struct XenPTRegGroupInfo {
+    uint8_t grp_id;
+    XenPTRegisterGroupType grp_type;
+    uint8_t grp_size;
+    xen_pt_reg_size_init_fn size_init;
+    XenPTRegInfo *emu_regs;
+};
+
+/* emul register group management table */
+typedef struct XenPTRegGroup {
+    QLIST_ENTRY(XenPTRegGroup) entries;
+    const XenPTRegGroupInfo *reg_grp;
+    uint32_t base_offset;
+    uint8_t size;
+    QLIST_HEAD(, XenPTReg) reg_tbl_list;
+} XenPTRegGroup;
+
+
+#define XEN_PT_UNASSIGNED_PIRQ (-1)
+typedef struct XenPTMSI {
+    uint16_t flags;
+    uint32_t addr_lo;  /* guest message address */
+    uint32_t addr_hi;  /* guest message upper address */
+    uint16_t data;     /* guest message data */
+    uint32_t ctrl_offset; /* saved control offset */
+    int pirq;          /* guest pirq corresponding */
+    bool initialized;  /* when guest MSI is initialized */
+    bool mapped;       /* when pirq is mapped */
+} XenPTMSI;
+
+typedef struct XenPTMSIXEntry {
+    int pirq;
+    uint64_t addr;
+    uint32_t data;
+    uint32_t vector_ctrl;
+    bool updated; /* indicate whether MSI ADDR or DATA is updated */
+} XenPTMSIXEntry;
+typedef struct XenPTMSIX {
+    uint32_t ctrl_offset;
+    bool enabled;
+    int total_entries;
+    int bar_index;
+    uint64_t table_base;
+    uint32_t table_offset_adjust; /* page align mmap */
+    uint64_t mmio_base_addr;
+    MemoryRegion mmio;
+    void *phys_iomem_base;
+    XenPTMSIXEntry msix_entry[0];
+} XenPTMSIX;
+
+struct XenPCIPassthroughState {
+    PCIDevice dev;
+
+    PCIHostDeviceAddress hostaddr;
+    bool is_virtfn;
+    XenHostPCIDevice real_device;
+    XenPTRegion bases[PCI_NUM_REGIONS]; /* Access regions */
+    QLIST_HEAD(, XenPTRegGroup) reg_grps;
+
+    uint32_t machine_irq;
+
+    XenPTMSI *msi;
+    XenPTMSIX *msix;
+
+    MemoryRegion bar[PCI_NUM_REGIONS - 1];
+    MemoryRegion rom;
+
+    MemoryListener memory_listener;
+};
+
+int xen_pt_config_init(XenPCIPassthroughState *s);
+void xen_pt_config_delete(XenPCIPassthroughState *s);
+XenPTRegGroup *xen_pt_find_reg_grp(XenPCIPassthroughState *s, uint32_t address);
+XenPTReg *xen_pt_find_reg(XenPTRegGroup *reg_grp, uint32_t address);
+int xen_pt_bar_offset_to_index(uint32_t offset);
+
+static inline pcibus_t xen_pt_get_emul_size(XenPTBarFlag flag, pcibus_t r_size)
+{
+    /* align resource size (memory type only) */
+    if (flag == XEN_PT_BAR_FLAG_MEM) {
+        return (r_size + XC_PAGE_SIZE - 1) & XC_PAGE_MASK;
+    } else {
+        return r_size;
+    }
+}
+
+/* INTx */
+/* The PCI Local Bus Specification, Rev. 3.0,
+ * Section 6.2.4 Miscellaneous Registers, pp 223
+ * outlines 5 valid values for the interrupt pin (intx).
+ *  0: For devices (or device functions) that don't use an interrupt in
+ *  1: INTA#
+ *  2: INTB#
+ *  3: INTC#
+ *  4: INTD#
+ *
+ * Xen uses the following 4 values for intx
+ *  0: INTA#
+ *  1: INTB#
+ *  2: INTC#
+ *  3: INTD#
+ *
+ * Observing that these list of values are not the same, xen_pt_pci_read_intx()
+ * uses the following mapping from hw to xen values.
+ * This seems to reflect the current usage within Xen.
+ *
+ * PCI hardware    | Xen | Notes
+ * ----------------+-----+----------------------------------------------------
+ * 0               | 0   | No interrupt
+ * 1               | 0   | INTA#
+ * 2               | 1   | INTB#
+ * 3               | 2   | INTC#
+ * 4               | 3   | INTD#
+ * any other value | 0   | This should never happen, log error message
+ */
+
+static inline uint8_t xen_pt_pci_read_intx(XenPCIPassthroughState *s)
+{
+    uint8_t v = 0;
+    xen_host_pci_get_byte(&s->real_device, PCI_INTERRUPT_PIN, &v);
+    return v;
+}
+
+static inline uint8_t xen_pt_pci_intx(XenPCIPassthroughState *s)
+{
+    uint8_t r_val = xen_pt_pci_read_intx(s);
+
+    XEN_PT_LOG(&s->dev, "intx=%i\n", r_val);
+    if (r_val < 1 || r_val > 4) {
+        XEN_PT_LOG(&s->dev, "Interrupt pin read from hardware is out of range:"
+                   " value=%i, acceptable range is 1 - 4\n", r_val);
+        r_val = 0;
+    } else {
+        r_val -= 1;
+    }
+
+    return r_val;
+}
+
+/* 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);
+
+int xen_pt_msix_init(XenPCIPassthroughState *s, uint32_t base);
+void xen_pt_msix_delete(XenPCIPassthroughState *s);
+int xen_pt_msix_update(XenPCIPassthroughState *s);
+int xen_pt_msix_update_remap(XenPCIPassthroughState *s, int bar_index);
+void xen_pt_msix_disable(XenPCIPassthroughState *s);
+
+static inline bool xen_pt_has_msix_mapping(XenPCIPassthroughState *s, int bar)
+{
+    return s->msix && s->msix->bar_index == bar;
+}
+
+
+#endif /* !XEN_PT_H */

hw/xen_pt_config_init.c

+/*
+ * Copyright (c) 2007, Neocleus Corporation.
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Alex Novik <alex@neocleus.com>
+ * Allen Kay <allen.m.kay@intel.com>
+ * Guy Zana <guy@neocleus.com>
+ *
+ * This file implements direct PCI assignment to a HVM guest
+ */
+
+#include "qemu-timer.h"
+#include "xen_backend.h"
+#include "xen_pt.h"
+
+#define XEN_PT_MERGE_VALUE(value, data, val_mask) \
+    (((value) & (val_mask)) | ((data) & ~(val_mask)))
+
+#define XEN_PT_INVALID_REG          0xFFFFFFFF      /* invalid register value */
+
+/* prototype */
+
+static int xen_pt_ptr_reg_init(XenPCIPassthroughState *s, XenPTRegInfo *reg,
+                               uint32_t real_offset, uint32_t *data);
+
+
+/* helper */
+
+/* A return value of 1 means the capability should NOT be exposed to guest. */
+static int xen_pt_hide_dev_cap(const XenHostPCIDevice *d, uint8_t grp_id)
+{
+    switch (grp_id) {
+    case PCI_CAP_ID_EXP:
+        /* The PCI Express Capability Structure of the VF of Intel 82599 10GbE
+         * Controller looks trivial, e.g., the PCI Express Capabilities
+         * Register is 0. We should not try to expose it to guest.
+         *
+         * The datasheet is available at
+         * http://download.intel.com/design/network/datashts/82599_datasheet.pdf
+         *
+         * See 'Table 9.7. VF PCIe Configuration Space' of the datasheet, the
+         * PCI Express Capability Structure of the VF of Intel 82599 10GbE
+         * Controller looks trivial, e.g., the PCI Express Capabilities
+         * Register is 0, so the Capability Version is 0 and
+         * xen_pt_pcie_size_init() would fail.
+         */
+        if (d->vendor_id == PCI_VENDOR_ID_INTEL &&
+            d->device_id == PCI_DEVICE_ID_INTEL_82599_SFP_VF) {
+            return 1;
+        }
+        break;
+    }
+    return 0;
+}
+
+/*   find emulate register group entry */
+XenPTRegGroup *xen_pt_find_reg_grp(XenPCIPassthroughState *s, uint32_t address)
+{
+    XenPTRegGroup *entry = NULL;
+
+    /* find register group entry */
+    QLIST_FOREACH(entry, &s->reg_grps, entries) {
+        /* check address */
+        if ((entry->base_offset <= address)
+            && ((entry->base_offset + entry->size) > address)) {
+            return entry;
+        }
+    }
+
+    /* group entry not found */
+    return NULL;
+}
+
+/* find emulate register entry */
+XenPTReg *xen_pt_find_reg(XenPTRegGroup *reg_grp, uint32_t address)
+{
+    XenPTReg *reg_entry = NULL;
+    XenPTRegInfo *reg = NULL;
+    uint32_t real_offset = 0;
+
+    /* find register entry */
+    QLIST_FOREACH(reg_entry, &reg_grp->reg_tbl_list, entries) {
+        reg = reg_entry->reg;
+        real_offset = reg_grp->base_offset + reg->offset;
+        /* check address */
+        if ((real_offset <= address)
+            && ((real_offset + reg->size) > address)) {
+            return reg_entry;
+        }
+    }
+
+    return NULL;
+}
+
+
+/****************
+ * general register functions
+ */
+
+/* register initialization function */
+
+static int xen_pt_common_reg_init(XenPCIPassthroughState *s,
+                                  XenPTRegInfo *reg, uint32_t real_offset,
+                                  uint32_t *data)
+{
+    *data = reg->init_val;
+    return 0;
+}
+
+/* Read register functions */
+
+static int xen_pt_byte_reg_read(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
+                                uint8_t *value, uint8_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint8_t valid_emu_mask = 0;
+
+    /* emulate byte register */
+    valid_emu_mask = reg->emu_mask & valid_mask;
+    *value = XEN_PT_MERGE_VALUE(*value, cfg_entry->data, ~valid_emu_mask);
+
+    return 0;
+}
+static int xen_pt_word_reg_read(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
+                                uint16_t *value, uint16_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint16_t valid_emu_mask = 0;
+
+    /* emulate word register */
+    valid_emu_mask = reg->emu_mask & valid_mask;
+    *value = XEN_PT_MERGE_VALUE(*value, cfg_entry->data, ~valid_emu_mask);
+
+    return 0;
+}
+static int xen_pt_long_reg_read(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
+                                uint32_t *value, uint32_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint32_t valid_emu_mask = 0;
+
+    /* emulate long register */
+    valid_emu_mask = reg->emu_mask & valid_mask;
+    *value = XEN_PT_MERGE_VALUE(*value, cfg_entry->data, ~valid_emu_mask);
+
+    return 0;
+}
+
+/* Write register functions */
+
+static int xen_pt_byte_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
+                                 uint8_t *val, uint8_t dev_value,
+                                 uint8_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint8_t writable_mask = 0;
+    uint8_t throughable_mask = 0;
+
+    /* modify emulate register */
+    writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+
+    /* create value for writing to I/O device register */
+    throughable_mask = ~reg->emu_mask & valid_mask;
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    return 0;
+}
+static int xen_pt_word_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
+                                 uint16_t *val, uint16_t dev_value,
+                                 uint16_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint16_t writable_mask = 0;
+    uint16_t throughable_mask = 0;
+
+    /* modify emulate register */
+    writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+
+    /* create value for writing to I/O device register */
+    throughable_mask = ~reg->emu_mask & valid_mask;
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    return 0;
+}
+static int xen_pt_long_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
+                                 uint32_t *val, uint32_t dev_value,
+                                 uint32_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint32_t writable_mask = 0;
+    uint32_t throughable_mask = 0;
+
+    /* modify emulate register */
+    writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+
+    /* create value for writing to I/O device register */
+    throughable_mask = ~reg->emu_mask & valid_mask;
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    return 0;
+}
+
+
+/* XenPTRegInfo declaration
+ * - only for emulated register (either a part or whole bit).
+ * - for passthrough register that need special behavior (like interacting with
+ *   other component), set emu_mask to all 0 and specify r/w func properly.
+ * - do NOT use ALL F for init_val, otherwise the tbl will not be registered.
+ */
+
+/********************
+ * Header Type0
+ */
+
+static int xen_pt_vendor_reg_init(XenPCIPassthroughState *s,
+                                  XenPTRegInfo *reg, uint32_t real_offset,
+                                  uint32_t *data)
+{
+    *data = s->real_device.vendor_id;
+    return 0;
+}
+static int xen_pt_device_reg_init(XenPCIPassthroughState *s,
+                                  XenPTRegInfo *reg, uint32_t real_offset,
+                                  uint32_t *data)
+{
+    *data = s->real_device.device_id;
+    return 0;
+}
+static int xen_pt_status_reg_init(XenPCIPassthroughState *s,
+                                  XenPTRegInfo *reg, uint32_t real_offset,
+                                  uint32_t *data)
+{
+    XenPTRegGroup *reg_grp_entry = NULL;
+    XenPTReg *reg_entry = NULL;
+    uint32_t reg_field = 0;
+
+    /* find Header register group */
+    reg_grp_entry = xen_pt_find_reg_grp(s, PCI_CAPABILITY_LIST);
+    if (reg_grp_entry) {
+        /* find Capabilities Pointer register */
+        reg_entry = xen_pt_find_reg(reg_grp_entry, PCI_CAPABILITY_LIST);
+        if (reg_entry) {
+            /* check Capabilities Pointer register */
+            if (reg_entry->data) {
+                reg_field |= PCI_STATUS_CAP_LIST;
+            } else {
+                reg_field &= ~PCI_STATUS_CAP_LIST;
+            }
+        } else {
+            xen_shutdown_fatal_error("Internal error: Couldn't find XenPTReg*"
+                                     " for Capabilities Pointer register."
+                                     " (%s)\n", __func__);
+            return -1;
+        }
+    } else {
+        xen_shutdown_fatal_error("Internal error: Couldn't find XenPTRegGroup"
+                                 " for Header. (%s)\n", __func__);
+        return -1;
+    }
+
+    *data = reg_field;
+    return 0;
+}
+static int xen_pt_header_type_reg_init(XenPCIPassthroughState *s,
+                                       XenPTRegInfo *reg, uint32_t real_offset,
+                                       uint32_t *data)
+{
+    /* read PCI_HEADER_TYPE */
+    *data = reg->init_val | 0x80;
+    return 0;
+}
+
+/* initialize Interrupt Pin register */
+static int xen_pt_irqpin_reg_init(XenPCIPassthroughState *s,
+                                  XenPTRegInfo *reg, uint32_t real_offset,
+                                  uint32_t *data)
+{
+    *data = xen_pt_pci_read_intx(s);
+    return 0;
+}
+
+/* Command register */
+static int xen_pt_cmd_reg_read(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
+                               uint16_t *value, uint16_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint16_t valid_emu_mask = 0;
+    uint16_t emu_mask = reg->emu_mask;
+
+    if (s->is_virtfn) {
+        emu_mask |= PCI_COMMAND_MEMORY;
+    }
+
+    /* emulate word register */
+    valid_emu_mask = emu_mask & valid_mask;
+    *value = XEN_PT_MERGE_VALUE(*value, cfg_entry->data, ~valid_emu_mask);
+
+    return 0;
+}
+static int xen_pt_cmd_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
+                                uint16_t *val, uint16_t dev_value,
+                                uint16_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint16_t writable_mask = 0;
+    uint16_t throughable_mask = 0;
+    uint16_t emu_mask = reg->emu_mask;
+
+    if (s->is_virtfn) {
+        emu_mask |= PCI_COMMAND_MEMORY;
+    }
+
+    /* modify emulate register */
+    writable_mask = ~reg->ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+
+    /* create value for writing to I/O device register */
+    throughable_mask = ~emu_mask & valid_mask;
+
+    if (*val & PCI_COMMAND_INTX_DISABLE) {
+        throughable_mask |= PCI_COMMAND_INTX_DISABLE;
+    } else {
+        if (s->machine_irq) {
+            throughable_mask |= PCI_COMMAND_INTX_DISABLE;
+        }
+    }
+
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    return 0;
+}
+
+/* BAR */
+#define XEN_PT_BAR_MEM_RO_MASK    0x0000000F  /* BAR ReadOnly mask(Memory) */
+#define XEN_PT_BAR_MEM_EMU_MASK   0xFFFFFFF0  /* BAR emul mask(Memory) */
+#define XEN_PT_BAR_IO_RO_MASK     0x00000003  /* BAR ReadOnly mask(I/O) */
+#define XEN_PT_BAR_IO_EMU_MASK    0xFFFFFFFC  /* BAR emul mask(I/O) */
+
+static XenPTBarFlag xen_pt_bar_reg_parse(XenPCIPassthroughState *s,
+                                         XenPTRegInfo *reg)
+{
+    PCIDevice *d = &s->dev;
+    XenPTRegion *region = NULL;
+    PCIIORegion *r;
+    int index = 0;
+
+    /* check 64bit BAR */
+    index = xen_pt_bar_offset_to_index(reg->offset);
+    if ((0 < index) && (index < PCI_ROM_SLOT)) {
+        int type = s->real_device.io_regions[index - 1].type;
+
+        if ((type & XEN_HOST_PCI_REGION_TYPE_MEM)
+            && (type & XEN_HOST_PCI_REGION_TYPE_MEM_64)) {
+            region = &s->bases[index - 1];
+            if (region->bar_flag != XEN_PT_BAR_FLAG_UPPER) {
+                return XEN_PT_BAR_FLAG_UPPER;
+            }
+        }
+    }
+
+    /* check unused BAR */
+    r = &d->io_regions[index];
+    if (r->size == 0) {
+        return XEN_PT_BAR_FLAG_UNUSED;
+    }
+
+    /* for ExpROM BAR */
+    if (index == PCI_ROM_SLOT) {
+        return XEN_PT_BAR_FLAG_MEM;
+    }
+
+    /* check BAR I/O indicator */
+    if (s->real_device.io_regions[index].type & XEN_HOST_PCI_REGION_TYPE_IO) {
+        return XEN_PT_BAR_FLAG_IO;
+    } else {
+        return XEN_PT_BAR_FLAG_MEM;
+    }
+}
+
+static inline uint32_t base_address_with_flags(XenHostPCIIORegion *hr)
+{
+    if (hr->type & XEN_HOST_PCI_REGION_TYPE_IO) {
+        return hr->base_addr | (hr->bus_flags & ~PCI_BASE_ADDRESS_IO_MASK);
+    } else {
+        return hr->base_addr | (hr->bus_flags & ~PCI_BASE_ADDRESS_MEM_MASK);
+    }
+}
+
+static int xen_pt_bar_reg_init(XenPCIPassthroughState *s, XenPTRegInfo *reg,
+                               uint32_t real_offset, uint32_t *data)
+{
+    uint32_t reg_field = 0;
+    int index;
+
+    index = xen_pt_bar_offset_to_index(reg->offset);
+    if (index < 0 || index >= PCI_NUM_REGIONS) {
+        XEN_PT_ERR(&s->dev, "Internal error: Invalid BAR index [%d].\n", index);
+        return -1;
+    }
+
+    /* set BAR flag */
+    s->bases[index].bar_flag = xen_pt_bar_reg_parse(s, reg);
+    if (s->bases[index].bar_flag == XEN_PT_BAR_FLAG_UNUSED) {
+        reg_field = XEN_PT_INVALID_REG;
+    }
+
+    *data = reg_field;
+    return 0;
+}
+static int xen_pt_bar_reg_read(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
+                               uint32_t *value, uint32_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint32_t valid_emu_mask = 0;
+    uint32_t bar_emu_mask = 0;
+    int index;
+
+    /* get BAR index */
+    index = xen_pt_bar_offset_to_index(reg->offset);
+    if (index < 0 || index >= PCI_NUM_REGIONS) {
+        XEN_PT_ERR(&s->dev, "Internal error: Invalid BAR index [%d].\n", index);
+        return -1;
+    }
+
+    /* use fixed-up value from kernel sysfs */
+    *value = base_address_with_flags(&s->real_device.io_regions[index]);
+
+    /* set emulate mask depend on BAR flag */
+    switch (s->bases[index].bar_flag) {
+    case XEN_PT_BAR_FLAG_MEM:
+        bar_emu_mask = XEN_PT_BAR_MEM_EMU_MASK;
+        break;
+    case XEN_PT_BAR_FLAG_IO:
+        bar_emu_mask = XEN_PT_BAR_IO_EMU_MASK;
+        break;
+    case XEN_PT_BAR_FLAG_UPPER:
+        bar_emu_mask = XEN_PT_BAR_ALLF;
+        break;
+    default:
+        break;
+    }
+
+    /* emulate BAR */
+    valid_emu_mask = bar_emu_mask & valid_mask;
+    *value = XEN_PT_MERGE_VALUE(*value, cfg_entry->data, ~valid_emu_mask);
+
+    return 0;
+}
+static int xen_pt_bar_reg_write(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
+                                uint32_t *val, uint32_t dev_value,
+                                uint32_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    XenPTRegion *base = NULL;
+    PCIDevice *d = &s->dev;
+    const PCIIORegion *r;
+    uint32_t writable_mask = 0;
+    uint32_t throughable_mask = 0;
+    uint32_t bar_emu_mask = 0;
+    uint32_t bar_ro_mask = 0;
+    uint32_t r_size = 0;
+    int index = 0;
+
+    index = xen_pt_bar_offset_to_index(reg->offset);
+    if (index < 0 || index >= PCI_NUM_REGIONS) {
+        XEN_PT_ERR(d, "Internal error: Invalid BAR index [%d].\n", index);
+        return -1;
+    }
+
+    r = &d->io_regions[index];
+    base = &s->bases[index];
+    r_size = xen_pt_get_emul_size(base->bar_flag, r->size);
+
+    /* set emulate mask and read-only mask values depend on the BAR flag */
+    switch (s->bases[index].bar_flag) {
+    case XEN_PT_BAR_FLAG_MEM:
+        bar_emu_mask = XEN_PT_BAR_MEM_EMU_MASK;
+        bar_ro_mask = XEN_PT_BAR_MEM_RO_MASK | (r_size - 1);
+        break;
+    case XEN_PT_BAR_FLAG_IO:
+        bar_emu_mask = XEN_PT_BAR_IO_EMU_MASK;
+        bar_ro_mask = XEN_PT_BAR_IO_RO_MASK | (r_size - 1);
+        break;
+    case XEN_PT_BAR_FLAG_UPPER:
+        bar_emu_mask = XEN_PT_BAR_ALLF;
+        bar_ro_mask = 0;    /* all upper 32bit are R/W */
+        break;
+    default:
+        break;
+    }
+
+    /* modify emulate register */
+    writable_mask = bar_emu_mask & ~bar_ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+
+    /* check whether we need to update the virtual region address or not */
+    switch (s->bases[index].bar_flag) {
+    case XEN_PT_BAR_FLAG_MEM:
+        /* nothing to do */
+        break;
+    case XEN_PT_BAR_FLAG_IO:
+        /* nothing to do */
+        break;
+    case XEN_PT_BAR_FLAG_UPPER:
+        if (cfg_entry->data) {
+            if (cfg_entry->data != (XEN_PT_BAR_ALLF & ~bar_ro_mask)) {
+                XEN_PT_WARN(d, "Guest attempt to set high MMIO Base Address. "
+                            "Ignore mapping. "
+                            "(offset: 0x%02x, high address: 0x%08x)\n",
+                            reg->offset, cfg_entry->data);
+            }
+        }
+        break;
+    default:
+        break;
+    }
+
+    /* create value for writing to I/O device register */
+    throughable_mask = ~bar_emu_mask & valid_mask;
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    return 0;
+}
+
+/* write Exp ROM BAR */
+static int xen_pt_exp_rom_bar_reg_write(XenPCIPassthroughState *s,
+                                        XenPTReg *cfg_entry, uint32_t *val,
+                                        uint32_t dev_value, uint32_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    XenPTRegion *base = NULL;
+    PCIDevice *d = (PCIDevice *)&s->dev;
+    uint32_t writable_mask = 0;
+    uint32_t throughable_mask = 0;
+    pcibus_t r_size = 0;
+    uint32_t bar_emu_mask = 0;
+    uint32_t bar_ro_mask = 0;
+
+    r_size = d->io_regions[PCI_ROM_SLOT].size;
+    base = &s->bases[PCI_ROM_SLOT];
+    /* align memory type resource size */
+    r_size = xen_pt_get_emul_size(base->bar_flag, r_size);
+
+    /* set emulate mask and read-only mask */
+    bar_emu_mask = reg->emu_mask;
+    bar_ro_mask = (reg->ro_mask | (r_size - 1)) & ~PCI_ROM_ADDRESS_ENABLE;
+
+    /* modify emulate register */
+    writable_mask = ~bar_ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+
+    /* create value for writing to I/O device register */
+    throughable_mask = ~bar_emu_mask & valid_mask;
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    return 0;
+}
+
+/* Header Type0 reg static infomation table */
+static XenPTRegInfo xen_pt_emu_reg_header0[] = {
+    /* Vendor ID reg */
+    {
+        .offset     = PCI_VENDOR_ID,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0xFFFF,
+        .emu_mask   = 0xFFFF,
+        .init       = xen_pt_vendor_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_word_reg_write,
+    },
+    /* Device ID reg */
+    {
+        .offset     = PCI_DEVICE_ID,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0xFFFF,
+        .emu_mask   = 0xFFFF,
+        .init       = xen_pt_device_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_word_reg_write,
+    },
+    /* Command reg */
+    {
+        .offset     = PCI_COMMAND,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0xF880,
+        .emu_mask   = 0x0740,
+        .init       = xen_pt_common_reg_init,
+        .u.w.read   = xen_pt_cmd_reg_read,
+        .u.w.write  = xen_pt_cmd_reg_write,
+    },
+    /* Capabilities Pointer reg */
+    {
+        .offset     = PCI_CAPABILITY_LIST,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0xFF,
+        .emu_mask   = 0xFF,
+        .init       = xen_pt_ptr_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    /* Status reg */
+    /* use emulated Cap Ptr value to initialize,
+     * so need to be declared after Cap Ptr reg
+     */
+    {
+        .offset     = PCI_STATUS,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0x06FF,
+        .emu_mask   = 0x0010,
+        .init       = xen_pt_status_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_word_reg_write,
+    },
+    /* Cache Line Size reg */
+    {
+        .offset     = PCI_CACHE_LINE_SIZE,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0x00,
+        .emu_mask   = 0xFF,
+        .init       = xen_pt_common_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    /* Latency Timer reg */
+    {
+        .offset     = PCI_LATENCY_TIMER,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0x00,
+        .emu_mask   = 0xFF,
+        .init       = xen_pt_common_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    /* Header Type reg */
+    {
+        .offset     = PCI_HEADER_TYPE,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0xFF,
+        .emu_mask   = 0x00,
+        .init       = xen_pt_header_type_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    /* Interrupt Line reg */
+    {
+        .offset     = PCI_INTERRUPT_LINE,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0x00,
+        .emu_mask   = 0xFF,
+        .init       = xen_pt_common_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    /* Interrupt Pin reg */
+    {
+        .offset     = PCI_INTERRUPT_PIN,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0xFF,
+        .emu_mask   = 0xFF,
+        .init       = xen_pt_irqpin_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    /* BAR 0 reg */
+    /* mask of BAR need to be decided later, depends on IO/MEM type */
+    {
+        .offset     = PCI_BASE_ADDRESS_0,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .init       = xen_pt_bar_reg_init,
+        .u.dw.read  = xen_pt_bar_reg_read,
+        .u.dw.write = xen_pt_bar_reg_write,
+    },
+    /* BAR 1 reg */
+    {
+        .offset     = PCI_BASE_ADDRESS_1,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .init       = xen_pt_bar_reg_init,
+        .u.dw.read  = xen_pt_bar_reg_read,
+        .u.dw.write = xen_pt_bar_reg_write,
+    },
+    /* BAR 2 reg */
+    {
+        .offset     = PCI_BASE_ADDRESS_2,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .init       = xen_pt_bar_reg_init,
+        .u.dw.read  = xen_pt_bar_reg_read,
+        .u.dw.write = xen_pt_bar_reg_write,
+    },
+    /* BAR 3 reg */
+    {
+        .offset     = PCI_BASE_ADDRESS_3,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .init       = xen_pt_bar_reg_init,
+        .u.dw.read  = xen_pt_bar_reg_read,
+        .u.dw.write = xen_pt_bar_reg_write,
+    },
+    /* BAR 4 reg */
+    {
+        .offset     = PCI_BASE_ADDRESS_4,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .init       = xen_pt_bar_reg_init,
+        .u.dw.read  = xen_pt_bar_reg_read,
+        .u.dw.write = xen_pt_bar_reg_write,
+    },
+    /* BAR 5 reg */
+    {
+        .offset     = PCI_BASE_ADDRESS_5,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .init       = xen_pt_bar_reg_init,
+        .u.dw.read  = xen_pt_bar_reg_read,
+        .u.dw.write = xen_pt_bar_reg_write,
+    },
+    /* Expansion ROM BAR reg */
+    {
+        .offset     = PCI_ROM_ADDRESS,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .ro_mask    = 0x000007FE,
+        .emu_mask   = 0xFFFFF800,
+        .init       = xen_pt_bar_reg_init,
+        .u.dw.read  = xen_pt_long_reg_read,
+        .u.dw.write = xen_pt_exp_rom_bar_reg_write,
+    },
+    {
+        .size = 0,
+    },
+};
+
+
+/*********************************
+ * Vital Product Data Capability
+ */
+
+/* Vital Product Data Capability Structure reg static infomation table */
+static XenPTRegInfo xen_pt_emu_reg_vpd[] = {
+    {
+        .offset     = PCI_CAP_LIST_NEXT,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0xFF,
+        .emu_mask   = 0xFF,
+        .init       = xen_pt_ptr_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    {
+        .size = 0,
+    },
+};
+
+
+/**************************************
+ * Vendor Specific Capability
+ */
+
+/* Vendor Specific Capability Structure reg static infomation table */
+static XenPTRegInfo xen_pt_emu_reg_vendor[] = {
+    {
+        .offset     = PCI_CAP_LIST_NEXT,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0xFF,
+        .emu_mask   = 0xFF,
+        .init       = xen_pt_ptr_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    {
+        .size = 0,
+    },
+};
+
+
+/*****************************
+ * PCI Express Capability
+ */
+
+static inline uint8_t get_capability_version(XenPCIPassthroughState *s,
+                                             uint32_t offset)
+{
+    uint8_t flags = pci_get_byte(s->dev.config + offset + PCI_EXP_FLAGS);
+    return flags & PCI_EXP_FLAGS_VERS;
+}
+
+static inline uint8_t get_device_type(XenPCIPassthroughState *s,
+                                      uint32_t offset)
+{
+    uint8_t flags = pci_get_byte(s->dev.config + offset + PCI_EXP_FLAGS);
+    return (flags & PCI_EXP_FLAGS_TYPE) >> 4;
+}
+
+/* initialize Link Control register */
+static int xen_pt_linkctrl_reg_init(XenPCIPassthroughState *s,
+                                    XenPTRegInfo *reg, uint32_t real_offset,
+                                    uint32_t *data)
+{
+    uint8_t cap_ver = get_capability_version(s, real_offset - reg->offset);
+    uint8_t dev_type = get_device_type(s, real_offset - reg->offset);
+
+    /* no need to initialize in case of Root Complex Integrated Endpoint
+     * with cap_ver 1.x
+     */
+    if ((dev_type == PCI_EXP_TYPE_RC_END) && (cap_ver == 1)) {
+        *data = XEN_PT_INVALID_REG;
+    }
+
+    *data = reg->init_val;
+    return 0;
+}
+/* initialize Device Control 2 register */
+static int xen_pt_devctrl2_reg_init(XenPCIPassthroughState *s,
+                                    XenPTRegInfo *reg, uint32_t real_offset,
+                                    uint32_t *data)
+{
+    uint8_t cap_ver = get_capability_version(s, real_offset - reg->offset);
+
+    /* no need to initialize in case of cap_ver 1.x */
+    if (cap_ver == 1) {
+        *data = XEN_PT_INVALID_REG;
+    }
+
+    *data = reg->init_val;
+    return 0;
+}
+/* initialize Link Control 2 register */
+static int xen_pt_linkctrl2_reg_init(XenPCIPassthroughState *s,
+                                     XenPTRegInfo *reg, uint32_t real_offset,
+                                     uint32_t *data)
+{
+    uint8_t cap_ver = get_capability_version(s, real_offset - reg->offset);
+    uint32_t reg_field = 0;
+
+    /* no need to initialize in case of cap_ver 1.x */
+    if (cap_ver == 1) {
+        reg_field = XEN_PT_INVALID_REG;
+    } else {
+        /* set Supported Link Speed */
+        uint8_t lnkcap = pci_get_byte(s->dev.config + real_offset - reg->offset
+                                      + PCI_EXP_LNKCAP);
+        reg_field |= PCI_EXP_LNKCAP_SLS & lnkcap;
+    }
+
+    *data = reg_field;
+    return 0;
+}
+
+/* PCI Express Capability Structure reg static infomation table */
+static XenPTRegInfo xen_pt_emu_reg_pcie[] = {
+    /* Next Pointer reg */
+    {
+        .offset     = PCI_CAP_LIST_NEXT,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0xFF,
+        .emu_mask   = 0xFF,
+        .init       = xen_pt_ptr_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    /* Device Capabilities reg */
+    {
+        .offset     = PCI_EXP_DEVCAP,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .ro_mask    = 0x1FFCFFFF,
+        .emu_mask   = 0x10000000,
+        .init       = xen_pt_common_reg_init,
+        .u.dw.read  = xen_pt_long_reg_read,
+        .u.dw.write = xen_pt_long_reg_write,
+    },
+    /* Device Control reg */
+    {
+        .offset     = PCI_EXP_DEVCTL,
+        .size       = 2,
+        .init_val   = 0x2810,
+        .ro_mask    = 0x8400,
+        .emu_mask   = 0xFFFF,
+        .init       = xen_pt_common_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_word_reg_write,
+    },
+    /* Link Control reg */
+    {
+        .offset     = PCI_EXP_LNKCTL,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0xFC34,
+        .emu_mask   = 0xFFFF,
+        .init       = xen_pt_linkctrl_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_word_reg_write,
+    },
+    /* Device Control 2 reg */
+    {
+        .offset     = 0x28,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0xFFE0,
+        .emu_mask   = 0xFFFF,
+        .init       = xen_pt_devctrl2_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_word_reg_write,
+    },
+    /* Link Control 2 reg */
+    {
+        .offset     = 0x30,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0xE040,
+        .emu_mask   = 0xFFFF,
+        .init       = xen_pt_linkctrl2_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_word_reg_write,
+    },
+    {
+        .size = 0,
+    },
+};
+
+
+/*********************************
+ * Power Management Capability
+ */
+
+/* read Power Management Control/Status register */
+static int xen_pt_pmcsr_reg_read(XenPCIPassthroughState *s, XenPTReg *cfg_entry,
+                                 uint16_t *value, uint16_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint16_t valid_emu_mask = reg->emu_mask;
+
+    valid_emu_mask |= PCI_PM_CTRL_STATE_MASK | PCI_PM_CTRL_NO_SOFT_RESET;
+
+    valid_emu_mask = valid_emu_mask & valid_mask;
+    *value = XEN_PT_MERGE_VALUE(*value, cfg_entry->data, ~valid_emu_mask);
+
+    return 0;
+}
+/* write Power Management Control/Status register */
+static int xen_pt_pmcsr_reg_write(XenPCIPassthroughState *s,
+                                  XenPTReg *cfg_entry, uint16_t *val,
+                                  uint16_t dev_value, uint16_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint16_t emu_mask = reg->emu_mask;
+    uint16_t writable_mask = 0;
+    uint16_t throughable_mask = 0;
+
+    emu_mask |= PCI_PM_CTRL_STATE_MASK | PCI_PM_CTRL_NO_SOFT_RESET;
+
+    /* modify emulate register */
+    writable_mask = emu_mask & ~reg->ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+
+    /* create value for writing to I/O device register */
+    throughable_mask = ~emu_mask & valid_mask;
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    return 0;
+}
+
+/* Power Management Capability reg static infomation table */
+static XenPTRegInfo xen_pt_emu_reg_pm[] = {
+    /* Next Pointer reg */
+    {
+        .offset     = PCI_CAP_LIST_NEXT,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0xFF,
+        .emu_mask   = 0xFF,
+        .init       = xen_pt_ptr_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    /* Power Management Capabilities reg */
+    {
+        .offset     = PCI_CAP_FLAGS,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0xFFFF,
+        .emu_mask   = 0xF9C8,
+        .init       = xen_pt_common_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_word_reg_write,
+    },
+    /* PCI Power Management Control/Status reg */
+    {
+        .offset     = PCI_PM_CTRL,
+        .size       = 2,
+        .init_val   = 0x0008,
+        .ro_mask    = 0xE1FC,
+        .emu_mask   = 0x8100,
+        .init       = xen_pt_common_reg_init,
+        .u.w.read   = xen_pt_pmcsr_reg_read,
+        .u.w.write  = xen_pt_pmcsr_reg_write,
+    },
+    {
+        .size = 0,
+    },
+};
+
+
+/********************************
+ * MSI Capability
+ */
+
+/* Helper */
+static bool xen_pt_msgdata_check_type(uint32_t offset, uint16_t flags)
+{
+    /* check the offset whether matches the type or not */
+    bool is_32 = (offset == PCI_MSI_DATA_32) && !(flags & PCI_MSI_FLAGS_64BIT);
+    bool is_64 = (offset == PCI_MSI_DATA_64) &&  (flags & PCI_MSI_FLAGS_64BIT);
+    return is_32 || is_64;
+}
+
+/* Message Control register */
+static int xen_pt_msgctrl_reg_init(XenPCIPassthroughState *s,
+                                   XenPTRegInfo *reg, uint32_t real_offset,
+                                   uint32_t *data)
+{
+    PCIDevice *d = &s->dev;
+    XenPTMSI *msi = s->msi;
+    uint16_t reg_field = 0;
+
+    /* use I/O device register's value as initial value */
+    reg_field = pci_get_word(d->config + real_offset);
+
+    if (reg_field & PCI_MSI_FLAGS_ENABLE) {
+        XEN_PT_LOG(&s->dev, "MSI already enabled, disabling it first\n");
+        xen_host_pci_set_word(&s->real_device, real_offset,
+                              reg_field & ~PCI_MSI_FLAGS_ENABLE);
+    }
+    msi->flags |= reg_field;
+    msi->ctrl_offset = real_offset;
+    msi->initialized = false;
+    msi->mapped = false;
+
+    *data = reg->init_val;
+    return 0;
+}
+static int xen_pt_msgctrl_reg_write(XenPCIPassthroughState *s,
+                                    XenPTReg *cfg_entry, uint16_t *val,
+                                    uint16_t dev_value, uint16_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    XenPTMSI *msi = s->msi;
+    uint16_t writable_mask = 0;
+    uint16_t throughable_mask = 0;
+    uint16_t raw_val;
+
+    /* Currently no support for multi-vector */
+    if (*val & PCI_MSI_FLAGS_QSIZE) {
+        XEN_PT_WARN(&s->dev, "Tries to set more than 1 vector ctrl %x\n", *val);
+    }
+
+    /* modify emulate register */
+    writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+    msi->flags |= cfg_entry->data & ~PCI_MSI_FLAGS_ENABLE;
+
+    /* create value for writing to I/O device register */
+    raw_val = *val;
+    throughable_mask = ~reg->emu_mask & valid_mask;
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    /* update MSI */
+    if (raw_val & PCI_MSI_FLAGS_ENABLE) {
+        /* setup MSI pirq for the first time */
+        if (!msi->initialized) {
+            /* Init physical one */
+            XEN_PT_LOG(&s->dev, "setup MSI\n");
+            if (xen_pt_msi_setup(s)) {
+                /* We do not broadcast the error to the framework code, so
+                 * that MSI errors are contained in MSI emulation code and
+                 * QEMU can go on running.
+                 * Guest MSI would be actually not working.
+                 */
+                *val &= ~PCI_MSI_FLAGS_ENABLE;
+                XEN_PT_WARN(&s->dev, "Can not map MSI.\n");
+                return 0;
+            }
+            if (xen_pt_msi_update(s)) {
+                *val &= ~PCI_MSI_FLAGS_ENABLE;
+                XEN_PT_WARN(&s->dev, "Can not bind MSI\n");
+                return 0;
+            }
+            msi->initialized = true;
+            msi->mapped = true;
+        }
+        msi->flags |= PCI_MSI_FLAGS_ENABLE;
+    } else {
+        msi->flags &= ~PCI_MSI_FLAGS_ENABLE;
+    }
+
+    /* pass through MSI_ENABLE bit */
+    *val &= ~PCI_MSI_FLAGS_ENABLE;
+    *val |= raw_val & PCI_MSI_FLAGS_ENABLE;
+
+    return 0;
+}
+
+/* initialize Message Upper Address register */
+static int xen_pt_msgaddr64_reg_init(XenPCIPassthroughState *s,
+                                     XenPTRegInfo *reg, uint32_t real_offset,
+                                     uint32_t *data)
+{
+    /* no need to initialize in case of 32 bit type */
+    if (!(s->msi->flags & PCI_MSI_FLAGS_64BIT)) {
+        *data = XEN_PT_INVALID_REG;
+    } else {
+        *data = reg->init_val;
+    }
+
+    return 0;
+}
+/* this function will be called twice (for 32 bit and 64 bit type) */
+/* initialize Message Data register */
+static int xen_pt_msgdata_reg_init(XenPCIPassthroughState *s,
+                                   XenPTRegInfo *reg, uint32_t real_offset,
+                                   uint32_t *data)
+{
+    uint32_t flags = s->msi->flags;
+    uint32_t offset = reg->offset;
+
+    /* check the offset whether matches the type or not */
+    if (xen_pt_msgdata_check_type(offset, flags)) {
+        *data = reg->init_val;
+    } else {
+        *data = XEN_PT_INVALID_REG;
+    }
+    return 0;
+}
+
+/* write Message Address register */
+static int xen_pt_msgaddr32_reg_write(XenPCIPassthroughState *s,
+                                      XenPTReg *cfg_entry, uint32_t *val,
+                                      uint32_t dev_value, uint32_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint32_t writable_mask = 0;
+    uint32_t throughable_mask = 0;
+    uint32_t old_addr = cfg_entry->data;
+
+    /* modify emulate register */
+    writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+    s->msi->addr_lo = cfg_entry->data;
+
+    /* create value for writing to I/O device register */
+    throughable_mask = ~reg->emu_mask & valid_mask;
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    /* update MSI */
+    if (cfg_entry->data != old_addr) {
+        if (s->msi->mapped) {
+            xen_pt_msi_update(s);
+        }
+    }
+
+    return 0;
+}
+/* write Message Upper Address register */
+static int xen_pt_msgaddr64_reg_write(XenPCIPassthroughState *s,
+                                      XenPTReg *cfg_entry, uint32_t *val,
+                                      uint32_t dev_value, uint32_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint32_t writable_mask = 0;
+    uint32_t throughable_mask = 0;
+    uint32_t old_addr = cfg_entry->data;
+
+    /* check whether the type is 64 bit or not */
+    if (!(s->msi->flags & PCI_MSI_FLAGS_64BIT)) {
+        XEN_PT_ERR(&s->dev,
+                   "Can't write to the upper address without 64 bit support\n");
+        return -1;
+    }
+
+    /* modify emulate register */
+    writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+    /* update the msi_info too */
+    s->msi->addr_hi = cfg_entry->data;
+
+    /* create value for writing to I/O device register */
+    throughable_mask = ~reg->emu_mask & valid_mask;
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    /* update MSI */
+    if (cfg_entry->data != old_addr) {
+        if (s->msi->mapped) {
+            xen_pt_msi_update(s);
+        }
+    }
+
+    return 0;
+}
+
+
+/* this function will be called twice (for 32 bit and 64 bit type) */
+/* write Message Data register */
+static int xen_pt_msgdata_reg_write(XenPCIPassthroughState *s,
+                                    XenPTReg *cfg_entry, uint16_t *val,
+                                    uint16_t dev_value, uint16_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    XenPTMSI *msi = s->msi;
+    uint16_t writable_mask = 0;
+    uint16_t throughable_mask = 0;
+    uint16_t old_data = cfg_entry->data;
+    uint32_t offset = reg->offset;
+
+    /* check the offset whether matches the type or not */
+    if (!xen_pt_msgdata_check_type(offset, msi->flags)) {
+        /* exit I/O emulator */
+        XEN_PT_ERR(&s->dev, "the offset does not match the 32/64 bit type!\n");
+        return -1;
+    }
+
+    /* modify emulate register */
+    writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+    /* update the msi_info too */
+    msi->data = cfg_entry->data;
+
+    /* create value for writing to I/O device register */
+    throughable_mask = ~reg->emu_mask & valid_mask;
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    /* update MSI */
+    if (cfg_entry->data != old_data) {
+        if (msi->mapped) {
+            xen_pt_msi_update(s);
+        }
+    }
+
+    return 0;
+}
+
+/* MSI Capability Structure reg static infomation table */
+static XenPTRegInfo xen_pt_emu_reg_msi[] = {
+    /* Next Pointer reg */
+    {
+        .offset     = PCI_CAP_LIST_NEXT,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0xFF,
+        .emu_mask   = 0xFF,
+        .init       = xen_pt_ptr_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    /* Message Control reg */
+    {
+        .offset     = PCI_MSI_FLAGS,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0xFF8E,
+        .emu_mask   = 0x007F,
+        .init       = xen_pt_msgctrl_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_msgctrl_reg_write,
+    },
+    /* Message Address reg */
+    {
+        .offset     = PCI_MSI_ADDRESS_LO,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .ro_mask    = 0x00000003,
+        .emu_mask   = 0xFFFFFFFF,
+        .no_wb      = 1,
+        .init       = xen_pt_common_reg_init,
+        .u.dw.read  = xen_pt_long_reg_read,
+        .u.dw.write = xen_pt_msgaddr32_reg_write,
+    },
+    /* Message Upper Address reg (if PCI_MSI_FLAGS_64BIT set) */
+    {
+        .offset     = PCI_MSI_ADDRESS_HI,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .ro_mask    = 0x00000000,
+        .emu_mask   = 0xFFFFFFFF,
+        .no_wb      = 1,
+        .init       = xen_pt_msgaddr64_reg_init,
+        .u.dw.read  = xen_pt_long_reg_read,
+        .u.dw.write = xen_pt_msgaddr64_reg_write,
+    },
+    /* Message Data reg (16 bits of data for 32-bit devices) */
+    {
+        .offset     = PCI_MSI_DATA_32,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0x0000,
+        .emu_mask   = 0xFFFF,
+        .no_wb      = 1,
+        .init       = xen_pt_msgdata_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_msgdata_reg_write,
+    },
+    /* Message Data reg (16 bits of data for 64-bit devices) */
+    {
+        .offset     = PCI_MSI_DATA_64,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0x0000,
+        .emu_mask   = 0xFFFF,
+        .no_wb      = 1,
+        .init       = xen_pt_msgdata_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_msgdata_reg_write,
+    },
+    {
+        .size = 0,
+    },
+};
+
+
+/**************************************
+ * MSI-X Capability
+ */
+
+/* Message Control register for MSI-X */
+static int xen_pt_msixctrl_reg_init(XenPCIPassthroughState *s,
+                                    XenPTRegInfo *reg, uint32_t real_offset,
+                                    uint32_t *data)
+{
+    PCIDevice *d = &s->dev;
+    uint16_t reg_field = 0;
+
+    /* use I/O device register's value as initial value */
+    reg_field = pci_get_word(d->config + real_offset);
+
+    if (reg_field & PCI_MSIX_FLAGS_ENABLE) {
+        XEN_PT_LOG(d, "MSIX already enabled, disabling it first\n");
+        xen_host_pci_set_word(&s->real_device, real_offset,
+                              reg_field & ~PCI_MSIX_FLAGS_ENABLE);
+    }
+
+    s->msix->ctrl_offset = real_offset;
+
+    *data = reg->init_val;
+    return 0;
+}
+static int xen_pt_msixctrl_reg_write(XenPCIPassthroughState *s,
+                                     XenPTReg *cfg_entry, uint16_t *val,
+                                     uint16_t dev_value, uint16_t valid_mask)
+{
+    XenPTRegInfo *reg = cfg_entry->reg;
+    uint16_t writable_mask = 0;
+    uint16_t throughable_mask = 0;
+    int debug_msix_enabled_old;
+
+    /* modify emulate register */
+    writable_mask = reg->emu_mask & ~reg->ro_mask & valid_mask;
+    cfg_entry->data = XEN_PT_MERGE_VALUE(*val, cfg_entry->data, writable_mask);
+
+    /* create value for writing to I/O device register */
+    throughable_mask = ~reg->emu_mask & valid_mask;
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    /* update MSI-X */
+    if ((*val & PCI_MSIX_FLAGS_ENABLE)
+        && !(*val & PCI_MSIX_FLAGS_MASKALL)) {
+        xen_pt_msix_update(s);
+    }
+
+    debug_msix_enabled_old = s->msix->enabled;
+    s->msix->enabled = !!(*val & PCI_MSIX_FLAGS_ENABLE);
+    if (s->msix->enabled != debug_msix_enabled_old) {
+        XEN_PT_LOG(&s->dev, "%s MSI-X\n",
+                   s->msix->enabled ? "enable" : "disable");
+    }
+
+    return 0;
+}
+
+/* MSI-X Capability Structure reg static infomation table */
+static XenPTRegInfo xen_pt_emu_reg_msix[] = {
+    /* Next Pointer reg */
+    {
+        .offset     = PCI_CAP_LIST_NEXT,
+        .size       = 1,
+        .init_val   = 0x00,
+        .ro_mask    = 0xFF,
+        .emu_mask   = 0xFF,
+        .init       = xen_pt_ptr_reg_init,
+        .u.b.read   = xen_pt_byte_reg_read,
+        .u.b.write  = xen_pt_byte_reg_write,
+    },
+    /* Message Control reg */
+    {
+        .offset     = PCI_MSI_FLAGS,
+        .size       = 2,
+        .init_val   = 0x0000,
+        .ro_mask    = 0x3FFF,
+        .emu_mask   = 0x0000,
+        .init       = xen_pt_msixctrl_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_msixctrl_reg_write,
+    },
+    {
+        .size = 0,
+    },
+};
+
+
+/****************************
+ * Capabilities
+ */
+
+/* capability structure register group size functions */
+
+static int xen_pt_reg_grp_size_init(XenPCIPassthroughState *s,
+                                    const XenPTRegGroupInfo *grp_reg,
+                                    uint32_t base_offset, uint8_t *size)
+{
+    *size = grp_reg->grp_size;
+    return 0;
+}
+/* get Vendor Specific Capability Structure register group size */
+static int xen_pt_vendor_size_init(XenPCIPassthroughState *s,
+                                   const XenPTRegGroupInfo *grp_reg,
+                                   uint32_t base_offset, uint8_t *size)
+{
+    *size = pci_get_byte(s->dev.config + base_offset + 0x02);
+    return 0;
+}
+/* get PCI Express Capability Structure register group size */
+static int xen_pt_pcie_size_init(XenPCIPassthroughState *s,
+                                 const XenPTRegGroupInfo *grp_reg,
+                                 uint32_t base_offset, uint8_t *size)
+{
+    PCIDevice *d = &s->dev;
+    uint8_t version = get_capability_version(s, base_offset);
+    uint8_t type = get_device_type(s, base_offset);
+    uint8_t pcie_size = 0;
+
+
+    /* calculate size depend on capability version and device/port type */
+    /* in case of PCI Express Base Specification Rev 1.x */
+    if (version == 1) {
+        /* The PCI Express Capabilities, Device Capabilities, and Device
+         * Status/Control registers are required for all PCI Express devices.
+         * The Link Capabilities and Link Status/Control are required for all
+         * Endpoints that are not Root Complex Integrated Endpoints. Endpoints
+         * are not required to implement registers other than those listed
+         * above and terminate the capability structure.
+         */
+        switch (type) {
+        case PCI_EXP_TYPE_ENDPOINT:
+        case PCI_EXP_TYPE_LEG_END:
+            pcie_size = 0x14;
+            break;
+        case PCI_EXP_TYPE_RC_END:
+            /* has no link */
+            pcie_size = 0x0C;
+            break;
+            /* only EndPoint passthrough is supported */
+        case PCI_EXP_TYPE_ROOT_PORT:
+        case PCI_EXP_TYPE_UPSTREAM:
+        case PCI_EXP_TYPE_DOWNSTREAM:
+        case PCI_EXP_TYPE_PCI_BRIDGE:
+        case PCI_EXP_TYPE_PCIE_BRIDGE:
+        case PCI_EXP_TYPE_RC_EC:
+        default:
+            XEN_PT_ERR(d, "Unsupported device/port type %#x.\n", type);
+            return -1;
+        }
+    }
+    /* in case of PCI Express Base Specification Rev 2.0 */
+    else if (version == 2) {
+        switch (type) {
+        case PCI_EXP_TYPE_ENDPOINT:
+        case PCI_EXP_TYPE_LEG_END:
+        case PCI_EXP_TYPE_RC_END:
+            /* For Functions that do not implement the registers,
+             * these spaces must be hardwired to 0b.
+             */
+            pcie_size = 0x3C;
+            break;
+            /* only EndPoint passthrough is supported */
+        case PCI_EXP_TYPE_ROOT_PORT:
+        case PCI_EXP_TYPE_UPSTREAM:
+        case PCI_EXP_TYPE_DOWNSTREAM:
+        case PCI_EXP_TYPE_PCI_BRIDGE:
+        case PCI_EXP_TYPE_PCIE_BRIDGE:
+        case PCI_EXP_TYPE_RC_EC:
+        default:
+            XEN_PT_ERR(d, "Unsupported device/port type %#x.\n", type);
+            return -1;
+        }
+    } else {
+        XEN_PT_ERR(d, "Unsupported capability version %#x.\n", version);
+        return -1;
+    }
+
+    *size = pcie_size;
+    return 0;
+}
+/* get MSI Capability Structure register group size */
+static int xen_pt_msi_size_init(XenPCIPassthroughState *s,
+                                const XenPTRegGroupInfo *grp_reg,
+                                uint32_t base_offset, uint8_t *size)
+{
+    PCIDevice *d = &s->dev;
+    uint16_t msg_ctrl = 0;
+    uint8_t msi_size = 0xa;
+
+    msg_ctrl = pci_get_word(d->config + (base_offset + PCI_MSI_FLAGS));
+
+    /* check if 64-bit address is capable of per-vector masking */
+    if (msg_ctrl & PCI_MSI_FLAGS_64BIT) {
+        msi_size += 4;
+    }
+    if (msg_ctrl & PCI_MSI_FLAGS_MASKBIT) {
+        msi_size += 10;
+    }
+
+    s->msi = g_new0(XenPTMSI, 1);
+    s->msi->pirq = XEN_PT_UNASSIGNED_PIRQ;
+
+    *size = msi_size;
+    return 0;
+}
+/* get MSI-X Capability Structure register group size */
+static int xen_pt_msix_size_init(XenPCIPassthroughState *s,
+                                 const XenPTRegGroupInfo *grp_reg,
+                                 uint32_t base_offset, uint8_t *size)
+{
+    int rc = 0;
+
+    rc = xen_pt_msix_init(s, base_offset);
+
+    if (rc < 0) {
+        XEN_PT_ERR(&s->dev, "Internal error: Invalid xen_pt_msix_init.\n");
+        return rc;
+    }
+
+    *size = grp_reg->grp_size;
+    return 0;
+}
+
+
+static const XenPTRegGroupInfo xen_pt_emu_reg_grps[] = {
+    /* Header Type0 reg group */
+    {
+        .grp_id      = 0xFF,
+        .grp_type    = XEN_PT_GRP_TYPE_EMU,
+        .grp_size    = 0x40,
+        .size_init   = xen_pt_reg_grp_size_init,
+        .emu_regs = xen_pt_emu_reg_header0,
+    },
+    /* PCI PowerManagement Capability reg group */
+    {
+        .grp_id      = PCI_CAP_ID_PM,
+        .grp_type    = XEN_PT_GRP_TYPE_EMU,
+        .grp_size    = PCI_PM_SIZEOF,
+        .size_init   = xen_pt_reg_grp_size_init,
+        .emu_regs = xen_pt_emu_reg_pm,
+    },
+    /* AGP Capability Structure reg group */
+    {
+        .grp_id     = PCI_CAP_ID_AGP,
+        .grp_type   = XEN_PT_GRP_TYPE_HARDWIRED,
+        .grp_size   = 0x30,
+        .size_init  = xen_pt_reg_grp_size_init,
+    },
+    /* Vital Product Data Capability Structure reg group */
+    {
+        .grp_id      = PCI_CAP_ID_VPD,
+        .grp_type    = XEN_PT_GRP_TYPE_EMU,
+        .grp_size    = 0x08,
+        .size_init   = xen_pt_reg_grp_size_init,
+        .emu_regs = xen_pt_emu_reg_vpd,
+    },
+    /* Slot Identification reg group */
+    {
+        .grp_id     = PCI_CAP_ID_SLOTID,
+        .grp_type   = XEN_PT_GRP_TYPE_HARDWIRED,
+        .grp_size   = 0x04,
+        .size_init  = xen_pt_reg_grp_size_init,
+    },
+    /* MSI Capability Structure reg group */
+    {
+        .grp_id      = PCI_CAP_ID_MSI,
+        .grp_type    = XEN_PT_GRP_TYPE_EMU,
+        .grp_size    = 0xFF,
+        .size_init   = xen_pt_msi_size_init,
+        .emu_regs = xen_pt_emu_reg_msi,
+    },
+    /* PCI-X Capabilities List Item reg group */
+    {
+        .grp_id     = PCI_CAP_ID_PCIX,
+        .grp_type   = XEN_PT_GRP_TYPE_HARDWIRED,
+        .grp_size   = 0x18,
+        .size_init  = xen_pt_reg_grp_size_init,
+    },
+    /* Vendor Specific Capability Structure reg group */
+    {
+        .grp_id      = PCI_CAP_ID_VNDR,
+        .grp_type    = XEN_PT_GRP_TYPE_EMU,
+        .grp_size    = 0xFF,
+        .size_init   = xen_pt_vendor_size_init,
+        .emu_regs = xen_pt_emu_reg_vendor,
+    },
+    /* SHPC Capability List Item reg group */
+    {
+        .grp_id     = PCI_CAP_ID_SHPC,
+        .grp_type   = XEN_PT_GRP_TYPE_HARDWIRED,
+        .grp_size   = 0x08,
+        .size_init  = xen_pt_reg_grp_size_init,
+    },
+    /* Subsystem ID and Subsystem Vendor ID Capability List Item reg group */
+    {
+        .grp_id     = PCI_CAP_ID_SSVID,
+        .grp_type   = XEN_PT_GRP_TYPE_HARDWIRED,
+        .grp_size   = 0x08,
+        .size_init  = xen_pt_reg_grp_size_init,
+    },
+    /* AGP 8x Capability Structure reg group */
+    {
+        .grp_id     = PCI_CAP_ID_AGP3,
+        .grp_type   = XEN_PT_GRP_TYPE_HARDWIRED,
+        .grp_size   = 0x30,
+        .size_init  = xen_pt_reg_grp_size_init,
+    },
+    /* PCI Express Capability Structure reg group */
+    {
+        .grp_id      = PCI_CAP_ID_EXP,
+        .grp_type    = XEN_PT_GRP_TYPE_EMU,
+        .grp_size    = 0xFF,
+        .size_init   = xen_pt_pcie_size_init,
+        .emu_regs = xen_pt_emu_reg_pcie,
+    },
+    /* MSI-X Capability Structure reg group */
+    {
+        .grp_id      = PCI_CAP_ID_MSIX,
+        .grp_type    = XEN_PT_GRP_TYPE_EMU,
+        .grp_size    = 0x0C,
+        .size_init   = xen_pt_msix_size_init,
+        .emu_regs = xen_pt_emu_reg_msix,
+    },
+    {
+        .grp_size = 0,
+    },
+};
+
+/* initialize Capabilities Pointer or Next Pointer register */
+static int xen_pt_ptr_reg_init(XenPCIPassthroughState *s,
+                               XenPTRegInfo *reg, uint32_t real_offset,
+                               uint32_t *data)
+{
+    int i;
+    uint8_t *config = s->dev.config;
+    uint32_t reg_field = pci_get_byte(config + real_offset);
+    uint8_t cap_id = 0;
+
+    /* find capability offset */
+    while (reg_field) {
+        for (i = 0; xen_pt_emu_reg_grps[i].grp_size != 0; i++) {
+            if (xen_pt_hide_dev_cap(&s->real_device,
+                                    xen_pt_emu_reg_grps[i].grp_id)) {
+                continue;
+            }
+
+            cap_id = pci_get_byte(config + reg_field + PCI_CAP_LIST_ID);
+            if (xen_pt_emu_reg_grps[i].grp_id == cap_id) {
+                if (xen_pt_emu_reg_grps[i].grp_type == XEN_PT_GRP_TYPE_EMU) {
+                    goto out;
+                }
+                /* ignore the 0 hardwired capability, find next one */
+                break;
+            }
+        }
+
+        /* next capability */
+        reg_field = pci_get_byte(config + reg_field + PCI_CAP_LIST_NEXT);
+    }
+
+out:
+    *data = reg_field;
+    return 0;
+}
+
+
+/*************
+ * Main
+ */
+
+static uint8_t find_cap_offset(XenPCIPassthroughState *s, uint8_t cap)
+{
+    uint8_t id;
+    unsigned max_cap = PCI_CAP_MAX;
+    uint8_t pos = PCI_CAPABILITY_LIST;
+    uint8_t status = 0;
+
+    if (xen_host_pci_get_byte(&s->real_device, PCI_STATUS, &status)) {
+        return 0;
+    }
+    if ((status & PCI_STATUS_CAP_LIST) == 0) {
+        return 0;
+    }
+
+    while (max_cap--) {
+        if (xen_host_pci_get_byte(&s->real_device, pos, &pos)) {
+            break;
+        }
+        if (pos < PCI_CONFIG_HEADER_SIZE) {
+            break;
+        }
+
+        pos &= ~3;
+        if (xen_host_pci_get_byte(&s->real_device,
+                                  pos + PCI_CAP_LIST_ID, &id)) {
+            break;
+        }
+
+        if (id == 0xff) {
+            break;
+        }
+        if (id == cap) {
+            return pos;
+        }
+
+        pos += PCI_CAP_LIST_NEXT;
+    }
+    return 0;
+}
+
+static int xen_pt_config_reg_init(XenPCIPassthroughState *s,
+                                  XenPTRegGroup *reg_grp, XenPTRegInfo *reg)
+{
+    XenPTReg *reg_entry;
+    uint32_t data = 0;
+    int rc = 0;
+
+    reg_entry = g_new0(XenPTReg, 1);
+    reg_entry->reg = reg;
+
+    if (reg->init) {
+        /* initialize emulate register */
+        rc = reg->init(s, reg_entry->reg,
+                       reg_grp->base_offset + reg->offset, &data);
+        if (rc < 0) {
+            free(reg_entry);
+            return rc;
+        }
+        if (data == XEN_PT_INVALID_REG) {
+            /* free unused BAR register entry */
+            free(reg_entry);
+            return 0;
+        }
+        /* set register value */
+        reg_entry->data = data;
+    }
+    /* list add register entry */
+    QLIST_INSERT_HEAD(&reg_grp->reg_tbl_list, reg_entry, entries);
+
+    return 0;
+}
+
+int xen_pt_config_init(XenPCIPassthroughState *s)
+{
+    int i, rc;
+
+    QLIST_INIT(&s->reg_grps);
+
+    for (i = 0; xen_pt_emu_reg_grps[i].grp_size != 0; i++) {
+        uint32_t reg_grp_offset = 0;
+        XenPTRegGroup *reg_grp_entry = NULL;
+
+        if (xen_pt_emu_reg_grps[i].grp_id != 0xFF) {
+            if (xen_pt_hide_dev_cap(&s->real_device,
+                                    xen_pt_emu_reg_grps[i].grp_id)) {
+                continue;
+            }
+
+            reg_grp_offset = find_cap_offset(s, xen_pt_emu_reg_grps[i].grp_id);
+
+            if (!reg_grp_offset) {
+                continue;
+            }
+        }
+
+        reg_grp_entry = g_new0(XenPTRegGroup, 1);
+        QLIST_INIT(&reg_grp_entry->reg_tbl_list);
+        QLIST_INSERT_HEAD(&s->reg_grps, reg_grp_entry, entries);
+
+        reg_grp_entry->base_offset = reg_grp_offset;
+        reg_grp_entry->reg_grp = xen_pt_emu_reg_grps + i;
+        if (xen_pt_emu_reg_grps[i].size_init) {
+            /* get register group size */
+            rc = xen_pt_emu_reg_grps[i].size_init(s, reg_grp_entry->reg_grp,
+                                                  reg_grp_offset,
+                                                  &reg_grp_entry->size);
+            if (rc < 0) {
+                xen_pt_config_delete(s);
+                return rc;
+            }
+        }
+
+        if (xen_pt_emu_reg_grps[i].grp_type == XEN_PT_GRP_TYPE_EMU) {
+            if (xen_pt_emu_reg_grps[i].emu_regs) {
+                int j = 0;
+                XenPTRegInfo *regs = xen_pt_emu_reg_grps[i].emu_regs;
+                /* initialize capability register */
+                for (j = 0; regs->size != 0; j++, regs++) {
+                    /* initialize capability register */
+                    rc = xen_pt_config_reg_init(s, reg_grp_entry, regs);
+                    if (rc < 0) {
+                        xen_pt_config_delete(s);
+                        return rc;
+                    }
+                }
+            }
+        }
+    }
+
+    return 0;
+}
+
+/* delete all emulate register */
+void xen_pt_config_delete(XenPCIPassthroughState *s)
+{
+    struct XenPTRegGroup *reg_group, *next_grp;
+    struct XenPTReg *reg, *next_reg;
+
+    /* free MSI/MSI-X info table */
+    if (s->msix) {
+        xen_pt_msix_delete(s);
+    }
+    if (s->msi) {
+        g_free(s->msi);
+    }
+
+    /* free all register group entry */
+    QLIST_FOREACH_SAFE(reg_group, &s->reg_grps, entries, next_grp) {
+        /* free all register entry */
+        QLIST_FOREACH_SAFE(reg, &reg_group->reg_tbl_list, entries, next_reg) {
+            QLIST_REMOVE(reg, entries);
+            g_free(reg);
+        }
+
+        QLIST_REMOVE(reg_group, entries);
+        g_free(reg_group);
+    }
+}

hw/xen_pt_msi.c

+/*
+ * Copyright (c) 2007, Intel Corporation.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Jiang Yunhong <yunhong.jiang@intel.com>
+ *
+ * This file implements direct PCI assignment to a HVM guest
+ */
+
+#include <sys/mman.h>
+
+#include "xen_backend.h"
+#include "xen_pt.h"
+#include "apic-msidef.h"
+
+
+#define XEN_PT_AUTO_ASSIGN -1
+
+/* shift count for gflags */
+#define XEN_PT_GFLAGS_SHIFT_DEST_ID        0
+#define XEN_PT_GFLAGS_SHIFT_RH             8
+#define XEN_PT_GFLAGS_SHIFT_DM             9
+#define XEN_PT_GFLAGSSHIFT_DELIV_MODE     12
+#define XEN_PT_GFLAGSSHIFT_TRG_MODE       15
+
+
+/*
+ * Helpers
+ */
+
+static inline uint8_t msi_vector(uint32_t data)
+{
+    return (data & MSI_DATA_VECTOR_MASK) >> MSI_DATA_VECTOR_SHIFT;
+}
+
+static inline uint8_t msi_dest_id(uint32_t addr)
+{
+    return (addr & MSI_ADDR_DEST_ID_MASK) >> MSI_ADDR_DEST_ID_SHIFT;
+}
+
+static inline uint32_t msi_ext_dest_id(uint32_t addr_hi)
+{
+    return addr_hi & 0xffffff00;
+}
+
+static uint32_t msi_gflags(uint32_t data, uint64_t addr)
+{
+    uint32_t result = 0;
+    int rh, dm, dest_id, deliv_mode, trig_mode;
+
+    rh = (addr >> MSI_ADDR_REDIRECTION_SHIFT) & 0x1;
+    dm = (addr >> MSI_ADDR_DEST_MODE_SHIFT) & 0x1;
+    dest_id = msi_dest_id(addr);
+    deliv_mode = (data >> MSI_DATA_DELIVERY_MODE_SHIFT) & 0x7;
+    trig_mode = (data >> MSI_DATA_TRIGGER_SHIFT) & 0x1;
+
+    result = dest_id | (rh << XEN_PT_GFLAGS_SHIFT_RH)
+        | (dm << XEN_PT_GFLAGS_SHIFT_DM)
+        | (deliv_mode << XEN_PT_GFLAGSSHIFT_DELIV_MODE)
+        | (trig_mode << XEN_PT_GFLAGSSHIFT_TRG_MODE);
+
+    return result;
+}
+
+static inline uint64_t msi_addr64(XenPTMSI *msi)
+{
+    return (uint64_t)msi->addr_hi << 32 | msi->addr_lo;
+}
+
+static int msi_msix_enable(XenPCIPassthroughState *s,
+                           uint32_t address,
+                           uint16_t flag,
+                           bool enable)
+{
+    uint16_t val = 0;
+
+    if (!address) {
+        return -1;
+    }
+
+    xen_host_pci_get_word(&s->real_device, address, &val);
+    if (enable) {
+        val |= flag;
+    } else {
+        val &= ~flag;
+    }
+    xen_host_pci_set_word(&s->real_device, address, val);
+    return 0;
+}
+
+static int msi_msix_setup(XenPCIPassthroughState *s,
+                          uint64_t addr,
+                          uint32_t data,
+                          int *ppirq,
+                          bool is_msix,
+                          int msix_entry,
+                          bool is_not_mapped)
+{
+    uint8_t gvec = msi_vector(data);
+    int rc = 0;
+
+    assert((!is_msix && msix_entry == 0) || is_msix);
+
+    if (gvec == 0) {
+        /* if gvec is 0, the guest is asking for a particular pirq that
+         * is passed as dest_id */
+        *ppirq = msi_ext_dest_id(addr >> 32) | msi_dest_id(addr);
+        if (!*ppirq) {
+            /* this probably identifies an misconfiguration of the guest,
+             * try the emulated path */
+            *ppirq = XEN_PT_UNASSIGNED_PIRQ;
+        } else {
+            XEN_PT_LOG(&s->dev, "requested pirq %d for MSI%s"
+                       " (vec: %#x, entry: %#x)\n",
+                       *ppirq, is_msix ? "-X" : "", gvec, msix_entry);
+        }
+    }
+
+    if (is_not_mapped) {
+        uint64_t table_base = 0;
+
+        if (is_msix) {
+            table_base = s->msix->table_base;
+        }
+
+        rc = xc_physdev_map_pirq_msi(xen_xc, xen_domid, XEN_PT_AUTO_ASSIGN,
+                                     ppirq, PCI_DEVFN(s->real_device.dev,
+                                                      s->real_device.func),
+                                     s->real_device.bus,
+                                     msix_entry, table_base);
+        if (rc) {
+            XEN_PT_ERR(&s->dev,
+                       "Mapping of MSI%s (rc: %i, vec: %#x, entry %#x)\n",
+                       is_msix ? "-X" : "", rc, gvec, msix_entry);
+            return rc;
+        }
+    }
+
+    return 0;
+}
+static int msi_msix_update(XenPCIPassthroughState *s,
+                           uint64_t addr,
+                           uint32_t data,
+                           int pirq,
+                           bool is_msix,
+                           int msix_entry,
+                           int *old_pirq)
+{
+    PCIDevice *d = &s->dev;
+    uint8_t gvec = msi_vector(data);
+    uint32_t gflags = msi_gflags(data, addr);
+    int rc = 0;
+    uint64_t table_addr = 0;
+
+    XEN_PT_LOG(d, "Updating MSI%s with pirq %d gvec %#x gflags %#x"
+               " (entry: %#x)\n",
+               is_msix ? "-X" : "", pirq, gvec, gflags, msix_entry);
+
+    if (is_msix) {
+        table_addr = s->msix->mmio_base_addr;
+    }
+
+    rc = xc_domain_update_msi_irq(xen_xc, xen_domid, gvec,
+                                  pirq, gflags, table_addr);
+
+    if (rc) {
+        XEN_PT_ERR(d, "Updating of MSI%s failed. (rc: %d)\n",
+                   is_msix ? "-X" : "", rc);
+
+        if (xc_physdev_unmap_pirq(xen_xc, xen_domid, *old_pirq)) {
+            XEN_PT_ERR(d, "Unmapping of MSI%s pirq %d failed.\n",
+                       is_msix ? "-X" : "", *old_pirq);
+        }
+        *old_pirq = XEN_PT_UNASSIGNED_PIRQ;
+    }
+    return rc;
+}
+
+static int msi_msix_disable(XenPCIPassthroughState *s,
+                            uint64_t addr,
+                            uint32_t data,
+                            int pirq,
+                            bool is_msix,
+                            bool is_binded)
+{
+    PCIDevice *d = &s->dev;
+    uint8_t gvec = msi_vector(data);
+    uint32_t gflags = msi_gflags(data, addr);
+    int rc = 0;
+
+    if (pirq == XEN_PT_UNASSIGNED_PIRQ) {
+        return 0;
+    }
+
+    if (is_binded) {
+        XEN_PT_LOG(d, "Unbind MSI%s with pirq %d, gvec %#x\n",
+                   is_msix ? "-X" : "", pirq, gvec);
+        rc = xc_domain_unbind_msi_irq(xen_xc, xen_domid, gvec, pirq, gflags);
+        if (rc) {
+            XEN_PT_ERR(d, "Unbinding of MSI%s failed. (pirq: %d, gvec: %#x)\n",
+                       is_msix ? "-X" : "", pirq, gvec);
+            return rc;
+        }
+    }
+
+    XEN_PT_LOG(d, "Unmap MSI%s pirq %d\n", is_msix ? "-X" : "", pirq);
+    rc = xc_physdev_unmap_pirq(xen_xc, xen_domid, pirq);
+    if (rc) {
+        XEN_PT_ERR(d, "Unmapping of MSI%s pirq %d failed. (rc: %i)\n",
+                   is_msix ? "-X" : "", pirq, rc);
+        return rc;
+    }
+
+    return 0;
+}
+
+/*
+ * MSI virtualization functions
+ */
+
+int xen_pt_msi_set_enable(XenPCIPassthroughState *s, bool enable)
+{
+    XEN_PT_LOG(&s->dev, "%s MSI.\n", enable ? "enabling" : "disabling");
+
+    if (!s->msi) {
+        return -1;
+    }
+
+    return msi_msix_enable(s, s->msi->ctrl_offset, PCI_MSI_FLAGS_ENABLE,
+                           enable);
+}
+
+/* setup physical msi, but don't enable it */
+int xen_pt_msi_setup(XenPCIPassthroughState *s)
+{
+    int pirq = XEN_PT_UNASSIGNED_PIRQ;
+    int rc = 0;
+    XenPTMSI *msi = s->msi;
+
+    if (msi->initialized) {
+        XEN_PT_ERR(&s->dev,
+                   "Setup physical MSI when it has been properly initialized.\n");
+        return -1;
+    }
+
+    rc = msi_msix_setup(s, msi_addr64(msi), msi->data, &pirq, false, 0, true);
+    if (rc) {
+        return rc;
+    }
+
+    if (pirq < 0) {
+        XEN_PT_ERR(&s->dev, "Invalid pirq number: %d.\n", pirq);
+        return -1;
+    }
+
+    msi->pirq = pirq;
+    XEN_PT_LOG(&s->dev, "MSI mapped with pirq %d.\n", pirq);
+
+    return 0;
+}
+
+int xen_pt_msi_update(XenPCIPassthroughState *s)
+{
+    XenPTMSI *msi = s->msi;
+    return msi_msix_update(s, msi_addr64(msi), msi->data, msi->pirq,
+                           false, 0, &msi->pirq);
+}
+
+void xen_pt_msi_disable(XenPCIPassthroughState *s)
+{
+    XenPTMSI *msi = s->msi;
+
+    if (!msi) {
+        return;
+    }
+
+    xen_pt_msi_set_enable(s, false);
+
+    msi_msix_disable(s, msi_addr64(msi), msi->data, msi->pirq, false,
+                     msi->initialized);
+
+    /* clear msi info */
+    msi->flags = 0;
+    msi->mapped = false;
+    msi->pirq = XEN_PT_UNASSIGNED_PIRQ;
+}
+
+/*
+ * MSI-X virtualization functions
+ */
+
+static int msix_set_enable(XenPCIPassthroughState *s, bool enabled)
+{
+    XEN_PT_LOG(&s->dev, "%s MSI-X.\n", enabled ? "enabling" : "disabling");
+
+    if (!s->msix) {
+        return -1;
+    }
+
+    return msi_msix_enable(s, s->msix->ctrl_offset, PCI_MSIX_FLAGS_ENABLE,
+                           enabled);
+}
+
+static int xen_pt_msix_update_one(XenPCIPassthroughState *s, int entry_nr)
+{
+    XenPTMSIXEntry *entry = NULL;
+    int pirq;
+    int rc;
+
+    if (entry_nr < 0 || entry_nr >= s->msix->total_entries) {
+        return -EINVAL;
+    }
+
+    entry = &s->msix->msix_entry[entry_nr];
+
+    if (!entry->updated) {
+        return 0;
+    }
+
+    pirq = entry->pirq;
+
+    rc = msi_msix_setup(s, entry->data, entry->data, &pirq, true, entry_nr,
+                        entry->pirq == XEN_PT_UNASSIGNED_PIRQ);
+    if (rc) {
+        return rc;
+    }
+    if (entry->pirq == XEN_PT_UNASSIGNED_PIRQ) {
+        entry->pirq = pirq;
+    }
+
+    rc = msi_msix_update(s, entry->addr, entry->data, pirq, true,
+                         entry_nr, &entry->pirq);
+
+    if (!rc) {
+        entry->updated = false;
+    }
+
+    return rc;
+}
+
+int xen_pt_msix_update(XenPCIPassthroughState *s)
+{
+    XenPTMSIX *msix = s->msix;
+    int i;
+
+    for (i = 0; i < msix->total_entries; i++) {
+        xen_pt_msix_update_one(s, i);
+    }
+
+    return 0;
+}
+
+void xen_pt_msix_disable(XenPCIPassthroughState *s)
+{
+    int i = 0;
+
+    msix_set_enable(s, false);
+
+    for (i = 0; i < s->msix->total_entries; i++) {
+        XenPTMSIXEntry *entry = &s->msix->msix_entry[i];
+
+        msi_msix_disable(s, entry->addr, entry->data, entry->pirq, true, true);
+
+        /* clear MSI-X info */
+        entry->pirq = XEN_PT_UNASSIGNED_PIRQ;
+        entry->updated = false;
+    }
+}
+
+int xen_pt_msix_update_remap(XenPCIPassthroughState *s, int bar_index)
+{
+    XenPTMSIXEntry *entry;
+    int i, ret;
+
+    if (!(s->msix && s->msix->bar_index == bar_index)) {
+        return 0;
+    }
+
+    for (i = 0; i < s->msix->total_entries; i++) {
+        entry = &s->msix->msix_entry[i];
+        if (entry->pirq != XEN_PT_UNASSIGNED_PIRQ) {
+            ret = xc_domain_unbind_pt_irq(xen_xc, xen_domid, entry->pirq,
+                                          PT_IRQ_TYPE_MSI, 0, 0, 0, 0);
+            if (ret) {
+                XEN_PT_ERR(&s->dev, "unbind MSI-X entry %d failed\n",
+                           entry->pirq);
+            }
+            entry->updated = true;
+        }
+    }
+    return xen_pt_msix_update(s);
+}
+
+static uint32_t get_entry_value(XenPTMSIXEntry *e, int offset)
+{
+    switch (offset) {
+    case PCI_MSIX_ENTRY_LOWER_ADDR:
+        return e->addr & UINT32_MAX;
+    case PCI_MSIX_ENTRY_UPPER_ADDR:
+        return e->addr >> 32;
+    case PCI_MSIX_ENTRY_DATA:
+        return e->data;
+    case PCI_MSIX_ENTRY_VECTOR_CTRL:
+        return e->vector_ctrl;
+    default:
+        return 0;
+    }
+}
+
+static void set_entry_value(XenPTMSIXEntry *e, int offset, uint32_t val)
+{
+    switch (offset) {
+    case PCI_MSIX_ENTRY_LOWER_ADDR:
+        e->addr = (e->addr & ((uint64_t)UINT32_MAX << 32)) | val;
+        break;
+    case PCI_MSIX_ENTRY_UPPER_ADDR:
+        e->addr = (uint64_t)val << 32 | (e->addr & UINT32_MAX);
+        break;
+    case PCI_MSIX_ENTRY_DATA:
+        e->data = val;
+        break;
+    case PCI_MSIX_ENTRY_VECTOR_CTRL:
+        e->vector_ctrl = val;
+        break;
+    }
+}
+
+static void pci_msix_write(void *opaque, target_phys_addr_t addr,
+                           uint64_t val, unsigned size)
+{
+    XenPCIPassthroughState *s = opaque;
+    XenPTMSIX *msix = s->msix;
+    XenPTMSIXEntry *entry;
+    int entry_nr, offset;
+
+    entry_nr = addr / PCI_MSIX_ENTRY_SIZE;
+    if (entry_nr < 0 || entry_nr >= msix->total_entries) {
+        XEN_PT_ERR(&s->dev, "asked MSI-X entry '%i' invalid!\n", entry_nr);
+        return;
+    }
+    entry = &msix->msix_entry[entry_nr];
+    offset = addr % PCI_MSIX_ENTRY_SIZE;
+
+    if (offset != PCI_MSIX_ENTRY_VECTOR_CTRL) {
+        const volatile uint32_t *vec_ctrl;
+
+        if (get_entry_value(entry, offset) == val) {
+            return;
+        }
+
+        /*
+         * If Xen intercepts the mask bit access, entry->vec_ctrl may not be
+         * up-to-date. Read from hardware directly.
+         */
+        vec_ctrl = s->msix->phys_iomem_base + entry_nr * PCI_MSIX_ENTRY_SIZE
+            + PCI_MSIX_ENTRY_VECTOR_CTRL;
+
+        if (msix->enabled && !(*vec_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT)) {
+            XEN_PT_ERR(&s->dev, "Can't update msix entry %d since MSI-X is"
+                       " already enabled.\n", entry_nr);
+            return;
+        }
+
+        entry->updated = true;
+    }
+
+    set_entry_value(entry, offset, val);
+
+    if (offset == PCI_MSIX_ENTRY_VECTOR_CTRL) {
+        if (msix->enabled && !(val & PCI_MSIX_ENTRY_CTRL_MASKBIT)) {
+            xen_pt_msix_update_one(s, entry_nr);
+        }
+    }
+}
+
+static uint64_t pci_msix_read(void *opaque, target_phys_addr_t addr,
+                              unsigned size)
+{
+    XenPCIPassthroughState *s = opaque;
+    XenPTMSIX *msix = s->msix;
+    int entry_nr, offset;
+
+    entry_nr = addr / PCI_MSIX_ENTRY_SIZE;
+    if (entry_nr < 0) {
+        XEN_PT_ERR(&s->dev, "asked MSI-X entry '%i' invalid!\n", entry_nr);
+        return 0;
+    }
+
+    offset = addr % PCI_MSIX_ENTRY_SIZE;
+
+    if (addr < msix->total_entries * PCI_MSIX_ENTRY_SIZE) {
+        return get_entry_value(&msix->msix_entry[entry_nr], offset);
+    } else {
+        /* Pending Bit Array (PBA) */
+        return *(uint32_t *)(msix->phys_iomem_base + addr);
+    }
+}
+
+static const MemoryRegionOps pci_msix_ops = {
+    .read = pci_msix_read,
+    .write = pci_msix_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .valid = {
+        .min_access_size = 4,
+        .max_access_size = 4,
+        .unaligned = false,
+    },
+};
+
+int xen_pt_msix_init(XenPCIPassthroughState *s, uint32_t base)
+{
+    uint8_t id = 0;
+    uint16_t control = 0;
+    uint32_t table_off = 0;
+    int i, total_entries, bar_index;
+    XenHostPCIDevice *hd = &s->real_device;
+    PCIDevice *d = &s->dev;
+    int fd = -1;
+    XenPTMSIX *msix = NULL;
+    int rc = 0;
+
+    rc = xen_host_pci_get_byte(hd, base + PCI_CAP_LIST_ID, &id);
+    if (rc) {
+        return rc;
+    }
+
+    if (id != PCI_CAP_ID_MSIX) {
+        XEN_PT_ERR(d, "Invalid id %#x base %#x\n", id, base);
+        return -1;
+    }
+
+    xen_host_pci_get_word(hd, base + PCI_MSIX_FLAGS, &control);
+    total_entries = control & PCI_MSIX_FLAGS_QSIZE;
+    total_entries += 1;
+
+    s->msix = g_malloc0(sizeof (XenPTMSIX)
+                        + total_entries * sizeof (XenPTMSIXEntry));
+    msix = s->msix;
+
+    msix->total_entries = total_entries;
+    for (i = 0; i < total_entries; i++) {
+        msix->msix_entry[i].pirq = XEN_PT_UNASSIGNED_PIRQ;
+    }
+
+    memory_region_init_io(&msix->mmio, &pci_msix_ops, s, "xen-pci-pt-msix",
+                          (total_entries * PCI_MSIX_ENTRY_SIZE
+                           + XC_PAGE_SIZE - 1)
+                          & XC_PAGE_MASK);
+
+    xen_host_pci_get_long(hd, base + PCI_MSIX_TABLE, &table_off);
+    bar_index = msix->bar_index = table_off & PCI_MSIX_FLAGS_BIRMASK;
+    table_off = table_off & ~PCI_MSIX_FLAGS_BIRMASK;
+    msix->table_base = s->real_device.io_regions[bar_index].base_addr;
+    XEN_PT_LOG(d, "get MSI-X table BAR base 0x%"PRIx64"\n", msix->table_base);
+
+    fd = open("/dev/mem", O_RDWR);
+    if (fd == -1) {
+        rc = -errno;
+        XEN_PT_ERR(d, "Can't open /dev/mem: %s\n", strerror(errno));
+        goto error_out;
+    }
+    XEN_PT_LOG(d, "table_off = %#x, total_entries = %d\n",
+               table_off, total_entries);
+    msix->table_offset_adjust = table_off & 0x0fff;
+    msix->phys_iomem_base =
+        mmap(NULL,
+             total_entries * PCI_MSIX_ENTRY_SIZE + msix->table_offset_adjust,
+             PROT_READ,
+             MAP_SHARED | MAP_LOCKED,
+             fd,
+             msix->table_base + table_off - msix->table_offset_adjust);
+    close(fd);
+    if (msix->phys_iomem_base == MAP_FAILED) {
+        rc = -errno;
+        XEN_PT_ERR(d, "Can't map physical MSI-X table: %s\n", strerror(errno));
+        goto error_out;
+    }
+    msix->phys_iomem_base = (char *)msix->phys_iomem_base
+        + msix->table_offset_adjust;
+
+    XEN_PT_LOG(d, "mapping physical MSI-X table to %p\n",
+               msix->phys_iomem_base);
+
+    memory_region_add_subregion_overlap(&s->bar[bar_index], table_off,
+                                        &msix->mmio,
+                                        2); /* Priority: pci default + 1 */
+
+    return 0;
+
+error_out:
+    memory_region_destroy(&msix->mmio);
+    g_free(s->msix);
+    s->msix = NULL;
+    return rc;
+}
+
+void xen_pt_msix_delete(XenPCIPassthroughState *s)
+{
+    XenPTMSIX *msix = s->msix;
+
+    if (!msix) {
+        return;
+    }
+
+    /* unmap the MSI-X memory mapped register area */
+    if (msix->phys_iomem_base) {
+        XEN_PT_LOG(&s->dev, "unmapping physical MSI-X table from %p\n",
+                   msix->phys_iomem_base);
+        munmap(msix->phys_iomem_base, msix->total_entries * PCI_MSIX_ENTRY_SIZE
+               + msix->table_offset_adjust);
+    }
+
+    memory_region_del_subregion(&s->bar[msix->bar_index], &msix->mmio);
+    memory_region_destroy(&msix->mmio);
+
+    g_free(s->msix);
+    s->msix = NULL;
+}

qemu-common.h

@@ -275,6 +275,13 @@ typedef enum LostTickPolicy {
     LOST_TICK_MAX
 } LostTickPolicy;
 
+typedef struct PCIHostDeviceAddress {
+    unsigned int domain;
+    unsigned int bus;
+    unsigned int slot;
+    unsigned int function;
+} PCIHostDeviceAddress;
+
 void tcg_exec_init(unsigned long tb_size);
 bool tcg_enabled(void);
 

xen-all.c

@@ -1191,3 +1191,15 @@ void xen_register_framebuffer(MemoryRegion *mr)
 {
     framebuffer = mr;
 }
+
+void xen_shutdown_fatal_error(const char *fmt, ...)
+{
+    va_list ap;
+
+    va_start(ap, fmt);
+    vfprintf(stderr, fmt, ap);
+    va_end(ap);
+    fprintf(stderr, "Will destroy the domain.\n");
+    /* destroy the domain */
+    qemu_system_shutdown_request();
+}