Add qemu 2.4.0

Change-Id: Ic99cbad4b61f8b127b7dc74d04576c0bcbaaf4f5
Signed-off-by: Yang Zhang <yang.z.zhang@intel.com>

9 files changed, 5192 insertions, 0 deletions

diff --git a/qemu/hw/xen/Makefile.objs b/qemu/hw/xen/Makefile.objs
new file mode 100644
index 000000000..a0ca0aa3d
--- /dev/null
+++ b/qemu/hw/xen/Makefile.objs
@@ -0,0 +1,5 @@
+# xen backend driver support
+common-obj-$(CONFIG_XEN_BACKEND) += xen_backend.o xen_devconfig.o
+
+obj-$(CONFIG_XEN_PCI_PASSTHROUGH) += xen-host-pci-device.o
+obj-$(CONFIG_XEN_PCI_PASSTHROUGH) += xen_pt.o xen_pt_config_init.o xen_pt_msi.o
diff --git a/qemu/hw/xen/xen-host-pci-device.c b/qemu/hw/xen/xen-host-pci-device.c
new file mode 100644
index 000000000..743b37b99
--- /dev/null
+++ b/qemu/hw/xen/xen-host-pci-device.c
@@ -0,0 +1,396 @@
+/*
+ * 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 resource file */
+#define XEN_HOST_PCI_RESOURCE_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_RESOURCE_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;
+    }
+}
diff --git a/qemu/hw/xen/xen-host-pci-device.h b/qemu/hw/xen/xen-host-pci-device.h
new file mode 100644
index 000000000..c2486f0c1
--- /dev/null
+++ b/qemu/hw/xen/xen-host-pci-device.h
@@ -0,0 +1,55 @@
+#ifndef XEN_HOST_PCI_DEVICE_H
+#define XEN_HOST_PCI_DEVICE_H
+
+#include "hw/pci/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_ */
diff --git a/qemu/hw/xen/xen_backend.c b/qemu/hw/xen/xen_backend.c
new file mode 100644
index 000000000..2510e2e4f
--- /dev/null
+++ b/qemu/hw/xen/xen_backend.c
@@ -0,0 +1,808 @@
+/*
+ *  xen backend driver infrastructure
+ *  (c) 2008 Gerd Hoffmann <kraxel@redhat.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; under version 2 of the License.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ *  Contributions after 2012-01-13 are licensed under the terms of the
+ *  GNU GPL, version 2 or (at your option) any later version.
+ */
+
+/*
+ * TODO: add some xenbus / xenstore concepts overview here.
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <stdarg.h>
+#include <string.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <sys/signal.h>
+
+#include "hw/hw.h"
+#include "sysemu/char.h"
+#include "qemu/log.h"
+#include "hw/xen/xen_backend.h"
+
+#include <xen/grant_table.h>
+
+/* ------------------------------------------------------------- */
+
+/* public */
+XenXC xen_xc = XC_HANDLER_INITIAL_VALUE;
+struct xs_handle *xenstore = NULL;
+const char *xen_protocol;
+
+/* private */
+static QTAILQ_HEAD(XenDeviceHead, XenDevice) xendevs = QTAILQ_HEAD_INITIALIZER(xendevs);
+static int debug = 0;
+
+/* ------------------------------------------------------------- */
+
+int xenstore_write_str(const char *base, const char *node, const char *val)
+{
+    char abspath[XEN_BUFSIZE];
+
+    snprintf(abspath, sizeof(abspath), "%s/%s", base, node);
+    if (!xs_write(xenstore, 0, abspath, val, strlen(val))) {
+        return -1;
+    }
+    return 0;
+}
+
+char *xenstore_read_str(const char *base, const char *node)
+{
+    char abspath[XEN_BUFSIZE];
+    unsigned int len;
+    char *str, *ret = NULL;
+
+    snprintf(abspath, sizeof(abspath), "%s/%s", base, node);
+    str = xs_read(xenstore, 0, abspath, &len);
+    if (str != NULL) {
+        /* move to qemu-allocated memory to make sure
+         * callers can savely g_free() stuff. */
+        ret = g_strdup(str);
+        free(str);
+    }
+    return ret;
+}
+
+int xenstore_write_int(const char *base, const char *node, int ival)
+{
+    char val[12];
+
+    snprintf(val, sizeof(val), "%d", ival);
+    return xenstore_write_str(base, node, val);
+}
+
+int xenstore_write_int64(const char *base, const char *node, int64_t ival)
+{
+    char val[21];
+
+    snprintf(val, sizeof(val), "%"PRId64, ival);
+    return xenstore_write_str(base, node, val);
+}
+
+int xenstore_read_int(const char *base, const char *node, int *ival)
+{
+    char *val;
+    int rc = -1;
+
+    val = xenstore_read_str(base, node);
+    if (val && 1 == sscanf(val, "%d", ival)) {
+        rc = 0;
+    }
+    g_free(val);
+    return rc;
+}
+
+int xenstore_read_uint64(const char *base, const char *node, uint64_t *uval)
+{
+    char *val;
+    int rc = -1;
+
+    val = xenstore_read_str(base, node);
+    if (val && 1 == sscanf(val, "%"SCNu64, uval)) {
+        rc = 0;
+    }
+    g_free(val);
+    return rc;
+}
+
+int xenstore_write_be_str(struct XenDevice *xendev, const char *node, const char *val)
+{
+    return xenstore_write_str(xendev->be, node, val);
+}
+
+int xenstore_write_be_int(struct XenDevice *xendev, const char *node, int ival)
+{
+    return xenstore_write_int(xendev->be, node, ival);
+}
+
+int xenstore_write_be_int64(struct XenDevice *xendev, const char *node, int64_t ival)
+{
+    return xenstore_write_int64(xendev->be, node, ival);
+}
+
+char *xenstore_read_be_str(struct XenDevice *xendev, const char *node)
+{
+    return xenstore_read_str(xendev->be, node);
+}
+
+int xenstore_read_be_int(struct XenDevice *xendev, const char *node, int *ival)
+{
+    return xenstore_read_int(xendev->be, node, ival);
+}
+
+char *xenstore_read_fe_str(struct XenDevice *xendev, const char *node)
+{
+    return xenstore_read_str(xendev->fe, node);
+}
+
+int xenstore_read_fe_int(struct XenDevice *xendev, const char *node, int *ival)
+{
+    return xenstore_read_int(xendev->fe, node, ival);
+}
+
+int xenstore_read_fe_uint64(struct XenDevice *xendev, const char *node, uint64_t *uval)
+{
+    return xenstore_read_uint64(xendev->fe, node, uval);
+}
+
+/* ------------------------------------------------------------- */
+
+const char *xenbus_strstate(enum xenbus_state state)
+{
+    static const char *const name[] = {
+        [ XenbusStateUnknown      ] = "Unknown",
+        [ XenbusStateInitialising ] = "Initialising",
+        [ XenbusStateInitWait     ] = "InitWait",
+        [ XenbusStateInitialised  ] = "Initialised",
+        [ XenbusStateConnected    ] = "Connected",
+        [ XenbusStateClosing      ] = "Closing",
+        [ XenbusStateClosed       ] = "Closed",
+    };
+    return (state < ARRAY_SIZE(name)) ? name[state] : "INVALID";
+}
+
+int xen_be_set_state(struct XenDevice *xendev, enum xenbus_state state)
+{
+    int rc;
+
+    rc = xenstore_write_be_int(xendev, "state", state);
+    if (rc < 0) {
+        return rc;
+    }
+    xen_be_printf(xendev, 1, "backend state: %s -> %s\n",
+                  xenbus_strstate(xendev->be_state), xenbus_strstate(state));
+    xendev->be_state = state;
+    return 0;
+}
+
+/* ------------------------------------------------------------- */
+
+struct XenDevice *xen_be_find_xendev(const char *type, int dom, int dev)
+{
+    struct XenDevice *xendev;
+
+    QTAILQ_FOREACH(xendev, &xendevs, next) {
+        if (xendev->dom != dom) {
+            continue;
+        }
+        if (xendev->dev != dev) {
+            continue;
+        }
+        if (strcmp(xendev->type, type) != 0) {
+            continue;
+        }
+        return xendev;
+    }
+    return NULL;
+}
+
+/*
+ * get xen backend device, allocate a new one if it doesn't exist.
+ */
+static struct XenDevice *xen_be_get_xendev(const char *type, int dom, int dev,
+                                           struct XenDevOps *ops)
+{
+    struct XenDevice *xendev;
+
+    xendev = xen_be_find_xendev(type, dom, dev);
+    if (xendev) {
+        return xendev;
+    }
+
+    /* init new xendev */
+    xendev = g_malloc0(ops->size);
+    xendev->type  = type;
+    xendev->dom   = dom;
+    xendev->dev   = dev;
+    xendev->ops   = ops;
+
+    snprintf(xendev->be, sizeof(xendev->be), "backend/%s/%d/%d",
+             xendev->type, xendev->dom, xendev->dev);
+    snprintf(xendev->name, sizeof(xendev->name), "%s-%d",
+             xendev->type, xendev->dev);
+
+    xendev->debug      = debug;
+    xendev->local_port = -1;
+
+    xendev->evtchndev = xen_xc_evtchn_open(NULL, 0);
+    if (xendev->evtchndev == XC_HANDLER_INITIAL_VALUE) {
+        xen_be_printf(NULL, 0, "can't open evtchn device\n");
+        g_free(xendev);
+        return NULL;
+    }
+    fcntl(xc_evtchn_fd(xendev->evtchndev), F_SETFD, FD_CLOEXEC);
+
+    if (ops->flags & DEVOPS_FLAG_NEED_GNTDEV) {
+        xendev->gnttabdev = xen_xc_gnttab_open(NULL, 0);
+        if (xendev->gnttabdev == XC_HANDLER_INITIAL_VALUE) {
+            xen_be_printf(NULL, 0, "can't open gnttab device\n");
+            xc_evtchn_close(xendev->evtchndev);
+            g_free(xendev);
+            return NULL;
+        }
+    } else {
+        xendev->gnttabdev = XC_HANDLER_INITIAL_VALUE;
+    }
+
+    QTAILQ_INSERT_TAIL(&xendevs, xendev, next);
+
+    if (xendev->ops->alloc) {
+        xendev->ops->alloc(xendev);
+    }
+
+    return xendev;
+}
+
+/*
+ * release xen backend device.
+ */
+static struct XenDevice *xen_be_del_xendev(int dom, int dev)
+{
+    struct XenDevice *xendev, *xnext;
+
+    /*
+     * This is pretty much like QTAILQ_FOREACH(xendev, &xendevs, next) but
+     * we save the next pointer in xnext because we might free xendev.
+     */
+    xnext = xendevs.tqh_first;
+    while (xnext) {
+        xendev = xnext;
+        xnext = xendev->next.tqe_next;
+
+        if (xendev->dom != dom) {
+            continue;
+        }
+        if (xendev->dev != dev && dev != -1) {
+            continue;
+        }
+
+        if (xendev->ops->free) {
+            xendev->ops->free(xendev);
+        }
+
+        if (xendev->fe) {
+            char token[XEN_BUFSIZE];
+            snprintf(token, sizeof(token), "fe:%p", xendev);
+            xs_unwatch(xenstore, xendev->fe, token);
+            g_free(xendev->fe);
+        }
+
+        if (xendev->evtchndev != XC_HANDLER_INITIAL_VALUE) {
+            xc_evtchn_close(xendev->evtchndev);
+        }
+        if (xendev->gnttabdev != XC_HANDLER_INITIAL_VALUE) {
+            xc_gnttab_close(xendev->gnttabdev);
+        }
+
+        QTAILQ_REMOVE(&xendevs, xendev, next);
+        g_free(xendev);
+    }
+    return NULL;
+}
+
+/*
+ * Sync internal data structures on xenstore updates.
+ * Node specifies the changed field.  node = NULL means
+ * update all fields (used for initialization).
+ */
+static void xen_be_backend_changed(struct XenDevice *xendev, const char *node)
+{
+    if (node == NULL  ||  strcmp(node, "online") == 0) {
+        if (xenstore_read_be_int(xendev, "online", &xendev->online) == -1) {
+            xendev->online = 0;
+        }
+    }
+
+    if (node) {
+        xen_be_printf(xendev, 2, "backend update: %s\n", node);
+        if (xendev->ops->backend_changed) {
+            xendev->ops->backend_changed(xendev, node);
+        }
+    }
+}
+
+static void xen_be_frontend_changed(struct XenDevice *xendev, const char *node)
+{
+    int fe_state;
+
+    if (node == NULL  ||  strcmp(node, "state") == 0) {
+        if (xenstore_read_fe_int(xendev, "state", &fe_state) == -1) {
+            fe_state = XenbusStateUnknown;
+        }
+        if (xendev->fe_state != fe_state) {
+            xen_be_printf(xendev, 1, "frontend state: %s -> %s\n",
+                          xenbus_strstate(xendev->fe_state),
+                          xenbus_strstate(fe_state));
+        }
+        xendev->fe_state = fe_state;
+    }
+    if (node == NULL  ||  strcmp(node, "protocol") == 0) {
+        g_free(xendev->protocol);
+        xendev->protocol = xenstore_read_fe_str(xendev, "protocol");
+        if (xendev->protocol) {
+            xen_be_printf(xendev, 1, "frontend protocol: %s\n", xendev->protocol);
+        }
+    }
+
+    if (node) {
+        xen_be_printf(xendev, 2, "frontend update: %s\n", node);
+        if (xendev->ops->frontend_changed) {
+            xendev->ops->frontend_changed(xendev, node);
+        }
+    }
+}
+
+/* ------------------------------------------------------------- */
+/* Check for possible state transitions and perform them.        */
+
+/*
+ * Initial xendev setup.  Read frontend path, register watch for it.
+ * Should succeed once xend finished setting up the backend device.
+ *
+ * Also sets initial state (-> Initializing) when done.  Which
+ * only affects the xendev->be_state variable as xenbus should
+ * already be put into that state by xend.
+ */
+static int xen_be_try_setup(struct XenDevice *xendev)
+{
+    char token[XEN_BUFSIZE];
+    int be_state;
+
+    if (xenstore_read_be_int(xendev, "state", &be_state) == -1) {
+        xen_be_printf(xendev, 0, "reading backend state failed\n");
+        return -1;
+    }
+
+    if (be_state != XenbusStateInitialising) {
+        xen_be_printf(xendev, 0, "initial backend state is wrong (%s)\n",
+                      xenbus_strstate(be_state));
+        return -1;
+    }
+
+    xendev->fe = xenstore_read_be_str(xendev, "frontend");
+    if (xendev->fe == NULL) {
+        xen_be_printf(xendev, 0, "reading frontend path failed\n");
+        return -1;
+    }
+
+    /* setup frontend watch */
+    snprintf(token, sizeof(token), "fe:%p", xendev);
+    if (!xs_watch(xenstore, xendev->fe, token)) {
+        xen_be_printf(xendev, 0, "watching frontend path (%s) failed\n",
+                      xendev->fe);
+        return -1;
+    }
+    xen_be_set_state(xendev, XenbusStateInitialising);
+
+    xen_be_backend_changed(xendev, NULL);
+    xen_be_frontend_changed(xendev, NULL);
+    return 0;
+}
+
+/*
+ * Try initialize xendev.  Prepare everything the backend can do
+ * without synchronizing with the frontend.  Fakes hotplug-status.  No
+ * hotplug involved here because this is about userspace drivers, thus
+ * there are kernel backend devices which could invoke hotplug.
+ *
+ * Goes to InitWait on success.
+ */
+static int xen_be_try_init(struct XenDevice *xendev)
+{
+    int rc = 0;
+
+    if (!xendev->online) {
+        xen_be_printf(xendev, 1, "not online\n");
+        return -1;
+    }
+
+    if (xendev->ops->init) {
+        rc = xendev->ops->init(xendev);
+    }
+    if (rc != 0) {
+        xen_be_printf(xendev, 1, "init() failed\n");
+        return rc;
+    }
+
+    xenstore_write_be_str(xendev, "hotplug-status", "connected");
+    xen_be_set_state(xendev, XenbusStateInitWait);
+    return 0;
+}
+
+/*
+ * Try to initialise xendev.  Depends on the frontend being ready
+ * for it (shared ring and evtchn info in xenstore, state being
+ * Initialised or Connected).
+ *
+ * Goes to Connected on success.
+ */
+static int xen_be_try_initialise(struct XenDevice *xendev)
+{
+    int rc = 0;
+
+    if (xendev->fe_state != XenbusStateInitialised  &&
+        xendev->fe_state != XenbusStateConnected) {
+        if (xendev->ops->flags & DEVOPS_FLAG_IGNORE_STATE) {
+            xen_be_printf(xendev, 2, "frontend not ready, ignoring\n");
+        } else {
+            xen_be_printf(xendev, 2, "frontend not ready (yet)\n");
+            return -1;
+        }
+    }
+
+    if (xendev->ops->initialise) {
+        rc = xendev->ops->initialise(xendev);
+    }
+    if (rc != 0) {
+        xen_be_printf(xendev, 0, "initialise() failed\n");
+        return rc;
+    }
+
+    xen_be_set_state(xendev, XenbusStateConnected);
+    return 0;
+}
+
+/*
+ * Try to let xendev know that it is connected.  Depends on the
+ * frontend being Connected.  Note that this may be called more
+ * than once since the backend state is not modified.
+ */
+static void xen_be_try_connected(struct XenDevice *xendev)
+{
+    if (!xendev->ops->connected) {
+        return;
+    }
+
+    if (xendev->fe_state != XenbusStateConnected) {
+        if (xendev->ops->flags & DEVOPS_FLAG_IGNORE_STATE) {
+            xen_be_printf(xendev, 2, "frontend not ready, ignoring\n");
+        } else {
+            xen_be_printf(xendev, 2, "frontend not ready (yet)\n");
+            return;
+        }
+    }
+
+    xendev->ops->connected(xendev);
+}
+
+/*
+ * Teardown connection.
+ *
+ * Goes to Closed when done.
+ */
+static void xen_be_disconnect(struct XenDevice *xendev, enum xenbus_state state)
+{
+    if (xendev->be_state != XenbusStateClosing &&
+        xendev->be_state != XenbusStateClosed  &&
+        xendev->ops->disconnect) {
+        xendev->ops->disconnect(xendev);
+    }
+    if (xendev->be_state != state) {
+        xen_be_set_state(xendev, state);
+    }
+}
+
+/*
+ * Try to reset xendev, for reconnection by another frontend instance.
+ */
+static int xen_be_try_reset(struct XenDevice *xendev)
+{
+    if (xendev->fe_state != XenbusStateInitialising) {
+        return -1;
+    }
+
+    xen_be_printf(xendev, 1, "device reset (for re-connect)\n");
+    xen_be_set_state(xendev, XenbusStateInitialising);
+    return 0;
+}
+
+/*
+ * state change dispatcher function
+ */
+void xen_be_check_state(struct XenDevice *xendev)
+{
+    int rc = 0;
+
+    /* frontend may request shutdown from almost anywhere */
+    if (xendev->fe_state == XenbusStateClosing ||
+        xendev->fe_state == XenbusStateClosed) {
+        xen_be_disconnect(xendev, xendev->fe_state);
+        return;
+    }
+
+    /* check for possible backend state transitions */
+    for (;;) {
+        switch (xendev->be_state) {
+        case XenbusStateUnknown:
+            rc = xen_be_try_setup(xendev);
+            break;
+        case XenbusStateInitialising:
+            rc = xen_be_try_init(xendev);
+            break;
+        case XenbusStateInitWait:
+            rc = xen_be_try_initialise(xendev);
+            break;
+        case XenbusStateConnected:
+            /* xendev->be_state doesn't change */
+            xen_be_try_connected(xendev);
+            rc = -1;
+            break;
+        case XenbusStateClosed:
+            rc = xen_be_try_reset(xendev);
+            break;
+        default:
+            rc = -1;
+        }
+        if (rc != 0) {
+            break;
+        }
+    }
+}
+
+/* ------------------------------------------------------------- */
+
+static int xenstore_scan(const char *type, int dom, struct XenDevOps *ops)
+{
+    struct XenDevice *xendev;
+    char path[XEN_BUFSIZE], token[XEN_BUFSIZE];
+    char **dev = NULL;
+    unsigned int cdev, j;
+
+    /* setup watch */
+    snprintf(token, sizeof(token), "be:%p:%d:%p", type, dom, ops);
+    snprintf(path, sizeof(path), "backend/%s/%d", type, dom);
+    if (!xs_watch(xenstore, path, token)) {
+        xen_be_printf(NULL, 0, "xen be: watching backend path (%s) failed\n", path);
+        return -1;
+    }
+
+    /* look for backends */
+    dev = xs_directory(xenstore, 0, path, &cdev);
+    if (!dev) {
+        return 0;
+    }
+    for (j = 0; j < cdev; j++) {
+        xendev = xen_be_get_xendev(type, dom, atoi(dev[j]), ops);
+        if (xendev == NULL) {
+            continue;
+        }
+        xen_be_check_state(xendev);
+    }
+    free(dev);
+    return 0;
+}
+
+static void xenstore_update_be(char *watch, char *type, int dom,
+                               struct XenDevOps *ops)
+{
+    struct XenDevice *xendev;
+    char path[XEN_BUFSIZE], *bepath;
+    unsigned int len, dev;
+
+    len = snprintf(path, sizeof(path), "backend/%s/%d", type, dom);
+    if (strncmp(path, watch, len) != 0) {
+        return;
+    }
+    if (sscanf(watch+len, "/%u/%255s", &dev, path) != 2) {
+        strcpy(path, "");
+        if (sscanf(watch+len, "/%u", &dev) != 1) {
+            dev = -1;
+        }
+    }
+    if (dev == -1) {
+        return;
+    }
+
+    xendev = xen_be_get_xendev(type, dom, dev, ops);
+    if (xendev != NULL) {
+        bepath = xs_read(xenstore, 0, xendev->be, &len);
+        if (bepath == NULL) {
+            xen_be_del_xendev(dom, dev);
+        } else {
+            free(bepath);
+            xen_be_backend_changed(xendev, path);
+            xen_be_check_state(xendev);
+        }
+    }
+}
+
+static void xenstore_update_fe(char *watch, struct XenDevice *xendev)
+{
+    char *node;
+    unsigned int len;
+
+    len = strlen(xendev->fe);
+    if (strncmp(xendev->fe, watch, len) != 0) {
+        return;
+    }
+    if (watch[len] != '/') {
+        return;
+    }
+    node = watch + len + 1;
+
+    xen_be_frontend_changed(xendev, node);
+    xen_be_check_state(xendev);
+}
+
+static void xenstore_update(void *unused)
+{
+    char **vec = NULL;
+    intptr_t type, ops, ptr;
+    unsigned int dom, count;
+
+    vec = xs_read_watch(xenstore, &count);
+    if (vec == NULL) {
+        goto cleanup;
+    }
+
+    if (sscanf(vec[XS_WATCH_TOKEN], "be:%" PRIxPTR ":%d:%" PRIxPTR,
+               &type, &dom, &ops) == 3) {
+        xenstore_update_be(vec[XS_WATCH_PATH], (void*)type, dom, (void*)ops);
+    }
+    if (sscanf(vec[XS_WATCH_TOKEN], "fe:%" PRIxPTR, &ptr) == 1) {
+        xenstore_update_fe(vec[XS_WATCH_PATH], (void*)ptr);
+    }
+
+cleanup:
+    free(vec);
+}
+
+static void xen_be_evtchn_event(void *opaque)
+{
+    struct XenDevice *xendev = opaque;
+    evtchn_port_t port;
+
+    port = xc_evtchn_pending(xendev->evtchndev);
+    if (port != xendev->local_port) {
+        xen_be_printf(xendev, 0, "xc_evtchn_pending returned %d (expected %d)\n",
+                      port, xendev->local_port);
+        return;
+    }
+    xc_evtchn_unmask(xendev->evtchndev, port);
+
+    if (xendev->ops->event) {
+        xendev->ops->event(xendev);
+    }
+}
+
+/* -------------------------------------------------------------------- */
+
+int xen_be_init(void)
+{
+    xenstore = xs_daemon_open();
+    if (!xenstore) {
+        xen_be_printf(NULL, 0, "can't connect to xenstored\n");
+        return -1;
+    }
+
+    qemu_set_fd_handler(xs_fileno(xenstore), xenstore_update, NULL, NULL);
+
+    if (xen_xc == XC_HANDLER_INITIAL_VALUE) {
+        /* Check if xen_init() have been called */
+        goto err;
+    }
+    return 0;
+
+err:
+    qemu_set_fd_handler(xs_fileno(xenstore), NULL, NULL, NULL);
+    xs_daemon_close(xenstore);
+    xenstore = NULL;
+
+    return -1;
+}
+
+int xen_be_register(const char *type, struct XenDevOps *ops)
+{
+    return xenstore_scan(type, xen_domid, ops);
+}
+
+int xen_be_bind_evtchn(struct XenDevice *xendev)
+{
+    if (xendev->local_port != -1) {
+        return 0;
+    }
+    xendev->local_port = xc_evtchn_bind_interdomain
+        (xendev->evtchndev, xendev->dom, xendev->remote_port);
+    if (xendev->local_port == -1) {
+        xen_be_printf(xendev, 0, "xc_evtchn_bind_interdomain failed\n");
+        return -1;
+    }
+    xen_be_printf(xendev, 2, "bind evtchn port %d\n", xendev->local_port);
+    qemu_set_fd_handler(xc_evtchn_fd(xendev->evtchndev),
+                        xen_be_evtchn_event, NULL, xendev);
+    return 0;
+}
+
+void xen_be_unbind_evtchn(struct XenDevice *xendev)
+{
+    if (xendev->local_port == -1) {
+        return;
+    }
+    qemu_set_fd_handler(xc_evtchn_fd(xendev->evtchndev), NULL, NULL, NULL);
+    xc_evtchn_unbind(xendev->evtchndev, xendev->local_port);
+    xen_be_printf(xendev, 2, "unbind evtchn port %d\n", xendev->local_port);
+    xendev->local_port = -1;
+}
+
+int xen_be_send_notify(struct XenDevice *xendev)
+{
+    return xc_evtchn_notify(xendev->evtchndev, xendev->local_port);
+}
+
+/*
+ * msg_level:
+ *  0 == errors (stderr + logfile).
+ *  1 == informative debug messages (logfile only).
+ *  2 == noisy debug messages (logfile only).
+ *  3 == will flood your log (logfile only).
+ */
+void xen_be_printf(struct XenDevice *xendev, int msg_level, const char *fmt, ...)
+{
+    va_list args;
+
+    if (xendev) {
+        if (msg_level > xendev->debug) {
+            return;
+        }
+        qemu_log("xen be: %s: ", xendev->name);
+        if (msg_level == 0) {
+            fprintf(stderr, "xen be: %s: ", xendev->name);
+        }
+    } else {
+        if (msg_level > debug) {
+            return;
+        }
+        qemu_log("xen be core: ");
+        if (msg_level == 0) {
+            fprintf(stderr, "xen be core: ");
+        }
+    }
+    va_start(args, fmt);
+    qemu_log_vprintf(fmt, args);
+    va_end(args);
+    if (msg_level == 0) {
+        va_start(args, fmt);
+        vfprintf(stderr, fmt, args);
+        va_end(args);
+    }
+    qemu_log_flush();
+}
diff --git a/qemu/hw/xen/xen_devconfig.c b/qemu/hw/xen/xen_devconfig.c
new file mode 100644
index 000000000..e138dbbec
--- /dev/null
+++ b/qemu/hw/xen/xen_devconfig.c
@@ -0,0 +1,175 @@
+#include "hw/xen/xen_backend.h"
+#include "sysemu/block-backend.h"
+#include "sysemu/blockdev.h"
+
+/* ------------------------------------------------------------- */
+
+struct xs_dirs {
+    char *xs_dir;
+    QTAILQ_ENTRY(xs_dirs) list;
+};
+static QTAILQ_HEAD(xs_dirs_head, xs_dirs) xs_cleanup = QTAILQ_HEAD_INITIALIZER(xs_cleanup);
+
+static void xen_config_cleanup_dir(char *dir)
+{
+    struct xs_dirs *d;
+
+    d = g_malloc(sizeof(*d));
+    d->xs_dir = dir;
+    QTAILQ_INSERT_TAIL(&xs_cleanup, d, list);
+}
+
+void xen_config_cleanup(void)
+{
+    struct xs_dirs *d;
+
+    QTAILQ_FOREACH(d, &xs_cleanup, list) {
+	xs_rm(xenstore, 0, d->xs_dir);
+    }
+}
+
+/* ------------------------------------------------------------- */
+
+static int xen_config_dev_mkdir(char *dev, int p)
+{
+    struct xs_permissions perms[2] = {{
+            .id    = 0, /* set owner: dom0 */
+        },{
+            .id    = xen_domid,
+            .perms = p,
+        }};
+
+    if (!xs_mkdir(xenstore, 0, dev)) {
+	xen_be_printf(NULL, 0, "xs_mkdir %s: failed\n", dev);
+	return -1;
+    }
+    xen_config_cleanup_dir(g_strdup(dev));
+
+    if (!xs_set_permissions(xenstore, 0, dev, perms, 2)) {
+	xen_be_printf(NULL, 0, "xs_set_permissions %s: failed\n", dev);
+	return -1;
+    }
+    return 0;
+}
+
+static int xen_config_dev_dirs(const char *ftype, const char *btype, int vdev,
+			       char *fe, char *be, int len)
+{
+    char *dom;
+
+    dom = xs_get_domain_path(xenstore, xen_domid);
+    snprintf(fe, len, "%s/device/%s/%d", dom, ftype, vdev);
+    free(dom);
+
+    dom = xs_get_domain_path(xenstore, 0);
+    snprintf(be, len, "%s/backend/%s/%d/%d", dom, btype, xen_domid, vdev);
+    free(dom);
+
+    xen_config_dev_mkdir(fe, XS_PERM_READ | XS_PERM_WRITE);
+    xen_config_dev_mkdir(be, XS_PERM_READ);
+    return 0;
+}
+
+static int xen_config_dev_all(char *fe, char *be)
+{
+    /* frontend */
+    if (xen_protocol)
+        xenstore_write_str(fe, "protocol", xen_protocol);
+
+    xenstore_write_int(fe, "state",           XenbusStateInitialising);
+    xenstore_write_int(fe, "backend-id",      0);
+    xenstore_write_str(fe, "backend",         be);
+
+    /* backend */
+    xenstore_write_str(be, "domain",          qemu_name ? qemu_name : "no-name");
+    xenstore_write_int(be, "online",          1);
+    xenstore_write_int(be, "state",           XenbusStateInitialising);
+    xenstore_write_int(be, "frontend-id",     xen_domid);
+    xenstore_write_str(be, "frontend",        fe);
+
+    return 0;
+}
+
+/* ------------------------------------------------------------- */
+
+int xen_config_dev_blk(DriveInfo *disk)
+{
+    char fe[256], be[256], device_name[32];
+    int vdev = 202 * 256 + 16 * disk->unit;
+    int cdrom = disk->media_cd;
+    const char *devtype = cdrom ? "cdrom" : "disk";
+    const char *mode    = cdrom ? "r"     : "w";
+    const char *filename = qemu_opt_get(disk->opts, "file");
+
+    snprintf(device_name, sizeof(device_name), "xvd%c", 'a' + disk->unit);
+    xen_be_printf(NULL, 1, "config disk %d [%s]: %s\n",
+                  disk->unit, device_name, filename);
+    xen_config_dev_dirs("vbd", "qdisk", vdev, fe, be, sizeof(fe));
+
+    /* frontend */
+    xenstore_write_int(fe, "virtual-device",  vdev);
+    xenstore_write_str(fe, "device-type",     devtype);
+
+    /* backend */
+    xenstore_write_str(be, "dev",             device_name);
+    xenstore_write_str(be, "type",            "file");
+    xenstore_write_str(be, "params",          filename);
+    xenstore_write_str(be, "mode",            mode);
+
+    /* common stuff */
+    return xen_config_dev_all(fe, be);
+}
+
+int xen_config_dev_nic(NICInfo *nic)
+{
+    char fe[256], be[256];
+    char mac[20];
+    int vlan_id = -1;
+
+    net_hub_id_for_client(nic->netdev, &vlan_id);
+    snprintf(mac, sizeof(mac), "%02x:%02x:%02x:%02x:%02x:%02x",
+             nic->macaddr.a[0], nic->macaddr.a[1], nic->macaddr.a[2],
+             nic->macaddr.a[3], nic->macaddr.a[4], nic->macaddr.a[5]);
+    xen_be_printf(NULL, 1, "config nic %d: mac=\"%s\"\n", vlan_id, mac);
+    xen_config_dev_dirs("vif", "qnic", vlan_id, fe, be, sizeof(fe));
+
+    /* frontend */
+    xenstore_write_int(fe, "handle",     vlan_id);
+    xenstore_write_str(fe, "mac",        mac);
+
+    /* backend */
+    xenstore_write_int(be, "handle",     vlan_id);
+    xenstore_write_str(be, "mac",        mac);
+
+    /* common stuff */
+    return xen_config_dev_all(fe, be);
+}
+
+int xen_config_dev_vfb(int vdev, const char *type)
+{
+    char fe[256], be[256];
+
+    xen_config_dev_dirs("vfb", "vfb", vdev, fe, be, sizeof(fe));
+
+    /* backend */
+    xenstore_write_str(be, "type",  type);
+
+    /* common stuff */
+    return xen_config_dev_all(fe, be);
+}
+
+int xen_config_dev_vkbd(int vdev)
+{
+    char fe[256], be[256];
+
+    xen_config_dev_dirs("vkbd", "vkbd", vdev, fe, be, sizeof(fe));
+    return xen_config_dev_all(fe, be);
+}
+
+int xen_config_dev_console(int vdev)
+{
+    char fe[256], be[256];
+
+    xen_config_dev_dirs("console", "console", vdev, fe, be, sizeof(fe));
+    return xen_config_dev_all(fe, be);
+}
diff --git a/qemu/hw/xen/xen_pt.c b/qemu/hw/xen/xen_pt.c
new file mode 100644
index 000000000..ed5fcaec0
--- /dev/null
+++ b/qemu/hw/xen/xen_pt.c
@@ -0,0 +1,885 @@
+/*
+ * 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 "hw/pci/pci.h"
+#include "hw/xen/xen.h"
+#include "hw/xen/xen_backend.h"
+#include "xen_pt.h"
+#include "qemu/range.h"
+#include "exec/address-spaces.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 = XEN_PT_DEVICE(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 = XEN_PT_DEVICE(d);
+    int index = 0;
+    XenPTRegGroup *reg_grp_entry = NULL;
+    int rc = 0;
+    uint32_t read_val = 0, wb_mask;
+    int emul_len = 0;
+    XenPTReg *reg_entry = NULL;
+    uint32_t find_addr = addr;
+    XenPTRegInfo *reg = NULL;
+    bool wp_flag = false;
+
+    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)) {
+        uint32_t chk = val;
+
+        if (index == PCI_ROM_SLOT)
+            chk |= (uint32_t)~PCI_ROM_ADDRESS_MASK;
+
+        if ((chk != 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);
+        wb_mask = 0;
+    } else {
+        wb_mask = 0xFFFFFFFF >> ((4 - len) << 3);
+    }
+
+    /* pass directly to the real device for passthrough type register group */
+    if (reg_grp_entry == NULL) {
+        if (!s->permissive) {
+            wb_mask = 0;
+            wp_flag = true;
+        }
+        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;
+            uint32_t wp_mask = reg->emu_mask | reg->ro_mask;
+
+            valid_mask <<= (find_addr - real_offset) << 3;
+            ptr_val = (uint8_t *)&val + (real_offset & 3);
+            if (!s->permissive) {
+                wp_mask |= reg->res_mask;
+            }
+            if (wp_mask == (0xFFFFFFFF >> ((4 - reg->size) << 3))) {
+                wb_mask &= ~((wp_mask >> ((find_addr - real_offset) << 3))
+                             << ((len - emul_len) << 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 */
+            if (!s->permissive) {
+                wb_mask &= ~(0xff << ((len - emul_len) << 3));
+                /* Unused BARs will make it here, but we don't want to issue
+                 * warnings for writes to them (bogus writes get dealt with
+                 * above).
+                 */
+                if (index < 0) {
+                    wp_flag = true;
+                }
+            }
+            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 (wp_flag && !s->permissive_warned) {
+        s->permissive_warned = true;
+        xen_pt_log(d, "Write-back to unknown field 0x%02x (partially) inhibited (0x%0*x)\n",
+                   addr, len * 2, wb_mask);
+        xen_pt_log(d, "If the device doesn't work, try enabling permissive mode\n");
+        xen_pt_log(d, "(unsafe) and if it helps report the problem to xen-devel\n");
+    }
+    for (index = 0; wb_mask; index += len) {
+        /* unknown regs are passed through */
+        while (!(wb_mask & 0xff)) {
+            index++;
+            wb_mask >>= 8;
+        }
+        len = 0;
+        do {
+            len++;
+            wb_mask >>= 8;
+        } while (wb_mask & 0xff);
+        rc = xen_host_pci_set_block(&s->real_device, addr + index,
+                                    (uint8_t *)&val + index, 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, hwaddr 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, hwaddr 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, uint16_t *cmd)
+{
+    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;
+            *cmd |= PCI_COMMAND_IO;
+        } else {
+            type = PCI_BASE_ADDRESS_SPACE_MEMORY;
+            if (r->type & XEN_HOST_PCI_REGION_TYPE_PREFETCH) {
+                type |= PCI_BASE_ADDRESS_MEM_PREFETCH;
+            }
+            if (r->type & XEN_HOST_PCI_REGION_TYPE_MEM_64) {
+                type |= PCI_BASE_ADDRESS_MEM_TYPE_64;
+            }
+            *cmd |= PCI_COMMAND_MEMORY;
+        }
+
+        memory_region_init_io(&s->bar[i], OBJECT(s), &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_io(&s->rom, OBJECT(s), &ops, &s->dev,
+                              "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;
+}
+
+/* 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 = int128_get64(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,
+                    int128_get64(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 = int128_get64(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! (err: %i)\n",
+                       adding ? "create new" : "remove old", errno);
+        }
+    } 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 = int128_get64(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! (err: %i)\n",
+                       adding ? "create new" : "remove old", errno);
+        }
+    }
+}
+
+static void xen_pt_region_add(MemoryListener *l, MemoryRegionSection *sec)
+{
+    XenPCIPassthroughState *s = container_of(l, XenPCIPassthroughState,
+                                             memory_listener);
+
+    memory_region_ref(sec->mr);
+    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);
+    memory_region_unref(sec->mr);
+}
+
+static void xen_pt_io_region_add(MemoryListener *l, MemoryRegionSection *sec)
+{
+    XenPCIPassthroughState *s = container_of(l, XenPCIPassthroughState,
+                                             io_listener);
+
+    memory_region_ref(sec->mr);
+    xen_pt_region_update(s, sec, true);
+}
+
+static void xen_pt_io_region_del(MemoryListener *l, MemoryRegionSection *sec)
+{
+    XenPCIPassthroughState *s = container_of(l, XenPCIPassthroughState,
+                                             io_listener);
+
+    xen_pt_region_update(s, sec, false);
+    memory_region_unref(sec->mr);
+}
+
+static const MemoryListener xen_pt_memory_listener = {
+    .region_add = xen_pt_region_add,
+    .region_del = xen_pt_region_del,
+    .priority = 10,
+};
+
+static const MemoryListener xen_pt_io_listener = {
+    .region_add = xen_pt_io_region_add,
+    .region_del = xen_pt_io_region_del,
+    .priority = 10,
+};
+
+/* init */
+
+static int xen_pt_initfn(PCIDevice *d)
+{
+    XenPCIPassthroughState *s = XEN_PT_DEVICE(d);
+    int rc = 0;
+    uint8_t machine_irq = 0;
+    uint16_t cmd = 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, s->real_device.bus,
+                   s->real_device.dev, s->real_device.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;
+    s->io_listener = xen_pt_io_listener;
+
+    /* Handle real device's MMIO/PIO BARs */
+    xen_pt_register_regions(s, &cmd);
+
+    /* reinitialize each config register to be emulated */
+    if (xen_pt_config_init(s)) {
+        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, (err: %d)\n",
+                   machine_irq, pirq, errno);
+
+        /* Disable PCI intx assertion (turn on bit10 of devctl) */
+        cmd |= 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! (err: %d)\n",
+                       e_intx, errno);
+
+            /* Disable PCI intx assertion (turn on bit10 of devctl) */
+            cmd |= 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!"
+                               " (err: %d)\n", machine_irq, errno);
+                }
+            }
+            s->machine_irq = 0;
+        }
+    }
+
+out:
+    if (cmd) {
+        xen_host_pci_set_word(&s->real_device, PCI_COMMAND,
+                              pci_get_word(d->config + PCI_COMMAND) | cmd);
+    }
+
+    memory_listener_register(&s->memory_listener, &s->dev.bus_master_as);
+    memory_listener_register(&s->io_listener, &address_space_io);
+    XEN_PT_LOG(d,
+               "Real physical device %02x:%02x.%d registered successfully!\n",
+               s->hostaddr.bus, s->hostaddr.slot, s->hostaddr.function);
+
+    return 0;
+}
+
+static void xen_pt_unregister_device(PCIDevice *d)
+{
+    XenPCIPassthroughState *s = XEN_PT_DEVICE(d);
+    uint8_t machine_irq = s->machine_irq;
+    uint8_t intx = xen_pt_pci_intx(s);
+    int rc;
+
+    if (machine_irq) {
+        rc = xc_domain_unbind_pt_irq(xen_xc, xen_domid, machine_irq,
+                                     PT_IRQ_TYPE_PCI,
+                                     pci_bus_num(d->bus),
+                                     PCI_SLOT(s->dev.devfn),
+                                     intx,
+                                     0 /* isa_irq */);
+        if (rc < 0) {
+            XEN_PT_ERR(d, "unbinding of interrupt INT%c failed."
+                       " (machine irq: %i, err: %d)"
+                       " But bravely continuing on..\n",
+                       'a' + intx, machine_irq, errno);
+        }
+    }
+
+    if (s->msi) {
+        xen_pt_msi_disable(s);
+    }
+    if (s->msix) {
+        xen_pt_msix_disable(s);
+    }
+
+    if (machine_irq) {
+        xen_pt_mapped_machine_irq[machine_irq]--;
+
+        if (xen_pt_mapped_machine_irq[machine_irq] == 0) {
+            rc = xc_physdev_unmap_pirq(xen_xc, xen_domid, machine_irq);
+
+            if (rc < 0) {
+                XEN_PT_ERR(d, "unmapping of interrupt %i failed. (err: %d)"
+                           " But bravely continuing on..\n",
+                           machine_irq, errno);
+            }
+        }
+    }
+
+    /* delete all emulated config registers */
+    xen_pt_config_delete(s);
+
+    memory_listener_unregister(&s->memory_listener);
+    memory_listener_unregister(&s->io_listener);
+
+    xen_host_pci_device_put(&s->real_device);
+}
+
+static Property xen_pci_passthrough_properties[] = {
+    DEFINE_PROP_PCI_HOST_DEVADDR("hostaddr", XenPCIPassthroughState, hostaddr),
+    DEFINE_PROP_BOOL("permissive", XenPCIPassthroughState, permissive, false),
+    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;
+    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+    dc->desc = "Assign an host PCI device with Xen";
+    dc->props = xen_pci_passthrough_properties;
+};
+
+static const TypeInfo xen_pci_passthrough_info = {
+    .name = TYPE_XEN_PT_DEVICE,
+    .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)
diff --git a/qemu/hw/xen/xen_pt.h b/qemu/hw/xen/xen_pt.h
new file mode 100644
index 000000000..393f36ccb
--- /dev/null
+++ b/qemu/hw/xen/xen_pt.h
@@ -0,0 +1,309 @@
+#ifndef XEN_PT_H
+#define XEN_PT_H
+
+#include "qemu-common.h"
+#include "hw/xen/xen_common.h"
+#include "hw/pci/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 const struct XenPTRegInfo XenPTRegInfo;
+typedef struct XenPTReg XenPTReg;
+
+typedef struct XenPCIPassthroughState XenPCIPassthroughState;
+
+#define TYPE_XEN_PT_DEVICE "xen-pci-passthrough"
+#define XEN_PT_DEVICE(obj) \
+    OBJECT_CHECK(XenPCIPassthroughState, (obj), TYPE_XEN_PT_DEVICE)
+
+/* 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 information */
+struct XenPTRegInfo {
+    uint32_t offset;
+    uint32_t size;
+    uint32_t init_val;
+    /* reg reserved field mask (ON:reserved, OFF:defined) */
+    uint32_t res_mask;
+    /* 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;
+    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 const struct XenPTRegGroupInfo XenPTRegGroupInfo;
+
+/* emul reg group size initialize method */
+typedef int (*xen_pt_reg_size_init_fn)
+    (XenPCIPassthroughState *, XenPTRegGroupInfo *,
+     uint32_t base_offset, uint8_t *size);
+
+/* emulated register group information */
+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;
+    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 */
+    bool warned;  /* avoid issuing (bogus) warning more than once */
+} 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;
+    bool permissive;
+    bool permissive_warned;
+    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;
+    MemoryListener io_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 */
diff --git a/qemu/hw/xen/xen_pt_config_init.c b/qemu/hw/xen/xen_pt_config_init.c
new file mode 100644
index 000000000..dd37be38a
--- /dev/null
+++ b/qemu/hw/xen/xen_pt_config_init.c
@@ -0,0 +1,1936 @@
+/*
+ * 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 "hw/xen/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;
+}
+
+static uint32_t get_throughable_mask(const XenPCIPassthroughState *s,
+                                     XenPTRegInfo *reg, uint32_t valid_mask)
+{
+    uint32_t throughable_mask = ~(reg->emu_mask | reg->ro_mask);
+
+    if (!s->permissive) {
+        throughable_mask &= ~reg->res_mask;
+    }
+
+    return throughable_mask & valid_mask;
+}
+
+/****************
+ * 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 = get_throughable_mask(s, reg, valid_mask);
+
+    /* 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 */
+    *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 = get_throughable_mask(s, reg, valid_mask);
+
+    /* 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 */
+    *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 = get_throughable_mask(s, reg, valid_mask);
+
+    /* 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 */
+    *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_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 = get_throughable_mask(s, reg, valid_mask);
+
+    /* 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 */
+    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 bool is_64bit_bar(PCIIORegion *r)
+{
+    return !!(r->type & PCI_BASE_ADDRESS_MEM_TYPE_64);
+}
+
+static uint64_t xen_pt_get_bar_size(PCIIORegion *r)
+{
+    if (is_64bit_bar(r)) {
+        uint64_t size64;
+        size64 = (r + 1)->size;
+        size64 <<= 32;
+        size64 += r->size;
+        return size64;
+    }
+    return r->size;
+}
+
+static XenPTBarFlag xen_pt_bar_reg_parse(XenPCIPassthroughState *s,
+                                         int index)
+{
+    PCIDevice *d = &s->dev;
+    XenPTRegion *region = NULL;
+    PCIIORegion *r;
+
+    /* check 64bit BAR */
+    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 (!xen_pt_get_bar_size(r)) {
+        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, index);
+    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 - 1) {
+        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 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;
+        if (!r_size) {
+            /* low 32 bits mask for 64 bit bars */
+            bar_ro_mask = XEN_PT_BAR_ALLF;
+        } else {
+            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 = r_size ? r_size - 1 : 0;
+        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_UPPER:
+    case XEN_PT_BAR_FLAG_MEM:
+        /* nothing to do */
+        break;
+    case XEN_PT_BAR_FLAG_IO:
+        /* nothing to do */
+        break;
+    default:
+        break;
+    }
+
+    /* create value for writing to I/O device register */
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, 0);
+
+    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 = get_throughable_mask(s, reg, valid_mask);
+    pcibus_t r_size = 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_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 */
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    return 0;
+}
+
+/* Header Type0 reg static information 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,
+        .res_mask   = 0xF880,
+        .emu_mask   = 0x0743,
+        .init       = xen_pt_common_reg_init,
+        .u.w.read   = xen_pt_word_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,
+        .res_mask   = 0x0007,
+        .ro_mask    = 0x06F8,
+        .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    = ~PCI_ROM_ADDRESS_MASK & ~PCI_ROM_ADDRESS_ENABLE,
+        .emu_mask   = (uint32_t)PCI_ROM_ADDRESS_MASK,
+        .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 information 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,
+    },
+    {
+        .offset     = PCI_VPD_ADDR,
+        .size       = 2,
+        .ro_mask    = 0x0003,
+        .emu_mask   = 0x0003,
+        .init       = xen_pt_common_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_word_reg_write,
+    },
+    {
+        .size = 0,
+    },
+};
+
+
+/**************************************
+ * Vendor Specific Capability
+ */
+
+/* Vendor Specific Capability Structure reg static information 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 information 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    = 0xFFFFFFFF,
+        .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,
+    },
+    /* Device Status reg */
+    {
+        .offset     = PCI_EXP_DEVSTA,
+        .size       = 2,
+        .res_mask   = 0xFFC0,
+        .ro_mask    = 0x0030,
+        .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,
+    },
+    /* Link Status reg */
+    {
+        .offset     = PCI_EXP_LNKSTA,
+        .size       = 2,
+        .ro_mask    = 0x3FFF,
+        .init       = xen_pt_common_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
+ */
+
+/* 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 writable_mask = 0;
+    uint16_t throughable_mask = get_throughable_mask(s, reg, valid_mask);
+
+    /* 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 */
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value & ~PCI_PM_CTRL_PME_STATUS,
+                              throughable_mask);
+
+    return 0;
+}
+
+/* Power Management Capability reg static information 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,
+        .res_mask   = 0x00F0,
+        .ro_mask    = 0xE10C,
+        .emu_mask   = 0x810B,
+        .init       = xen_pt_common_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_pmcsr_reg_write,
+    },
+    {
+        .size = 0,
+    },
+};
+
+
+/********************************
+ * MSI Capability
+ */
+
+/* Helper */
+#define xen_pt_msi_check_type(offset, flags, what) \
+        ((offset) == ((flags) & PCI_MSI_FLAGS_64BIT ? \
+                      PCI_MSI_##what##_64 : PCI_MSI_##what##_32))
+
+/* 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 = get_throughable_mask(s, reg, valid_mask);
+
+    /* 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 */
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, throughable_mask);
+
+    /* update MSI */
+    if (*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 if (msi->mapped) {
+        xen_pt_msi_disable(s);
+    }
+
+    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_msi_check_type(offset, flags, DATA)) {
+        *data = reg->init_val;
+    } else {
+        *data = XEN_PT_INVALID_REG;
+    }
+    return 0;
+}
+
+/* this function will be called twice (for 32 bit and 64 bit type) */
+/* initialize Mask register */
+static int xen_pt_mask_reg_init(XenPCIPassthroughState *s,
+                                XenPTRegInfo *reg, uint32_t real_offset,
+                                uint32_t *data)
+{
+    uint32_t flags = s->msi->flags;
+
+    /* check the offset whether matches the type or not */
+    if (!(flags & PCI_MSI_FLAGS_MASKBIT)) {
+        *data = XEN_PT_INVALID_REG;
+    } else if (xen_pt_msi_check_type(reg->offset, flags, MASK)) {
+        *data = reg->init_val;
+    } else {
+        *data = XEN_PT_INVALID_REG;
+    }
+    return 0;
+}
+
+/* this function will be called twice (for 32 bit and 64 bit type) */
+/* initialize Pending register */
+static int xen_pt_pending_reg_init(XenPCIPassthroughState *s,
+                                   XenPTRegInfo *reg, uint32_t real_offset,
+                                   uint32_t *data)
+{
+    uint32_t flags = s->msi->flags;
+
+    /* check the offset whether matches the type or not */
+    if (!(flags & PCI_MSI_FLAGS_MASKBIT)) {
+        *data = XEN_PT_INVALID_REG;
+    } else if (xen_pt_msi_check_type(reg->offset, flags, PENDING)) {
+        *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 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 */
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, 0);
+
+    /* 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 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 */
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, 0);
+
+    /* 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 old_data = cfg_entry->data;
+    uint32_t offset = reg->offset;
+
+    /* check the offset whether matches the type or not */
+    if (!xen_pt_msi_check_type(offset, msi->flags, DATA)) {
+        /* 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 */
+    *val = XEN_PT_MERGE_VALUE(*val, dev_value, 0);
+
+    /* update MSI */
+    if (cfg_entry->data != old_data) {
+        if (msi->mapped) {
+            xen_pt_msi_update(s);
+        }
+    }
+
+    return 0;
+}
+
+/* MSI Capability Structure reg static information 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,
+        .res_mask   = 0xFE00,
+        .ro_mask    = 0x018E,
+        .emu_mask   = 0x017E,
+        .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,
+        .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,
+        .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,
+        .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,
+        .init       = xen_pt_msgdata_reg_init,
+        .u.w.read   = xen_pt_word_reg_read,
+        .u.w.write  = xen_pt_msgdata_reg_write,
+    },
+    /* Mask reg (if PCI_MSI_FLAGS_MASKBIT set, for 32-bit devices) */
+    {
+        .offset     = PCI_MSI_MASK_32,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .ro_mask    = 0xFFFFFFFF,
+        .emu_mask   = 0xFFFFFFFF,
+        .init       = xen_pt_mask_reg_init,
+        .u.dw.read  = xen_pt_long_reg_read,
+        .u.dw.write = xen_pt_long_reg_write,
+    },
+    /* Mask reg (if PCI_MSI_FLAGS_MASKBIT set, for 64-bit devices) */
+    {
+        .offset     = PCI_MSI_MASK_64,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .ro_mask    = 0xFFFFFFFF,
+        .emu_mask   = 0xFFFFFFFF,
+        .init       = xen_pt_mask_reg_init,
+        .u.dw.read  = xen_pt_long_reg_read,
+        .u.dw.write = xen_pt_long_reg_write,
+    },
+    /* Pending reg (if PCI_MSI_FLAGS_MASKBIT set, for 32-bit devices) */
+    {
+        .offset     = PCI_MSI_MASK_32 + 4,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .ro_mask    = 0xFFFFFFFF,
+        .emu_mask   = 0x00000000,
+        .init       = xen_pt_pending_reg_init,
+        .u.dw.read  = xen_pt_long_reg_read,
+        .u.dw.write = xen_pt_long_reg_write,
+    },
+    /* Pending reg (if PCI_MSI_FLAGS_MASKBIT set, for 64-bit devices) */
+    {
+        .offset     = PCI_MSI_MASK_64 + 4,
+        .size       = 4,
+        .init_val   = 0x00000000,
+        .ro_mask    = 0xFFFFFFFF,
+        .emu_mask   = 0x00000000,
+        .init       = xen_pt_pending_reg_init,
+        .u.dw.read  = xen_pt_long_reg_read,
+        .u.dw.write = xen_pt_long_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 = get_throughable_mask(s, reg, valid_mask);
+    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 */
+    *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);
+    } else if (!(*val & PCI_MSIX_FLAGS_ENABLE) && s->msix->enabled) {
+        xen_pt_msix_disable(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 information 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,
+        .res_mask   = 0x3800,
+        .ro_mask    = 0x07FF,
+        .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) {
+            g_free(reg_entry);
+            return rc;
+        }
+        if (data == XEN_PT_INVALID_REG) {
+            /* free unused BAR register entry */
+            g_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);
+    }
+}
diff --git a/qemu/hw/xen/xen_pt_msi.c b/qemu/hw/xen/xen_pt_msi.c
new file mode 100644
index 000000000..263e0514a
--- /dev/null
+++ b/qemu/hw/xen/xen_pt_msi.c
@@ -0,0 +1,623 @@
+/*
+ * 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 "hw/xen/xen_backend.h"
+#include "xen_pt.h"
+#include "hw/i386/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 (err: %i, vec: %#x, entry %#x)\n",
+                       is_msix ? "-X" : "", errno, 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. (err: %d)\n",
+                   is_msix ? "-X" : "", errno);
+
+        if (xc_physdev_unmap_pirq(xen_xc, xen_domid, *old_pirq)) {
+            XEN_PT_ERR(d, "Unmapping of MSI%s pirq %d failed. (err: %d)\n",
+                       is_msix ? "-X" : "", *old_pirq, errno);
+        }
+        *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. (err: %d, pirq: %d, gvec: %#x)\n",
+                       is_msix ? "-X" : "", errno, 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. (err: %i)\n",
+                   is_msix ? "-X" : "", pirq, errno);
+        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 &= ~PCI_MSI_FLAGS_ENABLE;
+    msi->initialized = false;
+    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->addr, 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 (err: %d)\n",
+                           entry->pirq, errno);
+            }
+            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, hwaddr addr,
+                           uint64_t val, unsigned size)
+{
+    XenPCIPassthroughState *s = opaque;
+    XenPTMSIX *msix = s->msix;
+    XenPTMSIXEntry *entry;
+    unsigned int entry_nr, offset;
+
+    entry_nr = addr / PCI_MSIX_ENTRY_SIZE;
+    if (entry_nr >= msix->total_entries) {
+        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
+            && entry->pirq != XEN_PT_UNASSIGNED_PIRQ) {
+            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)) {
+            if (!entry->warned) {
+                entry->warned = true;
+                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, hwaddr 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, OBJECT(s), &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:
+    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);
+
+    g_free(s->msix);
+    s->msix = NULL;
+}