Introduce Xen PCI Passthrough, qdevice

A more complete history can be found here:
git://xenbits.xensource.com/qemu-xen-unstable.git

Signed-off-by: Allen Kay <allen.m.kay@intel.com>
Signed-off-by: Guy Zana <guy@neocleus.com>
Signed-off-by: Anthony PERARD <anthony.perard@citrix.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>

hw/i386/Makefile.objs

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

hw/xen_common.h

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

hw/xen_pt.c

@@ -0,0 +1,812 @@
+/*
+ * 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'.
+ */
+
+#include <sys/ioctl.h>
+
+#include "pci.h"
+#include "xen.h"
+#include "xen_backend.h"
+#include "xen_pt.h"
+#include "range.h"
+
+#define XEN_PT_NR_IRQS (256)
+static uint8_t xen_pt_mapped_machine_irq[XEN_PT_NR_IRQS] = {0};
+
+void xen_pt_log(const PCIDevice *d, const char *f, ...)
+{
+    va_list ap;
+
+    va_start(ap, f);
+    if (d) {
+        fprintf(stderr, "[%02x:%02x.%d] ", pci_bus_num(d->bus),
+                PCI_SLOT(d->devfn), PCI_FUNC(d->devfn));
+    }
+    vfprintf(stderr, f, ap);
+    va_end(ap);
+}
+
+/* Config Space */
+
+static int xen_pt_pci_config_access_check(PCIDevice *d, uint32_t addr, int len)
+{
+    /* check offset range */
+    if (addr >= 0xFF) {
+        XEN_PT_ERR(d, "Failed to access register with offset exceeding 0xFF. "
+                   "(addr: 0x%02x, len: %d)\n", addr, len);
+        return -1;
+    }
+
+    /* check read size */
+    if ((len != 1) && (len != 2) && (len != 4)) {
+        XEN_PT_ERR(d, "Failed to access register with invalid access length. "
+                   "(addr: 0x%02x, len: %d)\n", addr, len);
+        return -1;
+    }
+
+    /* check offset alignment */
+    if (addr & (len - 1)) {
+        XEN_PT_ERR(d, "Failed to access register with invalid access size "
+                   "alignment. (addr: 0x%02x, len: %d)\n", addr, len);
+        return -1;
+    }
+
+    return 0;
+}
+
+int xen_pt_bar_offset_to_index(uint32_t offset)
+{
+    int index = 0;
+
+    /* check Exp ROM BAR */
+    if (offset == PCI_ROM_ADDRESS) {
+        return PCI_ROM_SLOT;
+    }
+
+    /* calculate BAR index */
+    index = (offset - PCI_BASE_ADDRESS_0) >> 2;
+    if (index >= PCI_NUM_REGIONS) {
+        return -1;
+    }
+
+    return index;
+}
+
+static uint32_t xen_pt_pci_read_config(PCIDevice *d, uint32_t addr, int len)
+{
+    XenPCIPassthroughState *s = DO_UPCAST(XenPCIPassthroughState, dev, d);
+    uint32_t val = 0;
+    XenPTRegGroup *reg_grp_entry = NULL;
+    XenPTReg *reg_entry = NULL;
+    int rc = 0;
+    int emul_len = 0;
+    uint32_t find_addr = addr;
+
+    if (xen_pt_pci_config_access_check(d, addr, len)) {
+        goto exit;
+    }
+
+    /* find register group entry */
+    reg_grp_entry = xen_pt_find_reg_grp(s, addr);
+    if (reg_grp_entry) {
+        /* check 0-Hardwired register group */
+        if (reg_grp_entry->reg_grp->grp_type == XEN_PT_GRP_TYPE_HARDWIRED) {
+            /* no need to emulate, just return 0 */
+            val = 0;
+            goto exit;
+        }
+    }
+
+    /* read I/O device register value */
+    rc = xen_host_pci_get_block(&s->real_device, addr, (uint8_t *)&val, len);
+    if (rc < 0) {
+        XEN_PT_ERR(d, "pci_read_block failed. return value: %d.\n", rc);
+        memset(&val, 0xff, len);
+    }
+
+    /* just return the I/O device register value for
+     * passthrough type register group */
+    if (reg_grp_entry == NULL) {
+        goto exit;
+    }
+
+    /* adjust the read value to appropriate CFC-CFF window */
+    val <<= (addr & 3) << 3;
+    emul_len = len;
+
+    /* loop around the guest requested size */
+    while (emul_len > 0) {
+        /* find register entry to be emulated */
+        reg_entry = xen_pt_find_reg(reg_grp_entry, find_addr);
+        if (reg_entry) {
+            XenPTRegInfo *reg = reg_entry->reg;
+            uint32_t real_offset = reg_grp_entry->base_offset + reg->offset;
+            uint32_t valid_mask = 0xFFFFFFFF >> ((4 - emul_len) << 3);
+            uint8_t *ptr_val = NULL;
+
+            valid_mask <<= (find_addr - real_offset) << 3;
+            ptr_val = (uint8_t *)&val + (real_offset & 3);
+
+            /* do emulation based on register size */
+            switch (reg->size) {
+            case 1:
+                if (reg->u.b.read) {
+                    rc = reg->u.b.read(s, reg_entry, ptr_val, valid_mask);
+                }
+                break;
+            case 2:
+                if (reg->u.w.read) {
+                    rc = reg->u.w.read(s, reg_entry,
+                                       (uint16_t *)ptr_val, valid_mask);
+                }
+                break;
+            case 4:
+                if (reg->u.dw.read) {
+                    rc = reg->u.dw.read(s, reg_entry,
+                                        (uint32_t *)ptr_val, valid_mask);
+                }
+                break;
+            }
+
+            if (rc < 0) {
+                xen_shutdown_fatal_error("Internal error: Invalid read "
+                                         "emulation. (%s, rc: %d)\n",
+                                         __func__, rc);
+                return 0;
+            }
+
+            /* calculate next address to find */
+            emul_len -= reg->size;
+            if (emul_len > 0) {
+                find_addr = real_offset + reg->size;
+            }
+        } else {
+            /* nothing to do with passthrough type register,
+             * continue to find next byte */
+            emul_len--;
+            find_addr++;
+        }
+    }
+
+    /* need to shift back before returning them to pci bus emulator */
+    val >>= ((addr & 3) << 3);
+
+exit:
+    XEN_PT_LOG_CONFIG(d, addr, val, len);
+    return val;
+}
+
+static void xen_pt_pci_write_config(PCIDevice *d, uint32_t addr,
+                                    uint32_t val, int len)
+{
+    XenPCIPassthroughState *s = DO_UPCAST(XenPCIPassthroughState, dev, d);
+    int index = 0;
+    XenPTRegGroup *reg_grp_entry = NULL;
+    int rc = 0;
+    uint32_t read_val = 0;
+    int emul_len = 0;
+    XenPTReg *reg_entry = NULL;
+    uint32_t find_addr = addr;
+    XenPTRegInfo *reg = NULL;
+
+    if (xen_pt_pci_config_access_check(d, addr, len)) {
+        return;
+    }
+
+    XEN_PT_LOG_CONFIG(d, addr, val, len);
+
+    /* check unused BAR register */
+    index = xen_pt_bar_offset_to_index(addr);
+    if ((index >= 0) && (val > 0 && val < XEN_PT_BAR_ALLF) &&
+        (s->bases[index].bar_flag == XEN_PT_BAR_FLAG_UNUSED)) {
+        XEN_PT_WARN(d, "Guest attempt to set address to unused Base Address "
+                    "Register. (addr: 0x%02x, len: %d)\n", addr, len);
+    }
+
+    /* find register group entry */
+    reg_grp_entry = xen_pt_find_reg_grp(s, addr);
+    if (reg_grp_entry) {
+        /* check 0-Hardwired register group */
+        if (reg_grp_entry->reg_grp->grp_type == XEN_PT_GRP_TYPE_HARDWIRED) {
+            /* ignore silently */
+            XEN_PT_WARN(d, "Access to 0-Hardwired register. "
+                        "(addr: 0x%02x, len: %d)\n", addr, len);
+            return;
+        }
+    }
+
+    rc = xen_host_pci_get_block(&s->real_device, addr,
+                                (uint8_t *)&read_val, len);
+    if (rc < 0) {
+        XEN_PT_ERR(d, "pci_read_block failed. return value: %d.\n", rc);
+        memset(&read_val, 0xff, len);
+    }
+
+    /* pass directly to the real device for passthrough type register group */
+    if (reg_grp_entry == NULL) {
+        goto out;
+    }
+
+    memory_region_transaction_begin();
+    pci_default_write_config(d, addr, val, len);
+
+    /* adjust the read and write value to appropriate CFC-CFF window */
+    read_val <<= (addr & 3) << 3;
+    val <<= (addr & 3) << 3;
+    emul_len = len;
+
+    /* loop around the guest requested size */
+    while (emul_len > 0) {
+        /* find register entry to be emulated */
+        reg_entry = xen_pt_find_reg(reg_grp_entry, find_addr);
+        if (reg_entry) {
+            reg = reg_entry->reg;
+            uint32_t real_offset = reg_grp_entry->base_offset + reg->offset;
+            uint32_t valid_mask = 0xFFFFFFFF >> ((4 - emul_len) << 3);
+            uint8_t *ptr_val = NULL;
+
+            valid_mask <<= (find_addr - real_offset) << 3;
+            ptr_val = (uint8_t *)&val + (real_offset & 3);
+
+            /* do emulation based on register size */
+            switch (reg->size) {
+            case 1:
+                if (reg->u.b.write) {
+                    rc = reg->u.b.write(s, reg_entry, ptr_val,
+                                        read_val >> ((real_offset & 3) << 3),
+                                        valid_mask);
+                }
+                break;
+            case 2:
+                if (reg->u.w.write) {
+                    rc = reg->u.w.write(s, reg_entry, (uint16_t *)ptr_val,
+                                        (read_val >> ((real_offset & 3) << 3)),
+                                        valid_mask);
+                }
+                break;
+            case 4:
+                if (reg->u.dw.write) {
+                    rc = reg->u.dw.write(s, reg_entry, (uint32_t *)ptr_val,
+                                         (read_val >> ((real_offset & 3) << 3)),
+                                         valid_mask);
+                }
+                break;
+            }
+
+            if (rc < 0) {
+                xen_shutdown_fatal_error("Internal error: Invalid write"
+                                         " emulation. (%s, rc: %d)\n",
+                                         __func__, rc);
+                return;
+            }
+
+            /* calculate next address to find */
+            emul_len -= reg->size;
+            if (emul_len > 0) {
+                find_addr = real_offset + reg->size;
+            }
+        } else {
+            /* nothing to do with passthrough type register,
+             * continue to find next byte */
+            emul_len--;
+            find_addr++;
+        }
+    }
+
+    /* need to shift back before passing them to xen_host_pci_device */
+    val >>= (addr & 3) << 3;
+
+    memory_region_transaction_commit();
+
+out:
+    if (!(reg && reg->no_wb)) {
+        /* unknown regs are passed through */
+        rc = xen_host_pci_set_block(&s->real_device, addr,
+                                    (uint8_t *)&val, len);
+
+        if (rc < 0) {
+            XEN_PT_ERR(d, "pci_write_block failed. return value: %d.\n", rc);
+        }
+    }
+}
+
+/* register regions */
+
+static uint64_t xen_pt_bar_read(void *o, target_phys_addr_t addr,
+                                unsigned size)
+{
+    PCIDevice *d = o;
+    /* if this function is called, that probably means that there is a
+     * misconfiguration of the IOMMU. */
+    XEN_PT_ERR(d, "Should not read BAR through QEMU. @0x"TARGET_FMT_plx"\n",
+               addr);
+    return 0;
+}
+static void xen_pt_bar_write(void *o, target_phys_addr_t addr, uint64_t val,
+                             unsigned size)
+{
+    PCIDevice *d = o;
+    /* Same comment as xen_pt_bar_read function */
+    XEN_PT_ERR(d, "Should not write BAR through QEMU. @0x"TARGET_FMT_plx"\n",
+               addr);
+}
+
+static const MemoryRegionOps ops = {
+    .endianness = DEVICE_NATIVE_ENDIAN,
+    .read = xen_pt_bar_read,
+    .write = xen_pt_bar_write,
+};
+
+static int xen_pt_register_regions(XenPCIPassthroughState *s)
+{
+    int i = 0;
+    XenHostPCIDevice *d = &s->real_device;
+
+    /* Register PIO/MMIO BARs */
+    for (i = 0; i < PCI_ROM_SLOT; i++) {
+        XenHostPCIIORegion *r = &d->io_regions[i];
+        uint8_t type;
+
+        if (r->base_addr == 0 || r->size == 0) {
+            continue;
+        }
+
+        s->bases[i].access.u = r->base_addr;
+
+        if (r->type & XEN_HOST_PCI_REGION_TYPE_IO) {
+            type = PCI_BASE_ADDRESS_SPACE_IO;
+        } else {
+            type = PCI_BASE_ADDRESS_SPACE_MEMORY;
+            if (r->type & XEN_HOST_PCI_REGION_TYPE_PREFETCH) {
+                type |= PCI_BASE_ADDRESS_MEM_PREFETCH;
+            }
+        }
+
+        memory_region_init_io(&s->bar[i], &ops, &s->dev,
+                              "xen-pci-pt-bar", r->size);
+        pci_register_bar(&s->dev, i, type, &s->bar[i]);
+
+        XEN_PT_LOG(&s->dev, "IO region %i registered (size=0x%08"PRIx64
+                   " base_addr=0x%08"PRIx64" type: %#x)\n",
+                   i, r->size, r->base_addr, type);
+    }
+
+    /* Register expansion ROM address */
+    if (d->rom.base_addr && d->rom.size) {
+        uint32_t bar_data = 0;
+
+        /* Re-set BAR reported by OS, otherwise ROM can't be read. */
+        if (xen_host_pci_get_long(d, PCI_ROM_ADDRESS, &bar_data)) {
+            return 0;
+        }
+        if ((bar_data & PCI_ROM_ADDRESS_MASK) == 0) {
+            bar_data |= d->rom.base_addr & PCI_ROM_ADDRESS_MASK;
+            xen_host_pci_set_long(d, PCI_ROM_ADDRESS, bar_data);
+        }
+
+        s->bases[PCI_ROM_SLOT].access.maddr = d->rom.base_addr;
+
+        memory_region_init_rom_device(&s->rom, NULL, NULL,
+                                      "xen-pci-pt-rom", d->rom.size);
+        pci_register_bar(&s->dev, PCI_ROM_SLOT, PCI_BASE_ADDRESS_MEM_PREFETCH,
+                         &s->rom);
+
+        XEN_PT_LOG(&s->dev, "Expansion ROM registered (size=0x%08"PRIx64
+                   " base_addr=0x%08"PRIx64")\n",
+                   d->rom.size, d->rom.base_addr);
+    }
+
+    return 0;
+}
+
+static void xen_pt_unregister_regions(XenPCIPassthroughState *s)
+{
+    XenHostPCIDevice *d = &s->real_device;
+    int i;
+
+    for (i = 0; i < PCI_NUM_REGIONS - 1; i++) {
+        XenHostPCIIORegion *r = &d->io_regions[i];
+
+        if (r->base_addr == 0 || r->size == 0) {
+            continue;
+        }
+
+        memory_region_destroy(&s->bar[i]);
+    }
+    if (d->rom.base_addr && d->rom.size) {
+        memory_region_destroy(&s->rom);
+    }
+}
+
+/* region mapping */
+
+static int xen_pt_bar_from_region(XenPCIPassthroughState *s, MemoryRegion *mr)
+{
+    int i = 0;
+
+    for (i = 0; i < PCI_NUM_REGIONS - 1; i++) {
+        if (mr == &s->bar[i]) {
+            return i;
+        }
+    }
+    if (mr == &s->rom) {
+        return PCI_ROM_SLOT;
+    }
+    return -1;
+}
+
+/*
+ * This function checks if an io_region overlaps an io_region from another
+ * device.  The io_region to check is provided with (addr, size and type)
+ * A callback can be provided and will be called for every region that is
+ * overlapped.
+ * The return value indicates if the region is overlappsed */
+struct CheckBarArgs {
+    XenPCIPassthroughState *s;
+    pcibus_t addr;
+    pcibus_t size;
+    uint8_t type;
+    bool rc;
+};
+static void xen_pt_check_bar_overlap(PCIBus *bus, PCIDevice *d, void *opaque)
+{
+    struct CheckBarArgs *arg = opaque;
+    XenPCIPassthroughState *s = arg->s;
+    uint8_t type = arg->type;
+    int i;
+
+    if (d->devfn == s->dev.devfn) {
+        return;
+    }
+
+    /* xxx: This ignores bridges. */
+    for (i = 0; i < PCI_NUM_REGIONS; i++) {
+        const PCIIORegion *r = &d->io_regions[i];
+
+        if (!r->size) {
+            continue;
+        }
+        if ((type & PCI_BASE_ADDRESS_SPACE_IO)
+            != (r->type & PCI_BASE_ADDRESS_SPACE_IO)) {
+            continue;
+        }
+
+        if (ranges_overlap(arg->addr, arg->size, r->addr, r->size)) {
+            XEN_PT_WARN(&s->dev,
+                        "Overlapped to device [%02x:%02x.%d] Region: %i"
+                        " (addr: %#"FMT_PCIBUS", len: %#"FMT_PCIBUS")\n",
+                        pci_bus_num(bus), PCI_SLOT(d->devfn),
+                        PCI_FUNC(d->devfn), i, r->addr, r->size);
+            arg->rc = true;
+        }
+    }
+}
+
+static void xen_pt_region_update(XenPCIPassthroughState *s,
+                                 MemoryRegionSection *sec, bool adding)
+{
+    PCIDevice *d = &s->dev;
+    MemoryRegion *mr = sec->mr;
+    int bar = -1;
+    int rc;
+    int op = adding ? DPCI_ADD_MAPPING : DPCI_REMOVE_MAPPING;
+    struct CheckBarArgs args = {
+        .s = s,
+        .addr = sec->offset_within_address_space,
+        .size = sec->size,
+        .rc = false,
+    };
+
+    bar = xen_pt_bar_from_region(s, mr);
+    if (bar == -1) {
+        return;
+    }
+
+    args.type = d->io_regions[bar].type;
+    pci_for_each_device(d->bus, pci_bus_num(d->bus),
+                        xen_pt_check_bar_overlap, &args);
+    if (args.rc) {
+        XEN_PT_WARN(d, "Region: %d (addr: %#"FMT_PCIBUS
+                    ", len: %#"FMT_PCIBUS") is overlapped.\n",
+                    bar, sec->offset_within_address_space, sec->size);
+    }
+
+    if (d->io_regions[bar].type & PCI_BASE_ADDRESS_SPACE_IO) {
+        uint32_t guest_port = sec->offset_within_address_space;
+        uint32_t machine_port = s->bases[bar].access.pio_base;
+        uint32_t size = sec->size;
+        rc = xc_domain_ioport_mapping(xen_xc, xen_domid,
+                                      guest_port, machine_port, size,
+                                      op);
+        if (rc) {
+            XEN_PT_ERR(d, "%s ioport mapping failed! (rc: %i)\n",
+                       adding ? "create new" : "remove old", rc);
+        }
+    } else {
+        pcibus_t guest_addr = sec->offset_within_address_space;
+        pcibus_t machine_addr = s->bases[bar].access.maddr
+            + sec->offset_within_region;
+        pcibus_t size = sec->size;
+        rc = xc_domain_memory_mapping(xen_xc, xen_domid,
+                                      XEN_PFN(guest_addr + XC_PAGE_SIZE - 1),
+                                      XEN_PFN(machine_addr + XC_PAGE_SIZE - 1),
+                                      XEN_PFN(size + XC_PAGE_SIZE - 1),
+                                      op);
+        if (rc) {
+            XEN_PT_ERR(d, "%s mem mapping failed! (rc: %i)\n",
+                       adding ? "create new" : "remove old", rc);
+        }
+    }
+}
+
+static void xen_pt_begin(MemoryListener *l)
+{
+}
+
+static void xen_pt_commit(MemoryListener *l)
+{
+}
+
+static void xen_pt_region_add(MemoryListener *l, MemoryRegionSection *sec)
+{
+    XenPCIPassthroughState *s = container_of(l, XenPCIPassthroughState,
+                                             memory_listener);
+
+    xen_pt_region_update(s, sec, true);
+}
+
+static void xen_pt_region_del(MemoryListener *l, MemoryRegionSection *sec)
+{
+    XenPCIPassthroughState *s = container_of(l, XenPCIPassthroughState,
+                                             memory_listener);
+
+    xen_pt_region_update(s, sec, false);
+}
+
+static void xen_pt_region_nop(MemoryListener *l, MemoryRegionSection *s)
+{
+}
+
+static void xen_pt_log_fns(MemoryListener *l, MemoryRegionSection *s)
+{
+}
+
+static void xen_pt_log_global_fns(MemoryListener *l)
+{
+}
+
+static void xen_pt_eventfd_fns(MemoryListener *l, MemoryRegionSection *s,
+                               bool match_data, uint64_t data, int fd)
+{
+}
+
+static const MemoryListener xen_pt_memory_listener = {
+    .begin = xen_pt_begin,
+    .commit = xen_pt_commit,
+    .region_add = xen_pt_region_add,
+    .region_nop = xen_pt_region_nop,
+    .region_del = xen_pt_region_del,
+    .log_start = xen_pt_log_fns,
+    .log_stop = xen_pt_log_fns,
+    .log_sync = xen_pt_log_fns,
+    .log_global_start = xen_pt_log_global_fns,
+    .log_global_stop = xen_pt_log_global_fns,
+    .eventfd_add = xen_pt_eventfd_fns,
+    .eventfd_del = xen_pt_eventfd_fns,
+    .priority = 10,
+};
+
+/* init */
+
+static int xen_pt_initfn(PCIDevice *d)
+{
+    XenPCIPassthroughState *s = DO_UPCAST(XenPCIPassthroughState, dev, d);
+    int rc = 0;
+    uint8_t machine_irq = 0;
+    int pirq = XEN_PT_UNASSIGNED_PIRQ;
+
+    /* register real device */
+    XEN_PT_LOG(d, "Assigning real physical device %02x:%02x.%d"
+               " to devfn %#x\n",
+               s->hostaddr.bus, s->hostaddr.slot, s->hostaddr.function,
+               s->dev.devfn);
+
+    rc = xen_host_pci_device_get(&s->real_device,
+                                 s->hostaddr.domain, s->hostaddr.bus,
+                                 s->hostaddr.slot, s->hostaddr.function);
+    if (rc) {
+        XEN_PT_ERR(d, "Failed to \"open\" the real pci device. rc: %i\n", rc);
+        return -1;
+    }
+
+    s->is_virtfn = s->real_device.is_virtfn;
+    if (s->is_virtfn) {
+        XEN_PT_LOG(d, "%04x:%02x:%02x.%d is a SR-IOV Virtual Function\n",
+                   s->real_device.domain, bus, slot, func);
+    }
+
+    /* Initialize virtualized PCI configuration (Extended 256 Bytes) */
+    if (xen_host_pci_get_block(&s->real_device, 0, d->config,
+                               PCI_CONFIG_SPACE_SIZE) == -1) {
+        xen_host_pci_device_put(&s->real_device);
+        return -1;
+    }
+
+    s->memory_listener = xen_pt_memory_listener;
+
+    /* Handle real device's MMIO/PIO BARs */
+    xen_pt_register_regions(s);
+
+    /* Bind interrupt */
+    if (!s->dev.config[PCI_INTERRUPT_PIN]) {
+        XEN_PT_LOG(d, "no pin interrupt\n");
+        goto out;
+    }
+
+    machine_irq = s->real_device.irq;
+    rc = xc_physdev_map_pirq(xen_xc, xen_domid, machine_irq, &pirq);
+
+    if (rc < 0) {
+        XEN_PT_ERR(d, "Mapping machine irq %u to pirq %i failed, (rc: %d)\n",
+                   machine_irq, pirq, rc);
+
+        /* Disable PCI intx assertion (turn on bit10 of devctl) */
+        xen_host_pci_set_word(&s->real_device,
+                              PCI_COMMAND,
+                              pci_get_word(s->dev.config + PCI_COMMAND)
+                              | PCI_COMMAND_INTX_DISABLE);
+        machine_irq = 0;
+        s->machine_irq = 0;
+    } else {
+        machine_irq = pirq;
+        s->machine_irq = pirq;
+        xen_pt_mapped_machine_irq[machine_irq]++;
+    }
+
+    /* bind machine_irq to device */
+    if (machine_irq != 0) {
+        uint8_t e_intx = xen_pt_pci_intx(s);
+
+        rc = xc_domain_bind_pt_pci_irq(xen_xc, xen_domid, machine_irq,
+                                       pci_bus_num(d->bus),
+                                       PCI_SLOT(d->devfn),
+                                       e_intx);
+        if (rc < 0) {
+            XEN_PT_ERR(d, "Binding of interrupt %i failed! (rc: %d)\n",
+                       e_intx, rc);
+
+            /* Disable PCI intx assertion (turn on bit10 of devctl) */
+            xen_host_pci_set_word(&s->real_device, PCI_COMMAND,
+                                  *(uint16_t *)(&s->dev.config[PCI_COMMAND])
+                                  | PCI_COMMAND_INTX_DISABLE);
+            xen_pt_mapped_machine_irq[machine_irq]--;
+
+            if (xen_pt_mapped_machine_irq[machine_irq] == 0) {
+                if (xc_physdev_unmap_pirq(xen_xc, xen_domid, machine_irq)) {
+                    XEN_PT_ERR(d, "Unmapping of machine interrupt %i failed!"
+                               " (rc: %d)\n", machine_irq, rc);
+                }
+            }
+            s->machine_irq = 0;
+        }
+    }
+
+out:
+    memory_listener_register(&s->memory_listener, NULL);
+    XEN_PT_LOG(d, "Real physical device %02x:%02x.%d registered successfuly!\n",
+               bus, slot, func);
+
+    return 0;
+}
+
+static int xen_pt_unregister_device(PCIDevice *d)
+{
+    XenPCIPassthroughState *s = DO_UPCAST(XenPCIPassthroughState, dev, d);
+    uint8_t machine_irq = s->machine_irq;
+    uint8_t intx = xen_pt_pci_intx(s);
+    int rc;
+
+    if (machine_irq) {
+        rc = xc_domain_unbind_pt_irq(xen_xc, xen_domid, machine_irq,
+                                     PT_IRQ_TYPE_PCI,
+                                     pci_bus_num(d->bus),
+                                     PCI_SLOT(s->dev.devfn),
+                                     intx,
+                                     0 /* isa_irq */);
+        if (rc < 0) {
+            XEN_PT_ERR(d, "unbinding of interrupt INT%c failed."
+                       " (machine irq: %i, rc: %d)"
+                       " But bravely continuing on..\n",
+                       'a' + intx, machine_irq, rc);
+        }
+    }
+
+    if (machine_irq) {
+        xen_pt_mapped_machine_irq[machine_irq]--;
+
+        if (xen_pt_mapped_machine_irq[machine_irq] == 0) {
+            rc = xc_physdev_unmap_pirq(xen_xc, xen_domid, machine_irq);
+
+            if (rc < 0) {
+                XEN_PT_ERR(d, "unmapping of interrupt %i failed. (rc: %d)"
+                           " But bravely continuing on..\n",
+                           machine_irq, rc);
+            }
+        }
+    }
+
+    xen_pt_unregister_regions(s);
+    memory_listener_unregister(&s->memory_listener);
+
+    xen_host_pci_device_put(&s->real_device);
+
+    return 0;
+}
+
+static Property xen_pci_passthrough_properties[] = {
+    DEFINE_PROP_PCI_HOST_DEVADDR("hostaddr", XenPCIPassthroughState, hostaddr),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void xen_pci_passthrough_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    PCIDeviceClass *k = PCI_DEVICE_CLASS(klass);
+
+    k->init = xen_pt_initfn;
+    k->exit = xen_pt_unregister_device;
+    k->config_read = xen_pt_pci_read_config;
+    k->config_write = xen_pt_pci_write_config;
+    dc->desc = "Assign an host PCI device with Xen";
+    dc->props = xen_pci_passthrough_properties;
+};
+
+static TypeInfo xen_pci_passthrough_info = {
+    .name = "xen-pci-passthrough",
+    .parent = TYPE_PCI_DEVICE,
+    .instance_size = sizeof(XenPCIPassthroughState),
+    .class_init = xen_pci_passthrough_class_init,
+};
+
+static void xen_pci_passthrough_register_types(void)
+{
+    type_register_static(&xen_pci_passthrough_info);
+}
+
+type_init(xen_pci_passthrough_register_types)

hw/xen_pt.h

@@ -0,0 +1,248 @@
+#ifndef XEN_PT_H
+#define XEN_PT_H
+
+#include "qemu-common.h"
+#include "xen_common.h"
+#include "pci.h"
+#include "xen-host-pci-device.h"
+
+void xen_pt_log(const PCIDevice *d, const char *f, ...) GCC_FMT_ATTR(2, 3);
+
+#define XEN_PT_ERR(d, _f, _a...) xen_pt_log(d, "%s: Error: "_f, __func__, ##_a)
+
+#ifdef XEN_PT_LOGGING_ENABLED
+#  define XEN_PT_LOG(d, _f, _a...)  xen_pt_log(d, "%s: " _f, __func__, ##_a)
+#  define XEN_PT_WARN(d, _f, _a...) \
+    xen_pt_log(d, "%s: Warning: "_f, __func__, ##_a)
+#else
+#  define XEN_PT_LOG(d, _f, _a...)
+#  define XEN_PT_WARN(d, _f, _a...)
+#endif
+
+#ifdef XEN_PT_DEBUG_PCI_CONFIG_ACCESS
+#  define XEN_PT_LOG_CONFIG(d, addr, val, len) \
+    xen_pt_log(d, "%s: address=0x%04x val=0x%08x len=%d\n", \
+               __func__, addr, val, len)
+#else
+#  define XEN_PT_LOG_CONFIG(d, addr, val, len)
+#endif
+
+
+/* Helper */
+#define XEN_PFN(x) ((x) >> XC_PAGE_SHIFT)
+
+typedef struct XenPTRegInfo XenPTRegInfo;
+typedef struct XenPTReg XenPTReg;
+
+typedef struct XenPCIPassthroughState XenPCIPassthroughState;
+
+/* function type for config reg */
+typedef int (*xen_pt_conf_reg_init)
+    (XenPCIPassthroughState *, XenPTRegInfo *, uint32_t real_offset,
+     uint32_t *data);
+typedef int (*xen_pt_conf_dword_write)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint32_t *val, uint32_t dev_value, uint32_t valid_mask);
+typedef int (*xen_pt_conf_word_write)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint16_t *val, uint16_t dev_value, uint16_t valid_mask);
+typedef int (*xen_pt_conf_byte_write)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint8_t *val, uint8_t dev_value, uint8_t valid_mask);
+typedef int (*xen_pt_conf_dword_read)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint32_t *val, uint32_t valid_mask);
+typedef int (*xen_pt_conf_word_read)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint16_t *val, uint16_t valid_mask);
+typedef int (*xen_pt_conf_byte_read)
+    (XenPCIPassthroughState *, XenPTReg *cfg_entry,
+     uint8_t *val, uint8_t valid_mask);
+
+#define XEN_PT_BAR_ALLF 0xFFFFFFFF
+#define XEN_PT_BAR_UNMAPPED (-1)
+
+
+typedef enum {
+    XEN_PT_GRP_TYPE_HARDWIRED = 0,  /* 0 Hardwired reg group */
+    XEN_PT_GRP_TYPE_EMU,            /* emul reg group */
+} XenPTRegisterGroupType;
+
+typedef enum {
+    XEN_PT_BAR_FLAG_MEM = 0,        /* Memory type BAR */
+    XEN_PT_BAR_FLAG_IO,             /* I/O type BAR */
+    XEN_PT_BAR_FLAG_UPPER,          /* upper 64bit BAR */
+    XEN_PT_BAR_FLAG_UNUSED,         /* unused BAR */
+} XenPTBarFlag;
+
+
+typedef struct XenPTRegion {
+    /* BAR flag */
+    XenPTBarFlag bar_flag;
+    /* Translation of the emulated address */
+    union {
+        uint64_t maddr;
+        uint64_t pio_base;
+        uint64_t u;
+    } access;
+} XenPTRegion;
+
+/* XenPTRegInfo declaration
+ * - only for emulated register (either a part or whole bit).
+ * - for passthrough register that need special behavior (like interacting with
+ *   other component), set emu_mask to all 0 and specify r/w func properly.
+ * - do NOT use ALL F for init_val, otherwise the tbl will not be registered.
+ */
+
+/* emulated register infomation */
+struct XenPTRegInfo {
+    uint32_t offset;
+    uint32_t size;
+    uint32_t init_val;
+    /* reg read only field mask (ON:RO/ROS, OFF:other) */
+    uint32_t ro_mask;
+    /* reg emulate field mask (ON:emu, OFF:passthrough) */
+    uint32_t emu_mask;
+    /* no write back allowed */
+    uint32_t no_wb;
+    xen_pt_conf_reg_init init;
+    /* read/write function pointer
+     * for double_word/word/byte size */
+    union {
+        struct {
+            xen_pt_conf_dword_write write;
+            xen_pt_conf_dword_read read;
+        } dw;
+        struct {
+            xen_pt_conf_word_write write;
+            xen_pt_conf_word_read read;
+        } w;
+        struct {
+            xen_pt_conf_byte_write write;
+            xen_pt_conf_byte_read read;
+        } b;
+    } u;
+};
+
+/* emulated register management */
+struct XenPTReg {
+    QLIST_ENTRY(XenPTReg) entries;
+    XenPTRegInfo *reg;
+    uint32_t data; /* emulated value */
+};
+
+typedef struct XenPTRegGroupInfo XenPTRegGroupInfo;
+
+/* emul reg group size initialize method */
+typedef int (*xen_pt_reg_size_init_fn)
+    (XenPCIPassthroughState *, const XenPTRegGroupInfo *,
+     uint32_t base_offset, uint8_t *size);
+
+/* emulated register group infomation */
+struct XenPTRegGroupInfo {
+    uint8_t grp_id;
+    XenPTRegisterGroupType grp_type;
+    uint8_t grp_size;
+    xen_pt_reg_size_init_fn size_init;
+    XenPTRegInfo *emu_regs;
+};
+
+/* emul register group management table */
+typedef struct XenPTRegGroup {
+    QLIST_ENTRY(XenPTRegGroup) entries;
+    const XenPTRegGroupInfo *reg_grp;
+    uint32_t base_offset;
+    uint8_t size;
+    QLIST_HEAD(, XenPTReg) reg_tbl_list;
+} XenPTRegGroup;
+
+
+#define XEN_PT_UNASSIGNED_PIRQ (-1)
+
+struct XenPCIPassthroughState {
+    PCIDevice dev;
+
+    PCIHostDeviceAddress hostaddr;
+    bool is_virtfn;
+    XenHostPCIDevice real_device;
+    XenPTRegion bases[PCI_NUM_REGIONS]; /* Access regions */
+    QLIST_HEAD(, XenPTRegGroup) reg_grps;
+
+    uint32_t machine_irq;
+
+    MemoryRegion bar[PCI_NUM_REGIONS - 1];
+    MemoryRegion rom;
+
+    MemoryListener memory_listener;
+};
+
+int xen_pt_config_init(XenPCIPassthroughState *s);
+void xen_pt_config_delete(XenPCIPassthroughState *s);
+XenPTRegGroup *xen_pt_find_reg_grp(XenPCIPassthroughState *s, uint32_t address);
+XenPTReg *xen_pt_find_reg(XenPTRegGroup *reg_grp, uint32_t address);
+int xen_pt_bar_offset_to_index(uint32_t offset);
+
+static inline pcibus_t xen_pt_get_emul_size(XenPTBarFlag flag, pcibus_t r_size)
+{
+    /* align resource size (memory type only) */
+    if (flag == XEN_PT_BAR_FLAG_MEM) {
+        return (r_size + XC_PAGE_SIZE - 1) & XC_PAGE_MASK;
+    } else {
+        return r_size;
+    }
+}
+
+/* INTx */
+/* The PCI Local Bus Specification, Rev. 3.0,
+ * Section 6.2.4 Miscellaneous Registers, pp 223
+ * outlines 5 valid values for the interrupt pin (intx).
+ *  0: For devices (or device functions) that don't use an interrupt in
+ *  1: INTA#
+ *  2: INTB#
+ *  3: INTC#
+ *  4: INTD#
+ *
+ * Xen uses the following 4 values for intx
+ *  0: INTA#
+ *  1: INTB#
+ *  2: INTC#
+ *  3: INTD#
+ *
+ * Observing that these list of values are not the same, xen_pt_pci_read_intx()
+ * uses the following mapping from hw to xen values.
+ * This seems to reflect the current usage within Xen.
+ *
+ * PCI hardware    | Xen | Notes
+ * ----------------+-----+----------------------------------------------------
+ * 0               | 0   | No interrupt
+ * 1               | 0   | INTA#
+ * 2               | 1   | INTB#
+ * 3               | 2   | INTC#
+ * 4               | 3   | INTD#
+ * any other value | 0   | This should never happen, log error message
+ */
+
+static inline uint8_t xen_pt_pci_read_intx(XenPCIPassthroughState *s)
+{
+    uint8_t v = 0;
+    xen_host_pci_get_byte(&s->real_device, PCI_INTERRUPT_PIN, &v);
+    return v;
+}
+
+static inline uint8_t xen_pt_pci_intx(XenPCIPassthroughState *s)
+{
+    uint8_t r_val = xen_pt_pci_read_intx(s);
+
+    XEN_PT_LOG(&s->dev, "intx=%i\n", r_val);
+    if (r_val < 1 || r_val > 4) {
+        XEN_PT_LOG(&s->dev, "Interrupt pin read from hardware is out of range:"
+                   " value=%i, acceptable range is 1 - 4\n", r_val);
+        r_val = 0;
+    } else {
+        r_val -= 1;
+    }
+
+    return r_val;
+}
+
+#endif /* !XEN_PT_H */

hw/xen_pt_config_init.c

@@ -0,0 +1,11 @@
+#include "xen_pt.h"
+
+XenPTRegGroup *xen_pt_find_reg_grp(XenPCIPassthroughState *s, uint32_t address)
+{
+    return NULL;
+}
+
+XenPTReg *xen_pt_find_reg(XenPTRegGroup *reg_grp, uint32_t address)
+{
+    return NULL;
+}

xen-all.c

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