Add qemu 2.4.0

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

13 files changed, 6901 insertions, 0 deletions

diff --git a/qemu/hw/pci/Makefile.objs b/qemu/hw/pci/Makefile.objs
new file mode 100644
index 000000000..9f905e634
--- /dev/null
+++ b/qemu/hw/pci/Makefile.objs
@@ -0,0 +1,9 @@
+common-obj-$(CONFIG_PCI) += pci.o pci_bridge.o
+common-obj-$(CONFIG_PCI) += msix.o msi.o
+common-obj-$(CONFIG_PCI) += shpc.o
+common-obj-$(CONFIG_PCI) += slotid_cap.o
+common-obj-$(CONFIG_PCI) += pci_host.o pcie_host.o
+common-obj-$(CONFIG_PCI) += pcie.o pcie_aer.o pcie_port.o
+
+common-obj-$(call lnot,$(CONFIG_PCI)) += pci-stub.o
+common-obj-$(CONFIG_ALL) += pci-stub.o
diff --git a/qemu/hw/pci/msi.c b/qemu/hw/pci/msi.c
new file mode 100644
index 000000000..f9c048442
--- /dev/null
+++ b/qemu/hw/pci/msi.c
@@ -0,0 +1,400 @@
+/*
+ * msi.c
+ *
+ * Copyright (c) 2010 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+
+ * 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/>.
+ */
+
+#include "hw/pci/msi.h"
+#include "qemu/range.h"
+
+/* PCI_MSI_ADDRESS_LO */
+#define PCI_MSI_ADDRESS_LO_MASK         (~0x3)
+
+/* If we get rid of cap allocator, we won't need those. */
+#define PCI_MSI_32_SIZEOF       0x0a
+#define PCI_MSI_64_SIZEOF       0x0e
+#define PCI_MSI_32M_SIZEOF      0x14
+#define PCI_MSI_64M_SIZEOF      0x18
+
+#define PCI_MSI_VECTORS_MAX     32
+
+/* Flag for interrupt controller to declare MSI/MSI-X support */
+bool msi_supported;
+
+/* If we get rid of cap allocator, we won't need this. */
+static inline uint8_t msi_cap_sizeof(uint16_t flags)
+{
+    switch (flags & (PCI_MSI_FLAGS_MASKBIT | PCI_MSI_FLAGS_64BIT)) {
+    case PCI_MSI_FLAGS_MASKBIT | PCI_MSI_FLAGS_64BIT:
+        return PCI_MSI_64M_SIZEOF;
+    case PCI_MSI_FLAGS_64BIT:
+        return PCI_MSI_64_SIZEOF;
+    case PCI_MSI_FLAGS_MASKBIT:
+        return PCI_MSI_32M_SIZEOF;
+    case 0:
+        return PCI_MSI_32_SIZEOF;
+    default:
+        abort();
+        break;
+    }
+    return 0;
+}
+
+//#define MSI_DEBUG
+
+#ifdef MSI_DEBUG
+# define MSI_DPRINTF(fmt, ...)                                          \
+    fprintf(stderr, "%s:%d " fmt, __func__, __LINE__, ## __VA_ARGS__)
+#else
+# define MSI_DPRINTF(fmt, ...)  do { } while (0)
+#endif
+#define MSI_DEV_PRINTF(dev, fmt, ...)                                   \
+    MSI_DPRINTF("%s:%x " fmt, (dev)->name, (dev)->devfn, ## __VA_ARGS__)
+
+static inline unsigned int msi_nr_vectors(uint16_t flags)
+{
+    return 1U <<
+        ((flags & PCI_MSI_FLAGS_QSIZE) >> ctz32(PCI_MSI_FLAGS_QSIZE));
+}
+
+static inline uint8_t msi_flags_off(const PCIDevice* dev)
+{
+    return dev->msi_cap + PCI_MSI_FLAGS;
+}
+
+static inline uint8_t msi_address_lo_off(const PCIDevice* dev)
+{
+    return dev->msi_cap + PCI_MSI_ADDRESS_LO;
+}
+
+static inline uint8_t msi_address_hi_off(const PCIDevice* dev)
+{
+    return dev->msi_cap + PCI_MSI_ADDRESS_HI;
+}
+
+static inline uint8_t msi_data_off(const PCIDevice* dev, bool msi64bit)
+{
+    return dev->msi_cap + (msi64bit ? PCI_MSI_DATA_64 : PCI_MSI_DATA_32);
+}
+
+static inline uint8_t msi_mask_off(const PCIDevice* dev, bool msi64bit)
+{
+    return dev->msi_cap + (msi64bit ? PCI_MSI_MASK_64 : PCI_MSI_MASK_32);
+}
+
+static inline uint8_t msi_pending_off(const PCIDevice* dev, bool msi64bit)
+{
+    return dev->msi_cap + (msi64bit ? PCI_MSI_PENDING_64 : PCI_MSI_PENDING_32);
+}
+
+/*
+ * Special API for POWER to configure the vectors through
+ * a side channel. Should never be used by devices.
+ */
+void msi_set_message(PCIDevice *dev, MSIMessage msg)
+{
+    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
+    bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
+
+    if (msi64bit) {
+        pci_set_quad(dev->config + msi_address_lo_off(dev), msg.address);
+    } else {
+        pci_set_long(dev->config + msi_address_lo_off(dev), msg.address);
+    }
+    pci_set_word(dev->config + msi_data_off(dev, msi64bit), msg.data);
+}
+
+MSIMessage msi_get_message(PCIDevice *dev, unsigned int vector)
+{
+    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
+    bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
+    unsigned int nr_vectors = msi_nr_vectors(flags);
+    MSIMessage msg;
+
+    assert(vector < nr_vectors);
+
+    if (msi64bit) {
+        msg.address = pci_get_quad(dev->config + msi_address_lo_off(dev));
+    } else {
+        msg.address = pci_get_long(dev->config + msi_address_lo_off(dev));
+    }
+
+    /* upper bit 31:16 is zero */
+    msg.data = pci_get_word(dev->config + msi_data_off(dev, msi64bit));
+    if (nr_vectors > 1) {
+        msg.data &= ~(nr_vectors - 1);
+        msg.data |= vector;
+    }
+
+    return msg;
+}
+
+bool msi_enabled(const PCIDevice *dev)
+{
+    return msi_present(dev) &&
+        (pci_get_word(dev->config + msi_flags_off(dev)) &
+         PCI_MSI_FLAGS_ENABLE);
+}
+
+int msi_init(struct PCIDevice *dev, uint8_t offset,
+             unsigned int nr_vectors, bool msi64bit, bool msi_per_vector_mask)
+{
+    unsigned int vectors_order;
+    uint16_t flags;
+    uint8_t cap_size;
+    int config_offset;
+
+    if (!msi_supported) {
+        return -ENOTSUP;
+    }
+
+    MSI_DEV_PRINTF(dev,
+                   "init offset: 0x%"PRIx8" vector: %"PRId8
+                   " 64bit %d mask %d\n",
+                   offset, nr_vectors, msi64bit, msi_per_vector_mask);
+
+    assert(!(nr_vectors & (nr_vectors - 1)));   /* power of 2 */
+    assert(nr_vectors > 0);
+    assert(nr_vectors <= PCI_MSI_VECTORS_MAX);
+    /* the nr of MSI vectors is up to 32 */
+    vectors_order = ctz32(nr_vectors);
+
+    flags = vectors_order << ctz32(PCI_MSI_FLAGS_QMASK);
+    if (msi64bit) {
+        flags |= PCI_MSI_FLAGS_64BIT;
+    }
+    if (msi_per_vector_mask) {
+        flags |= PCI_MSI_FLAGS_MASKBIT;
+    }
+
+    cap_size = msi_cap_sizeof(flags);
+    config_offset = pci_add_capability(dev, PCI_CAP_ID_MSI, offset, cap_size);
+    if (config_offset < 0) {
+        return config_offset;
+    }
+
+    dev->msi_cap = config_offset;
+    dev->cap_present |= QEMU_PCI_CAP_MSI;
+
+    pci_set_word(dev->config + msi_flags_off(dev), flags);
+    pci_set_word(dev->wmask + msi_flags_off(dev),
+                 PCI_MSI_FLAGS_QSIZE | PCI_MSI_FLAGS_ENABLE);
+    pci_set_long(dev->wmask + msi_address_lo_off(dev),
+                 PCI_MSI_ADDRESS_LO_MASK);
+    if (msi64bit) {
+        pci_set_long(dev->wmask + msi_address_hi_off(dev), 0xffffffff);
+    }
+    pci_set_word(dev->wmask + msi_data_off(dev, msi64bit), 0xffff);
+
+    if (msi_per_vector_mask) {
+        /* Make mask bits 0 to nr_vectors - 1 writable. */
+        pci_set_long(dev->wmask + msi_mask_off(dev, msi64bit),
+                     0xffffffff >> (PCI_MSI_VECTORS_MAX - nr_vectors));
+    }
+    return config_offset;
+}
+
+void msi_uninit(struct PCIDevice *dev)
+{
+    uint16_t flags;
+    uint8_t cap_size;
+
+    if (!msi_present(dev)) {
+        return;
+    }
+    flags = pci_get_word(dev->config + msi_flags_off(dev));
+    cap_size = msi_cap_sizeof(flags);
+    pci_del_capability(dev, PCI_CAP_ID_MSI, cap_size);
+    dev->cap_present &= ~QEMU_PCI_CAP_MSI;
+
+    MSI_DEV_PRINTF(dev, "uninit\n");
+}
+
+void msi_reset(PCIDevice *dev)
+{
+    uint16_t flags;
+    bool msi64bit;
+
+    if (!msi_present(dev)) {
+        return;
+    }
+
+    flags = pci_get_word(dev->config + msi_flags_off(dev));
+    flags &= ~(PCI_MSI_FLAGS_QSIZE | PCI_MSI_FLAGS_ENABLE);
+    msi64bit = flags & PCI_MSI_FLAGS_64BIT;
+
+    pci_set_word(dev->config + msi_flags_off(dev), flags);
+    pci_set_long(dev->config + msi_address_lo_off(dev), 0);
+    if (msi64bit) {
+        pci_set_long(dev->config + msi_address_hi_off(dev), 0);
+    }
+    pci_set_word(dev->config + msi_data_off(dev, msi64bit), 0);
+    if (flags & PCI_MSI_FLAGS_MASKBIT) {
+        pci_set_long(dev->config + msi_mask_off(dev, msi64bit), 0);
+        pci_set_long(dev->config + msi_pending_off(dev, msi64bit), 0);
+    }
+    MSI_DEV_PRINTF(dev, "reset\n");
+}
+
+static bool msi_is_masked(const PCIDevice *dev, unsigned int vector)
+{
+    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
+    uint32_t mask;
+    assert(vector < PCI_MSI_VECTORS_MAX);
+
+    if (!(flags & PCI_MSI_FLAGS_MASKBIT)) {
+        return false;
+    }
+
+    mask = pci_get_long(dev->config +
+                        msi_mask_off(dev, flags & PCI_MSI_FLAGS_64BIT));
+    return mask & (1U << vector);
+}
+
+void msi_notify(PCIDevice *dev, unsigned int vector)
+{
+    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
+    bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
+    unsigned int nr_vectors = msi_nr_vectors(flags);
+    MSIMessage msg;
+
+    assert(vector < nr_vectors);
+    if (msi_is_masked(dev, vector)) {
+        assert(flags & PCI_MSI_FLAGS_MASKBIT);
+        pci_long_test_and_set_mask(
+            dev->config + msi_pending_off(dev, msi64bit), 1U << vector);
+        MSI_DEV_PRINTF(dev, "pending vector 0x%x\n", vector);
+        return;
+    }
+
+    msg = msi_get_message(dev, vector);
+
+    MSI_DEV_PRINTF(dev,
+                   "notify vector 0x%x"
+                   " address: 0x%"PRIx64" data: 0x%"PRIx32"\n",
+                   vector, msg.address, msg.data);
+    msi_send_message(dev, msg);
+}
+
+void msi_send_message(PCIDevice *dev, MSIMessage msg)
+{
+    MemTxAttrs attrs = {};
+
+    attrs.stream_id = (pci_bus_num(dev->bus) << 8) | dev->devfn;
+    address_space_stl_le(&dev->bus_master_as, msg.address, msg.data,
+                         attrs, NULL);
+}
+
+/* Normally called by pci_default_write_config(). */
+void msi_write_config(PCIDevice *dev, uint32_t addr, uint32_t val, int len)
+{
+    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
+    bool msi64bit = flags & PCI_MSI_FLAGS_64BIT;
+    bool msi_per_vector_mask = flags & PCI_MSI_FLAGS_MASKBIT;
+    unsigned int nr_vectors;
+    uint8_t log_num_vecs;
+    uint8_t log_max_vecs;
+    unsigned int vector;
+    uint32_t pending;
+
+    if (!msi_present(dev) ||
+        !ranges_overlap(addr, len, dev->msi_cap, msi_cap_sizeof(flags))) {
+        return;
+    }
+
+#ifdef MSI_DEBUG
+    MSI_DEV_PRINTF(dev, "addr 0x%"PRIx32" val 0x%"PRIx32" len %d\n",
+                   addr, val, len);
+    MSI_DEV_PRINTF(dev, "ctrl: 0x%"PRIx16" address: 0x%"PRIx32,
+                   flags,
+                   pci_get_long(dev->config + msi_address_lo_off(dev)));
+    if (msi64bit) {
+        fprintf(stderr, " address-hi: 0x%"PRIx32,
+                pci_get_long(dev->config + msi_address_hi_off(dev)));
+    }
+    fprintf(stderr, " data: 0x%"PRIx16,
+            pci_get_word(dev->config + msi_data_off(dev, msi64bit)));
+    if (flags & PCI_MSI_FLAGS_MASKBIT) {
+        fprintf(stderr, " mask 0x%"PRIx32" pending 0x%"PRIx32,
+                pci_get_long(dev->config + msi_mask_off(dev, msi64bit)),
+                pci_get_long(dev->config + msi_pending_off(dev, msi64bit)));
+    }
+    fprintf(stderr, "\n");
+#endif
+
+    if (!(flags & PCI_MSI_FLAGS_ENABLE)) {
+        return;
+    }
+
+    /*
+     * Now MSI is enabled, clear INTx# interrupts.
+     * the driver is prohibited from writing enable bit to mask
+     * a service request. But the guest OS could do this.
+     * So we just discard the interrupts as moderate fallback.
+     *
+     * 6.8.3.3. Enabling Operation
+     *   While enabled for MSI or MSI-X operation, a function is prohibited
+     *   from using its INTx# pin (if implemented) to request
+     *   service (MSI, MSI-X, and INTx# are mutually exclusive).
+     */
+    pci_device_deassert_intx(dev);
+
+    /*
+     * nr_vectors might be set bigger than capable. So clamp it.
+     * This is not legal by spec, so we can do anything we like,
+     * just don't crash the host
+     */
+    log_num_vecs =
+        (flags & PCI_MSI_FLAGS_QSIZE) >> ctz32(PCI_MSI_FLAGS_QSIZE);
+    log_max_vecs =
+        (flags & PCI_MSI_FLAGS_QMASK) >> ctz32(PCI_MSI_FLAGS_QMASK);
+    if (log_num_vecs > log_max_vecs) {
+        flags &= ~PCI_MSI_FLAGS_QSIZE;
+        flags |= log_max_vecs << ctz32(PCI_MSI_FLAGS_QSIZE);
+        pci_set_word(dev->config + msi_flags_off(dev), flags);
+    }
+
+    if (!msi_per_vector_mask) {
+        /* if per vector masking isn't supported,
+           there is no pending interrupt. */
+        return;
+    }
+
+    nr_vectors = msi_nr_vectors(flags);
+
+    /* This will discard pending interrupts, if any. */
+    pending = pci_get_long(dev->config + msi_pending_off(dev, msi64bit));
+    pending &= 0xffffffff >> (PCI_MSI_VECTORS_MAX - nr_vectors);
+    pci_set_long(dev->config + msi_pending_off(dev, msi64bit), pending);
+
+    /* deliver pending interrupts which are unmasked */
+    for (vector = 0; vector < nr_vectors; ++vector) {
+        if (msi_is_masked(dev, vector) || !(pending & (1U << vector))) {
+            continue;
+        }
+
+        pci_long_test_and_clear_mask(
+            dev->config + msi_pending_off(dev, msi64bit), 1U << vector);
+        msi_notify(dev, vector);
+    }
+}
+
+unsigned int msi_nr_vectors_allocated(const PCIDevice *dev)
+{
+    uint16_t flags = pci_get_word(dev->config + msi_flags_off(dev));
+    return msi_nr_vectors(flags);
+}
diff --git a/qemu/hw/pci/msix.c b/qemu/hw/pci/msix.c
new file mode 100644
index 000000000..7716bf364
--- /dev/null
+++ b/qemu/hw/pci/msix.c
@@ -0,0 +1,608 @@
+/*
+ * MSI-X device support
+ *
+ * This module includes support for MSI-X in pci devices.
+ *
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ *
+ *  Copyright (c) 2009, Red Hat Inc, Michael S. Tsirkin (mst@redhat.com)
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Contributions after 2012-01-13 are licensed under the terms of the
+ * GNU GPL, version 2 or (at your option) any later version.
+ */
+
+#include "hw/hw.h"
+#include "hw/pci/msi.h"
+#include "hw/pci/msix.h"
+#include "hw/pci/pci.h"
+#include "qemu/range.h"
+
+#define MSIX_CAP_LENGTH 12
+
+/* MSI enable bit and maskall bit are in byte 1 in FLAGS register */
+#define MSIX_CONTROL_OFFSET (PCI_MSIX_FLAGS + 1)
+#define MSIX_ENABLE_MASK (PCI_MSIX_FLAGS_ENABLE >> 8)
+#define MSIX_MASKALL_MASK (PCI_MSIX_FLAGS_MASKALL >> 8)
+
+MSIMessage msix_get_message(PCIDevice *dev, unsigned vector)
+{
+    uint8_t *table_entry = dev->msix_table + vector * PCI_MSIX_ENTRY_SIZE;
+    MSIMessage msg;
+
+    msg.address = pci_get_quad(table_entry + PCI_MSIX_ENTRY_LOWER_ADDR);
+    msg.data = pci_get_long(table_entry + PCI_MSIX_ENTRY_DATA);
+    return msg;
+}
+
+/*
+ * Special API for POWER to configure the vectors through
+ * a side channel. Should never be used by devices.
+ */
+void msix_set_message(PCIDevice *dev, int vector, struct MSIMessage msg)
+{
+    uint8_t *table_entry = dev->msix_table + vector * PCI_MSIX_ENTRY_SIZE;
+
+    pci_set_quad(table_entry + PCI_MSIX_ENTRY_LOWER_ADDR, msg.address);
+    pci_set_long(table_entry + PCI_MSIX_ENTRY_DATA, msg.data);
+    table_entry[PCI_MSIX_ENTRY_VECTOR_CTRL] &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
+}
+
+static uint8_t msix_pending_mask(int vector)
+{
+    return 1 << (vector % 8);
+}
+
+static uint8_t *msix_pending_byte(PCIDevice *dev, int vector)
+{
+    return dev->msix_pba + vector / 8;
+}
+
+static int msix_is_pending(PCIDevice *dev, int vector)
+{
+    return *msix_pending_byte(dev, vector) & msix_pending_mask(vector);
+}
+
+void msix_set_pending(PCIDevice *dev, unsigned int vector)
+{
+    *msix_pending_byte(dev, vector) |= msix_pending_mask(vector);
+}
+
+static void msix_clr_pending(PCIDevice *dev, int vector)
+{
+    *msix_pending_byte(dev, vector) &= ~msix_pending_mask(vector);
+}
+
+static bool msix_vector_masked(PCIDevice *dev, unsigned int vector, bool fmask)
+{
+    unsigned offset = vector * PCI_MSIX_ENTRY_SIZE + PCI_MSIX_ENTRY_VECTOR_CTRL;
+    return fmask || dev->msix_table[offset] & PCI_MSIX_ENTRY_CTRL_MASKBIT;
+}
+
+bool msix_is_masked(PCIDevice *dev, unsigned int vector)
+{
+    return msix_vector_masked(dev, vector, dev->msix_function_masked);
+}
+
+static void msix_fire_vector_notifier(PCIDevice *dev,
+                                      unsigned int vector, bool is_masked)
+{
+    MSIMessage msg;
+    int ret;
+
+    if (!dev->msix_vector_use_notifier) {
+        return;
+    }
+    if (is_masked) {
+        dev->msix_vector_release_notifier(dev, vector);
+    } else {
+        msg = msix_get_message(dev, vector);
+        ret = dev->msix_vector_use_notifier(dev, vector, msg);
+        assert(ret >= 0);
+    }
+}
+
+static void msix_handle_mask_update(PCIDevice *dev, int vector, bool was_masked)
+{
+    bool is_masked = msix_is_masked(dev, vector);
+
+    if (is_masked == was_masked) {
+        return;
+    }
+
+    msix_fire_vector_notifier(dev, vector, is_masked);
+
+    if (!is_masked && msix_is_pending(dev, vector)) {
+        msix_clr_pending(dev, vector);
+        msix_notify(dev, vector);
+    }
+}
+
+static void msix_update_function_masked(PCIDevice *dev)
+{
+    dev->msix_function_masked = !msix_enabled(dev) ||
+        (dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] & MSIX_MASKALL_MASK);
+}
+
+/* Handle MSI-X capability config write. */
+void msix_write_config(PCIDevice *dev, uint32_t addr,
+                       uint32_t val, int len)
+{
+    unsigned enable_pos = dev->msix_cap + MSIX_CONTROL_OFFSET;
+    int vector;
+    bool was_masked;
+
+    if (!msix_present(dev) || !range_covers_byte(addr, len, enable_pos)) {
+        return;
+    }
+
+    was_masked = dev->msix_function_masked;
+    msix_update_function_masked(dev);
+
+    if (!msix_enabled(dev)) {
+        return;
+    }
+
+    pci_device_deassert_intx(dev);
+
+    if (dev->msix_function_masked == was_masked) {
+        return;
+    }
+
+    for (vector = 0; vector < dev->msix_entries_nr; ++vector) {
+        msix_handle_mask_update(dev, vector,
+                                msix_vector_masked(dev, vector, was_masked));
+    }
+}
+
+static uint64_t msix_table_mmio_read(void *opaque, hwaddr addr,
+                                     unsigned size)
+{
+    PCIDevice *dev = opaque;
+
+    return pci_get_long(dev->msix_table + addr);
+}
+
+static void msix_table_mmio_write(void *opaque, hwaddr addr,
+                                  uint64_t val, unsigned size)
+{
+    PCIDevice *dev = opaque;
+    int vector = addr / PCI_MSIX_ENTRY_SIZE;
+    bool was_masked;
+
+    was_masked = msix_is_masked(dev, vector);
+    pci_set_long(dev->msix_table + addr, val);
+    msix_handle_mask_update(dev, vector, was_masked);
+}
+
+static const MemoryRegionOps msix_table_mmio_ops = {
+    .read = msix_table_mmio_read,
+    .write = msix_table_mmio_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .valid = {
+        .min_access_size = 4,
+        .max_access_size = 4,
+    },
+};
+
+static uint64_t msix_pba_mmio_read(void *opaque, hwaddr addr,
+                                   unsigned size)
+{
+    PCIDevice *dev = opaque;
+    if (dev->msix_vector_poll_notifier) {
+        unsigned vector_start = addr * 8;
+        unsigned vector_end = MIN(addr + size * 8, dev->msix_entries_nr);
+        dev->msix_vector_poll_notifier(dev, vector_start, vector_end);
+    }
+
+    return pci_get_long(dev->msix_pba + addr);
+}
+
+static const MemoryRegionOps msix_pba_mmio_ops = {
+    .read = msix_pba_mmio_read,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .valid = {
+        .min_access_size = 4,
+        .max_access_size = 4,
+    },
+};
+
+static void msix_mask_all(struct PCIDevice *dev, unsigned nentries)
+{
+    int vector;
+
+    for (vector = 0; vector < nentries; ++vector) {
+        unsigned offset =
+            vector * PCI_MSIX_ENTRY_SIZE + PCI_MSIX_ENTRY_VECTOR_CTRL;
+        bool was_masked = msix_is_masked(dev, vector);
+
+        dev->msix_table[offset] |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
+        msix_handle_mask_update(dev, vector, was_masked);
+    }
+}
+
+/* Initialize the MSI-X structures */
+int msix_init(struct PCIDevice *dev, unsigned short nentries,
+              MemoryRegion *table_bar, uint8_t table_bar_nr,
+              unsigned table_offset, MemoryRegion *pba_bar,
+              uint8_t pba_bar_nr, unsigned pba_offset, uint8_t cap_pos)
+{
+    int cap;
+    unsigned table_size, pba_size;
+    uint8_t *config;
+
+    /* Nothing to do if MSI is not supported by interrupt controller */
+    if (!msi_supported) {
+        return -ENOTSUP;
+    }
+
+    if (nentries < 1 || nentries > PCI_MSIX_FLAGS_QSIZE + 1) {
+        return -EINVAL;
+    }
+
+    table_size = nentries * PCI_MSIX_ENTRY_SIZE;
+    pba_size = QEMU_ALIGN_UP(nentries, 64) / 8;
+
+    /* Sanity test: table & pba don't overlap, fit within BARs, min aligned */
+    if ((table_bar_nr == pba_bar_nr &&
+         ranges_overlap(table_offset, table_size, pba_offset, pba_size)) ||
+        table_offset + table_size > memory_region_size(table_bar) ||
+        pba_offset + pba_size > memory_region_size(pba_bar) ||
+        (table_offset | pba_offset) & PCI_MSIX_FLAGS_BIRMASK) {
+        return -EINVAL;
+    }
+
+    cap = pci_add_capability(dev, PCI_CAP_ID_MSIX, cap_pos, MSIX_CAP_LENGTH);
+    if (cap < 0) {
+        return cap;
+    }
+
+    dev->msix_cap = cap;
+    dev->cap_present |= QEMU_PCI_CAP_MSIX;
+    config = dev->config + cap;
+
+    pci_set_word(config + PCI_MSIX_FLAGS, nentries - 1);
+    dev->msix_entries_nr = nentries;
+    dev->msix_function_masked = true;
+
+    pci_set_long(config + PCI_MSIX_TABLE, table_offset | table_bar_nr);
+    pci_set_long(config + PCI_MSIX_PBA, pba_offset | pba_bar_nr);
+
+    /* Make flags bit writable. */
+    dev->wmask[cap + MSIX_CONTROL_OFFSET] |= MSIX_ENABLE_MASK |
+                                             MSIX_MASKALL_MASK;
+
+    dev->msix_table = g_malloc0(table_size);
+    dev->msix_pba = g_malloc0(pba_size);
+    dev->msix_entry_used = g_malloc0(nentries * sizeof *dev->msix_entry_used);
+
+    msix_mask_all(dev, nentries);
+
+    memory_region_init_io(&dev->msix_table_mmio, OBJECT(dev), &msix_table_mmio_ops, dev,
+                          "msix-table", table_size);
+    memory_region_add_subregion(table_bar, table_offset, &dev->msix_table_mmio);
+    memory_region_init_io(&dev->msix_pba_mmio, OBJECT(dev), &msix_pba_mmio_ops, dev,
+                          "msix-pba", pba_size);
+    memory_region_add_subregion(pba_bar, pba_offset, &dev->msix_pba_mmio);
+
+    return 0;
+}
+
+int msix_init_exclusive_bar(PCIDevice *dev, unsigned short nentries,
+                            uint8_t bar_nr)
+{
+    int ret;
+    char *name;
+    uint32_t bar_size = 4096;
+    uint32_t bar_pba_offset = bar_size / 2;
+    uint32_t bar_pba_size = (nentries / 8 + 1) * 8;
+
+    /*
+     * Migration compatibility dictates that this remains a 4k
+     * BAR with the vector table in the lower half and PBA in
+     * the upper half for nentries which is lower or equal to 128.
+     * No need to care about using more than 65 entries for legacy
+     * machine types who has at most 64 queues.
+     */
+    if (nentries * PCI_MSIX_ENTRY_SIZE > bar_pba_offset) {
+        bar_pba_offset = nentries * PCI_MSIX_ENTRY_SIZE;
+    }
+
+    if (bar_pba_offset + bar_pba_size > 4096) {
+        bar_size = bar_pba_offset + bar_pba_size;
+    }
+
+    if (bar_size & (bar_size - 1)) {
+        bar_size = 1 << qemu_fls(bar_size);
+    }
+
+    name = g_strdup_printf("%s-msix", dev->name);
+    memory_region_init(&dev->msix_exclusive_bar, OBJECT(dev), name, bar_size);
+    g_free(name);
+
+    ret = msix_init(dev, nentries, &dev->msix_exclusive_bar, bar_nr,
+                    0, &dev->msix_exclusive_bar,
+                    bar_nr, bar_pba_offset,
+                    0);
+    if (ret) {
+        return ret;
+    }
+
+    pci_register_bar(dev, bar_nr, PCI_BASE_ADDRESS_SPACE_MEMORY,
+                     &dev->msix_exclusive_bar);
+
+    return 0;
+}
+
+static void msix_free_irq_entries(PCIDevice *dev)
+{
+    int vector;
+
+    for (vector = 0; vector < dev->msix_entries_nr; ++vector) {
+        dev->msix_entry_used[vector] = 0;
+        msix_clr_pending(dev, vector);
+    }
+}
+
+static void msix_clear_all_vectors(PCIDevice *dev)
+{
+    int vector;
+
+    for (vector = 0; vector < dev->msix_entries_nr; ++vector) {
+        msix_clr_pending(dev, vector);
+    }
+}
+
+/* Clean up resources for the device. */
+void msix_uninit(PCIDevice *dev, MemoryRegion *table_bar, MemoryRegion *pba_bar)
+{
+    if (!msix_present(dev)) {
+        return;
+    }
+    pci_del_capability(dev, PCI_CAP_ID_MSIX, MSIX_CAP_LENGTH);
+    dev->msix_cap = 0;
+    msix_free_irq_entries(dev);
+    dev->msix_entries_nr = 0;
+    memory_region_del_subregion(pba_bar, &dev->msix_pba_mmio);
+    g_free(dev->msix_pba);
+    dev->msix_pba = NULL;
+    memory_region_del_subregion(table_bar, &dev->msix_table_mmio);
+    g_free(dev->msix_table);
+    dev->msix_table = NULL;
+    g_free(dev->msix_entry_used);
+    dev->msix_entry_used = NULL;
+    dev->cap_present &= ~QEMU_PCI_CAP_MSIX;
+}
+
+void msix_uninit_exclusive_bar(PCIDevice *dev)
+{
+    if (msix_present(dev)) {
+        msix_uninit(dev, &dev->msix_exclusive_bar, &dev->msix_exclusive_bar);
+    }
+}
+
+void msix_save(PCIDevice *dev, QEMUFile *f)
+{
+    unsigned n = dev->msix_entries_nr;
+
+    if (!msix_present(dev)) {
+        return;
+    }
+
+    qemu_put_buffer(f, dev->msix_table, n * PCI_MSIX_ENTRY_SIZE);
+    qemu_put_buffer(f, dev->msix_pba, (n + 7) / 8);
+}
+
+/* Should be called after restoring the config space. */
+void msix_load(PCIDevice *dev, QEMUFile *f)
+{
+    unsigned n = dev->msix_entries_nr;
+    unsigned int vector;
+
+    if (!msix_present(dev)) {
+        return;
+    }
+
+    msix_clear_all_vectors(dev);
+    qemu_get_buffer(f, dev->msix_table, n * PCI_MSIX_ENTRY_SIZE);
+    qemu_get_buffer(f, dev->msix_pba, (n + 7) / 8);
+    msix_update_function_masked(dev);
+
+    for (vector = 0; vector < n; vector++) {
+        msix_handle_mask_update(dev, vector, true);
+    }
+}
+
+/* Does device support MSI-X? */
+int msix_present(PCIDevice *dev)
+{
+    return dev->cap_present & QEMU_PCI_CAP_MSIX;
+}
+
+/* Is MSI-X enabled? */
+int msix_enabled(PCIDevice *dev)
+{
+    return (dev->cap_present & QEMU_PCI_CAP_MSIX) &&
+        (dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] &
+         MSIX_ENABLE_MASK);
+}
+
+/* Send an MSI-X message */
+void msix_notify(PCIDevice *dev, unsigned vector)
+{
+    MSIMessage msg;
+
+    if (vector >= dev->msix_entries_nr || !dev->msix_entry_used[vector])
+        return;
+    if (msix_is_masked(dev, vector)) {
+        msix_set_pending(dev, vector);
+        return;
+    }
+
+    msg = msix_get_message(dev, vector);
+
+    msi_send_message(dev, msg);
+}
+
+void msix_reset(PCIDevice *dev)
+{
+    if (!msix_present(dev)) {
+        return;
+    }
+    msix_clear_all_vectors(dev);
+    dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] &=
+	    ~dev->wmask[dev->msix_cap + MSIX_CONTROL_OFFSET];
+    memset(dev->msix_table, 0, dev->msix_entries_nr * PCI_MSIX_ENTRY_SIZE);
+    memset(dev->msix_pba, 0, QEMU_ALIGN_UP(dev->msix_entries_nr, 64) / 8);
+    msix_mask_all(dev, dev->msix_entries_nr);
+}
+
+/* PCI spec suggests that devices make it possible for software to configure
+ * less vectors than supported by the device, but does not specify a standard
+ * mechanism for devices to do so.
+ *
+ * We support this by asking devices to declare vectors software is going to
+ * actually use, and checking this on the notification path. Devices that
+ * don't want to follow the spec suggestion can declare all vectors as used. */
+
+/* Mark vector as used. */
+int msix_vector_use(PCIDevice *dev, unsigned vector)
+{
+    if (vector >= dev->msix_entries_nr)
+        return -EINVAL;
+    dev->msix_entry_used[vector]++;
+    return 0;
+}
+
+/* Mark vector as unused. */
+void msix_vector_unuse(PCIDevice *dev, unsigned vector)
+{
+    if (vector >= dev->msix_entries_nr || !dev->msix_entry_used[vector]) {
+        return;
+    }
+    if (--dev->msix_entry_used[vector]) {
+        return;
+    }
+    msix_clr_pending(dev, vector);
+}
+
+void msix_unuse_all_vectors(PCIDevice *dev)
+{
+    if (!msix_present(dev)) {
+        return;
+    }
+    msix_free_irq_entries(dev);
+}
+
+unsigned int msix_nr_vectors_allocated(const PCIDevice *dev)
+{
+    return dev->msix_entries_nr;
+}
+
+static int msix_set_notifier_for_vector(PCIDevice *dev, unsigned int vector)
+{
+    MSIMessage msg;
+
+    if (msix_is_masked(dev, vector)) {
+        return 0;
+    }
+    msg = msix_get_message(dev, vector);
+    return dev->msix_vector_use_notifier(dev, vector, msg);
+}
+
+static void msix_unset_notifier_for_vector(PCIDevice *dev, unsigned int vector)
+{
+    if (msix_is_masked(dev, vector)) {
+        return;
+    }
+    dev->msix_vector_release_notifier(dev, vector);
+}
+
+int msix_set_vector_notifiers(PCIDevice *dev,
+                              MSIVectorUseNotifier use_notifier,
+                              MSIVectorReleaseNotifier release_notifier,
+                              MSIVectorPollNotifier poll_notifier)
+{
+    int vector, ret;
+
+    assert(use_notifier && release_notifier);
+
+    dev->msix_vector_use_notifier = use_notifier;
+    dev->msix_vector_release_notifier = release_notifier;
+    dev->msix_vector_poll_notifier = poll_notifier;
+
+    if ((dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] &
+        (MSIX_ENABLE_MASK | MSIX_MASKALL_MASK)) == MSIX_ENABLE_MASK) {
+        for (vector = 0; vector < dev->msix_entries_nr; vector++) {
+            ret = msix_set_notifier_for_vector(dev, vector);
+            if (ret < 0) {
+                goto undo;
+            }
+        }
+    }
+    if (dev->msix_vector_poll_notifier) {
+        dev->msix_vector_poll_notifier(dev, 0, dev->msix_entries_nr);
+    }
+    return 0;
+
+undo:
+    while (--vector >= 0) {
+        msix_unset_notifier_for_vector(dev, vector);
+    }
+    dev->msix_vector_use_notifier = NULL;
+    dev->msix_vector_release_notifier = NULL;
+    return ret;
+}
+
+void msix_unset_vector_notifiers(PCIDevice *dev)
+{
+    int vector;
+
+    assert(dev->msix_vector_use_notifier &&
+           dev->msix_vector_release_notifier);
+
+    if ((dev->config[dev->msix_cap + MSIX_CONTROL_OFFSET] &
+        (MSIX_ENABLE_MASK | MSIX_MASKALL_MASK)) == MSIX_ENABLE_MASK) {
+        for (vector = 0; vector < dev->msix_entries_nr; vector++) {
+            msix_unset_notifier_for_vector(dev, vector);
+        }
+    }
+    dev->msix_vector_use_notifier = NULL;
+    dev->msix_vector_release_notifier = NULL;
+    dev->msix_vector_poll_notifier = NULL;
+}
+
+static void put_msix_state(QEMUFile *f, void *pv, size_t size)
+{
+    msix_save(pv, f);
+}
+
+static int get_msix_state(QEMUFile *f, void *pv, size_t size)
+{
+    msix_load(pv, f);
+    return 0;
+}
+
+static VMStateInfo vmstate_info_msix = {
+    .name = "msix state",
+    .get  = get_msix_state,
+    .put  = put_msix_state,
+};
+
+const VMStateDescription vmstate_msix = {
+    .name = "msix",
+    .fields = (VMStateField[]) {
+        {
+            .name         = "msix",
+            .version_id   = 0,
+            .field_exists = NULL,
+            .size         = 0,   /* ouch */
+            .info         = &vmstate_info_msix,
+            .flags        = VMS_SINGLE,
+            .offset       = 0,
+        },
+        VMSTATE_END_OF_LIST()
+    }
+};
diff --git a/qemu/hw/pci/pci-stub.c b/qemu/hw/pci/pci-stub.c
new file mode 100644
index 000000000..063a7c242
--- /dev/null
+++ b/qemu/hw/pci/pci-stub.c
@@ -0,0 +1,36 @@
+/*
+ * PCI stubs for platforms that don't support pci bus.
+ *
+ * Copyright (c) 2010 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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/>.
+ */
+
+#include "sysemu/sysemu.h"
+#include "monitor/monitor.h"
+#include "qapi/qmp/qerror.h"
+#include "hw/pci/pci.h"
+#include "qmp-commands.h"
+
+PciInfoList *qmp_query_pci(Error **errp)
+{
+    error_setg(errp, QERR_UNSUPPORTED);
+    return NULL;
+}
+
+void hmp_pcie_aer_inject_error(Monitor *mon, const QDict *qdict)
+{
+    monitor_printf(mon, "PCI devices not supported\n");
+}
diff --git a/qemu/hw/pci/pci.c b/qemu/hw/pci/pci.c
new file mode 100644
index 000000000..a017614d4
--- /dev/null
+++ b/qemu/hw/pci/pci.c
@@ -0,0 +1,2472 @@
+/*
+ * QEMU PCI bus manager
+ *
+ * Copyright (c) 2004 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to deal
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+#include "hw/hw.h"
+#include "hw/pci/pci.h"
+#include "hw/pci/pci_bridge.h"
+#include "hw/pci/pci_bus.h"
+#include "hw/pci/pci_host.h"
+#include "monitor/monitor.h"
+#include "net/net.h"
+#include "sysemu/sysemu.h"
+#include "hw/loader.h"
+#include "qemu/error-report.h"
+#include "qemu/range.h"
+#include "qmp-commands.h"
+#include "trace.h"
+#include "hw/pci/msi.h"
+#include "hw/pci/msix.h"
+#include "exec/address-spaces.h"
+#include "hw/hotplug.h"
+
+//#define DEBUG_PCI
+#ifdef DEBUG_PCI
+# define PCI_DPRINTF(format, ...)       printf(format, ## __VA_ARGS__)
+#else
+# define PCI_DPRINTF(format, ...)       do { } while (0)
+#endif
+
+static void pcibus_dev_print(Monitor *mon, DeviceState *dev, int indent);
+static char *pcibus_get_dev_path(DeviceState *dev);
+static char *pcibus_get_fw_dev_path(DeviceState *dev);
+static void pcibus_reset(BusState *qbus);
+
+static Property pci_props[] = {
+    DEFINE_PROP_PCI_DEVFN("addr", PCIDevice, devfn, -1),
+    DEFINE_PROP_STRING("romfile", PCIDevice, romfile),
+    DEFINE_PROP_UINT32("rombar",  PCIDevice, rom_bar, 1),
+    DEFINE_PROP_BIT("multifunction", PCIDevice, cap_present,
+                    QEMU_PCI_CAP_MULTIFUNCTION_BITNR, false),
+    DEFINE_PROP_BIT("command_serr_enable", PCIDevice, cap_present,
+                    QEMU_PCI_CAP_SERR_BITNR, true),
+    DEFINE_PROP_END_OF_LIST()
+};
+
+static const VMStateDescription vmstate_pcibus = {
+    .name = "PCIBUS",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_INT32_EQUAL(nirq, PCIBus),
+        VMSTATE_VARRAY_INT32(irq_count, PCIBus,
+                             nirq, 0, vmstate_info_int32,
+                             int32_t),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static void pci_bus_realize(BusState *qbus, Error **errp)
+{
+    PCIBus *bus = PCI_BUS(qbus);
+
+    vmstate_register(NULL, -1, &vmstate_pcibus, bus);
+}
+
+static void pci_bus_unrealize(BusState *qbus, Error **errp)
+{
+    PCIBus *bus = PCI_BUS(qbus);
+
+    vmstate_unregister(NULL, &vmstate_pcibus, bus);
+}
+
+static bool pcibus_is_root(PCIBus *bus)
+{
+    return !bus->parent_dev;
+}
+
+static int pcibus_num(PCIBus *bus)
+{
+    if (pcibus_is_root(bus)) {
+        return 0; /* pci host bridge */
+    }
+    return bus->parent_dev->config[PCI_SECONDARY_BUS];
+}
+
+static uint16_t pcibus_numa_node(PCIBus *bus)
+{
+    return NUMA_NODE_UNASSIGNED;
+}
+
+static void pci_bus_class_init(ObjectClass *klass, void *data)
+{
+    BusClass *k = BUS_CLASS(klass);
+    PCIBusClass *pbc = PCI_BUS_CLASS(klass);
+
+    k->print_dev = pcibus_dev_print;
+    k->get_dev_path = pcibus_get_dev_path;
+    k->get_fw_dev_path = pcibus_get_fw_dev_path;
+    k->realize = pci_bus_realize;
+    k->unrealize = pci_bus_unrealize;
+    k->reset = pcibus_reset;
+
+    pbc->is_root = pcibus_is_root;
+    pbc->bus_num = pcibus_num;
+    pbc->numa_node = pcibus_numa_node;
+}
+
+static const TypeInfo pci_bus_info = {
+    .name = TYPE_PCI_BUS,
+    .parent = TYPE_BUS,
+    .instance_size = sizeof(PCIBus),
+    .class_size = sizeof(PCIBusClass),
+    .class_init = pci_bus_class_init,
+};
+
+static const TypeInfo pcie_bus_info = {
+    .name = TYPE_PCIE_BUS,
+    .parent = TYPE_PCI_BUS,
+};
+
+static PCIBus *pci_find_bus_nr(PCIBus *bus, int bus_num);
+static void pci_update_mappings(PCIDevice *d);
+static void pci_irq_handler(void *opaque, int irq_num, int level);
+static void pci_add_option_rom(PCIDevice *pdev, bool is_default_rom, Error **);
+static void pci_del_option_rom(PCIDevice *pdev);
+
+static uint16_t pci_default_sub_vendor_id = PCI_SUBVENDOR_ID_REDHAT_QUMRANET;
+static uint16_t pci_default_sub_device_id = PCI_SUBDEVICE_ID_QEMU;
+
+static QLIST_HEAD(, PCIHostState) pci_host_bridges;
+
+int pci_bar(PCIDevice *d, int reg)
+{
+    uint8_t type;
+
+    if (reg != PCI_ROM_SLOT)
+        return PCI_BASE_ADDRESS_0 + reg * 4;
+
+    type = d->config[PCI_HEADER_TYPE] & ~PCI_HEADER_TYPE_MULTI_FUNCTION;
+    return type == PCI_HEADER_TYPE_BRIDGE ? PCI_ROM_ADDRESS1 : PCI_ROM_ADDRESS;
+}
+
+static inline int pci_irq_state(PCIDevice *d, int irq_num)
+{
+	return (d->irq_state >> irq_num) & 0x1;
+}
+
+static inline void pci_set_irq_state(PCIDevice *d, int irq_num, int level)
+{
+	d->irq_state &= ~(0x1 << irq_num);
+	d->irq_state |= level << irq_num;
+}
+
+static void pci_change_irq_level(PCIDevice *pci_dev, int irq_num, int change)
+{
+    PCIBus *bus;
+    for (;;) {
+        bus = pci_dev->bus;
+        irq_num = bus->map_irq(pci_dev, irq_num);
+        if (bus->set_irq)
+            break;
+        pci_dev = bus->parent_dev;
+    }
+    bus->irq_count[irq_num] += change;
+    bus->set_irq(bus->irq_opaque, irq_num, bus->irq_count[irq_num] != 0);
+}
+
+int pci_bus_get_irq_level(PCIBus *bus, int irq_num)
+{
+    assert(irq_num >= 0);
+    assert(irq_num < bus->nirq);
+    return !!bus->irq_count[irq_num];
+}
+
+/* Update interrupt status bit in config space on interrupt
+ * state change. */
+static void pci_update_irq_status(PCIDevice *dev)
+{
+    if (dev->irq_state) {
+        dev->config[PCI_STATUS] |= PCI_STATUS_INTERRUPT;
+    } else {
+        dev->config[PCI_STATUS] &= ~PCI_STATUS_INTERRUPT;
+    }
+}
+
+void pci_device_deassert_intx(PCIDevice *dev)
+{
+    int i;
+    for (i = 0; i < PCI_NUM_PINS; ++i) {
+        pci_irq_handler(dev, i, 0);
+    }
+}
+
+static void pci_do_device_reset(PCIDevice *dev)
+{
+    int r;
+
+    pci_device_deassert_intx(dev);
+    assert(dev->irq_state == 0);
+
+    /* Clear all writable bits */
+    pci_word_test_and_clear_mask(dev->config + PCI_COMMAND,
+                                 pci_get_word(dev->wmask + PCI_COMMAND) |
+                                 pci_get_word(dev->w1cmask + PCI_COMMAND));
+    pci_word_test_and_clear_mask(dev->config + PCI_STATUS,
+                                 pci_get_word(dev->wmask + PCI_STATUS) |
+                                 pci_get_word(dev->w1cmask + PCI_STATUS));
+    dev->config[PCI_CACHE_LINE_SIZE] = 0x0;
+    dev->config[PCI_INTERRUPT_LINE] = 0x0;
+    for (r = 0; r < PCI_NUM_REGIONS; ++r) {
+        PCIIORegion *region = &dev->io_regions[r];
+        if (!region->size) {
+            continue;
+        }
+
+        if (!(region->type & PCI_BASE_ADDRESS_SPACE_IO) &&
+            region->type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+            pci_set_quad(dev->config + pci_bar(dev, r), region->type);
+        } else {
+            pci_set_long(dev->config + pci_bar(dev, r), region->type);
+        }
+    }
+    pci_update_mappings(dev);
+
+    msi_reset(dev);
+    msix_reset(dev);
+}
+
+/*
+ * This function is called on #RST and FLR.
+ * FLR if PCI_EXP_DEVCTL_BCR_FLR is set
+ */
+void pci_device_reset(PCIDevice *dev)
+{
+    qdev_reset_all(&dev->qdev);
+    pci_do_device_reset(dev);
+}
+
+/*
+ * Trigger pci bus reset under a given bus.
+ * Called via qbus_reset_all on RST# assert, after the devices
+ * have been reset qdev_reset_all-ed already.
+ */
+static void pcibus_reset(BusState *qbus)
+{
+    PCIBus *bus = DO_UPCAST(PCIBus, qbus, qbus);
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(bus->devices); ++i) {
+        if (bus->devices[i]) {
+            pci_do_device_reset(bus->devices[i]);
+        }
+    }
+
+    for (i = 0; i < bus->nirq; i++) {
+        assert(bus->irq_count[i] == 0);
+    }
+}
+
+static void pci_host_bus_register(PCIBus *bus, DeviceState *parent)
+{
+    PCIHostState *host_bridge = PCI_HOST_BRIDGE(parent);
+
+    QLIST_INSERT_HEAD(&pci_host_bridges, host_bridge, next);
+}
+
+PCIBus *pci_find_primary_bus(void)
+{
+    PCIBus *primary_bus = NULL;
+    PCIHostState *host;
+
+    QLIST_FOREACH(host, &pci_host_bridges, next) {
+        if (primary_bus) {
+            /* We have multiple root buses, refuse to select a primary */
+            return NULL;
+        }
+        primary_bus = host->bus;
+    }
+
+    return primary_bus;
+}
+
+PCIBus *pci_device_root_bus(const PCIDevice *d)
+{
+    PCIBus *bus = d->bus;
+
+    while (!pci_bus_is_root(bus)) {
+        d = bus->parent_dev;
+        assert(d != NULL);
+
+        bus = d->bus;
+    }
+
+    return bus;
+}
+
+const char *pci_root_bus_path(PCIDevice *dev)
+{
+    PCIBus *rootbus = pci_device_root_bus(dev);
+    PCIHostState *host_bridge = PCI_HOST_BRIDGE(rootbus->qbus.parent);
+    PCIHostBridgeClass *hc = PCI_HOST_BRIDGE_GET_CLASS(host_bridge);
+
+    assert(host_bridge->bus == rootbus);
+
+    if (hc->root_bus_path) {
+        return (*hc->root_bus_path)(host_bridge, rootbus);
+    }
+
+    return rootbus->qbus.name;
+}
+
+static void pci_bus_init(PCIBus *bus, DeviceState *parent,
+                         const char *name,
+                         MemoryRegion *address_space_mem,
+                         MemoryRegion *address_space_io,
+                         uint8_t devfn_min)
+{
+    assert(PCI_FUNC(devfn_min) == 0);
+    bus->devfn_min = devfn_min;
+    bus->address_space_mem = address_space_mem;
+    bus->address_space_io = address_space_io;
+
+    /* host bridge */
+    QLIST_INIT(&bus->child);
+
+    pci_host_bus_register(bus, parent);
+}
+
+bool pci_bus_is_express(PCIBus *bus)
+{
+    return object_dynamic_cast(OBJECT(bus), TYPE_PCIE_BUS);
+}
+
+bool pci_bus_is_root(PCIBus *bus)
+{
+    return PCI_BUS_GET_CLASS(bus)->is_root(bus);
+}
+
+void pci_bus_new_inplace(PCIBus *bus, size_t bus_size, DeviceState *parent,
+                         const char *name,
+                         MemoryRegion *address_space_mem,
+                         MemoryRegion *address_space_io,
+                         uint8_t devfn_min, const char *typename)
+{
+    qbus_create_inplace(bus, bus_size, typename, parent, name);
+    pci_bus_init(bus, parent, name, address_space_mem,
+                 address_space_io, devfn_min);
+}
+
+PCIBus *pci_bus_new(DeviceState *parent, const char *name,
+                    MemoryRegion *address_space_mem,
+                    MemoryRegion *address_space_io,
+                    uint8_t devfn_min, const char *typename)
+{
+    PCIBus *bus;
+
+    bus = PCI_BUS(qbus_create(typename, parent, name));
+    pci_bus_init(bus, parent, name, address_space_mem,
+                 address_space_io, devfn_min);
+    return bus;
+}
+
+void pci_bus_irqs(PCIBus *bus, pci_set_irq_fn set_irq, pci_map_irq_fn map_irq,
+                  void *irq_opaque, int nirq)
+{
+    bus->set_irq = set_irq;
+    bus->map_irq = map_irq;
+    bus->irq_opaque = irq_opaque;
+    bus->nirq = nirq;
+    bus->irq_count = g_malloc0(nirq * sizeof(bus->irq_count[0]));
+}
+
+PCIBus *pci_register_bus(DeviceState *parent, const char *name,
+                         pci_set_irq_fn set_irq, pci_map_irq_fn map_irq,
+                         void *irq_opaque,
+                         MemoryRegion *address_space_mem,
+                         MemoryRegion *address_space_io,
+                         uint8_t devfn_min, int nirq, const char *typename)
+{
+    PCIBus *bus;
+
+    bus = pci_bus_new(parent, name, address_space_mem,
+                      address_space_io, devfn_min, typename);
+    pci_bus_irqs(bus, set_irq, map_irq, irq_opaque, nirq);
+    return bus;
+}
+
+int pci_bus_num(PCIBus *s)
+{
+    return PCI_BUS_GET_CLASS(s)->bus_num(s);
+}
+
+int pci_bus_numa_node(PCIBus *bus)
+{
+    return PCI_BUS_GET_CLASS(bus)->numa_node(bus);
+}
+
+static int get_pci_config_device(QEMUFile *f, void *pv, size_t size)
+{
+    PCIDevice *s = container_of(pv, PCIDevice, config);
+    PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(s);
+    uint8_t *config;
+    int i;
+
+    assert(size == pci_config_size(s));
+    config = g_malloc(size);
+
+    qemu_get_buffer(f, config, size);
+    for (i = 0; i < size; ++i) {
+        if ((config[i] ^ s->config[i]) &
+            s->cmask[i] & ~s->wmask[i] & ~s->w1cmask[i]) {
+            error_report("%s: Bad config data: i=0x%x read: %x device: %x "
+                         "cmask: %x wmask: %x w1cmask:%x", __func__,
+                         i, config[i], s->config[i],
+                         s->cmask[i], s->wmask[i], s->w1cmask[i]);
+            g_free(config);
+            return -EINVAL;
+        }
+    }
+    memcpy(s->config, config, size);
+
+    pci_update_mappings(s);
+    if (pc->is_bridge) {
+        PCIBridge *b = PCI_BRIDGE(s);
+        pci_bridge_update_mappings(b);
+    }
+
+    memory_region_set_enabled(&s->bus_master_enable_region,
+                              pci_get_word(s->config + PCI_COMMAND)
+                              & PCI_COMMAND_MASTER);
+
+    g_free(config);
+    return 0;
+}
+
+/* just put buffer */
+static void put_pci_config_device(QEMUFile *f, void *pv, size_t size)
+{
+    const uint8_t **v = pv;
+    assert(size == pci_config_size(container_of(pv, PCIDevice, config)));
+    qemu_put_buffer(f, *v, size);
+}
+
+static VMStateInfo vmstate_info_pci_config = {
+    .name = "pci config",
+    .get  = get_pci_config_device,
+    .put  = put_pci_config_device,
+};
+
+static int get_pci_irq_state(QEMUFile *f, void *pv, size_t size)
+{
+    PCIDevice *s = container_of(pv, PCIDevice, irq_state);
+    uint32_t irq_state[PCI_NUM_PINS];
+    int i;
+    for (i = 0; i < PCI_NUM_PINS; ++i) {
+        irq_state[i] = qemu_get_be32(f);
+        if (irq_state[i] != 0x1 && irq_state[i] != 0) {
+            fprintf(stderr, "irq state %d: must be 0 or 1.\n",
+                    irq_state[i]);
+            return -EINVAL;
+        }
+    }
+
+    for (i = 0; i < PCI_NUM_PINS; ++i) {
+        pci_set_irq_state(s, i, irq_state[i]);
+    }
+
+    return 0;
+}
+
+static void put_pci_irq_state(QEMUFile *f, void *pv, size_t size)
+{
+    int i;
+    PCIDevice *s = container_of(pv, PCIDevice, irq_state);
+
+    for (i = 0; i < PCI_NUM_PINS; ++i) {
+        qemu_put_be32(f, pci_irq_state(s, i));
+    }
+}
+
+static VMStateInfo vmstate_info_pci_irq_state = {
+    .name = "pci irq state",
+    .get  = get_pci_irq_state,
+    .put  = put_pci_irq_state,
+};
+
+const VMStateDescription vmstate_pci_device = {
+    .name = "PCIDevice",
+    .version_id = 2,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_INT32_POSITIVE_LE(version_id, PCIDevice),
+        VMSTATE_BUFFER_UNSAFE_INFO(config, PCIDevice, 0,
+                                   vmstate_info_pci_config,
+                                   PCI_CONFIG_SPACE_SIZE),
+        VMSTATE_BUFFER_UNSAFE_INFO(irq_state, PCIDevice, 2,
+				   vmstate_info_pci_irq_state,
+				   PCI_NUM_PINS * sizeof(int32_t)),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+const VMStateDescription vmstate_pcie_device = {
+    .name = "PCIEDevice",
+    .version_id = 2,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_INT32_POSITIVE_LE(version_id, PCIDevice),
+        VMSTATE_BUFFER_UNSAFE_INFO(config, PCIDevice, 0,
+                                   vmstate_info_pci_config,
+                                   PCIE_CONFIG_SPACE_SIZE),
+        VMSTATE_BUFFER_UNSAFE_INFO(irq_state, PCIDevice, 2,
+				   vmstate_info_pci_irq_state,
+				   PCI_NUM_PINS * sizeof(int32_t)),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static inline const VMStateDescription *pci_get_vmstate(PCIDevice *s)
+{
+    return pci_is_express(s) ? &vmstate_pcie_device : &vmstate_pci_device;
+}
+
+void pci_device_save(PCIDevice *s, QEMUFile *f)
+{
+    /* Clear interrupt status bit: it is implicit
+     * in irq_state which we are saving.
+     * This makes us compatible with old devices
+     * which never set or clear this bit. */
+    s->config[PCI_STATUS] &= ~PCI_STATUS_INTERRUPT;
+    vmstate_save_state(f, pci_get_vmstate(s), s, NULL);
+    /* Restore the interrupt status bit. */
+    pci_update_irq_status(s);
+}
+
+int pci_device_load(PCIDevice *s, QEMUFile *f)
+{
+    int ret;
+    ret = vmstate_load_state(f, pci_get_vmstate(s), s, s->version_id);
+    /* Restore the interrupt status bit. */
+    pci_update_irq_status(s);
+    return ret;
+}
+
+static void pci_set_default_subsystem_id(PCIDevice *pci_dev)
+{
+    pci_set_word(pci_dev->config + PCI_SUBSYSTEM_VENDOR_ID,
+                 pci_default_sub_vendor_id);
+    pci_set_word(pci_dev->config + PCI_SUBSYSTEM_ID,
+                 pci_default_sub_device_id);
+}
+
+/*
+ * Parse [[<domain>:]<bus>:]<slot>, return -1 on error if funcp == NULL
+ *       [[<domain>:]<bus>:]<slot>.<func>, return -1 on error
+ */
+static int pci_parse_devaddr(const char *addr, int *domp, int *busp,
+                             unsigned int *slotp, unsigned int *funcp)
+{
+    const char *p;
+    char *e;
+    unsigned long val;
+    unsigned long dom = 0, bus = 0;
+    unsigned int slot = 0;
+    unsigned int func = 0;
+
+    p = addr;
+    val = strtoul(p, &e, 16);
+    if (e == p)
+	return -1;
+    if (*e == ':') {
+	bus = val;
+	p = e + 1;
+	val = strtoul(p, &e, 16);
+	if (e == p)
+	    return -1;
+	if (*e == ':') {
+	    dom = bus;
+	    bus = val;
+	    p = e + 1;
+	    val = strtoul(p, &e, 16);
+	    if (e == p)
+		return -1;
+	}
+    }
+
+    slot = val;
+
+    if (funcp != NULL) {
+        if (*e != '.')
+            return -1;
+
+        p = e + 1;
+        val = strtoul(p, &e, 16);
+        if (e == p)
+            return -1;
+
+        func = val;
+    }
+
+    /* if funcp == NULL func is 0 */
+    if (dom > 0xffff || bus > 0xff || slot > 0x1f || func > 7)
+	return -1;
+
+    if (*e)
+	return -1;
+
+    *domp = dom;
+    *busp = bus;
+    *slotp = slot;
+    if (funcp != NULL)
+        *funcp = func;
+    return 0;
+}
+
+static PCIBus *pci_get_bus_devfn(int *devfnp, PCIBus *root,
+                                 const char *devaddr)
+{
+    int dom, bus;
+    unsigned slot;
+
+    if (!root) {
+        fprintf(stderr, "No primary PCI bus\n");
+        return NULL;
+    }
+
+    assert(!root->parent_dev);
+
+    if (!devaddr) {
+        *devfnp = -1;
+        return pci_find_bus_nr(root, 0);
+    }
+
+    if (pci_parse_devaddr(devaddr, &dom, &bus, &slot, NULL) < 0) {
+        return NULL;
+    }
+
+    if (dom != 0) {
+        fprintf(stderr, "No support for non-zero PCI domains\n");
+        return NULL;
+    }
+
+    *devfnp = PCI_DEVFN(slot, 0);
+    return pci_find_bus_nr(root, bus);
+}
+
+static void pci_init_cmask(PCIDevice *dev)
+{
+    pci_set_word(dev->cmask + PCI_VENDOR_ID, 0xffff);
+    pci_set_word(dev->cmask + PCI_DEVICE_ID, 0xffff);
+    dev->cmask[PCI_STATUS] = PCI_STATUS_CAP_LIST;
+    dev->cmask[PCI_REVISION_ID] = 0xff;
+    dev->cmask[PCI_CLASS_PROG] = 0xff;
+    pci_set_word(dev->cmask + PCI_CLASS_DEVICE, 0xffff);
+    dev->cmask[PCI_HEADER_TYPE] = 0xff;
+    dev->cmask[PCI_CAPABILITY_LIST] = 0xff;
+}
+
+static void pci_init_wmask(PCIDevice *dev)
+{
+    int config_size = pci_config_size(dev);
+
+    dev->wmask[PCI_CACHE_LINE_SIZE] = 0xff;
+    dev->wmask[PCI_INTERRUPT_LINE] = 0xff;
+    pci_set_word(dev->wmask + PCI_COMMAND,
+                 PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER |
+                 PCI_COMMAND_INTX_DISABLE);
+    if (dev->cap_present & QEMU_PCI_CAP_SERR) {
+        pci_word_test_and_set_mask(dev->wmask + PCI_COMMAND, PCI_COMMAND_SERR);
+    }
+
+    memset(dev->wmask + PCI_CONFIG_HEADER_SIZE, 0xff,
+           config_size - PCI_CONFIG_HEADER_SIZE);
+}
+
+static void pci_init_w1cmask(PCIDevice *dev)
+{
+    /*
+     * Note: It's okay to set w1cmask even for readonly bits as
+     * long as their value is hardwired to 0.
+     */
+    pci_set_word(dev->w1cmask + PCI_STATUS,
+                 PCI_STATUS_PARITY | PCI_STATUS_SIG_TARGET_ABORT |
+                 PCI_STATUS_REC_TARGET_ABORT | PCI_STATUS_REC_MASTER_ABORT |
+                 PCI_STATUS_SIG_SYSTEM_ERROR | PCI_STATUS_DETECTED_PARITY);
+}
+
+static void pci_init_mask_bridge(PCIDevice *d)
+{
+    /* PCI_PRIMARY_BUS, PCI_SECONDARY_BUS, PCI_SUBORDINATE_BUS and
+       PCI_SEC_LETENCY_TIMER */
+    memset(d->wmask + PCI_PRIMARY_BUS, 0xff, 4);
+
+    /* base and limit */
+    d->wmask[PCI_IO_BASE] = PCI_IO_RANGE_MASK & 0xff;
+    d->wmask[PCI_IO_LIMIT] = PCI_IO_RANGE_MASK & 0xff;
+    pci_set_word(d->wmask + PCI_MEMORY_BASE,
+                 PCI_MEMORY_RANGE_MASK & 0xffff);
+    pci_set_word(d->wmask + PCI_MEMORY_LIMIT,
+                 PCI_MEMORY_RANGE_MASK & 0xffff);
+    pci_set_word(d->wmask + PCI_PREF_MEMORY_BASE,
+                 PCI_PREF_RANGE_MASK & 0xffff);
+    pci_set_word(d->wmask + PCI_PREF_MEMORY_LIMIT,
+                 PCI_PREF_RANGE_MASK & 0xffff);
+
+    /* PCI_PREF_BASE_UPPER32 and PCI_PREF_LIMIT_UPPER32 */
+    memset(d->wmask + PCI_PREF_BASE_UPPER32, 0xff, 8);
+
+    /* Supported memory and i/o types */
+    d->config[PCI_IO_BASE] |= PCI_IO_RANGE_TYPE_16;
+    d->config[PCI_IO_LIMIT] |= PCI_IO_RANGE_TYPE_16;
+    pci_word_test_and_set_mask(d->config + PCI_PREF_MEMORY_BASE,
+                               PCI_PREF_RANGE_TYPE_64);
+    pci_word_test_and_set_mask(d->config + PCI_PREF_MEMORY_LIMIT,
+                               PCI_PREF_RANGE_TYPE_64);
+
+    /*
+     * TODO: Bridges default to 10-bit VGA decoding but we currently only
+     * implement 16-bit decoding (no alias support).
+     */
+    pci_set_word(d->wmask + PCI_BRIDGE_CONTROL,
+                 PCI_BRIDGE_CTL_PARITY |
+                 PCI_BRIDGE_CTL_SERR |
+                 PCI_BRIDGE_CTL_ISA |
+                 PCI_BRIDGE_CTL_VGA |
+                 PCI_BRIDGE_CTL_VGA_16BIT |
+                 PCI_BRIDGE_CTL_MASTER_ABORT |
+                 PCI_BRIDGE_CTL_BUS_RESET |
+                 PCI_BRIDGE_CTL_FAST_BACK |
+                 PCI_BRIDGE_CTL_DISCARD |
+                 PCI_BRIDGE_CTL_SEC_DISCARD |
+                 PCI_BRIDGE_CTL_DISCARD_SERR);
+    /* Below does not do anything as we never set this bit, put here for
+     * completeness. */
+    pci_set_word(d->w1cmask + PCI_BRIDGE_CONTROL,
+                 PCI_BRIDGE_CTL_DISCARD_STATUS);
+    d->cmask[PCI_IO_BASE] |= PCI_IO_RANGE_TYPE_MASK;
+    d->cmask[PCI_IO_LIMIT] |= PCI_IO_RANGE_TYPE_MASK;
+    pci_word_test_and_set_mask(d->cmask + PCI_PREF_MEMORY_BASE,
+                               PCI_PREF_RANGE_TYPE_MASK);
+    pci_word_test_and_set_mask(d->cmask + PCI_PREF_MEMORY_LIMIT,
+                               PCI_PREF_RANGE_TYPE_MASK);
+}
+
+static void pci_init_multifunction(PCIBus *bus, PCIDevice *dev, Error **errp)
+{
+    uint8_t slot = PCI_SLOT(dev->devfn);
+    uint8_t func;
+
+    if (dev->cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
+        dev->config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION;
+    }
+
+    /*
+     * multifunction bit is interpreted in two ways as follows.
+     *   - all functions must set the bit to 1.
+     *     Example: Intel X53
+     *   - function 0 must set the bit, but the rest function (> 0)
+     *     is allowed to leave the bit to 0.
+     *     Example: PIIX3(also in qemu), PIIX4(also in qemu), ICH10,
+     *
+     * So OS (at least Linux) checks the bit of only function 0,
+     * and doesn't see the bit of function > 0.
+     *
+     * The below check allows both interpretation.
+     */
+    if (PCI_FUNC(dev->devfn)) {
+        PCIDevice *f0 = bus->devices[PCI_DEVFN(slot, 0)];
+        if (f0 && !(f0->cap_present & QEMU_PCI_CAP_MULTIFUNCTION)) {
+            /* function 0 should set multifunction bit */
+            error_setg(errp, "PCI: single function device can't be populated "
+                       "in function %x.%x", slot, PCI_FUNC(dev->devfn));
+            return;
+        }
+        return;
+    }
+
+    if (dev->cap_present & QEMU_PCI_CAP_MULTIFUNCTION) {
+        return;
+    }
+    /* function 0 indicates single function, so function > 0 must be NULL */
+    for (func = 1; func < PCI_FUNC_MAX; ++func) {
+        if (bus->devices[PCI_DEVFN(slot, func)]) {
+            error_setg(errp, "PCI: %x.0 indicates single function, "
+                       "but %x.%x is already populated.",
+                       slot, slot, func);
+            return;
+        }
+    }
+}
+
+static void pci_config_alloc(PCIDevice *pci_dev)
+{
+    int config_size = pci_config_size(pci_dev);
+
+    pci_dev->config = g_malloc0(config_size);
+    pci_dev->cmask = g_malloc0(config_size);
+    pci_dev->wmask = g_malloc0(config_size);
+    pci_dev->w1cmask = g_malloc0(config_size);
+    pci_dev->used = g_malloc0(config_size);
+}
+
+static void pci_config_free(PCIDevice *pci_dev)
+{
+    g_free(pci_dev->config);
+    g_free(pci_dev->cmask);
+    g_free(pci_dev->wmask);
+    g_free(pci_dev->w1cmask);
+    g_free(pci_dev->used);
+}
+
+static void do_pci_unregister_device(PCIDevice *pci_dev)
+{
+    pci_dev->bus->devices[pci_dev->devfn] = NULL;
+    pci_config_free(pci_dev);
+
+    address_space_destroy(&pci_dev->bus_master_as);
+}
+
+/* -1 for devfn means auto assign */
+static PCIDevice *do_pci_register_device(PCIDevice *pci_dev, PCIBus *bus,
+                                         const char *name, int devfn,
+                                         Error **errp)
+{
+    PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(pci_dev);
+    PCIConfigReadFunc *config_read = pc->config_read;
+    PCIConfigWriteFunc *config_write = pc->config_write;
+    Error *local_err = NULL;
+    AddressSpace *dma_as;
+
+    if (devfn < 0) {
+        for(devfn = bus->devfn_min ; devfn < ARRAY_SIZE(bus->devices);
+            devfn += PCI_FUNC_MAX) {
+            if (!bus->devices[devfn])
+                goto found;
+        }
+        error_setg(errp, "PCI: no slot/function available for %s, all in use",
+                   name);
+        return NULL;
+    found: ;
+    } else if (bus->devices[devfn]) {
+        error_setg(errp, "PCI: slot %d function %d not available for %s,"
+                   " in use by %s",
+                   PCI_SLOT(devfn), PCI_FUNC(devfn), name,
+                   bus->devices[devfn]->name);
+        return NULL;
+    }
+
+    pci_dev->bus = bus;
+    pci_dev->devfn = devfn;
+    dma_as = pci_device_iommu_address_space(pci_dev);
+
+    memory_region_init_alias(&pci_dev->bus_master_enable_region,
+                             OBJECT(pci_dev), "bus master",
+                             dma_as->root, 0, memory_region_size(dma_as->root));
+    memory_region_set_enabled(&pci_dev->bus_master_enable_region, false);
+    address_space_init(&pci_dev->bus_master_as, &pci_dev->bus_master_enable_region,
+                       name);
+
+    pstrcpy(pci_dev->name, sizeof(pci_dev->name), name);
+    pci_dev->irq_state = 0;
+    pci_config_alloc(pci_dev);
+
+    pci_config_set_vendor_id(pci_dev->config, pc->vendor_id);
+    pci_config_set_device_id(pci_dev->config, pc->device_id);
+    pci_config_set_revision(pci_dev->config, pc->revision);
+    pci_config_set_class(pci_dev->config, pc->class_id);
+
+    if (!pc->is_bridge) {
+        if (pc->subsystem_vendor_id || pc->subsystem_id) {
+            pci_set_word(pci_dev->config + PCI_SUBSYSTEM_VENDOR_ID,
+                         pc->subsystem_vendor_id);
+            pci_set_word(pci_dev->config + PCI_SUBSYSTEM_ID,
+                         pc->subsystem_id);
+        } else {
+            pci_set_default_subsystem_id(pci_dev);
+        }
+    } else {
+        /* subsystem_vendor_id/subsystem_id are only for header type 0 */
+        assert(!pc->subsystem_vendor_id);
+        assert(!pc->subsystem_id);
+    }
+    pci_init_cmask(pci_dev);
+    pci_init_wmask(pci_dev);
+    pci_init_w1cmask(pci_dev);
+    if (pc->is_bridge) {
+        pci_init_mask_bridge(pci_dev);
+    }
+    pci_init_multifunction(bus, pci_dev, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        do_pci_unregister_device(pci_dev);
+        return NULL;
+    }
+
+    if (!config_read)
+        config_read = pci_default_read_config;
+    if (!config_write)
+        config_write = pci_default_write_config;
+    pci_dev->config_read = config_read;
+    pci_dev->config_write = config_write;
+    bus->devices[devfn] = pci_dev;
+    pci_dev->version_id = 2; /* Current pci device vmstate version */
+    return pci_dev;
+}
+
+static void pci_unregister_io_regions(PCIDevice *pci_dev)
+{
+    PCIIORegion *r;
+    int i;
+
+    for(i = 0; i < PCI_NUM_REGIONS; i++) {
+        r = &pci_dev->io_regions[i];
+        if (!r->size || r->addr == PCI_BAR_UNMAPPED)
+            continue;
+        memory_region_del_subregion(r->address_space, r->memory);
+    }
+
+    pci_unregister_vga(pci_dev);
+}
+
+static void pci_qdev_unrealize(DeviceState *dev, Error **errp)
+{
+    PCIDevice *pci_dev = PCI_DEVICE(dev);
+    PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(pci_dev);
+
+    pci_unregister_io_regions(pci_dev);
+    pci_del_option_rom(pci_dev);
+
+    if (pc->exit) {
+        pc->exit(pci_dev);
+    }
+
+    do_pci_unregister_device(pci_dev);
+}
+
+void pci_register_bar(PCIDevice *pci_dev, int region_num,
+                      uint8_t type, MemoryRegion *memory)
+{
+    PCIIORegion *r;
+    uint32_t addr;
+    uint64_t wmask;
+    pcibus_t size = memory_region_size(memory);
+
+    assert(region_num >= 0);
+    assert(region_num < PCI_NUM_REGIONS);
+    if (size & (size-1)) {
+        fprintf(stderr, "ERROR: PCI region size must be pow2 "
+                    "type=0x%x, size=0x%"FMT_PCIBUS"\n", type, size);
+        exit(1);
+    }
+
+    r = &pci_dev->io_regions[region_num];
+    r->addr = PCI_BAR_UNMAPPED;
+    r->size = size;
+    r->type = type;
+    r->memory = NULL;
+
+    wmask = ~(size - 1);
+    addr = pci_bar(pci_dev, region_num);
+    if (region_num == PCI_ROM_SLOT) {
+        /* ROM enable bit is writable */
+        wmask |= PCI_ROM_ADDRESS_ENABLE;
+    }
+    pci_set_long(pci_dev->config + addr, type);
+    if (!(r->type & PCI_BASE_ADDRESS_SPACE_IO) &&
+        r->type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+        pci_set_quad(pci_dev->wmask + addr, wmask);
+        pci_set_quad(pci_dev->cmask + addr, ~0ULL);
+    } else {
+        pci_set_long(pci_dev->wmask + addr, wmask & 0xffffffff);
+        pci_set_long(pci_dev->cmask + addr, 0xffffffff);
+    }
+    pci_dev->io_regions[region_num].memory = memory;
+    pci_dev->io_regions[region_num].address_space
+        = type & PCI_BASE_ADDRESS_SPACE_IO
+        ? pci_dev->bus->address_space_io
+        : pci_dev->bus->address_space_mem;
+}
+
+static void pci_update_vga(PCIDevice *pci_dev)
+{
+    uint16_t cmd;
+
+    if (!pci_dev->has_vga) {
+        return;
+    }
+
+    cmd = pci_get_word(pci_dev->config + PCI_COMMAND);
+
+    memory_region_set_enabled(pci_dev->vga_regions[QEMU_PCI_VGA_MEM],
+                              cmd & PCI_COMMAND_MEMORY);
+    memory_region_set_enabled(pci_dev->vga_regions[QEMU_PCI_VGA_IO_LO],
+                              cmd & PCI_COMMAND_IO);
+    memory_region_set_enabled(pci_dev->vga_regions[QEMU_PCI_VGA_IO_HI],
+                              cmd & PCI_COMMAND_IO);
+}
+
+void pci_register_vga(PCIDevice *pci_dev, MemoryRegion *mem,
+                      MemoryRegion *io_lo, MemoryRegion *io_hi)
+{
+    assert(!pci_dev->has_vga);
+
+    assert(memory_region_size(mem) == QEMU_PCI_VGA_MEM_SIZE);
+    pci_dev->vga_regions[QEMU_PCI_VGA_MEM] = mem;
+    memory_region_add_subregion_overlap(pci_dev->bus->address_space_mem,
+                                        QEMU_PCI_VGA_MEM_BASE, mem, 1);
+
+    assert(memory_region_size(io_lo) == QEMU_PCI_VGA_IO_LO_SIZE);
+    pci_dev->vga_regions[QEMU_PCI_VGA_IO_LO] = io_lo;
+    memory_region_add_subregion_overlap(pci_dev->bus->address_space_io,
+                                        QEMU_PCI_VGA_IO_LO_BASE, io_lo, 1);
+
+    assert(memory_region_size(io_hi) == QEMU_PCI_VGA_IO_HI_SIZE);
+    pci_dev->vga_regions[QEMU_PCI_VGA_IO_HI] = io_hi;
+    memory_region_add_subregion_overlap(pci_dev->bus->address_space_io,
+                                        QEMU_PCI_VGA_IO_HI_BASE, io_hi, 1);
+    pci_dev->has_vga = true;
+
+    pci_update_vga(pci_dev);
+}
+
+void pci_unregister_vga(PCIDevice *pci_dev)
+{
+    if (!pci_dev->has_vga) {
+        return;
+    }
+
+    memory_region_del_subregion(pci_dev->bus->address_space_mem,
+                                pci_dev->vga_regions[QEMU_PCI_VGA_MEM]);
+    memory_region_del_subregion(pci_dev->bus->address_space_io,
+                                pci_dev->vga_regions[QEMU_PCI_VGA_IO_LO]);
+    memory_region_del_subregion(pci_dev->bus->address_space_io,
+                                pci_dev->vga_regions[QEMU_PCI_VGA_IO_HI]);
+    pci_dev->has_vga = false;
+}
+
+pcibus_t pci_get_bar_addr(PCIDevice *pci_dev, int region_num)
+{
+    return pci_dev->io_regions[region_num].addr;
+}
+
+static pcibus_t pci_bar_address(PCIDevice *d,
+				int reg, uint8_t type, pcibus_t size)
+{
+    pcibus_t new_addr, last_addr;
+    int bar = pci_bar(d, reg);
+    uint16_t cmd = pci_get_word(d->config + PCI_COMMAND);
+
+    if (type & PCI_BASE_ADDRESS_SPACE_IO) {
+        if (!(cmd & PCI_COMMAND_IO)) {
+            return PCI_BAR_UNMAPPED;
+        }
+        new_addr = pci_get_long(d->config + bar) & ~(size - 1);
+        last_addr = new_addr + size - 1;
+        /* Check if 32 bit BAR wraps around explicitly.
+         * TODO: make priorities correct and remove this work around.
+         */
+        if (last_addr <= new_addr || new_addr == 0 || last_addr >= UINT32_MAX) {
+            return PCI_BAR_UNMAPPED;
+        }
+        return new_addr;
+    }
+
+    if (!(cmd & PCI_COMMAND_MEMORY)) {
+        return PCI_BAR_UNMAPPED;
+    }
+    if (type & PCI_BASE_ADDRESS_MEM_TYPE_64) {
+        new_addr = pci_get_quad(d->config + bar);
+    } else {
+        new_addr = pci_get_long(d->config + bar);
+    }
+    /* the ROM slot has a specific enable bit */
+    if (reg == PCI_ROM_SLOT && !(new_addr & PCI_ROM_ADDRESS_ENABLE)) {
+        return PCI_BAR_UNMAPPED;
+    }
+    new_addr &= ~(size - 1);
+    last_addr = new_addr + size - 1;
+    /* NOTE: we do not support wrapping */
+    /* XXX: as we cannot support really dynamic
+       mappings, we handle specific values as invalid
+       mappings. */
+    if (last_addr <= new_addr || new_addr == 0 ||
+        last_addr == PCI_BAR_UNMAPPED) {
+        return PCI_BAR_UNMAPPED;
+    }
+
+    /* Now pcibus_t is 64bit.
+     * Check if 32 bit BAR wraps around explicitly.
+     * Without this, PC ide doesn't work well.
+     * TODO: remove this work around.
+     */
+    if  (!(type & PCI_BASE_ADDRESS_MEM_TYPE_64) && last_addr >= UINT32_MAX) {
+        return PCI_BAR_UNMAPPED;
+    }
+
+    /*
+     * OS is allowed to set BAR beyond its addressable
+     * bits. For example, 32 bit OS can set 64bit bar
+     * to >4G. Check it. TODO: we might need to support
+     * it in the future for e.g. PAE.
+     */
+    if (last_addr >= HWADDR_MAX) {
+        return PCI_BAR_UNMAPPED;
+    }
+
+    return new_addr;
+}
+
+static void pci_update_mappings(PCIDevice *d)
+{
+    PCIIORegion *r;
+    int i;
+    pcibus_t new_addr;
+
+    for(i = 0; i < PCI_NUM_REGIONS; i++) {
+        r = &d->io_regions[i];
+
+        /* this region isn't registered */
+        if (!r->size)
+            continue;
+
+        new_addr = pci_bar_address(d, i, r->type, r->size);
+
+        /* This bar isn't changed */
+        if (new_addr == r->addr)
+            continue;
+
+        /* now do the real mapping */
+        if (r->addr != PCI_BAR_UNMAPPED) {
+            trace_pci_update_mappings_del(d, pci_bus_num(d->bus),
+                                          PCI_FUNC(d->devfn),
+                                          PCI_SLOT(d->devfn),
+                                          i, r->addr, r->size);
+            memory_region_del_subregion(r->address_space, r->memory);
+        }
+        r->addr = new_addr;
+        if (r->addr != PCI_BAR_UNMAPPED) {
+            trace_pci_update_mappings_add(d, pci_bus_num(d->bus),
+                                          PCI_FUNC(d->devfn),
+                                          PCI_SLOT(d->devfn),
+                                          i, r->addr, r->size);
+            memory_region_add_subregion_overlap(r->address_space,
+                                                r->addr, r->memory, 1);
+        }
+    }
+
+    pci_update_vga(d);
+}
+
+static inline int pci_irq_disabled(PCIDevice *d)
+{
+    return pci_get_word(d->config + PCI_COMMAND) & PCI_COMMAND_INTX_DISABLE;
+}
+
+/* Called after interrupt disabled field update in config space,
+ * assert/deassert interrupts if necessary.
+ * Gets original interrupt disable bit value (before update). */
+static void pci_update_irq_disabled(PCIDevice *d, int was_irq_disabled)
+{
+    int i, disabled = pci_irq_disabled(d);
+    if (disabled == was_irq_disabled)
+        return;
+    for (i = 0; i < PCI_NUM_PINS; ++i) {
+        int state = pci_irq_state(d, i);
+        pci_change_irq_level(d, i, disabled ? -state : state);
+    }
+}
+
+uint32_t pci_default_read_config(PCIDevice *d,
+                                 uint32_t address, int len)
+{
+    uint32_t val = 0;
+
+    memcpy(&val, d->config + address, len);
+    return le32_to_cpu(val);
+}
+
+void pci_default_write_config(PCIDevice *d, uint32_t addr, uint32_t val_in, int l)
+{
+    int i, was_irq_disabled = pci_irq_disabled(d);
+    uint32_t val = val_in;
+
+    for (i = 0; i < l; val >>= 8, ++i) {
+        uint8_t wmask = d->wmask[addr + i];
+        uint8_t w1cmask = d->w1cmask[addr + i];
+        assert(!(wmask & w1cmask));
+        d->config[addr + i] = (d->config[addr + i] & ~wmask) | (val & wmask);
+        d->config[addr + i] &= ~(val & w1cmask); /* W1C: Write 1 to Clear */
+    }
+    if (ranges_overlap(addr, l, PCI_BASE_ADDRESS_0, 24) ||
+        ranges_overlap(addr, l, PCI_ROM_ADDRESS, 4) ||
+        ranges_overlap(addr, l, PCI_ROM_ADDRESS1, 4) ||
+        range_covers_byte(addr, l, PCI_COMMAND))
+        pci_update_mappings(d);
+
+    if (range_covers_byte(addr, l, PCI_COMMAND)) {
+        pci_update_irq_disabled(d, was_irq_disabled);
+        memory_region_set_enabled(&d->bus_master_enable_region,
+                                  pci_get_word(d->config + PCI_COMMAND)
+                                    & PCI_COMMAND_MASTER);
+    }
+
+    msi_write_config(d, addr, val_in, l);
+    msix_write_config(d, addr, val_in, l);
+}
+
+/***********************************************************/
+/* generic PCI irq support */
+
+/* 0 <= irq_num <= 3. level must be 0 or 1 */
+static void pci_irq_handler(void *opaque, int irq_num, int level)
+{
+    PCIDevice *pci_dev = opaque;
+    int change;
+
+    change = level - pci_irq_state(pci_dev, irq_num);
+    if (!change)
+        return;
+
+    pci_set_irq_state(pci_dev, irq_num, level);
+    pci_update_irq_status(pci_dev);
+    if (pci_irq_disabled(pci_dev))
+        return;
+    pci_change_irq_level(pci_dev, irq_num, change);
+}
+
+static inline int pci_intx(PCIDevice *pci_dev)
+{
+    return pci_get_byte(pci_dev->config + PCI_INTERRUPT_PIN) - 1;
+}
+
+qemu_irq pci_allocate_irq(PCIDevice *pci_dev)
+{
+    int intx = pci_intx(pci_dev);
+
+    return qemu_allocate_irq(pci_irq_handler, pci_dev, intx);
+}
+
+void pci_set_irq(PCIDevice *pci_dev, int level)
+{
+    int intx = pci_intx(pci_dev);
+    pci_irq_handler(pci_dev, intx, level);
+}
+
+/* Special hooks used by device assignment */
+void pci_bus_set_route_irq_fn(PCIBus *bus, pci_route_irq_fn route_intx_to_irq)
+{
+    assert(pci_bus_is_root(bus));
+    bus->route_intx_to_irq = route_intx_to_irq;
+}
+
+PCIINTxRoute pci_device_route_intx_to_irq(PCIDevice *dev, int pin)
+{
+    PCIBus *bus;
+
+    do {
+         bus = dev->bus;
+         pin = bus->map_irq(dev, pin);
+         dev = bus->parent_dev;
+    } while (dev);
+
+    if (!bus->route_intx_to_irq) {
+        error_report("PCI: Bug - unimplemented PCI INTx routing (%s)",
+                     object_get_typename(OBJECT(bus->qbus.parent)));
+        return (PCIINTxRoute) { PCI_INTX_DISABLED, -1 };
+    }
+
+    return bus->route_intx_to_irq(bus->irq_opaque, pin);
+}
+
+bool pci_intx_route_changed(PCIINTxRoute *old, PCIINTxRoute *new)
+{
+    return old->mode != new->mode || old->irq != new->irq;
+}
+
+void pci_bus_fire_intx_routing_notifier(PCIBus *bus)
+{
+    PCIDevice *dev;
+    PCIBus *sec;
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(bus->devices); ++i) {
+        dev = bus->devices[i];
+        if (dev && dev->intx_routing_notifier) {
+            dev->intx_routing_notifier(dev);
+        }
+    }
+
+    QLIST_FOREACH(sec, &bus->child, sibling) {
+        pci_bus_fire_intx_routing_notifier(sec);
+    }
+}
+
+void pci_device_set_intx_routing_notifier(PCIDevice *dev,
+                                          PCIINTxRoutingNotifier notifier)
+{
+    dev->intx_routing_notifier = notifier;
+}
+
+/*
+ * PCI-to-PCI bridge specification
+ * 9.1: Interrupt routing. Table 9-1
+ *
+ * the PCI Express Base Specification, Revision 2.1
+ * 2.2.8.1: INTx interrutp signaling - Rules
+ *          the Implementation Note
+ *          Table 2-20
+ */
+/*
+ * 0 <= pin <= 3 0 = INTA, 1 = INTB, 2 = INTC, 3 = INTD
+ * 0-origin unlike PCI interrupt pin register.
+ */
+int pci_swizzle_map_irq_fn(PCIDevice *pci_dev, int pin)
+{
+    return (pin + PCI_SLOT(pci_dev->devfn)) % PCI_NUM_PINS;
+}
+
+/***********************************************************/
+/* monitor info on PCI */
+
+typedef struct {
+    uint16_t class;
+    const char *desc;
+    const char *fw_name;
+    uint16_t fw_ign_bits;
+} pci_class_desc;
+
+static const pci_class_desc pci_class_descriptions[] =
+{
+    { 0x0001, "VGA controller", "display"},
+    { 0x0100, "SCSI controller", "scsi"},
+    { 0x0101, "IDE controller", "ide"},
+    { 0x0102, "Floppy controller", "fdc"},
+    { 0x0103, "IPI controller", "ipi"},
+    { 0x0104, "RAID controller", "raid"},
+    { 0x0106, "SATA controller"},
+    { 0x0107, "SAS controller"},
+    { 0x0180, "Storage controller"},
+    { 0x0200, "Ethernet controller", "ethernet"},
+    { 0x0201, "Token Ring controller", "token-ring"},
+    { 0x0202, "FDDI controller", "fddi"},
+    { 0x0203, "ATM controller", "atm"},
+    { 0x0280, "Network controller"},
+    { 0x0300, "VGA controller", "display", 0x00ff},
+    { 0x0301, "XGA controller"},
+    { 0x0302, "3D controller"},
+    { 0x0380, "Display controller"},
+    { 0x0400, "Video controller", "video"},
+    { 0x0401, "Audio controller", "sound"},
+    { 0x0402, "Phone"},
+    { 0x0403, "Audio controller", "sound"},
+    { 0x0480, "Multimedia controller"},
+    { 0x0500, "RAM controller", "memory"},
+    { 0x0501, "Flash controller", "flash"},
+    { 0x0580, "Memory controller"},
+    { 0x0600, "Host bridge", "host"},
+    { 0x0601, "ISA bridge", "isa"},
+    { 0x0602, "EISA bridge", "eisa"},
+    { 0x0603, "MC bridge", "mca"},
+    { 0x0604, "PCI bridge", "pci-bridge"},
+    { 0x0605, "PCMCIA bridge", "pcmcia"},
+    { 0x0606, "NUBUS bridge", "nubus"},
+    { 0x0607, "CARDBUS bridge", "cardbus"},
+    { 0x0608, "RACEWAY bridge"},
+    { 0x0680, "Bridge"},
+    { 0x0700, "Serial port", "serial"},
+    { 0x0701, "Parallel port", "parallel"},
+    { 0x0800, "Interrupt controller", "interrupt-controller"},
+    { 0x0801, "DMA controller", "dma-controller"},
+    { 0x0802, "Timer", "timer"},
+    { 0x0803, "RTC", "rtc"},
+    { 0x0900, "Keyboard", "keyboard"},
+    { 0x0901, "Pen", "pen"},
+    { 0x0902, "Mouse", "mouse"},
+    { 0x0A00, "Dock station", "dock", 0x00ff},
+    { 0x0B00, "i386 cpu", "cpu", 0x00ff},
+    { 0x0c00, "Fireware contorller", "fireware"},
+    { 0x0c01, "Access bus controller", "access-bus"},
+    { 0x0c02, "SSA controller", "ssa"},
+    { 0x0c03, "USB controller", "usb"},
+    { 0x0c04, "Fibre channel controller", "fibre-channel"},
+    { 0x0c05, "SMBus"},
+    { 0, NULL}
+};
+
+static void pci_for_each_device_under_bus(PCIBus *bus,
+                                          void (*fn)(PCIBus *b, PCIDevice *d,
+                                                     void *opaque),
+                                          void *opaque)
+{
+    PCIDevice *d;
+    int devfn;
+
+    for(devfn = 0; devfn < ARRAY_SIZE(bus->devices); devfn++) {
+        d = bus->devices[devfn];
+        if (d) {
+            fn(bus, d, opaque);
+        }
+    }
+}
+
+void pci_for_each_device(PCIBus *bus, int bus_num,
+                         void (*fn)(PCIBus *b, PCIDevice *d, void *opaque),
+                         void *opaque)
+{
+    bus = pci_find_bus_nr(bus, bus_num);
+
+    if (bus) {
+        pci_for_each_device_under_bus(bus, fn, opaque);
+    }
+}
+
+static const pci_class_desc *get_class_desc(int class)
+{
+    const pci_class_desc *desc;
+
+    desc = pci_class_descriptions;
+    while (desc->desc && class != desc->class) {
+        desc++;
+    }
+
+    return desc;
+}
+
+static PciDeviceInfoList *qmp_query_pci_devices(PCIBus *bus, int bus_num);
+
+static PciMemoryRegionList *qmp_query_pci_regions(const PCIDevice *dev)
+{
+    PciMemoryRegionList *head = NULL, *cur_item = NULL;
+    int i;
+
+    for (i = 0; i < PCI_NUM_REGIONS; i++) {
+        const PCIIORegion *r = &dev->io_regions[i];
+        PciMemoryRegionList *region;
+
+        if (!r->size) {
+            continue;
+        }
+
+        region = g_malloc0(sizeof(*region));
+        region->value = g_malloc0(sizeof(*region->value));
+
+        if (r->type & PCI_BASE_ADDRESS_SPACE_IO) {
+            region->value->type = g_strdup("io");
+        } else {
+            region->value->type = g_strdup("memory");
+            region->value->has_prefetch = true;
+            region->value->prefetch = !!(r->type & PCI_BASE_ADDRESS_MEM_PREFETCH);
+            region->value->has_mem_type_64 = true;
+            region->value->mem_type_64 = !!(r->type & PCI_BASE_ADDRESS_MEM_TYPE_64);
+        }
+
+        region->value->bar = i;
+        region->value->address = r->addr;
+        region->value->size = r->size;
+
+        /* XXX: waiting for the qapi to support GSList */
+        if (!cur_item) {
+            head = cur_item = region;
+        } else {
+            cur_item->next = region;
+            cur_item = region;
+        }
+    }
+
+    return head;
+}
+
+static PciBridgeInfo *qmp_query_pci_bridge(PCIDevice *dev, PCIBus *bus,
+                                           int bus_num)
+{
+    PciBridgeInfo *info;
+    PciMemoryRange *range;
+
+    info = g_new0(PciBridgeInfo, 1);
+
+    info->bus = g_new0(PciBusInfo, 1);
+    info->bus->number = dev->config[PCI_PRIMARY_BUS];
+    info->bus->secondary = dev->config[PCI_SECONDARY_BUS];
+    info->bus->subordinate = dev->config[PCI_SUBORDINATE_BUS];
+
+    range = info->bus->io_range = g_new0(PciMemoryRange, 1);
+    range->base = pci_bridge_get_base(dev, PCI_BASE_ADDRESS_SPACE_IO);
+    range->limit = pci_bridge_get_limit(dev, PCI_BASE_ADDRESS_SPACE_IO);
+
+    range = info->bus->memory_range = g_new0(PciMemoryRange, 1);
+    range->base = pci_bridge_get_base(dev, PCI_BASE_ADDRESS_SPACE_MEMORY);
+    range->limit = pci_bridge_get_limit(dev, PCI_BASE_ADDRESS_SPACE_MEMORY);
+
+    range = info->bus->prefetchable_range = g_new0(PciMemoryRange, 1);
+    range->base = pci_bridge_get_base(dev, PCI_BASE_ADDRESS_MEM_PREFETCH);
+    range->limit = pci_bridge_get_limit(dev, PCI_BASE_ADDRESS_MEM_PREFETCH);
+
+    if (dev->config[PCI_SECONDARY_BUS] != 0) {
+        PCIBus *child_bus = pci_find_bus_nr(bus, dev->config[PCI_SECONDARY_BUS]);
+        if (child_bus) {
+            info->has_devices = true;
+            info->devices = qmp_query_pci_devices(child_bus, dev->config[PCI_SECONDARY_BUS]);
+        }
+    }
+
+    return info;
+}
+
+static PciDeviceInfo *qmp_query_pci_device(PCIDevice *dev, PCIBus *bus,
+                                           int bus_num)
+{
+    const pci_class_desc *desc;
+    PciDeviceInfo *info;
+    uint8_t type;
+    int class;
+
+    info = g_new0(PciDeviceInfo, 1);
+    info->bus = bus_num;
+    info->slot = PCI_SLOT(dev->devfn);
+    info->function = PCI_FUNC(dev->devfn);
+
+    info->class_info = g_new0(PciDeviceClass, 1);
+    class = pci_get_word(dev->config + PCI_CLASS_DEVICE);
+    info->class_info->q_class = class;
+    desc = get_class_desc(class);
+    if (desc->desc) {
+        info->class_info->has_desc = true;
+        info->class_info->desc = g_strdup(desc->desc);
+    }
+
+    info->id = g_new0(PciDeviceId, 1);
+    info->id->vendor = pci_get_word(dev->config + PCI_VENDOR_ID);
+    info->id->device = pci_get_word(dev->config + PCI_DEVICE_ID);
+    info->regions = qmp_query_pci_regions(dev);
+    info->qdev_id = g_strdup(dev->qdev.id ? dev->qdev.id : "");
+
+    if (dev->config[PCI_INTERRUPT_PIN] != 0) {
+        info->has_irq = true;
+        info->irq = dev->config[PCI_INTERRUPT_LINE];
+    }
+
+    type = dev->config[PCI_HEADER_TYPE] & ~PCI_HEADER_TYPE_MULTI_FUNCTION;
+    if (type == PCI_HEADER_TYPE_BRIDGE) {
+        info->has_pci_bridge = true;
+        info->pci_bridge = qmp_query_pci_bridge(dev, bus, bus_num);
+    }
+
+    return info;
+}
+
+static PciDeviceInfoList *qmp_query_pci_devices(PCIBus *bus, int bus_num)
+{
+    PciDeviceInfoList *info, *head = NULL, *cur_item = NULL;
+    PCIDevice *dev;
+    int devfn;
+
+    for (devfn = 0; devfn < ARRAY_SIZE(bus->devices); devfn++) {
+        dev = bus->devices[devfn];
+        if (dev) {
+            info = g_malloc0(sizeof(*info));
+            info->value = qmp_query_pci_device(dev, bus, bus_num);
+
+            /* XXX: waiting for the qapi to support GSList */
+            if (!cur_item) {
+                head = cur_item = info;
+            } else {
+                cur_item->next = info;
+                cur_item = info;
+            }
+        }
+    }
+
+    return head;
+}
+
+static PciInfo *qmp_query_pci_bus(PCIBus *bus, int bus_num)
+{
+    PciInfo *info = NULL;
+
+    bus = pci_find_bus_nr(bus, bus_num);
+    if (bus) {
+        info = g_malloc0(sizeof(*info));
+        info->bus = bus_num;
+        info->devices = qmp_query_pci_devices(bus, bus_num);
+    }
+
+    return info;
+}
+
+PciInfoList *qmp_query_pci(Error **errp)
+{
+    PciInfoList *info, *head = NULL, *cur_item = NULL;
+    PCIHostState *host_bridge;
+
+    QLIST_FOREACH(host_bridge, &pci_host_bridges, next) {
+        info = g_malloc0(sizeof(*info));
+        info->value = qmp_query_pci_bus(host_bridge->bus,
+                                        pci_bus_num(host_bridge->bus));
+
+        /* XXX: waiting for the qapi to support GSList */
+        if (!cur_item) {
+            head = cur_item = info;
+        } else {
+            cur_item->next = info;
+            cur_item = info;
+        }
+    }
+
+    return head;
+}
+
+static const char * const pci_nic_models[] = {
+    "ne2k_pci",
+    "i82551",
+    "i82557b",
+    "i82559er",
+    "rtl8139",
+    "e1000",
+    "pcnet",
+    "virtio",
+    NULL
+};
+
+static const char * const pci_nic_names[] = {
+    "ne2k_pci",
+    "i82551",
+    "i82557b",
+    "i82559er",
+    "rtl8139",
+    "e1000",
+    "pcnet",
+    "virtio-net-pci",
+    NULL
+};
+
+/* Initialize a PCI NIC.  */
+PCIDevice *pci_nic_init_nofail(NICInfo *nd, PCIBus *rootbus,
+                               const char *default_model,
+                               const char *default_devaddr)
+{
+    const char *devaddr = nd->devaddr ? nd->devaddr : default_devaddr;
+    Error *err = NULL;
+    PCIBus *bus;
+    PCIDevice *pci_dev;
+    DeviceState *dev;
+    int devfn;
+    int i;
+
+    if (qemu_show_nic_models(nd->model, pci_nic_models)) {
+        exit(0);
+    }
+
+    i = qemu_find_nic_model(nd, pci_nic_models, default_model);
+    if (i < 0) {
+        exit(1);
+    }
+
+    bus = pci_get_bus_devfn(&devfn, rootbus, devaddr);
+    if (!bus) {
+        error_report("Invalid PCI device address %s for device %s",
+                     devaddr, pci_nic_names[i]);
+        exit(1);
+    }
+
+    pci_dev = pci_create(bus, devfn, pci_nic_names[i]);
+    dev = &pci_dev->qdev;
+    qdev_set_nic_properties(dev, nd);
+
+    object_property_set_bool(OBJECT(dev), true, "realized", &err);
+    if (err) {
+        error_report_err(err);
+        object_unparent(OBJECT(dev));
+        exit(1);
+    }
+
+    return pci_dev;
+}
+
+PCIDevice *pci_vga_init(PCIBus *bus)
+{
+    switch (vga_interface_type) {
+    case VGA_CIRRUS:
+        return pci_create_simple(bus, -1, "cirrus-vga");
+    case VGA_QXL:
+        return pci_create_simple(bus, -1, "qxl-vga");
+    case VGA_STD:
+        return pci_create_simple(bus, -1, "VGA");
+    case VGA_VMWARE:
+        return pci_create_simple(bus, -1, "vmware-svga");
+    case VGA_VIRTIO:
+        return pci_create_simple(bus, -1, "virtio-vga");
+    case VGA_NONE:
+    default: /* Other non-PCI types. Checking for unsupported types is already
+                done in vl.c. */
+        return NULL;
+    }
+}
+
+/* Whether a given bus number is in range of the secondary
+ * bus of the given bridge device. */
+static bool pci_secondary_bus_in_range(PCIDevice *dev, int bus_num)
+{
+    return !(pci_get_word(dev->config + PCI_BRIDGE_CONTROL) &
+             PCI_BRIDGE_CTL_BUS_RESET) /* Don't walk the bus if it's reset. */ &&
+        dev->config[PCI_SECONDARY_BUS] <= bus_num &&
+        bus_num <= dev->config[PCI_SUBORDINATE_BUS];
+}
+
+/* Whether a given bus number is in a range of a root bus */
+static bool pci_root_bus_in_range(PCIBus *bus, int bus_num)
+{
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(bus->devices); ++i) {
+        PCIDevice *dev = bus->devices[i];
+
+        if (dev && PCI_DEVICE_GET_CLASS(dev)->is_bridge) {
+            if (pci_secondary_bus_in_range(dev, bus_num)) {
+                return true;
+            }
+        }
+    }
+
+    return false;
+}
+
+static PCIBus *pci_find_bus_nr(PCIBus *bus, int bus_num)
+{
+    PCIBus *sec;
+
+    if (!bus) {
+        return NULL;
+    }
+
+    if (pci_bus_num(bus) == bus_num) {
+        return bus;
+    }
+
+    /* Consider all bus numbers in range for the host pci bridge. */
+    if (!pci_bus_is_root(bus) &&
+        !pci_secondary_bus_in_range(bus->parent_dev, bus_num)) {
+        return NULL;
+    }
+
+    /* try child bus */
+    for (; bus; bus = sec) {
+        QLIST_FOREACH(sec, &bus->child, sibling) {
+            if (pci_bus_num(sec) == bus_num) {
+                return sec;
+            }
+            /* PXB buses assumed to be children of bus 0 */
+            if (pci_bus_is_root(sec)) {
+                if (pci_root_bus_in_range(sec, bus_num)) {
+                    break;
+                }
+            } else {
+                if (pci_secondary_bus_in_range(sec->parent_dev, bus_num)) {
+                    break;
+                }
+            }
+        }
+    }
+
+    return NULL;
+}
+
+void pci_for_each_bus_depth_first(PCIBus *bus,
+                                  void *(*begin)(PCIBus *bus, void *parent_state),
+                                  void (*end)(PCIBus *bus, void *state),
+                                  void *parent_state)
+{
+    PCIBus *sec;
+    void *state;
+
+    if (!bus) {
+        return;
+    }
+
+    if (begin) {
+        state = begin(bus, parent_state);
+    } else {
+        state = parent_state;
+    }
+
+    QLIST_FOREACH(sec, &bus->child, sibling) {
+        pci_for_each_bus_depth_first(sec, begin, end, state);
+    }
+
+    if (end) {
+        end(bus, state);
+    }
+}
+
+
+PCIDevice *pci_find_device(PCIBus *bus, int bus_num, uint8_t devfn)
+{
+    bus = pci_find_bus_nr(bus, bus_num);
+
+    if (!bus)
+        return NULL;
+
+    return bus->devices[devfn];
+}
+
+static void pci_qdev_realize(DeviceState *qdev, Error **errp)
+{
+    PCIDevice *pci_dev = (PCIDevice *)qdev;
+    PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(pci_dev);
+    Error *local_err = NULL;
+    PCIBus *bus;
+    bool is_default_rom;
+
+    /* initialize cap_present for pci_is_express() and pci_config_size() */
+    if (pc->is_express) {
+        pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS;
+    }
+
+    bus = PCI_BUS(qdev_get_parent_bus(qdev));
+    pci_dev = do_pci_register_device(pci_dev, bus,
+                                     object_get_typename(OBJECT(qdev)),
+                                     pci_dev->devfn, errp);
+    if (pci_dev == NULL)
+        return;
+
+    if (pc->realize) {
+        pc->realize(pci_dev, &local_err);
+        if (local_err) {
+            error_propagate(errp, local_err);
+            do_pci_unregister_device(pci_dev);
+            return;
+        }
+    }
+
+    /* rom loading */
+    is_default_rom = false;
+    if (pci_dev->romfile == NULL && pc->romfile != NULL) {
+        pci_dev->romfile = g_strdup(pc->romfile);
+        is_default_rom = true;
+    }
+
+    pci_add_option_rom(pci_dev, is_default_rom, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        pci_qdev_unrealize(DEVICE(pci_dev), NULL);
+        return;
+    }
+}
+
+static void pci_default_realize(PCIDevice *dev, Error **errp)
+{
+    PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev);
+
+    if (pc->init) {
+        if (pc->init(dev) < 0) {
+            error_setg(errp, "Device initialization failed");
+            return;
+        }
+    }
+}
+
+PCIDevice *pci_create_multifunction(PCIBus *bus, int devfn, bool multifunction,
+                                    const char *name)
+{
+    DeviceState *dev;
+
+    dev = qdev_create(&bus->qbus, name);
+    qdev_prop_set_int32(dev, "addr", devfn);
+    qdev_prop_set_bit(dev, "multifunction", multifunction);
+    return PCI_DEVICE(dev);
+}
+
+PCIDevice *pci_create_simple_multifunction(PCIBus *bus, int devfn,
+                                           bool multifunction,
+                                           const char *name)
+{
+    PCIDevice *dev = pci_create_multifunction(bus, devfn, multifunction, name);
+    qdev_init_nofail(&dev->qdev);
+    return dev;
+}
+
+PCIDevice *pci_create(PCIBus *bus, int devfn, const char *name)
+{
+    return pci_create_multifunction(bus, devfn, false, name);
+}
+
+PCIDevice *pci_create_simple(PCIBus *bus, int devfn, const char *name)
+{
+    return pci_create_simple_multifunction(bus, devfn, false, name);
+}
+
+static uint8_t pci_find_space(PCIDevice *pdev, uint8_t size)
+{
+    int offset = PCI_CONFIG_HEADER_SIZE;
+    int i;
+    for (i = PCI_CONFIG_HEADER_SIZE; i < PCI_CONFIG_SPACE_SIZE; ++i) {
+        if (pdev->used[i])
+            offset = i + 1;
+        else if (i - offset + 1 == size)
+            return offset;
+    }
+    return 0;
+}
+
+static uint8_t pci_find_capability_list(PCIDevice *pdev, uint8_t cap_id,
+                                        uint8_t *prev_p)
+{
+    uint8_t next, prev;
+
+    if (!(pdev->config[PCI_STATUS] & PCI_STATUS_CAP_LIST))
+        return 0;
+
+    for (prev = PCI_CAPABILITY_LIST; (next = pdev->config[prev]);
+         prev = next + PCI_CAP_LIST_NEXT)
+        if (pdev->config[next + PCI_CAP_LIST_ID] == cap_id)
+            break;
+
+    if (prev_p)
+        *prev_p = prev;
+    return next;
+}
+
+static uint8_t pci_find_capability_at_offset(PCIDevice *pdev, uint8_t offset)
+{
+    uint8_t next, prev, found = 0;
+
+    if (!(pdev->used[offset])) {
+        return 0;
+    }
+
+    assert(pdev->config[PCI_STATUS] & PCI_STATUS_CAP_LIST);
+
+    for (prev = PCI_CAPABILITY_LIST; (next = pdev->config[prev]);
+         prev = next + PCI_CAP_LIST_NEXT) {
+        if (next <= offset && next > found) {
+            found = next;
+        }
+    }
+    return found;
+}
+
+/* Patch the PCI vendor and device ids in a PCI rom image if necessary.
+   This is needed for an option rom which is used for more than one device. */
+static void pci_patch_ids(PCIDevice *pdev, uint8_t *ptr, int size)
+{
+    uint16_t vendor_id;
+    uint16_t device_id;
+    uint16_t rom_vendor_id;
+    uint16_t rom_device_id;
+    uint16_t rom_magic;
+    uint16_t pcir_offset;
+    uint8_t checksum;
+
+    /* Words in rom data are little endian (like in PCI configuration),
+       so they can be read / written with pci_get_word / pci_set_word. */
+
+    /* Only a valid rom will be patched. */
+    rom_magic = pci_get_word(ptr);
+    if (rom_magic != 0xaa55) {
+        PCI_DPRINTF("Bad ROM magic %04x\n", rom_magic);
+        return;
+    }
+    pcir_offset = pci_get_word(ptr + 0x18);
+    if (pcir_offset + 8 >= size || memcmp(ptr + pcir_offset, "PCIR", 4)) {
+        PCI_DPRINTF("Bad PCIR offset 0x%x or signature\n", pcir_offset);
+        return;
+    }
+
+    vendor_id = pci_get_word(pdev->config + PCI_VENDOR_ID);
+    device_id = pci_get_word(pdev->config + PCI_DEVICE_ID);
+    rom_vendor_id = pci_get_word(ptr + pcir_offset + 4);
+    rom_device_id = pci_get_word(ptr + pcir_offset + 6);
+
+    PCI_DPRINTF("%s: ROM id %04x%04x / PCI id %04x%04x\n", pdev->romfile,
+                vendor_id, device_id, rom_vendor_id, rom_device_id);
+
+    checksum = ptr[6];
+
+    if (vendor_id != rom_vendor_id) {
+        /* Patch vendor id and checksum (at offset 6 for etherboot roms). */
+        checksum += (uint8_t)rom_vendor_id + (uint8_t)(rom_vendor_id >> 8);
+        checksum -= (uint8_t)vendor_id + (uint8_t)(vendor_id >> 8);
+        PCI_DPRINTF("ROM checksum %02x / %02x\n", ptr[6], checksum);
+        ptr[6] = checksum;
+        pci_set_word(ptr + pcir_offset + 4, vendor_id);
+    }
+
+    if (device_id != rom_device_id) {
+        /* Patch device id and checksum (at offset 6 for etherboot roms). */
+        checksum += (uint8_t)rom_device_id + (uint8_t)(rom_device_id >> 8);
+        checksum -= (uint8_t)device_id + (uint8_t)(device_id >> 8);
+        PCI_DPRINTF("ROM checksum %02x / %02x\n", ptr[6], checksum);
+        ptr[6] = checksum;
+        pci_set_word(ptr + pcir_offset + 6, device_id);
+    }
+}
+
+/* Add an option rom for the device */
+static void pci_add_option_rom(PCIDevice *pdev, bool is_default_rom,
+                               Error **errp)
+{
+    int size;
+    char *path;
+    void *ptr;
+    char name[32];
+    const VMStateDescription *vmsd;
+
+    if (!pdev->romfile)
+        return;
+    if (strlen(pdev->romfile) == 0)
+        return;
+
+    if (!pdev->rom_bar) {
+        /*
+         * Load rom via fw_cfg instead of creating a rom bar,
+         * for 0.11 compatibility.
+         */
+        int class = pci_get_word(pdev->config + PCI_CLASS_DEVICE);
+
+        /*
+         * Hot-plugged devices can't use the option ROM
+         * if the rom bar is disabled.
+         */
+        if (DEVICE(pdev)->hotplugged) {
+            error_setg(errp, "Hot-plugged device without ROM bar"
+                       " can't have an option ROM");
+            return;
+        }
+
+        if (class == 0x0300) {
+            rom_add_vga(pdev->romfile);
+        } else {
+            rom_add_option(pdev->romfile, -1);
+        }
+        return;
+    }
+
+    path = qemu_find_file(QEMU_FILE_TYPE_BIOS, pdev->romfile);
+    if (path == NULL) {
+        path = g_strdup(pdev->romfile);
+    }
+
+    size = get_image_size(path);
+    if (size < 0) {
+        error_setg(errp, "failed to find romfile \"%s\"", pdev->romfile);
+        g_free(path);
+        return;
+    } else if (size == 0) {
+        error_setg(errp, "romfile \"%s\" is empty", pdev->romfile);
+        g_free(path);
+        return;
+    }
+    if (size & (size - 1)) {
+        size = 1 << qemu_fls(size);
+    }
+
+    vmsd = qdev_get_vmsd(DEVICE(pdev));
+
+    if (vmsd) {
+        snprintf(name, sizeof(name), "%s.rom", vmsd->name);
+    } else {
+        snprintf(name, sizeof(name), "%s.rom", object_get_typename(OBJECT(pdev)));
+    }
+    pdev->has_rom = true;
+    memory_region_init_ram(&pdev->rom, OBJECT(pdev), name, size, &error_abort);
+    vmstate_register_ram(&pdev->rom, &pdev->qdev);
+    ptr = memory_region_get_ram_ptr(&pdev->rom);
+    load_image(path, ptr);
+    g_free(path);
+
+    if (is_default_rom) {
+        /* Only the default rom images will be patched (if needed). */
+        pci_patch_ids(pdev, ptr, size);
+    }
+
+    pci_register_bar(pdev, PCI_ROM_SLOT, 0, &pdev->rom);
+}
+
+static void pci_del_option_rom(PCIDevice *pdev)
+{
+    if (!pdev->has_rom)
+        return;
+
+    vmstate_unregister_ram(&pdev->rom, &pdev->qdev);
+    pdev->has_rom = false;
+}
+
+/*
+ * if offset = 0,
+ * Find and reserve space and add capability to the linked list
+ * in pci config space
+ */
+int pci_add_capability(PCIDevice *pdev, uint8_t cap_id,
+                       uint8_t offset, uint8_t size)
+{
+    int ret;
+    Error *local_err = NULL;
+
+    ret = pci_add_capability2(pdev, cap_id, offset, size, &local_err);
+    if (local_err) {
+        assert(ret < 0);
+        error_report_err(local_err);
+    } else {
+        /* success implies a positive offset in config space */
+        assert(ret > 0);
+    }
+    return ret;
+}
+
+int pci_add_capability2(PCIDevice *pdev, uint8_t cap_id,
+                       uint8_t offset, uint8_t size,
+                       Error **errp)
+{
+    uint8_t *config;
+    int i, overlapping_cap;
+
+    if (!offset) {
+        offset = pci_find_space(pdev, size);
+        if (!offset) {
+            error_setg(errp, "out of PCI config space");
+            return -ENOSPC;
+        }
+    } else {
+        /* Verify that capabilities don't overlap.  Note: device assignment
+         * depends on this check to verify that the device is not broken.
+         * Should never trigger for emulated devices, but it's helpful
+         * for debugging these. */
+        for (i = offset; i < offset + size; i++) {
+            overlapping_cap = pci_find_capability_at_offset(pdev, i);
+            if (overlapping_cap) {
+                error_setg(errp, "%s:%02x:%02x.%x "
+                           "Attempt to add PCI capability %x at offset "
+                           "%x overlaps existing capability %x at offset %x",
+                           pci_root_bus_path(pdev), pci_bus_num(pdev->bus),
+                           PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn),
+                           cap_id, offset, overlapping_cap, i);
+                return -EINVAL;
+            }
+        }
+    }
+
+    config = pdev->config + offset;
+    config[PCI_CAP_LIST_ID] = cap_id;
+    config[PCI_CAP_LIST_NEXT] = pdev->config[PCI_CAPABILITY_LIST];
+    pdev->config[PCI_CAPABILITY_LIST] = offset;
+    pdev->config[PCI_STATUS] |= PCI_STATUS_CAP_LIST;
+    memset(pdev->used + offset, 0xFF, QEMU_ALIGN_UP(size, 4));
+    /* Make capability read-only by default */
+    memset(pdev->wmask + offset, 0, size);
+    /* Check capability by default */
+    memset(pdev->cmask + offset, 0xFF, size);
+    return offset;
+}
+
+/* Unlink capability from the pci config space. */
+void pci_del_capability(PCIDevice *pdev, uint8_t cap_id, uint8_t size)
+{
+    uint8_t prev, offset = pci_find_capability_list(pdev, cap_id, &prev);
+    if (!offset)
+        return;
+    pdev->config[prev] = pdev->config[offset + PCI_CAP_LIST_NEXT];
+    /* Make capability writable again */
+    memset(pdev->wmask + offset, 0xff, size);
+    memset(pdev->w1cmask + offset, 0, size);
+    /* Clear cmask as device-specific registers can't be checked */
+    memset(pdev->cmask + offset, 0, size);
+    memset(pdev->used + offset, 0, QEMU_ALIGN_UP(size, 4));
+
+    if (!pdev->config[PCI_CAPABILITY_LIST])
+        pdev->config[PCI_STATUS] &= ~PCI_STATUS_CAP_LIST;
+}
+
+uint8_t pci_find_capability(PCIDevice *pdev, uint8_t cap_id)
+{
+    return pci_find_capability_list(pdev, cap_id, NULL);
+}
+
+static void pcibus_dev_print(Monitor *mon, DeviceState *dev, int indent)
+{
+    PCIDevice *d = (PCIDevice *)dev;
+    const pci_class_desc *desc;
+    char ctxt[64];
+    PCIIORegion *r;
+    int i, class;
+
+    class = pci_get_word(d->config + PCI_CLASS_DEVICE);
+    desc = pci_class_descriptions;
+    while (desc->desc && class != desc->class)
+        desc++;
+    if (desc->desc) {
+        snprintf(ctxt, sizeof(ctxt), "%s", desc->desc);
+    } else {
+        snprintf(ctxt, sizeof(ctxt), "Class %04x", class);
+    }
+
+    monitor_printf(mon, "%*sclass %s, addr %02x:%02x.%x, "
+                   "pci id %04x:%04x (sub %04x:%04x)\n",
+                   indent, "", ctxt, pci_bus_num(d->bus),
+                   PCI_SLOT(d->devfn), PCI_FUNC(d->devfn),
+                   pci_get_word(d->config + PCI_VENDOR_ID),
+                   pci_get_word(d->config + PCI_DEVICE_ID),
+                   pci_get_word(d->config + PCI_SUBSYSTEM_VENDOR_ID),
+                   pci_get_word(d->config + PCI_SUBSYSTEM_ID));
+    for (i = 0; i < PCI_NUM_REGIONS; i++) {
+        r = &d->io_regions[i];
+        if (!r->size)
+            continue;
+        monitor_printf(mon, "%*sbar %d: %s at 0x%"FMT_PCIBUS
+                       " [0x%"FMT_PCIBUS"]\n",
+                       indent, "",
+                       i, r->type & PCI_BASE_ADDRESS_SPACE_IO ? "i/o" : "mem",
+                       r->addr, r->addr + r->size - 1);
+    }
+}
+
+static char *pci_dev_fw_name(DeviceState *dev, char *buf, int len)
+{
+    PCIDevice *d = (PCIDevice *)dev;
+    const char *name = NULL;
+    const pci_class_desc *desc =  pci_class_descriptions;
+    int class = pci_get_word(d->config + PCI_CLASS_DEVICE);
+
+    while (desc->desc &&
+          (class & ~desc->fw_ign_bits) !=
+          (desc->class & ~desc->fw_ign_bits)) {
+        desc++;
+    }
+
+    if (desc->desc) {
+        name = desc->fw_name;
+    }
+
+    if (name) {
+        pstrcpy(buf, len, name);
+    } else {
+        snprintf(buf, len, "pci%04x,%04x",
+                 pci_get_word(d->config + PCI_VENDOR_ID),
+                 pci_get_word(d->config + PCI_DEVICE_ID));
+    }
+
+    return buf;
+}
+
+static char *pcibus_get_fw_dev_path(DeviceState *dev)
+{
+    PCIDevice *d = (PCIDevice *)dev;
+    char path[50], name[33];
+    int off;
+
+    off = snprintf(path, sizeof(path), "%s@%x",
+                   pci_dev_fw_name(dev, name, sizeof name),
+                   PCI_SLOT(d->devfn));
+    if (PCI_FUNC(d->devfn))
+        snprintf(path + off, sizeof(path) + off, ",%x", PCI_FUNC(d->devfn));
+    return g_strdup(path);
+}
+
+static char *pcibus_get_dev_path(DeviceState *dev)
+{
+    PCIDevice *d = container_of(dev, PCIDevice, qdev);
+    PCIDevice *t;
+    int slot_depth;
+    /* Path format: Domain:00:Slot.Function:Slot.Function....:Slot.Function.
+     * 00 is added here to make this format compatible with
+     * domain:Bus:Slot.Func for systems without nested PCI bridges.
+     * Slot.Function list specifies the slot and function numbers for all
+     * devices on the path from root to the specific device. */
+    const char *root_bus_path;
+    int root_bus_len;
+    char slot[] = ":SS.F";
+    int slot_len = sizeof slot - 1 /* For '\0' */;
+    int path_len;
+    char *path, *p;
+    int s;
+
+    root_bus_path = pci_root_bus_path(d);
+    root_bus_len = strlen(root_bus_path);
+
+    /* Calculate # of slots on path between device and root. */;
+    slot_depth = 0;
+    for (t = d; t; t = t->bus->parent_dev) {
+        ++slot_depth;
+    }
+
+    path_len = root_bus_len + slot_len * slot_depth;
+
+    /* Allocate memory, fill in the terminating null byte. */
+    path = g_malloc(path_len + 1 /* For '\0' */);
+    path[path_len] = '\0';
+
+    memcpy(path, root_bus_path, root_bus_len);
+
+    /* Fill in slot numbers. We walk up from device to root, so need to print
+     * them in the reverse order, last to first. */
+    p = path + path_len;
+    for (t = d; t; t = t->bus->parent_dev) {
+        p -= slot_len;
+        s = snprintf(slot, sizeof slot, ":%02x.%x",
+                     PCI_SLOT(t->devfn), PCI_FUNC(t->devfn));
+        assert(s == slot_len);
+        memcpy(p, slot, slot_len);
+    }
+
+    return path;
+}
+
+static int pci_qdev_find_recursive(PCIBus *bus,
+                                   const char *id, PCIDevice **pdev)
+{
+    DeviceState *qdev = qdev_find_recursive(&bus->qbus, id);
+    if (!qdev) {
+        return -ENODEV;
+    }
+
+    /* roughly check if given qdev is pci device */
+    if (object_dynamic_cast(OBJECT(qdev), TYPE_PCI_DEVICE)) {
+        *pdev = PCI_DEVICE(qdev);
+        return 0;
+    }
+    return -EINVAL;
+}
+
+int pci_qdev_find_device(const char *id, PCIDevice **pdev)
+{
+    PCIHostState *host_bridge;
+    int rc = -ENODEV;
+
+    QLIST_FOREACH(host_bridge, &pci_host_bridges, next) {
+        int tmp = pci_qdev_find_recursive(host_bridge->bus, id, pdev);
+        if (!tmp) {
+            rc = 0;
+            break;
+        }
+        if (tmp != -ENODEV) {
+            rc = tmp;
+        }
+    }
+
+    return rc;
+}
+
+MemoryRegion *pci_address_space(PCIDevice *dev)
+{
+    return dev->bus->address_space_mem;
+}
+
+MemoryRegion *pci_address_space_io(PCIDevice *dev)
+{
+    return dev->bus->address_space_io;
+}
+
+static void pci_device_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *k = DEVICE_CLASS(klass);
+    PCIDeviceClass *pc = PCI_DEVICE_CLASS(klass);
+
+    k->realize = pci_qdev_realize;
+    k->unrealize = pci_qdev_unrealize;
+    k->bus_type = TYPE_PCI_BUS;
+    k->props = pci_props;
+    pc->realize = pci_default_realize;
+}
+
+AddressSpace *pci_device_iommu_address_space(PCIDevice *dev)
+{
+    PCIBus *bus = PCI_BUS(dev->bus);
+
+    if (bus->iommu_fn) {
+        return bus->iommu_fn(bus, bus->iommu_opaque, dev->devfn);
+    }
+
+    if (bus->parent_dev) {
+        /** We are ignoring the bus master DMA bit of the bridge
+         *  as it would complicate things such as VFIO for no good reason */
+        return pci_device_iommu_address_space(bus->parent_dev);
+    }
+
+    return &address_space_memory;
+}
+
+void pci_setup_iommu(PCIBus *bus, PCIIOMMUFunc fn, void *opaque)
+{
+    bus->iommu_fn = fn;
+    bus->iommu_opaque = opaque;
+}
+
+static void pci_dev_get_w64(PCIBus *b, PCIDevice *dev, void *opaque)
+{
+    Range *range = opaque;
+    PCIDeviceClass *pc = PCI_DEVICE_GET_CLASS(dev);
+    uint16_t cmd = pci_get_word(dev->config + PCI_COMMAND);
+    int i;
+
+    if (!(cmd & PCI_COMMAND_MEMORY)) {
+        return;
+    }
+
+    if (pc->is_bridge) {
+        pcibus_t base = pci_bridge_get_base(dev, PCI_BASE_ADDRESS_MEM_PREFETCH);
+        pcibus_t limit = pci_bridge_get_limit(dev, PCI_BASE_ADDRESS_MEM_PREFETCH);
+
+        base = MAX(base, 0x1ULL << 32);
+
+        if (limit >= base) {
+            Range pref_range;
+            pref_range.begin = base;
+            pref_range.end = limit + 1;
+            range_extend(range, &pref_range);
+        }
+    }
+    for (i = 0; i < PCI_NUM_REGIONS; ++i) {
+        PCIIORegion *r = &dev->io_regions[i];
+        Range region_range;
+
+        if (!r->size ||
+            (r->type & PCI_BASE_ADDRESS_SPACE_IO) ||
+            !(r->type & PCI_BASE_ADDRESS_MEM_TYPE_64)) {
+            continue;
+        }
+        region_range.begin = pci_bar_address(dev, i, r->type, r->size);
+        region_range.end = region_range.begin + r->size;
+
+        if (region_range.begin == PCI_BAR_UNMAPPED) {
+            continue;
+        }
+
+        region_range.begin = MAX(region_range.begin, 0x1ULL << 32);
+
+        if (region_range.end - 1 >= region_range.begin) {
+            range_extend(range, &region_range);
+        }
+    }
+}
+
+void pci_bus_get_w64_range(PCIBus *bus, Range *range)
+{
+    range->begin = range->end = 0;
+    pci_for_each_device_under_bus(bus, pci_dev_get_w64, range);
+}
+
+static const TypeInfo pci_device_type_info = {
+    .name = TYPE_PCI_DEVICE,
+    .parent = TYPE_DEVICE,
+    .instance_size = sizeof(PCIDevice),
+    .abstract = true,
+    .class_size = sizeof(PCIDeviceClass),
+    .class_init = pci_device_class_init,
+};
+
+static void pci_register_types(void)
+{
+    type_register_static(&pci_bus_info);
+    type_register_static(&pcie_bus_info);
+    type_register_static(&pci_device_type_info);
+}
+
+type_init(pci_register_types)
diff --git a/qemu/hw/pci/pci_bridge.c b/qemu/hw/pci/pci_bridge.c
new file mode 100644
index 000000000..40c97b155
--- /dev/null
+++ b/qemu/hw/pci/pci_bridge.c
@@ -0,0 +1,419 @@
+/*
+ * QEMU PCI bus manager
+ *
+ * Copyright (c) 2004 Fabrice Bellard
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to dea
+
+ * in the Software without restriction, including without limitation the rights
+ * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+ * copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM
+
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+ * THE SOFTWARE.
+ */
+/*
+ * split out from pci.c
+ * Copyright (c) 2010 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ */
+
+#include "hw/pci/pci_bridge.h"
+#include "hw/pci/pci_bus.h"
+#include "qemu/range.h"
+
+/* PCI bridge subsystem vendor ID helper functions */
+#define PCI_SSVID_SIZEOF        8
+#define PCI_SSVID_SVID          4
+#define PCI_SSVID_SSID          6
+
+int pci_bridge_ssvid_init(PCIDevice *dev, uint8_t offset,
+                          uint16_t svid, uint16_t ssid)
+{
+    int pos;
+    pos = pci_add_capability(dev, PCI_CAP_ID_SSVID, offset, PCI_SSVID_SIZEOF);
+    if (pos < 0) {
+        return pos;
+    }
+
+    pci_set_word(dev->config + pos + PCI_SSVID_SVID, svid);
+    pci_set_word(dev->config + pos + PCI_SSVID_SSID, ssid);
+    return pos;
+}
+
+/* Accessor function to get parent bridge device from pci bus. */
+PCIDevice *pci_bridge_get_device(PCIBus *bus)
+{
+    return bus->parent_dev;
+}
+
+/* Accessor function to get secondary bus from pci-to-pci bridge device */
+PCIBus *pci_bridge_get_sec_bus(PCIBridge *br)
+{
+    return &br->sec_bus;
+}
+
+static uint32_t pci_config_get_io_base(const PCIDevice *d,
+                                       uint32_t base, uint32_t base_upper16)
+{
+    uint32_t val;
+
+    val = ((uint32_t)d->config[base] & PCI_IO_RANGE_MASK) << 8;
+    if (d->config[base] & PCI_IO_RANGE_TYPE_32) {
+        val |= (uint32_t)pci_get_word(d->config + base_upper16) << 16;
+    }
+    return val;
+}
+
+static pcibus_t pci_config_get_memory_base(const PCIDevice *d, uint32_t base)
+{
+    return ((pcibus_t)pci_get_word(d->config + base) & PCI_MEMORY_RANGE_MASK)
+        << 16;
+}
+
+static pcibus_t pci_config_get_pref_base(const PCIDevice *d,
+                                         uint32_t base, uint32_t upper)
+{
+    pcibus_t tmp;
+    pcibus_t val;
+
+    tmp = (pcibus_t)pci_get_word(d->config + base);
+    val = (tmp & PCI_PREF_RANGE_MASK) << 16;
+    if (tmp & PCI_PREF_RANGE_TYPE_64) {
+        val |= (pcibus_t)pci_get_long(d->config + upper) << 32;
+    }
+    return val;
+}
+
+/* accessor function to get bridge filtering base address */
+pcibus_t pci_bridge_get_base(const PCIDevice *bridge, uint8_t type)
+{
+    pcibus_t base;
+    if (type & PCI_BASE_ADDRESS_SPACE_IO) {
+        base = pci_config_get_io_base(bridge,
+                                      PCI_IO_BASE, PCI_IO_BASE_UPPER16);
+    } else {
+        if (type & PCI_BASE_ADDRESS_MEM_PREFETCH) {
+            base = pci_config_get_pref_base(
+                bridge, PCI_PREF_MEMORY_BASE, PCI_PREF_BASE_UPPER32);
+        } else {
+            base = pci_config_get_memory_base(bridge, PCI_MEMORY_BASE);
+        }
+    }
+
+    return base;
+}
+
+/* accessor funciton to get bridge filtering limit */
+pcibus_t pci_bridge_get_limit(const PCIDevice *bridge, uint8_t type)
+{
+    pcibus_t limit;
+    if (type & PCI_BASE_ADDRESS_SPACE_IO) {
+        limit = pci_config_get_io_base(bridge,
+                                      PCI_IO_LIMIT, PCI_IO_LIMIT_UPPER16);
+        limit |= 0xfff;         /* PCI bridge spec 3.2.5.6. */
+    } else {
+        if (type & PCI_BASE_ADDRESS_MEM_PREFETCH) {
+            limit = pci_config_get_pref_base(
+                bridge, PCI_PREF_MEMORY_LIMIT, PCI_PREF_LIMIT_UPPER32);
+        } else {
+            limit = pci_config_get_memory_base(bridge, PCI_MEMORY_LIMIT);
+        }
+        limit |= 0xfffff;       /* PCI bridge spec 3.2.5.{1, 8}. */
+    }
+    return limit;
+}
+
+static void pci_bridge_init_alias(PCIBridge *bridge, MemoryRegion *alias,
+                                  uint8_t type, const char *name,
+                                  MemoryRegion *space,
+                                  MemoryRegion *parent_space,
+                                  bool enabled)
+{
+    PCIDevice *bridge_dev = PCI_DEVICE(bridge);
+    pcibus_t base = pci_bridge_get_base(bridge_dev, type);
+    pcibus_t limit = pci_bridge_get_limit(bridge_dev, type);
+    /* TODO: this doesn't handle base = 0 limit = 2^64 - 1 correctly.
+     * Apparently no way to do this with existing memory APIs. */
+    pcibus_t size = enabled && limit >= base ? limit + 1 - base : 0;
+
+    memory_region_init_alias(alias, OBJECT(bridge), name, space, base, size);
+    memory_region_add_subregion_overlap(parent_space, base, alias, 1);
+}
+
+static void pci_bridge_init_vga_aliases(PCIBridge *br, PCIBus *parent,
+                                        MemoryRegion *alias_vga)
+{
+    PCIDevice *pd = PCI_DEVICE(br);
+    uint16_t brctl = pci_get_word(pd->config + PCI_BRIDGE_CONTROL);
+
+    memory_region_init_alias(&alias_vga[QEMU_PCI_VGA_IO_LO], OBJECT(br),
+                             "pci_bridge_vga_io_lo", &br->address_space_io,
+                             QEMU_PCI_VGA_IO_LO_BASE, QEMU_PCI_VGA_IO_LO_SIZE);
+    memory_region_init_alias(&alias_vga[QEMU_PCI_VGA_IO_HI], OBJECT(br),
+                             "pci_bridge_vga_io_hi", &br->address_space_io,
+                             QEMU_PCI_VGA_IO_HI_BASE, QEMU_PCI_VGA_IO_HI_SIZE);
+    memory_region_init_alias(&alias_vga[QEMU_PCI_VGA_MEM], OBJECT(br),
+                             "pci_bridge_vga_mem", &br->address_space_mem,
+                             QEMU_PCI_VGA_MEM_BASE, QEMU_PCI_VGA_MEM_SIZE);
+
+    if (brctl & PCI_BRIDGE_CTL_VGA) {
+        pci_register_vga(pd, &alias_vga[QEMU_PCI_VGA_MEM],
+                         &alias_vga[QEMU_PCI_VGA_IO_LO],
+                         &alias_vga[QEMU_PCI_VGA_IO_HI]);
+    }
+}
+
+static PCIBridgeWindows *pci_bridge_region_init(PCIBridge *br)
+{
+    PCIDevice *pd = PCI_DEVICE(br);
+    PCIBus *parent = pd->bus;
+    PCIBridgeWindows *w = g_new(PCIBridgeWindows, 1);
+    uint16_t cmd = pci_get_word(pd->config + PCI_COMMAND);
+
+    pci_bridge_init_alias(br, &w->alias_pref_mem,
+                          PCI_BASE_ADDRESS_MEM_PREFETCH,
+                          "pci_bridge_pref_mem",
+                          &br->address_space_mem,
+                          parent->address_space_mem,
+                          cmd & PCI_COMMAND_MEMORY);
+    pci_bridge_init_alias(br, &w->alias_mem,
+                          PCI_BASE_ADDRESS_SPACE_MEMORY,
+                          "pci_bridge_mem",
+                          &br->address_space_mem,
+                          parent->address_space_mem,
+                          cmd & PCI_COMMAND_MEMORY);
+    pci_bridge_init_alias(br, &w->alias_io,
+                          PCI_BASE_ADDRESS_SPACE_IO,
+                          "pci_bridge_io",
+                          &br->address_space_io,
+                          parent->address_space_io,
+                          cmd & PCI_COMMAND_IO);
+
+    pci_bridge_init_vga_aliases(br, parent, w->alias_vga);
+
+    return w;
+}
+
+static void pci_bridge_region_del(PCIBridge *br, PCIBridgeWindows *w)
+{
+    PCIDevice *pd = PCI_DEVICE(br);
+    PCIBus *parent = pd->bus;
+
+    memory_region_del_subregion(parent->address_space_io, &w->alias_io);
+    memory_region_del_subregion(parent->address_space_mem, &w->alias_mem);
+    memory_region_del_subregion(parent->address_space_mem, &w->alias_pref_mem);
+    pci_unregister_vga(pd);
+}
+
+static void pci_bridge_region_cleanup(PCIBridge *br, PCIBridgeWindows *w)
+{
+    object_unparent(OBJECT(&w->alias_io));
+    object_unparent(OBJECT(&w->alias_mem));
+    object_unparent(OBJECT(&w->alias_pref_mem));
+    object_unparent(OBJECT(&w->alias_vga[QEMU_PCI_VGA_IO_LO]));
+    object_unparent(OBJECT(&w->alias_vga[QEMU_PCI_VGA_IO_HI]));
+    object_unparent(OBJECT(&w->alias_vga[QEMU_PCI_VGA_MEM]));
+    g_free(w);
+}
+
+void pci_bridge_update_mappings(PCIBridge *br)
+{
+    PCIBridgeWindows *w = br->windows;
+
+    /* Make updates atomic to: handle the case of one VCPU updating the bridge
+     * while another accesses an unaffected region. */
+    memory_region_transaction_begin();
+    pci_bridge_region_del(br, br->windows);
+    br->windows = pci_bridge_region_init(br);
+    memory_region_transaction_commit();
+    pci_bridge_region_cleanup(br, w);
+}
+
+/* default write_config function for PCI-to-PCI bridge */
+void pci_bridge_write_config(PCIDevice *d,
+                             uint32_t address, uint32_t val, int len)
+{
+    PCIBridge *s = PCI_BRIDGE(d);
+    uint16_t oldctl = pci_get_word(d->config + PCI_BRIDGE_CONTROL);
+    uint16_t newctl;
+
+    pci_default_write_config(d, address, val, len);
+
+    if (ranges_overlap(address, len, PCI_COMMAND, 2) ||
+
+        /* io base/limit */
+        ranges_overlap(address, len, PCI_IO_BASE, 2) ||
+
+        /* memory base/limit, prefetchable base/limit and
+           io base/limit upper 16 */
+        ranges_overlap(address, len, PCI_MEMORY_BASE, 20) ||
+
+        /* vga enable */
+        ranges_overlap(address, len, PCI_BRIDGE_CONTROL, 2)) {
+        pci_bridge_update_mappings(s);
+    }
+
+    newctl = pci_get_word(d->config + PCI_BRIDGE_CONTROL);
+    if (~oldctl & newctl & PCI_BRIDGE_CTL_BUS_RESET) {
+        /* Trigger hot reset on 0->1 transition. */
+        qbus_reset_all(&s->sec_bus.qbus);
+    }
+}
+
+void pci_bridge_disable_base_limit(PCIDevice *dev)
+{
+    uint8_t *conf = dev->config;
+
+    pci_byte_test_and_set_mask(conf + PCI_IO_BASE,
+                               PCI_IO_RANGE_MASK & 0xff);
+    pci_byte_test_and_clear_mask(conf + PCI_IO_LIMIT,
+                                 PCI_IO_RANGE_MASK & 0xff);
+    pci_word_test_and_set_mask(conf + PCI_MEMORY_BASE,
+                               PCI_MEMORY_RANGE_MASK & 0xffff);
+    pci_word_test_and_clear_mask(conf + PCI_MEMORY_LIMIT,
+                                 PCI_MEMORY_RANGE_MASK & 0xffff);
+    pci_word_test_and_set_mask(conf + PCI_PREF_MEMORY_BASE,
+                               PCI_PREF_RANGE_MASK & 0xffff);
+    pci_word_test_and_clear_mask(conf + PCI_PREF_MEMORY_LIMIT,
+                                 PCI_PREF_RANGE_MASK & 0xffff);
+    pci_set_long(conf + PCI_PREF_BASE_UPPER32, 0);
+    pci_set_long(conf + PCI_PREF_LIMIT_UPPER32, 0);
+}
+
+/* reset bridge specific configuration registers */
+void pci_bridge_reset(DeviceState *qdev)
+{
+    PCIDevice *dev = PCI_DEVICE(qdev);
+    uint8_t *conf = dev->config;
+
+    conf[PCI_PRIMARY_BUS] = 0;
+    conf[PCI_SECONDARY_BUS] = 0;
+    conf[PCI_SUBORDINATE_BUS] = 0;
+    conf[PCI_SEC_LATENCY_TIMER] = 0;
+
+    /*
+     * the default values for base/limit registers aren't specified
+     * in the PCI-to-PCI-bridge spec. So we don't thouch them here.
+     * Each implementation can override it.
+     * typical implementation does
+     * zero base/limit registers or
+     * disable forwarding: pci_bridge_disable_base_limit()
+     * If disable forwarding is wanted, call pci_bridge_disable_base_limit()
+     * after this function.
+     */
+    pci_byte_test_and_clear_mask(conf + PCI_IO_BASE,
+                                 PCI_IO_RANGE_MASK & 0xff);
+    pci_byte_test_and_clear_mask(conf + PCI_IO_LIMIT,
+                                 PCI_IO_RANGE_MASK & 0xff);
+    pci_word_test_and_clear_mask(conf + PCI_MEMORY_BASE,
+                                 PCI_MEMORY_RANGE_MASK & 0xffff);
+    pci_word_test_and_clear_mask(conf + PCI_MEMORY_LIMIT,
+                                 PCI_MEMORY_RANGE_MASK & 0xffff);
+    pci_word_test_and_clear_mask(conf + PCI_PREF_MEMORY_BASE,
+                                 PCI_PREF_RANGE_MASK & 0xffff);
+    pci_word_test_and_clear_mask(conf + PCI_PREF_MEMORY_LIMIT,
+                                 PCI_PREF_RANGE_MASK & 0xffff);
+    pci_set_long(conf + PCI_PREF_BASE_UPPER32, 0);
+    pci_set_long(conf + PCI_PREF_LIMIT_UPPER32, 0);
+
+    pci_set_word(conf + PCI_BRIDGE_CONTROL, 0);
+}
+
+/* default qdev initialization function for PCI-to-PCI bridge */
+int pci_bridge_initfn(PCIDevice *dev, const char *typename)
+{
+    PCIBus *parent = dev->bus;
+    PCIBridge *br = PCI_BRIDGE(dev);
+    PCIBus *sec_bus = &br->sec_bus;
+
+    pci_word_test_and_set_mask(dev->config + PCI_STATUS,
+                               PCI_STATUS_66MHZ | PCI_STATUS_FAST_BACK);
+
+    /*
+     * TODO: We implement VGA Enable in the Bridge Control Register
+     * therefore per the PCI to PCI bridge spec we must also implement
+     * VGA Palette Snooping.  When done, set this bit writable:
+     *
+     * pci_word_test_and_set_mask(dev->wmask + PCI_COMMAND,
+     *                            PCI_COMMAND_VGA_PALETTE);
+     */
+
+    pci_config_set_class(dev->config, PCI_CLASS_BRIDGE_PCI);
+    dev->config[PCI_HEADER_TYPE] =
+        (dev->config[PCI_HEADER_TYPE] & PCI_HEADER_TYPE_MULTI_FUNCTION) |
+        PCI_HEADER_TYPE_BRIDGE;
+    pci_set_word(dev->config + PCI_SEC_STATUS,
+                 PCI_STATUS_66MHZ | PCI_STATUS_FAST_BACK);
+
+    /*
+     * If we don't specify the name, the bus will be addressed as <id>.0, where
+     * id is the device id.
+     * Since PCI Bridge devices have a single bus each, we don't need the index:
+     * let users address the bus using the device name.
+     */
+    if (!br->bus_name && dev->qdev.id && *dev->qdev.id) {
+	    br->bus_name = dev->qdev.id;
+    }
+
+    qbus_create_inplace(sec_bus, sizeof(br->sec_bus), typename, DEVICE(dev),
+                        br->bus_name);
+    sec_bus->parent_dev = dev;
+    sec_bus->map_irq = br->map_irq ? br->map_irq : pci_swizzle_map_irq_fn;
+    sec_bus->address_space_mem = &br->address_space_mem;
+    memory_region_init(&br->address_space_mem, OBJECT(br), "pci_bridge_pci", UINT64_MAX);
+    sec_bus->address_space_io = &br->address_space_io;
+    memory_region_init(&br->address_space_io, OBJECT(br), "pci_bridge_io", 65536);
+    br->windows = pci_bridge_region_init(br);
+    QLIST_INIT(&sec_bus->child);
+    QLIST_INSERT_HEAD(&parent->child, sec_bus, sibling);
+    return 0;
+}
+
+/* default qdev clean up function for PCI-to-PCI bridge */
+void pci_bridge_exitfn(PCIDevice *pci_dev)
+{
+    PCIBridge *s = PCI_BRIDGE(pci_dev);
+    assert(QLIST_EMPTY(&s->sec_bus.child));
+    QLIST_REMOVE(&s->sec_bus, sibling);
+    pci_bridge_region_del(s, s->windows);
+    pci_bridge_region_cleanup(s, s->windows);
+    /* object_unparent() is called automatically during device deletion */
+}
+
+/*
+ * before qdev initialization(qdev_init()), this function sets bus_name and
+ * map_irq callback which are necessry for pci_bridge_initfn() to
+ * initialize bus.
+ */
+void pci_bridge_map_irq(PCIBridge *br, const char* bus_name,
+                        pci_map_irq_fn map_irq)
+{
+    br->map_irq = map_irq;
+    br->bus_name = bus_name;
+}
+
+static const TypeInfo pci_bridge_type_info = {
+    .name = TYPE_PCI_BRIDGE,
+    .parent = TYPE_PCI_DEVICE,
+    .instance_size = sizeof(PCIBridge),
+    .abstract = true,
+};
+
+static void pci_bridge_register_types(void)
+{
+    type_register_static(&pci_bridge_type_info);
+}
+
+type_init(pci_bridge_register_types)
diff --git a/qemu/hw/pci/pci_host.c b/qemu/hw/pci/pci_host.c
new file mode 100644
index 000000000..3e26f9256
--- /dev/null
+++ b/qemu/hw/pci/pci_host.c
@@ -0,0 +1,191 @@
+/*
+ * pci_host.c
+ *
+ * Copyright (c) 2009 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+
+ * 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/>.
+ */
+
+#include "hw/pci/pci.h"
+#include "hw/pci/pci_host.h"
+#include "trace.h"
+
+/* debug PCI */
+//#define DEBUG_PCI
+
+#ifdef DEBUG_PCI
+#define PCI_DPRINTF(fmt, ...) \
+do { printf("pci_host_data: " fmt , ## __VA_ARGS__); } while (0)
+#else
+#define PCI_DPRINTF(fmt, ...)
+#endif
+
+/*
+ * PCI address
+ * bit 16 - 24: bus number
+ * bit  8 - 15: devfun number
+ * bit  0 -  7: offset in configuration space of a given pci device
+ */
+
+/* the helper function to get a PCIDevice* for a given pci address */
+static inline PCIDevice *pci_dev_find_by_addr(PCIBus *bus, uint32_t addr)
+{
+    uint8_t bus_num = addr >> 16;
+    uint8_t devfn = addr >> 8;
+
+    return pci_find_device(bus, bus_num, devfn);
+}
+
+void pci_host_config_write_common(PCIDevice *pci_dev, uint32_t addr,
+                                  uint32_t limit, uint32_t val, uint32_t len)
+{
+    assert(len <= 4);
+    trace_pci_cfg_write(pci_dev->name, PCI_SLOT(pci_dev->devfn),
+                        PCI_FUNC(pci_dev->devfn), addr, val);
+    pci_dev->config_write(pci_dev, addr, val, MIN(len, limit - addr));
+}
+
+uint32_t pci_host_config_read_common(PCIDevice *pci_dev, uint32_t addr,
+                                     uint32_t limit, uint32_t len)
+{
+    uint32_t ret;
+
+    assert(len <= 4);
+    ret = pci_dev->config_read(pci_dev, addr, MIN(len, limit - addr));
+    trace_pci_cfg_read(pci_dev->name, PCI_SLOT(pci_dev->devfn),
+                       PCI_FUNC(pci_dev->devfn), addr, ret);
+
+    return ret;
+}
+
+void pci_data_write(PCIBus *s, uint32_t addr, uint32_t val, int len)
+{
+    PCIDevice *pci_dev = pci_dev_find_by_addr(s, addr);
+    uint32_t config_addr = addr & (PCI_CONFIG_SPACE_SIZE - 1);
+
+    if (!pci_dev) {
+        return;
+    }
+
+    PCI_DPRINTF("%s: %s: addr=%02" PRIx32 " val=%08" PRIx32 " len=%d\n",
+                __func__, pci_dev->name, config_addr, val, len);
+    pci_host_config_write_common(pci_dev, config_addr, PCI_CONFIG_SPACE_SIZE,
+                                 val, len);
+}
+
+uint32_t pci_data_read(PCIBus *s, uint32_t addr, int len)
+{
+    PCIDevice *pci_dev = pci_dev_find_by_addr(s, addr);
+    uint32_t config_addr = addr & (PCI_CONFIG_SPACE_SIZE - 1);
+    uint32_t val;
+
+    if (!pci_dev) {
+        return ~0x0;
+    }
+
+    val = pci_host_config_read_common(pci_dev, config_addr,
+                                      PCI_CONFIG_SPACE_SIZE, len);
+    PCI_DPRINTF("%s: %s: addr=%02"PRIx32" val=%08"PRIx32" len=%d\n",
+                __func__, pci_dev->name, config_addr, val, len);
+
+    return val;
+}
+
+static void pci_host_config_write(void *opaque, hwaddr addr,
+                                  uint64_t val, unsigned len)
+{
+    PCIHostState *s = opaque;
+
+    PCI_DPRINTF("%s addr " TARGET_FMT_plx " len %d val %"PRIx64"\n",
+                __func__, addr, len, val);
+    if (addr != 0 || len != 4) {
+        return;
+    }
+    s->config_reg = val;
+}
+
+static uint64_t pci_host_config_read(void *opaque, hwaddr addr,
+                                     unsigned len)
+{
+    PCIHostState *s = opaque;
+    uint32_t val = s->config_reg;
+
+    PCI_DPRINTF("%s addr " TARGET_FMT_plx " len %d val %"PRIx32"\n",
+                __func__, addr, len, val);
+    return val;
+}
+
+static void pci_host_data_write(void *opaque, hwaddr addr,
+                                uint64_t val, unsigned len)
+{
+    PCIHostState *s = opaque;
+    PCI_DPRINTF("write addr " TARGET_FMT_plx " len %d val %x\n",
+                addr, len, (unsigned)val);
+    if (s->config_reg & (1u << 31))
+        pci_data_write(s->bus, s->config_reg | (addr & 3), val, len);
+}
+
+static uint64_t pci_host_data_read(void *opaque,
+                                   hwaddr addr, unsigned len)
+{
+    PCIHostState *s = opaque;
+    uint32_t val;
+    if (!(s->config_reg & (1U << 31))) {
+        return 0xffffffff;
+    }
+    val = pci_data_read(s->bus, s->config_reg | (addr & 3), len);
+    PCI_DPRINTF("read addr " TARGET_FMT_plx " len %d val %x\n",
+                addr, len, val);
+    return val;
+}
+
+const MemoryRegionOps pci_host_conf_le_ops = {
+    .read = pci_host_config_read,
+    .write = pci_host_config_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+};
+
+const MemoryRegionOps pci_host_conf_be_ops = {
+    .read = pci_host_config_read,
+    .write = pci_host_config_write,
+    .endianness = DEVICE_BIG_ENDIAN,
+};
+
+const MemoryRegionOps pci_host_data_le_ops = {
+    .read = pci_host_data_read,
+    .write = pci_host_data_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+};
+
+const MemoryRegionOps pci_host_data_be_ops = {
+    .read = pci_host_data_read,
+    .write = pci_host_data_write,
+    .endianness = DEVICE_BIG_ENDIAN,
+};
+
+static const TypeInfo pci_host_type_info = {
+    .name = TYPE_PCI_HOST_BRIDGE,
+    .parent = TYPE_SYS_BUS_DEVICE,
+    .abstract = true,
+    .class_size = sizeof(PCIHostBridgeClass),
+    .instance_size = sizeof(PCIHostState),
+};
+
+static void pci_host_register_types(void)
+{
+    type_register_static(&pci_host_type_info);
+}
+
+type_init(pci_host_register_types)
diff --git a/qemu/hw/pci/pcie.c b/qemu/hw/pci/pcie.c
new file mode 100644
index 000000000..6e28985bd
--- /dev/null
+++ b/qemu/hw/pci/pcie.c
@@ -0,0 +1,634 @@
+/*
+ * pcie.c
+ *
+ * Copyright (c) 2010 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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/>.
+ */
+
+#include "qemu-common.h"
+#include "hw/pci/pci_bridge.h"
+#include "hw/pci/pcie.h"
+#include "hw/pci/msix.h"
+#include "hw/pci/msi.h"
+#include "hw/pci/pci_bus.h"
+#include "hw/pci/pcie_regs.h"
+#include "qemu/range.h"
+
+//#define DEBUG_PCIE
+#ifdef DEBUG_PCIE
+# define PCIE_DPRINTF(fmt, ...)                                         \
+    fprintf(stderr, "%s:%d " fmt, __func__, __LINE__, ## __VA_ARGS__)
+#else
+# define PCIE_DPRINTF(fmt, ...) do {} while (0)
+#endif
+#define PCIE_DEV_PRINTF(dev, fmt, ...)                                  \
+    PCIE_DPRINTF("%s:%x "fmt, (dev)->name, (dev)->devfn, ## __VA_ARGS__)
+
+
+/***************************************************************************
+ * pci express capability helper functions
+ */
+int pcie_cap_init(PCIDevice *dev, uint8_t offset, uint8_t type, uint8_t port)
+{
+    int pos;
+    uint8_t *exp_cap;
+
+    assert(pci_is_express(dev));
+
+    pos = pci_add_capability(dev, PCI_CAP_ID_EXP, offset,
+                                 PCI_EXP_VER2_SIZEOF);
+    if (pos < 0) {
+        return pos;
+    }
+    dev->exp.exp_cap = pos;
+    exp_cap = dev->config + pos;
+
+    /* capability register
+       interrupt message number defaults to 0 */
+    pci_set_word(exp_cap + PCI_EXP_FLAGS,
+                 ((type << PCI_EXP_FLAGS_TYPE_SHIFT) & PCI_EXP_FLAGS_TYPE) |
+                 PCI_EXP_FLAGS_VER2);
+
+    /* device capability register
+     * table 7-12:
+     * roll based error reporting bit must be set by all
+     * Functions conforming to the ECN, PCI Express Base
+     * Specification, Revision 1.1., or subsequent PCI Express Base
+     * Specification revisions.
+     */
+    pci_set_long(exp_cap + PCI_EXP_DEVCAP, PCI_EXP_DEVCAP_RBER);
+
+    pci_set_long(exp_cap + PCI_EXP_LNKCAP,
+                 (port << PCI_EXP_LNKCAP_PN_SHIFT) |
+                 PCI_EXP_LNKCAP_ASPMS_0S |
+                 PCI_EXP_LNK_MLW_1 |
+                 PCI_EXP_LNK_LS_25);
+
+    pci_set_word(exp_cap + PCI_EXP_LNKSTA,
+                 PCI_EXP_LNK_MLW_1 | PCI_EXP_LNK_LS_25 |PCI_EXP_LNKSTA_DLLLA);
+
+    pci_set_long(exp_cap + PCI_EXP_DEVCAP2,
+                 PCI_EXP_DEVCAP2_EFF | PCI_EXP_DEVCAP2_EETLPP);
+
+    pci_set_word(dev->wmask + pos + PCI_EXP_DEVCTL2, PCI_EXP_DEVCTL2_EETLPPB);
+    return pos;
+}
+
+int pcie_endpoint_cap_init(PCIDevice *dev, uint8_t offset)
+{
+    uint8_t type = PCI_EXP_TYPE_ENDPOINT;
+
+    /*
+     * Windows guests will report Code 10, device cannot start, if
+     * a regular Endpoint type is exposed on a root complex.  These
+     * should instead be Root Complex Integrated Endpoints.
+     */
+    if (pci_bus_is_express(dev->bus) && pci_bus_is_root(dev->bus)) {
+        type = PCI_EXP_TYPE_RC_END;
+    }
+
+    return pcie_cap_init(dev, offset, type, 0);
+}
+
+void pcie_cap_exit(PCIDevice *dev)
+{
+    pci_del_capability(dev, PCI_CAP_ID_EXP, PCI_EXP_VER2_SIZEOF);
+}
+
+uint8_t pcie_cap_get_type(const PCIDevice *dev)
+{
+    uint32_t pos = dev->exp.exp_cap;
+    assert(pos > 0);
+    return (pci_get_word(dev->config + pos + PCI_EXP_FLAGS) &
+            PCI_EXP_FLAGS_TYPE) >> PCI_EXP_FLAGS_TYPE_SHIFT;
+}
+
+/* MSI/MSI-X */
+/* pci express interrupt message number */
+/* 7.8.2 PCI Express Capabilities Register: Interrupt Message Number */
+void pcie_cap_flags_set_vector(PCIDevice *dev, uint8_t vector)
+{
+    uint8_t *exp_cap = dev->config + dev->exp.exp_cap;
+    assert(vector < 32);
+    pci_word_test_and_clear_mask(exp_cap + PCI_EXP_FLAGS, PCI_EXP_FLAGS_IRQ);
+    pci_word_test_and_set_mask(exp_cap + PCI_EXP_FLAGS,
+                               vector << PCI_EXP_FLAGS_IRQ_SHIFT);
+}
+
+uint8_t pcie_cap_flags_get_vector(PCIDevice *dev)
+{
+    return (pci_get_word(dev->config + dev->exp.exp_cap + PCI_EXP_FLAGS) &
+            PCI_EXP_FLAGS_IRQ) >> PCI_EXP_FLAGS_IRQ_SHIFT;
+}
+
+void pcie_cap_deverr_init(PCIDevice *dev)
+{
+    uint32_t pos = dev->exp.exp_cap;
+    pci_long_test_and_set_mask(dev->config + pos + PCI_EXP_DEVCAP,
+                               PCI_EXP_DEVCAP_RBER);
+    pci_long_test_and_set_mask(dev->wmask + pos + PCI_EXP_DEVCTL,
+                               PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE |
+                               PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE);
+    pci_long_test_and_set_mask(dev->w1cmask + pos + PCI_EXP_DEVSTA,
+                               PCI_EXP_DEVSTA_CED | PCI_EXP_DEVSTA_NFED |
+                               PCI_EXP_DEVSTA_FED | PCI_EXP_DEVSTA_URD);
+}
+
+void pcie_cap_deverr_reset(PCIDevice *dev)
+{
+    uint8_t *devctl = dev->config + dev->exp.exp_cap + PCI_EXP_DEVCTL;
+    pci_long_test_and_clear_mask(devctl,
+                                 PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE |
+                                 PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE);
+}
+
+static void hotplug_event_update_event_status(PCIDevice *dev)
+{
+    uint32_t pos = dev->exp.exp_cap;
+    uint8_t *exp_cap = dev->config + pos;
+    uint16_t sltctl = pci_get_word(exp_cap + PCI_EXP_SLTCTL);
+    uint16_t sltsta = pci_get_word(exp_cap + PCI_EXP_SLTSTA);
+
+    dev->exp.hpev_notified = (sltctl & PCI_EXP_SLTCTL_HPIE) &&
+        (sltsta & sltctl & PCI_EXP_HP_EV_SUPPORTED);
+}
+
+static void hotplug_event_notify(PCIDevice *dev)
+{
+    bool prev = dev->exp.hpev_notified;
+
+    hotplug_event_update_event_status(dev);
+
+    if (prev == dev->exp.hpev_notified) {
+        return;
+    }
+
+    /* Note: the logic above does not take into account whether interrupts
+     * are masked. The result is that interrupt will be sent when it is
+     * subsequently unmasked. This appears to be legal: Section 6.7.3.4:
+     * The Port may optionally send an MSI when there are hot-plug events that
+     * occur while interrupt generation is disabled, and interrupt generation is
+     * subsequently enabled. */
+    if (msix_enabled(dev)) {
+        msix_notify(dev, pcie_cap_flags_get_vector(dev));
+    } else if (msi_enabled(dev)) {
+        msi_notify(dev, pcie_cap_flags_get_vector(dev));
+    } else {
+        pci_set_irq(dev, dev->exp.hpev_notified);
+    }
+}
+
+static void hotplug_event_clear(PCIDevice *dev)
+{
+    hotplug_event_update_event_status(dev);
+    if (!msix_enabled(dev) && !msi_enabled(dev) && !dev->exp.hpev_notified) {
+        pci_irq_deassert(dev);
+    }
+}
+
+/*
+ * A PCI Express Hot-Plug Event has occurred, so update slot status register
+ * and notify OS of the event if necessary.
+ *
+ * 6.7.3 PCI Express Hot-Plug Events
+ * 6.7.3.4 Software Notification of Hot-Plug Events
+ */
+static void pcie_cap_slot_event(PCIDevice *dev, PCIExpressHotPlugEvent event)
+{
+    /* Minor optimization: if nothing changed - no event is needed. */
+    if (pci_word_test_and_set_mask(dev->config + dev->exp.exp_cap +
+                                   PCI_EXP_SLTSTA, event)) {
+        return;
+    }
+    hotplug_event_notify(dev);
+}
+
+static void pcie_cap_slot_hotplug_common(PCIDevice *hotplug_dev,
+                                         DeviceState *dev,
+                                         uint8_t **exp_cap, Error **errp)
+{
+    *exp_cap = hotplug_dev->config + hotplug_dev->exp.exp_cap;
+    uint16_t sltsta = pci_get_word(*exp_cap + PCI_EXP_SLTSTA);
+
+    PCIE_DEV_PRINTF(PCI_DEVICE(dev), "hotplug state: 0x%x\n", sltsta);
+    if (sltsta & PCI_EXP_SLTSTA_EIS) {
+        /* the slot is electromechanically locked.
+         * This error is propagated up to qdev and then to HMP/QMP.
+         */
+        error_setg_errno(errp, EBUSY, "slot is electromechanically locked");
+    }
+}
+
+void pcie_cap_slot_hotplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
+                              Error **errp)
+{
+    uint8_t *exp_cap;
+    PCIDevice *pci_dev = PCI_DEVICE(dev);
+
+    pcie_cap_slot_hotplug_common(PCI_DEVICE(hotplug_dev), dev, &exp_cap, errp);
+
+    /* Don't send event when device is enabled during qemu machine creation:
+     * it is present on boot, no hotplug event is necessary. We do send an
+     * event when the device is disabled later. */
+    if (!dev->hotplugged) {
+        pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
+                                   PCI_EXP_SLTSTA_PDS);
+        return;
+    }
+
+    /* TODO: multifunction hot-plug.
+     * Right now, only a device of function = 0 is allowed to be
+     * hot plugged/unplugged.
+     */
+    assert(PCI_FUNC(pci_dev->devfn) == 0);
+
+    pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
+                               PCI_EXP_SLTSTA_PDS);
+    pcie_cap_slot_event(PCI_DEVICE(hotplug_dev),
+                        PCI_EXP_HP_EV_PDC | PCI_EXP_HP_EV_ABP);
+}
+
+void pcie_cap_slot_hot_unplug_request_cb(HotplugHandler *hotplug_dev,
+                                         DeviceState *dev, Error **errp)
+{
+    uint8_t *exp_cap;
+
+    pcie_cap_slot_hotplug_common(PCI_DEVICE(hotplug_dev), dev, &exp_cap, errp);
+
+    pcie_cap_slot_push_attention_button(PCI_DEVICE(hotplug_dev));
+}
+
+/* pci express slot for pci express root/downstream port
+   PCI express capability slot registers */
+void pcie_cap_slot_init(PCIDevice *dev, uint16_t slot)
+{
+    uint32_t pos = dev->exp.exp_cap;
+
+    pci_word_test_and_set_mask(dev->config + pos + PCI_EXP_FLAGS,
+                               PCI_EXP_FLAGS_SLOT);
+
+    pci_long_test_and_clear_mask(dev->config + pos + PCI_EXP_SLTCAP,
+                                 ~PCI_EXP_SLTCAP_PSN);
+    pci_long_test_and_set_mask(dev->config + pos + PCI_EXP_SLTCAP,
+                               (slot << PCI_EXP_SLTCAP_PSN_SHIFT) |
+                               PCI_EXP_SLTCAP_EIP |
+                               PCI_EXP_SLTCAP_HPS |
+                               PCI_EXP_SLTCAP_HPC |
+                               PCI_EXP_SLTCAP_PIP |
+                               PCI_EXP_SLTCAP_AIP |
+                               PCI_EXP_SLTCAP_ABP);
+
+    if (dev->cap_present & QEMU_PCIE_SLTCAP_PCP) {
+        pci_long_test_and_set_mask(dev->config + pos + PCI_EXP_SLTCAP,
+                                   PCI_EXP_SLTCAP_PCP);
+        pci_word_test_and_clear_mask(dev->config + pos + PCI_EXP_SLTCTL,
+                                     PCI_EXP_SLTCTL_PCC);
+        pci_word_test_and_set_mask(dev->wmask + pos + PCI_EXP_SLTCTL,
+                                   PCI_EXP_SLTCTL_PCC);
+    }
+
+    pci_word_test_and_clear_mask(dev->config + pos + PCI_EXP_SLTCTL,
+                                 PCI_EXP_SLTCTL_PIC |
+                                 PCI_EXP_SLTCTL_AIC);
+    pci_word_test_and_set_mask(dev->config + pos + PCI_EXP_SLTCTL,
+                               PCI_EXP_SLTCTL_PIC_OFF |
+                               PCI_EXP_SLTCTL_AIC_OFF);
+    pci_word_test_and_set_mask(dev->wmask + pos + PCI_EXP_SLTCTL,
+                               PCI_EXP_SLTCTL_PIC |
+                               PCI_EXP_SLTCTL_AIC |
+                               PCI_EXP_SLTCTL_HPIE |
+                               PCI_EXP_SLTCTL_CCIE |
+                               PCI_EXP_SLTCTL_PDCE |
+                               PCI_EXP_SLTCTL_ABPE);
+    /* Although reading PCI_EXP_SLTCTL_EIC returns always 0,
+     * make the bit writable here in order to detect 1b is written.
+     * pcie_cap_slot_write_config() test-and-clear the bit, so
+     * this bit always returns 0 to the guest.
+     */
+    pci_word_test_and_set_mask(dev->wmask + pos + PCI_EXP_SLTCTL,
+                               PCI_EXP_SLTCTL_EIC);
+
+    pci_word_test_and_set_mask(dev->w1cmask + pos + PCI_EXP_SLTSTA,
+                               PCI_EXP_HP_EV_SUPPORTED);
+
+    dev->exp.hpev_notified = false;
+
+    qbus_set_hotplug_handler(BUS(pci_bridge_get_sec_bus(PCI_BRIDGE(dev))),
+                             DEVICE(dev), NULL);
+}
+
+void pcie_cap_slot_reset(PCIDevice *dev)
+{
+    uint8_t *exp_cap = dev->config + dev->exp.exp_cap;
+    uint8_t port_type = pcie_cap_get_type(dev);
+
+    assert(port_type == PCI_EXP_TYPE_DOWNSTREAM ||
+           port_type == PCI_EXP_TYPE_ROOT_PORT);
+
+    PCIE_DEV_PRINTF(dev, "reset\n");
+
+    pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTCTL,
+                                 PCI_EXP_SLTCTL_EIC |
+                                 PCI_EXP_SLTCTL_PIC |
+                                 PCI_EXP_SLTCTL_AIC |
+                                 PCI_EXP_SLTCTL_HPIE |
+                                 PCI_EXP_SLTCTL_CCIE |
+                                 PCI_EXP_SLTCTL_PDCE |
+                                 PCI_EXP_SLTCTL_ABPE);
+    pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTCTL,
+                               PCI_EXP_SLTCTL_AIC_OFF);
+
+    if (dev->cap_present & QEMU_PCIE_SLTCAP_PCP) {
+        /* Downstream ports enforce device number 0. */
+        bool populated = pci_bridge_get_sec_bus(PCI_BRIDGE(dev))->devices[0];
+        uint16_t pic;
+
+        if (populated) {
+            pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTCTL,
+                                         PCI_EXP_SLTCTL_PCC);
+        } else {
+            pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTCTL,
+                                       PCI_EXP_SLTCTL_PCC);
+        }
+
+        pic = populated ? PCI_EXP_SLTCTL_PIC_ON : PCI_EXP_SLTCTL_PIC_OFF;
+        pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTCTL, pic);
+    }
+
+    pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTSTA,
+                                 PCI_EXP_SLTSTA_EIS |/* on reset,
+                                                        the lock is released */
+                                 PCI_EXP_SLTSTA_CC |
+                                 PCI_EXP_SLTSTA_PDC |
+                                 PCI_EXP_SLTSTA_ABP);
+
+    hotplug_event_update_event_status(dev);
+}
+
+static void pcie_unplug_device(PCIBus *bus, PCIDevice *dev, void *opaque)
+{
+    object_unparent(OBJECT(dev));
+}
+
+void pcie_cap_slot_write_config(PCIDevice *dev,
+                                uint32_t addr, uint32_t val, int len)
+{
+    uint32_t pos = dev->exp.exp_cap;
+    uint8_t *exp_cap = dev->config + pos;
+    uint16_t sltsta = pci_get_word(exp_cap + PCI_EXP_SLTSTA);
+
+    if (ranges_overlap(addr, len, pos + PCI_EXP_SLTSTA, 2)) {
+        hotplug_event_clear(dev);
+    }
+
+    if (!ranges_overlap(addr, len, pos + PCI_EXP_SLTCTL, 2)) {
+        return;
+    }
+
+    if (pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTCTL,
+                                     PCI_EXP_SLTCTL_EIC)) {
+        sltsta ^= PCI_EXP_SLTSTA_EIS; /* toggle PCI_EXP_SLTSTA_EIS bit */
+        pci_set_word(exp_cap + PCI_EXP_SLTSTA, sltsta);
+        PCIE_DEV_PRINTF(dev, "PCI_EXP_SLTCTL_EIC: "
+                        "sltsta -> 0x%02"PRIx16"\n",
+                        sltsta);
+    }
+
+    /*
+     * If the slot is polulated, power indicator is off and power
+     * controller is off, it is safe to detach the devices.
+     */
+    if ((sltsta & PCI_EXP_SLTSTA_PDS) && (val & PCI_EXP_SLTCTL_PCC) &&
+        ((val & PCI_EXP_SLTCTL_PIC_OFF) == PCI_EXP_SLTCTL_PIC_OFF)) {
+            PCIBus *sec_bus = pci_bridge_get_sec_bus(PCI_BRIDGE(dev));
+            pci_for_each_device(sec_bus, pci_bus_num(sec_bus),
+                                pcie_unplug_device, NULL);
+
+            pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTSTA,
+                                         PCI_EXP_SLTSTA_PDS);
+            pci_word_test_and_set_mask(exp_cap + PCI_EXP_SLTSTA,
+                                       PCI_EXP_SLTSTA_PDC);
+    }
+
+    hotplug_event_notify(dev);
+
+    /* 
+     * 6.7.3.2 Command Completed Events
+     *
+     * Software issues a command to a hot-plug capable Downstream Port by
+     * issuing a write transaction that targets any portion of the Port’s Slot
+     * Control register. A single write to the Slot Control register is
+     * considered to be a single command, even if the write affects more than
+     * one field in the Slot Control register. In response to this transaction,
+     * the Port must carry out the requested actions and then set the
+     * associated status field for the command completed event. */
+
+    /* Real hardware might take a while to complete requested command because
+     * physical movement would be involved like locking the electromechanical
+     * lock.  However in our case, command is completed instantaneously above,
+     * so send a command completion event right now.
+     */
+    pcie_cap_slot_event(dev, PCI_EXP_HP_EV_CCI);
+}
+
+int pcie_cap_slot_post_load(void *opaque, int version_id)
+{
+    PCIDevice *dev = opaque;
+    hotplug_event_update_event_status(dev);
+    return 0;
+}
+
+void pcie_cap_slot_push_attention_button(PCIDevice *dev)
+{
+    pcie_cap_slot_event(dev, PCI_EXP_HP_EV_ABP);
+}
+
+/* root control/capabilities/status. PME isn't emulated for now */
+void pcie_cap_root_init(PCIDevice *dev)
+{
+    pci_set_word(dev->wmask + dev->exp.exp_cap + PCI_EXP_RTCTL,
+                 PCI_EXP_RTCTL_SECEE | PCI_EXP_RTCTL_SENFEE |
+                 PCI_EXP_RTCTL_SEFEE);
+}
+
+void pcie_cap_root_reset(PCIDevice *dev)
+{
+    pci_set_word(dev->config + dev->exp.exp_cap + PCI_EXP_RTCTL, 0);
+}
+
+/* function level reset(FLR) */
+void pcie_cap_flr_init(PCIDevice *dev)
+{
+    pci_long_test_and_set_mask(dev->config + dev->exp.exp_cap + PCI_EXP_DEVCAP,
+                               PCI_EXP_DEVCAP_FLR);
+
+    /* Although reading BCR_FLR returns always 0,
+     * the bit is made writable here in order to detect the 1b is written
+     * pcie_cap_flr_write_config() test-and-clear the bit, so
+     * this bit always returns 0 to the guest.
+     */
+    pci_word_test_and_set_mask(dev->wmask + dev->exp.exp_cap + PCI_EXP_DEVCTL,
+                               PCI_EXP_DEVCTL_BCR_FLR);
+}
+
+void pcie_cap_flr_write_config(PCIDevice *dev,
+                               uint32_t addr, uint32_t val, int len)
+{
+    uint8_t *devctl = dev->config + dev->exp.exp_cap + PCI_EXP_DEVCTL;
+    if (pci_get_word(devctl) & PCI_EXP_DEVCTL_BCR_FLR) {
+        /* Clear PCI_EXP_DEVCTL_BCR_FLR after invoking the reset handler
+           so the handler can detect FLR by looking at this bit. */
+        pci_device_reset(dev);
+        pci_word_test_and_clear_mask(devctl, PCI_EXP_DEVCTL_BCR_FLR);
+    }
+}
+
+/* Alternative Routing-ID Interpretation (ARI)
+ * forwarding support for root and downstream ports
+ */
+void pcie_cap_arifwd_init(PCIDevice *dev)
+{
+    uint32_t pos = dev->exp.exp_cap;
+    pci_long_test_and_set_mask(dev->config + pos + PCI_EXP_DEVCAP2,
+                               PCI_EXP_DEVCAP2_ARI);
+    pci_long_test_and_set_mask(dev->wmask + pos + PCI_EXP_DEVCTL2,
+                               PCI_EXP_DEVCTL2_ARI);
+}
+
+void pcie_cap_arifwd_reset(PCIDevice *dev)
+{
+    uint8_t *devctl2 = dev->config + dev->exp.exp_cap + PCI_EXP_DEVCTL2;
+    pci_long_test_and_clear_mask(devctl2, PCI_EXP_DEVCTL2_ARI);
+}
+
+bool pcie_cap_is_arifwd_enabled(const PCIDevice *dev)
+{
+    if (!pci_is_express(dev)) {
+        return false;
+    }
+    if (!dev->exp.exp_cap) {
+        return false;
+    }
+
+    return pci_get_long(dev->config + dev->exp.exp_cap + PCI_EXP_DEVCTL2) &
+        PCI_EXP_DEVCTL2_ARI;
+}
+
+/**************************************************************************
+ * pci express extended capability list management functions
+ * uint16_t ext_cap_id (16 bit)
+ * uint8_t cap_ver (4 bit)
+ * uint16_t cap_offset (12 bit)
+ * uint16_t ext_cap_size
+ */
+
+static uint16_t pcie_find_capability_list(PCIDevice *dev, uint16_t cap_id,
+                                          uint16_t *prev_p)
+{
+    uint16_t prev = 0;
+    uint16_t next;
+    uint32_t header = pci_get_long(dev->config + PCI_CONFIG_SPACE_SIZE);
+
+    if (!header) {
+        /* no extended capability */
+        next = 0;
+        goto out;
+    }
+    for (next = PCI_CONFIG_SPACE_SIZE; next;
+         prev = next, next = PCI_EXT_CAP_NEXT(header)) {
+
+        assert(next >= PCI_CONFIG_SPACE_SIZE);
+        assert(next <= PCIE_CONFIG_SPACE_SIZE - 8);
+
+        header = pci_get_long(dev->config + next);
+        if (PCI_EXT_CAP_ID(header) == cap_id) {
+            break;
+        }
+    }
+
+out:
+    if (prev_p) {
+        *prev_p = prev;
+    }
+    return next;
+}
+
+uint16_t pcie_find_capability(PCIDevice *dev, uint16_t cap_id)
+{
+    return pcie_find_capability_list(dev, cap_id, NULL);
+}
+
+static void pcie_ext_cap_set_next(PCIDevice *dev, uint16_t pos, uint16_t next)
+{
+    uint32_t header = pci_get_long(dev->config + pos);
+    assert(!(next & (PCI_EXT_CAP_ALIGN - 1)));
+    header = (header & ~PCI_EXT_CAP_NEXT_MASK) |
+        ((next << PCI_EXT_CAP_NEXT_SHIFT) & PCI_EXT_CAP_NEXT_MASK);
+    pci_set_long(dev->config + pos, header);
+}
+
+/*
+ * caller must supply valid (offset, size) * such that the range shouldn't
+ * overlap with other capability or other registers.
+ * This function doesn't check it.
+ */
+void pcie_add_capability(PCIDevice *dev,
+                         uint16_t cap_id, uint8_t cap_ver,
+                         uint16_t offset, uint16_t size)
+{
+    uint32_t header;
+    uint16_t next;
+
+    assert(offset >= PCI_CONFIG_SPACE_SIZE);
+    assert(offset < offset + size);
+    assert(offset + size < PCIE_CONFIG_SPACE_SIZE);
+    assert(size >= 8);
+    assert(pci_is_express(dev));
+
+    if (offset == PCI_CONFIG_SPACE_SIZE) {
+        header = pci_get_long(dev->config + offset);
+        next = PCI_EXT_CAP_NEXT(header);
+    } else {
+        uint16_t prev;
+
+        /* 0 is reserved cap id. use internally to find the last capability
+           in the linked list */
+        next = pcie_find_capability_list(dev, 0, &prev);
+
+        assert(prev >= PCI_CONFIG_SPACE_SIZE);
+        assert(next == 0);
+        pcie_ext_cap_set_next(dev, prev, offset);
+    }
+    pci_set_long(dev->config + offset, PCI_EXT_CAP(cap_id, cap_ver, next));
+
+    /* Make capability read-only by default */
+    memset(dev->wmask + offset, 0, size);
+    memset(dev->w1cmask + offset, 0, size);
+    /* Check capability by default */
+    memset(dev->cmask + offset, 0xFF, size);
+}
+
+/**************************************************************************
+ * pci express extended capability helper functions
+ */
+
+/* ARI */
+void pcie_ari_init(PCIDevice *dev, uint16_t offset, uint16_t nextfn)
+{
+    pcie_add_capability(dev, PCI_EXT_CAP_ID_ARI, PCI_ARI_VER,
+                        offset, PCI_ARI_SIZEOF);
+    pci_set_long(dev->config + offset + PCI_ARI_CAP, (nextfn & 0xff) << 8);
+}
diff --git a/qemu/hw/pci/pcie_aer.c b/qemu/hw/pci/pcie_aer.c
new file mode 100644
index 000000000..f1847ac21
--- /dev/null
+++ b/qemu/hw/pci/pcie_aer.c
@@ -0,0 +1,1042 @@
+/*
+ * pcie_aer.c
+ *
+ * Copyright (c) 2010 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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/>.
+ */
+
+#include "sysemu/sysemu.h"
+#include "qapi/qmp/types.h"
+#include "monitor/monitor.h"
+#include "hw/pci/pci_bridge.h"
+#include "hw/pci/pcie.h"
+#include "hw/pci/msix.h"
+#include "hw/pci/msi.h"
+#include "hw/pci/pci_bus.h"
+#include "hw/pci/pcie_regs.h"
+
+//#define DEBUG_PCIE
+#ifdef DEBUG_PCIE
+# define PCIE_DPRINTF(fmt, ...)                                         \
+    fprintf(stderr, "%s:%d " fmt, __func__, __LINE__, ## __VA_ARGS__)
+#else
+# define PCIE_DPRINTF(fmt, ...) do {} while (0)
+#endif
+#define PCIE_DEV_PRINTF(dev, fmt, ...)                                  \
+    PCIE_DPRINTF("%s:%x "fmt, (dev)->name, (dev)->devfn, ## __VA_ARGS__)
+
+#define PCI_ERR_SRC_COR_OFFS    0
+#define PCI_ERR_SRC_UNCOR_OFFS  2
+
+/* From 6.2.7 Error Listing and Rules. Table 6-2, 6-3 and 6-4 */
+static uint32_t pcie_aer_uncor_default_severity(uint32_t status)
+{
+    switch (status) {
+    case PCI_ERR_UNC_INTN:
+    case PCI_ERR_UNC_DLP:
+    case PCI_ERR_UNC_SDN:
+    case PCI_ERR_UNC_RX_OVER:
+    case PCI_ERR_UNC_FCP:
+    case PCI_ERR_UNC_MALF_TLP:
+        return PCI_ERR_ROOT_CMD_FATAL_EN;
+    case PCI_ERR_UNC_POISON_TLP:
+    case PCI_ERR_UNC_ECRC:
+    case PCI_ERR_UNC_UNSUP:
+    case PCI_ERR_UNC_COMP_TIME:
+    case PCI_ERR_UNC_COMP_ABORT:
+    case PCI_ERR_UNC_UNX_COMP:
+    case PCI_ERR_UNC_ACSV:
+    case PCI_ERR_UNC_MCBTLP:
+    case PCI_ERR_UNC_ATOP_EBLOCKED:
+    case PCI_ERR_UNC_TLP_PRF_BLOCKED:
+        return PCI_ERR_ROOT_CMD_NONFATAL_EN;
+    default:
+        abort();
+        break;
+    }
+    return PCI_ERR_ROOT_CMD_FATAL_EN;
+}
+
+static int aer_log_add_err(PCIEAERLog *aer_log, const PCIEAERErr *err)
+{
+    if (aer_log->log_num == aer_log->log_max) {
+        return -1;
+    }
+    memcpy(&aer_log->log[aer_log->log_num], err, sizeof *err);
+    aer_log->log_num++;
+    return 0;
+}
+
+static void aer_log_del_err(PCIEAERLog *aer_log, PCIEAERErr *err)
+{
+    assert(aer_log->log_num);
+    *err = aer_log->log[0];
+    aer_log->log_num--;
+    memmove(&aer_log->log[0], &aer_log->log[1],
+            aer_log->log_num * sizeof *err);
+}
+
+static void aer_log_clear_all_err(PCIEAERLog *aer_log)
+{
+    aer_log->log_num = 0;
+}
+
+int pcie_aer_init(PCIDevice *dev, uint16_t offset)
+{
+    PCIExpressDevice *exp;
+
+    pcie_add_capability(dev, PCI_EXT_CAP_ID_ERR, PCI_ERR_VER,
+                        offset, PCI_ERR_SIZEOF);
+    exp = &dev->exp;
+    exp->aer_cap = offset;
+
+    /* log_max is property */
+    if (dev->exp.aer_log.log_max == PCIE_AER_LOG_MAX_UNSET) {
+        dev->exp.aer_log.log_max = PCIE_AER_LOG_MAX_DEFAULT;
+    }
+    /* clip down the value to avoid unreasobale memory usage */
+    if (dev->exp.aer_log.log_max > PCIE_AER_LOG_MAX_LIMIT) {
+        return -EINVAL;
+    }
+    dev->exp.aer_log.log = g_malloc0(sizeof dev->exp.aer_log.log[0] *
+                                        dev->exp.aer_log.log_max);
+
+    pci_set_long(dev->w1cmask + offset + PCI_ERR_UNCOR_STATUS,
+                 PCI_ERR_UNC_SUPPORTED);
+
+    pci_set_long(dev->config + offset + PCI_ERR_UNCOR_SEVER,
+                 PCI_ERR_UNC_SEVERITY_DEFAULT);
+    pci_set_long(dev->wmask + offset + PCI_ERR_UNCOR_SEVER,
+                 PCI_ERR_UNC_SUPPORTED);
+
+    pci_long_test_and_set_mask(dev->w1cmask + offset + PCI_ERR_COR_STATUS,
+                               PCI_ERR_COR_SUPPORTED);
+
+    pci_set_long(dev->config + offset + PCI_ERR_COR_MASK,
+                 PCI_ERR_COR_MASK_DEFAULT);
+    pci_set_long(dev->wmask + offset + PCI_ERR_COR_MASK,
+                 PCI_ERR_COR_SUPPORTED);
+
+    /* capabilities and control. multiple header logging is supported */
+    if (dev->exp.aer_log.log_max > 0) {
+        pci_set_long(dev->config + offset + PCI_ERR_CAP,
+                     PCI_ERR_CAP_ECRC_GENC | PCI_ERR_CAP_ECRC_CHKC |
+                     PCI_ERR_CAP_MHRC);
+        pci_set_long(dev->wmask + offset + PCI_ERR_CAP,
+                     PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE |
+                     PCI_ERR_CAP_MHRE);
+    } else {
+        pci_set_long(dev->config + offset + PCI_ERR_CAP,
+                     PCI_ERR_CAP_ECRC_GENC | PCI_ERR_CAP_ECRC_CHKC);
+        pci_set_long(dev->wmask + offset + PCI_ERR_CAP,
+                     PCI_ERR_CAP_ECRC_GENE | PCI_ERR_CAP_ECRC_CHKE);
+    }
+
+    switch (pcie_cap_get_type(dev)) {
+    case PCI_EXP_TYPE_ROOT_PORT:
+        /* this case will be set by pcie_aer_root_init() */
+        /* fallthrough */
+    case PCI_EXP_TYPE_DOWNSTREAM:
+    case PCI_EXP_TYPE_UPSTREAM:
+        pci_word_test_and_set_mask(dev->wmask + PCI_BRIDGE_CONTROL,
+                                   PCI_BRIDGE_CTL_SERR);
+        pci_long_test_and_set_mask(dev->w1cmask + PCI_STATUS,
+                                   PCI_SEC_STATUS_RCV_SYSTEM_ERROR);
+        break;
+    default:
+        /* nothing */
+        break;
+    }
+    return 0;
+}
+
+void pcie_aer_exit(PCIDevice *dev)
+{
+    g_free(dev->exp.aer_log.log);
+}
+
+static void pcie_aer_update_uncor_status(PCIDevice *dev)
+{
+    uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+    PCIEAERLog *aer_log = &dev->exp.aer_log;
+
+    uint16_t i;
+    for (i = 0; i < aer_log->log_num; i++) {
+        pci_long_test_and_set_mask(aer_cap + PCI_ERR_UNCOR_STATUS,
+                                   dev->exp.aer_log.log[i].status);
+    }
+}
+
+/*
+ * return value:
+ * true: error message needs to be sent up
+ * false: error message is masked
+ *
+ * 6.2.6 Error Message Control
+ * Figure 6-3
+ * all pci express devices part
+ */
+static bool
+pcie_aer_msg_alldev(PCIDevice *dev, const PCIEAERMsg *msg)
+{
+    if (!(pcie_aer_msg_is_uncor(msg) &&
+          (pci_get_word(dev->config + PCI_COMMAND) & PCI_COMMAND_SERR))) {
+        return false;
+    }
+
+    /* Signaled System Error
+     *
+     * 7.5.1.1 Command register
+     * Bit 8 SERR# Enable
+     *
+     * When Set, this bit enables reporting of Non-fatal and Fatal
+     * errors detected by the Function to the Root Complex. Note that
+     * errors are reported if enabled either through this bit or through
+     * the PCI Express specific bits in the Device Control register (see
+     * Section 7.8.4).
+     */
+    pci_word_test_and_set_mask(dev->config + PCI_STATUS,
+                               PCI_STATUS_SIG_SYSTEM_ERROR);
+
+    if (!(msg->severity &
+          pci_get_word(dev->config + dev->exp.exp_cap + PCI_EXP_DEVCTL))) {
+        return false;
+    }
+
+    /* send up error message */
+    return true;
+}
+
+/*
+ * return value:
+ * true: error message is sent up
+ * false: error message is masked
+ *
+ * 6.2.6 Error Message Control
+ * Figure 6-3
+ * virtual pci bridge part
+ */
+static bool pcie_aer_msg_vbridge(PCIDevice *dev, const PCIEAERMsg *msg)
+{
+    uint16_t bridge_control = pci_get_word(dev->config + PCI_BRIDGE_CONTROL);
+
+    if (pcie_aer_msg_is_uncor(msg)) {
+        /* Received System Error */
+        pci_word_test_and_set_mask(dev->config + PCI_SEC_STATUS,
+                                   PCI_SEC_STATUS_RCV_SYSTEM_ERROR);
+    }
+
+    if (!(bridge_control & PCI_BRIDGE_CTL_SERR)) {
+        return false;
+    }
+    return true;
+}
+
+void pcie_aer_root_set_vector(PCIDevice *dev, unsigned int vector)
+{
+    uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+    assert(vector < PCI_ERR_ROOT_IRQ_MAX);
+    pci_long_test_and_clear_mask(aer_cap + PCI_ERR_ROOT_STATUS,
+                                 PCI_ERR_ROOT_IRQ);
+    pci_long_test_and_set_mask(aer_cap + PCI_ERR_ROOT_STATUS,
+                               vector << PCI_ERR_ROOT_IRQ_SHIFT);
+}
+
+static unsigned int pcie_aer_root_get_vector(PCIDevice *dev)
+{
+    uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+    uint32_t root_status = pci_get_long(aer_cap + PCI_ERR_ROOT_STATUS);
+    return (root_status & PCI_ERR_ROOT_IRQ) >> PCI_ERR_ROOT_IRQ_SHIFT;
+}
+
+/* Given a status register, get corresponding bits in the command register */
+static uint32_t pcie_aer_status_to_cmd(uint32_t status)
+{
+    uint32_t cmd = 0;
+    if (status & PCI_ERR_ROOT_COR_RCV) {
+        cmd |= PCI_ERR_ROOT_CMD_COR_EN;
+    }
+    if (status & PCI_ERR_ROOT_NONFATAL_RCV) {
+        cmd |= PCI_ERR_ROOT_CMD_NONFATAL_EN;
+    }
+    if (status & PCI_ERR_ROOT_FATAL_RCV) {
+        cmd |= PCI_ERR_ROOT_CMD_FATAL_EN;
+    }
+    return cmd;
+}
+
+static void pcie_aer_root_notify(PCIDevice *dev)
+{
+    if (msix_enabled(dev)) {
+        msix_notify(dev, pcie_aer_root_get_vector(dev));
+    } else if (msi_enabled(dev)) {
+        msi_notify(dev, pcie_aer_root_get_vector(dev));
+    } else {
+        pci_irq_assert(dev);
+    }
+}
+
+/*
+ * 6.2.6 Error Message Control
+ * Figure 6-3
+ * root port part
+ */
+static void pcie_aer_msg_root_port(PCIDevice *dev, const PCIEAERMsg *msg)
+{
+    uint16_t cmd;
+    uint8_t *aer_cap;
+    uint32_t root_cmd;
+    uint32_t root_status, prev_status;
+
+    cmd = pci_get_word(dev->config + PCI_COMMAND);
+    aer_cap = dev->config + dev->exp.aer_cap;
+    root_cmd = pci_get_long(aer_cap + PCI_ERR_ROOT_COMMAND);
+    prev_status = root_status = pci_get_long(aer_cap + PCI_ERR_ROOT_STATUS);
+
+    if (cmd & PCI_COMMAND_SERR) {
+        /* System Error.
+         *
+         * The way to report System Error is platform specific and
+         * it isn't implemented in qemu right now.
+         * So just discard the error for now.
+         * OS which cares of aer would receive errors via
+         * native aer mechanims, so this wouldn't matter.
+         */
+    }
+
+    /* Errro Message Received: Root Error Status register */
+    switch (msg->severity) {
+    case PCI_ERR_ROOT_CMD_COR_EN:
+        if (root_status & PCI_ERR_ROOT_COR_RCV) {
+            root_status |= PCI_ERR_ROOT_MULTI_COR_RCV;
+        } else {
+            pci_set_word(aer_cap + PCI_ERR_ROOT_ERR_SRC + PCI_ERR_SRC_COR_OFFS,
+                         msg->source_id);
+        }
+        root_status |= PCI_ERR_ROOT_COR_RCV;
+        break;
+    case PCI_ERR_ROOT_CMD_NONFATAL_EN:
+        root_status |= PCI_ERR_ROOT_NONFATAL_RCV;
+        break;
+    case PCI_ERR_ROOT_CMD_FATAL_EN:
+        if (!(root_status & PCI_ERR_ROOT_UNCOR_RCV)) {
+            root_status |= PCI_ERR_ROOT_FIRST_FATAL;
+        }
+        root_status |= PCI_ERR_ROOT_FATAL_RCV;
+        break;
+    default:
+        abort();
+        break;
+    }
+    if (pcie_aer_msg_is_uncor(msg)) {
+        if (root_status & PCI_ERR_ROOT_UNCOR_RCV) {
+            root_status |= PCI_ERR_ROOT_MULTI_UNCOR_RCV;
+        } else {
+            pci_set_word(aer_cap + PCI_ERR_ROOT_ERR_SRC +
+                         PCI_ERR_SRC_UNCOR_OFFS, msg->source_id);
+        }
+        root_status |= PCI_ERR_ROOT_UNCOR_RCV;
+    }
+    pci_set_long(aer_cap + PCI_ERR_ROOT_STATUS, root_status);
+
+    /* 6.2.4.1.2 Interrupt Generation */
+    /* All the above did was set some bits in the status register.
+     * Specifically these that match message severity.
+     * The below code relies on this fact. */
+    if (!(root_cmd & msg->severity) ||
+        (pcie_aer_status_to_cmd(prev_status) & root_cmd)) {
+        /* Condition is not being set or was already true so nothing to do. */
+        return;
+    }
+
+    pcie_aer_root_notify(dev);
+}
+
+/*
+ * 6.2.6 Error Message Control Figure 6-3
+ *
+ * Walk up the bus tree from the device, propagate the error message.
+ */
+static void pcie_aer_msg(PCIDevice *dev, const PCIEAERMsg *msg)
+{
+    uint8_t type;
+
+    while (dev) {
+        if (!pci_is_express(dev)) {
+            /* just ignore it */
+            /* TODO: Shouldn't we set PCI_STATUS_SIG_SYSTEM_ERROR?
+             * Consider e.g. a PCI bridge above a PCI Express device. */
+            return;
+        }
+
+        type = pcie_cap_get_type(dev);
+        if ((type == PCI_EXP_TYPE_ROOT_PORT ||
+            type == PCI_EXP_TYPE_UPSTREAM ||
+            type == PCI_EXP_TYPE_DOWNSTREAM) &&
+            !pcie_aer_msg_vbridge(dev, msg)) {
+                return;
+        }
+        if (!pcie_aer_msg_alldev(dev, msg)) {
+            return;
+        }
+        if (type == PCI_EXP_TYPE_ROOT_PORT) {
+            pcie_aer_msg_root_port(dev, msg);
+            /* Root port can notify system itself,
+               or send the error message to root complex event collector. */
+            /*
+             * if root port is associated with an event collector,
+             * return the root complex event collector here.
+             * For now root complex event collector isn't supported.
+             */
+            return;
+        }
+        dev = pci_bridge_get_device(dev->bus);
+    }
+}
+
+static void pcie_aer_update_log(PCIDevice *dev, const PCIEAERErr *err)
+{
+    uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+    uint8_t first_bit = ctz32(err->status);
+    uint32_t errcap = pci_get_long(aer_cap + PCI_ERR_CAP);
+    int i;
+
+    assert(err->status);
+    assert(!(err->status & (err->status - 1)));
+
+    errcap &= ~(PCI_ERR_CAP_FEP_MASK | PCI_ERR_CAP_TLP);
+    errcap |= PCI_ERR_CAP_FEP(first_bit);
+
+    if (err->flags & PCIE_AER_ERR_HEADER_VALID) {
+        for (i = 0; i < ARRAY_SIZE(err->header); ++i) {
+            /* 7.10.8 Header Log Register */
+            uint8_t *header_log =
+                aer_cap + PCI_ERR_HEADER_LOG + i * sizeof err->header[0];
+            stl_be_p(header_log, err->header[i]);
+        }
+    } else {
+        assert(!(err->flags & PCIE_AER_ERR_TLP_PREFIX_PRESENT));
+        memset(aer_cap + PCI_ERR_HEADER_LOG, 0, PCI_ERR_HEADER_LOG_SIZE);
+    }
+
+    if ((err->flags & PCIE_AER_ERR_TLP_PREFIX_PRESENT) &&
+        (pci_get_long(dev->config + dev->exp.exp_cap + PCI_EXP_DEVCAP2) &
+         PCI_EXP_DEVCAP2_EETLPP)) {
+        for (i = 0; i < ARRAY_SIZE(err->prefix); ++i) {
+            /* 7.10.12 tlp prefix log register */
+            uint8_t *prefix_log =
+                aer_cap + PCI_ERR_TLP_PREFIX_LOG + i * sizeof err->prefix[0];
+            stl_be_p(prefix_log, err->prefix[i]);
+        }
+        errcap |= PCI_ERR_CAP_TLP;
+    } else {
+        memset(aer_cap + PCI_ERR_TLP_PREFIX_LOG, 0,
+               PCI_ERR_TLP_PREFIX_LOG_SIZE);
+    }
+    pci_set_long(aer_cap + PCI_ERR_CAP, errcap);
+}
+
+static void pcie_aer_clear_log(PCIDevice *dev)
+{
+    uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+
+    pci_long_test_and_clear_mask(aer_cap + PCI_ERR_CAP,
+                                 PCI_ERR_CAP_FEP_MASK | PCI_ERR_CAP_TLP);
+
+    memset(aer_cap + PCI_ERR_HEADER_LOG, 0, PCI_ERR_HEADER_LOG_SIZE);
+    memset(aer_cap + PCI_ERR_TLP_PREFIX_LOG, 0, PCI_ERR_TLP_PREFIX_LOG_SIZE);
+}
+
+static void pcie_aer_clear_error(PCIDevice *dev)
+{
+    uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+    uint32_t errcap = pci_get_long(aer_cap + PCI_ERR_CAP);
+    PCIEAERLog *aer_log = &dev->exp.aer_log;
+    PCIEAERErr err;
+
+    if (!(errcap & PCI_ERR_CAP_MHRE) || !aer_log->log_num) {
+        pcie_aer_clear_log(dev);
+        return;
+    }
+
+    /*
+     * If more errors are queued, set corresponding bits in uncorrectable
+     * error status.
+     * We emulate uncorrectable error status register as W1CS.
+     * So set bit in uncorrectable error status here again for multiple
+     * error recording support.
+     *
+     * 6.2.4.2 Multiple Error Handling(Advanced Error Reporting Capability)
+     */
+    pcie_aer_update_uncor_status(dev);
+
+    aer_log_del_err(aer_log, &err);
+    pcie_aer_update_log(dev, &err);
+}
+
+static int pcie_aer_record_error(PCIDevice *dev,
+                                 const PCIEAERErr *err)
+{
+    uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+    uint32_t errcap = pci_get_long(aer_cap + PCI_ERR_CAP);
+    int fep = PCI_ERR_CAP_FEP(errcap);
+
+    assert(err->status);
+    assert(!(err->status & (err->status - 1)));
+
+    if (errcap & PCI_ERR_CAP_MHRE &&
+        (pci_get_long(aer_cap + PCI_ERR_UNCOR_STATUS) & (1U << fep))) {
+        /*  Not first error. queue error */
+        if (aer_log_add_err(&dev->exp.aer_log, err) < 0) {
+            /* overflow */
+            return -1;
+        }
+        return 0;
+    }
+
+    pcie_aer_update_log(dev, err);
+    return 0;
+}
+
+typedef struct PCIEAERInject {
+    PCIDevice *dev;
+    uint8_t *aer_cap;
+    const PCIEAERErr *err;
+    uint16_t devctl;
+    uint16_t devsta;
+    uint32_t error_status;
+    bool unsupported_request;
+    bool log_overflow;
+    PCIEAERMsg msg;
+} PCIEAERInject;
+
+static bool pcie_aer_inject_cor_error(PCIEAERInject *inj,
+                                      uint32_t uncor_status,
+                                      bool is_advisory_nonfatal)
+{
+    PCIDevice *dev = inj->dev;
+
+    inj->devsta |= PCI_EXP_DEVSTA_CED;
+    if (inj->unsupported_request) {
+        inj->devsta |= PCI_EXP_DEVSTA_URD;
+    }
+    pci_set_word(dev->config + dev->exp.exp_cap + PCI_EXP_DEVSTA, inj->devsta);
+
+    if (inj->aer_cap) {
+        uint32_t mask;
+        pci_long_test_and_set_mask(inj->aer_cap + PCI_ERR_COR_STATUS,
+                                   inj->error_status);
+        mask = pci_get_long(inj->aer_cap + PCI_ERR_COR_MASK);
+        if (mask & inj->error_status) {
+            return false;
+        }
+        if (is_advisory_nonfatal) {
+            uint32_t uncor_mask =
+                pci_get_long(inj->aer_cap + PCI_ERR_UNCOR_MASK);
+            if (!(uncor_mask & uncor_status)) {
+                inj->log_overflow = !!pcie_aer_record_error(dev, inj->err);
+            }
+            pci_long_test_and_set_mask(inj->aer_cap + PCI_ERR_UNCOR_STATUS,
+                                       uncor_status);
+        }
+    }
+
+    if (inj->unsupported_request && !(inj->devctl & PCI_EXP_DEVCTL_URRE)) {
+        return false;
+    }
+    if (!(inj->devctl & PCI_EXP_DEVCTL_CERE)) {
+        return false;
+    }
+
+    inj->msg.severity = PCI_ERR_ROOT_CMD_COR_EN;
+    return true;
+}
+
+static bool pcie_aer_inject_uncor_error(PCIEAERInject *inj, bool is_fatal)
+{
+    PCIDevice *dev = inj->dev;
+    uint16_t cmd;
+
+    if (is_fatal) {
+        inj->devsta |= PCI_EXP_DEVSTA_FED;
+    } else {
+        inj->devsta |= PCI_EXP_DEVSTA_NFED;
+    }
+    if (inj->unsupported_request) {
+        inj->devsta |= PCI_EXP_DEVSTA_URD;
+    }
+    pci_set_long(dev->config + dev->exp.exp_cap + PCI_EXP_DEVSTA, inj->devsta);
+
+    if (inj->aer_cap) {
+        uint32_t mask = pci_get_long(inj->aer_cap + PCI_ERR_UNCOR_MASK);
+        if (mask & inj->error_status) {
+            pci_long_test_and_set_mask(inj->aer_cap + PCI_ERR_UNCOR_STATUS,
+                                       inj->error_status);
+            return false;
+        }
+
+        inj->log_overflow = !!pcie_aer_record_error(dev, inj->err);
+        pci_long_test_and_set_mask(inj->aer_cap + PCI_ERR_UNCOR_STATUS,
+                                   inj->error_status);
+    }
+
+    cmd = pci_get_word(dev->config + PCI_COMMAND);
+    if (inj->unsupported_request &&
+        !(inj->devctl & PCI_EXP_DEVCTL_URRE) && !(cmd & PCI_COMMAND_SERR)) {
+        return false;
+    }
+    if (is_fatal) {
+        if (!((cmd & PCI_COMMAND_SERR) ||
+              (inj->devctl & PCI_EXP_DEVCTL_FERE))) {
+            return false;
+        }
+        inj->msg.severity = PCI_ERR_ROOT_CMD_FATAL_EN;
+    } else {
+        if (!((cmd & PCI_COMMAND_SERR) ||
+              (inj->devctl & PCI_EXP_DEVCTL_NFERE))) {
+            return false;
+        }
+        inj->msg.severity = PCI_ERR_ROOT_CMD_NONFATAL_EN;
+    }
+    return true;
+}
+
+/*
+ * non-Function specific error must be recorded in all functions.
+ * It is the responsibility of the caller of this function.
+ * It is also caller's responsibility to determine which function should
+ * report the error.
+ *
+ * 6.2.4 Error Logging
+ * 6.2.5 Sequence of Device Error Signaling and Logging Operations
+ * Figure 6-2: Flowchart Showing Sequence of Device Error Signaling and Logging
+ *             Operations
+ */
+int pcie_aer_inject_error(PCIDevice *dev, const PCIEAERErr *err)
+{
+    uint8_t *aer_cap = NULL;
+    uint16_t devctl = 0;
+    uint16_t devsta = 0;
+    uint32_t error_status = err->status;
+    PCIEAERInject inj;
+
+    if (!pci_is_express(dev)) {
+        return -ENOSYS;
+    }
+
+    if (err->flags & PCIE_AER_ERR_IS_CORRECTABLE) {
+        error_status &= PCI_ERR_COR_SUPPORTED;
+    } else {
+        error_status &= PCI_ERR_UNC_SUPPORTED;
+    }
+
+    /* invalid status bit. one and only one bit must be set */
+    if (!error_status || (error_status & (error_status - 1))) {
+        return -EINVAL;
+    }
+
+    if (dev->exp.aer_cap) {
+        uint8_t *exp_cap = dev->config + dev->exp.exp_cap;
+        aer_cap = dev->config + dev->exp.aer_cap;
+        devctl = pci_get_long(exp_cap + PCI_EXP_DEVCTL);
+        devsta = pci_get_long(exp_cap + PCI_EXP_DEVSTA);
+    }
+
+    inj.dev = dev;
+    inj.aer_cap = aer_cap;
+    inj.err = err;
+    inj.devctl = devctl;
+    inj.devsta = devsta;
+    inj.error_status = error_status;
+    inj.unsupported_request = !(err->flags & PCIE_AER_ERR_IS_CORRECTABLE) &&
+        err->status == PCI_ERR_UNC_UNSUP;
+    inj.log_overflow = false;
+
+    if (err->flags & PCIE_AER_ERR_IS_CORRECTABLE) {
+        if (!pcie_aer_inject_cor_error(&inj, 0, false)) {
+            return 0;
+        }
+    } else {
+        bool is_fatal =
+            pcie_aer_uncor_default_severity(error_status) ==
+            PCI_ERR_ROOT_CMD_FATAL_EN;
+        if (aer_cap) {
+            is_fatal =
+                error_status & pci_get_long(aer_cap + PCI_ERR_UNCOR_SEVER);
+        }
+        if (!is_fatal && (err->flags & PCIE_AER_ERR_MAYBE_ADVISORY)) {
+            inj.error_status = PCI_ERR_COR_ADV_NONFATAL;
+            if (!pcie_aer_inject_cor_error(&inj, error_status, true)) {
+                return 0;
+            }
+        } else {
+            if (!pcie_aer_inject_uncor_error(&inj, is_fatal)) {
+                return 0;
+            }
+        }
+    }
+
+    /* send up error message */
+    inj.msg.source_id = err->source_id;
+    pcie_aer_msg(dev, &inj.msg);
+
+    if (inj.log_overflow) {
+        PCIEAERErr header_log_overflow = {
+            .status = PCI_ERR_COR_HL_OVERFLOW,
+            .flags = PCIE_AER_ERR_IS_CORRECTABLE,
+        };
+        int ret = pcie_aer_inject_error(dev, &header_log_overflow);
+        assert(!ret);
+    }
+    return 0;
+}
+
+void pcie_aer_write_config(PCIDevice *dev,
+                           uint32_t addr, uint32_t val, int len)
+{
+    uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+    uint32_t errcap = pci_get_long(aer_cap + PCI_ERR_CAP);
+    uint32_t first_error = 1U << PCI_ERR_CAP_FEP(errcap);
+    uint32_t uncorsta = pci_get_long(aer_cap + PCI_ERR_UNCOR_STATUS);
+
+    /* uncorrectable error */
+    if (!(uncorsta & first_error)) {
+        /* the bit that corresponds to the first error is cleared */
+        pcie_aer_clear_error(dev);
+    } else if (errcap & PCI_ERR_CAP_MHRE) {
+        /* When PCI_ERR_CAP_MHRE is enabled and the first error isn't cleared
+         * nothing should happen. So we have to revert the modification to
+         * the register.
+         */
+        pcie_aer_update_uncor_status(dev);
+    } else {
+        /* capability & control
+         * PCI_ERR_CAP_MHRE might be cleared, so clear of header log.
+         */
+        aer_log_clear_all_err(&dev->exp.aer_log);
+    }
+}
+
+void pcie_aer_root_init(PCIDevice *dev)
+{
+    uint16_t pos = dev->exp.aer_cap;
+
+    pci_set_long(dev->wmask + pos + PCI_ERR_ROOT_COMMAND,
+                 PCI_ERR_ROOT_CMD_EN_MASK);
+    pci_set_long(dev->w1cmask + pos + PCI_ERR_ROOT_STATUS,
+                 PCI_ERR_ROOT_STATUS_REPORT_MASK);
+    /* PCI_ERR_ROOT_IRQ is RO but devices change it using a
+     * device-specific method.
+     */
+    pci_set_long(dev->cmask + pos + PCI_ERR_ROOT_STATUS,
+                 ~PCI_ERR_ROOT_IRQ);
+}
+
+void pcie_aer_root_reset(PCIDevice *dev)
+{
+    uint8_t* aer_cap = dev->config + dev->exp.aer_cap;
+
+    pci_set_long(aer_cap + PCI_ERR_ROOT_COMMAND, 0);
+
+    /*
+     * Advanced Error Interrupt Message Number in Root Error Status Register
+     * must be updated by chip dependent code because it's chip dependent
+     * which number is used.
+     */
+}
+
+void pcie_aer_root_write_config(PCIDevice *dev,
+                                uint32_t addr, uint32_t val, int len,
+                                uint32_t root_cmd_prev)
+{
+    uint8_t *aer_cap = dev->config + dev->exp.aer_cap;
+    uint32_t root_status = pci_get_long(aer_cap + PCI_ERR_ROOT_STATUS);
+    uint32_t enabled_cmd = pcie_aer_status_to_cmd(root_status);
+    uint32_t root_cmd = pci_get_long(aer_cap + PCI_ERR_ROOT_COMMAND);
+    /* 6.2.4.1.2 Interrupt Generation */
+    if (!msix_enabled(dev) && !msi_enabled(dev)) {
+        pci_set_irq(dev, !!(root_cmd & enabled_cmd));
+        return;
+    }
+
+    if ((root_cmd_prev & enabled_cmd) || !(root_cmd & enabled_cmd)) {
+        /* Send MSI on transition from false to true. */
+        return;
+    }
+
+    pcie_aer_root_notify(dev);
+}
+
+static const VMStateDescription vmstate_pcie_aer_err = {
+    .name = "PCIE_AER_ERROR",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT32(status, PCIEAERErr),
+        VMSTATE_UINT16(source_id, PCIEAERErr),
+        VMSTATE_UINT16(flags, PCIEAERErr),
+        VMSTATE_UINT32_ARRAY(header, PCIEAERErr, 4),
+        VMSTATE_UINT32_ARRAY(prefix, PCIEAERErr, 4),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static bool pcie_aer_state_log_num_valid(void *opaque, int version_id)
+{
+    PCIEAERLog *s = opaque;
+
+    return s->log_num <= s->log_max;
+}
+
+const VMStateDescription vmstate_pcie_aer_log = {
+    .name = "PCIE_AER_ERROR_LOG",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT16(log_num, PCIEAERLog),
+        VMSTATE_UINT16_EQUAL(log_max, PCIEAERLog),
+        VMSTATE_VALIDATE("log_num <= log_max", pcie_aer_state_log_num_valid),
+        VMSTATE_STRUCT_VARRAY_POINTER_UINT16(log, PCIEAERLog, log_num,
+                              vmstate_pcie_aer_err, PCIEAERErr),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+typedef struct PCIEAERErrorName {
+    const char *name;
+    uint32_t val;
+    bool correctable;
+} PCIEAERErrorName;
+
+/*
+ * AER error name -> value conversion table
+ * This naming scheme is same to linux aer-injection tool.
+ */
+static const struct PCIEAERErrorName pcie_aer_error_list[] = {
+    {
+        .name = "TRAIN",
+        .val = PCI_ERR_UNC_TRAIN,
+        .correctable = false,
+    }, {
+        .name = "DLP",
+        .val = PCI_ERR_UNC_DLP,
+        .correctable = false,
+    }, {
+        .name = "SDN",
+        .val = PCI_ERR_UNC_SDN,
+        .correctable = false,
+    }, {
+        .name = "POISON_TLP",
+        .val = PCI_ERR_UNC_POISON_TLP,
+        .correctable = false,
+    }, {
+        .name = "FCP",
+        .val = PCI_ERR_UNC_FCP,
+        .correctable = false,
+    }, {
+        .name = "COMP_TIME",
+        .val = PCI_ERR_UNC_COMP_TIME,
+        .correctable = false,
+    }, {
+        .name = "COMP_ABORT",
+        .val = PCI_ERR_UNC_COMP_ABORT,
+        .correctable = false,
+    }, {
+        .name = "UNX_COMP",
+        .val = PCI_ERR_UNC_UNX_COMP,
+        .correctable = false,
+    }, {
+        .name = "RX_OVER",
+        .val = PCI_ERR_UNC_RX_OVER,
+        .correctable = false,
+    }, {
+        .name = "MALF_TLP",
+        .val = PCI_ERR_UNC_MALF_TLP,
+        .correctable = false,
+    }, {
+        .name = "ECRC",
+        .val = PCI_ERR_UNC_ECRC,
+        .correctable = false,
+    }, {
+        .name = "UNSUP",
+        .val = PCI_ERR_UNC_UNSUP,
+        .correctable = false,
+    }, {
+        .name = "ACSV",
+        .val = PCI_ERR_UNC_ACSV,
+        .correctable = false,
+    }, {
+        .name = "INTN",
+        .val = PCI_ERR_UNC_INTN,
+        .correctable = false,
+    }, {
+        .name = "MCBTLP",
+        .val = PCI_ERR_UNC_MCBTLP,
+        .correctable = false,
+    }, {
+        .name = "ATOP_EBLOCKED",
+        .val = PCI_ERR_UNC_ATOP_EBLOCKED,
+        .correctable = false,
+    }, {
+        .name = "TLP_PRF_BLOCKED",
+        .val = PCI_ERR_UNC_TLP_PRF_BLOCKED,
+        .correctable = false,
+    }, {
+        .name = "RCVR",
+        .val = PCI_ERR_COR_RCVR,
+        .correctable = true,
+    }, {
+        .name = "BAD_TLP",
+        .val = PCI_ERR_COR_BAD_TLP,
+        .correctable = true,
+    }, {
+        .name = "BAD_DLLP",
+        .val = PCI_ERR_COR_BAD_DLLP,
+        .correctable = true,
+    }, {
+        .name = "REP_ROLL",
+        .val = PCI_ERR_COR_REP_ROLL,
+        .correctable = true,
+    }, {
+        .name = "REP_TIMER",
+        .val = PCI_ERR_COR_REP_TIMER,
+        .correctable = true,
+    }, {
+        .name = "ADV_NONFATAL",
+        .val = PCI_ERR_COR_ADV_NONFATAL,
+        .correctable = true,
+    }, {
+        .name = "INTERNAL",
+        .val = PCI_ERR_COR_INTERNAL,
+        .correctable = true,
+    }, {
+        .name = "HL_OVERFLOW",
+        .val = PCI_ERR_COR_HL_OVERFLOW,
+        .correctable = true,
+    },
+};
+
+static int pcie_aer_parse_error_string(const char *error_name,
+                                       uint32_t *status, bool *correctable)
+{
+    int i;
+
+    for (i = 0; i < ARRAY_SIZE(pcie_aer_error_list); i++) {
+        const  PCIEAERErrorName *e = &pcie_aer_error_list[i];
+        if (strcmp(error_name, e->name)) {
+            continue;
+        }
+
+        *status = e->val;
+        *correctable = e->correctable;
+        return 0;
+    }
+    return -EINVAL;
+}
+
+static int do_pcie_aer_inject_error(Monitor *mon,
+                                    const QDict *qdict, QObject **ret_data)
+{
+    const char *id = qdict_get_str(qdict, "id");
+    const char *error_name;
+    uint32_t error_status;
+    bool correctable;
+    PCIDevice *dev;
+    PCIEAERErr err;
+    int ret;
+
+    ret = pci_qdev_find_device(id, &dev);
+    if (ret < 0) {
+        monitor_printf(mon,
+                       "id or pci device path is invalid or device not "
+                       "found. %s\n", id);
+        return ret;
+    }
+    if (!pci_is_express(dev)) {
+        monitor_printf(mon, "the device doesn't support pci express. %s\n",
+                       id);
+        return -ENOSYS;
+    }
+
+    error_name = qdict_get_str(qdict, "error_status");
+    if (pcie_aer_parse_error_string(error_name, &error_status, &correctable)) {
+        char *e = NULL;
+        error_status = strtoul(error_name, &e, 0);
+        correctable = qdict_get_try_bool(qdict, "correctable", false);
+        if (!e || *e != '\0') {
+            monitor_printf(mon, "invalid error status value. \"%s\"",
+                           error_name);
+            return -EINVAL;
+        }
+    }
+    err.status = error_status;
+    err.source_id = (pci_bus_num(dev->bus) << 8) | dev->devfn;
+
+    err.flags = 0;
+    if (correctable) {
+        err.flags |= PCIE_AER_ERR_IS_CORRECTABLE;
+    }
+    if (qdict_get_try_bool(qdict, "advisory_non_fatal", false)) {
+        err.flags |= PCIE_AER_ERR_MAYBE_ADVISORY;
+    }
+    if (qdict_haskey(qdict, "header0")) {
+        err.flags |= PCIE_AER_ERR_HEADER_VALID;
+    }
+    if (qdict_haskey(qdict, "prefix0")) {
+        err.flags |= PCIE_AER_ERR_TLP_PREFIX_PRESENT;
+    }
+
+    err.header[0] = qdict_get_try_int(qdict, "header0", 0);
+    err.header[1] = qdict_get_try_int(qdict, "header1", 0);
+    err.header[2] = qdict_get_try_int(qdict, "header2", 0);
+    err.header[3] = qdict_get_try_int(qdict, "header3", 0);
+
+    err.prefix[0] = qdict_get_try_int(qdict, "prefix0", 0);
+    err.prefix[1] = qdict_get_try_int(qdict, "prefix1", 0);
+    err.prefix[2] = qdict_get_try_int(qdict, "prefix2", 0);
+    err.prefix[3] = qdict_get_try_int(qdict, "prefix3", 0);
+
+    ret = pcie_aer_inject_error(dev, &err);
+    *ret_data = qobject_from_jsonf("{'id': %s, "
+                                   "'root_bus': %s, 'bus': %d, 'devfn': %d, "
+                                   "'ret': %d}",
+                                   id, pci_root_bus_path(dev),
+                                   pci_bus_num(dev->bus), dev->devfn,
+                                   ret);
+    assert(*ret_data);
+
+    return 0;
+}
+
+void hmp_pcie_aer_inject_error(Monitor *mon, const QDict *qdict)
+{
+    QObject *data;
+    int devfn;
+
+    if (do_pcie_aer_inject_error(mon, qdict, &data) < 0) {
+        return;
+    }
+
+    assert(qobject_type(data) == QTYPE_QDICT);
+    qdict = qobject_to_qdict(data);
+
+    devfn = (int)qdict_get_int(qdict, "devfn");
+    monitor_printf(mon, "OK id: %s root bus: %s, bus: %x devfn: %x.%x\n",
+                   qdict_get_str(qdict, "id"),
+                   qdict_get_str(qdict, "root_bus"),
+                   (int) qdict_get_int(qdict, "bus"),
+                   PCI_SLOT(devfn), PCI_FUNC(devfn));
+}
diff --git a/qemu/hw/pci/pcie_host.c b/qemu/hw/pci/pcie_host.c
new file mode 100644
index 000000000..d8afba863
--- /dev/null
+++ b/qemu/hw/pci/pcie_host.c
@@ -0,0 +1,146 @@
+/*
+ * pcie_host.c
+ * utility functions for pci express host bridge.
+ *
+ * Copyright (c) 2009 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+
+ * 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/>.
+ */
+
+#include "hw/hw.h"
+#include "hw/pci/pci.h"
+#include "hw/pci/pcie_host.h"
+#include "exec/address-spaces.h"
+
+/* a helper function to get a PCIDevice for a given mmconfig address */
+static inline PCIDevice *pcie_dev_find_by_mmcfg_addr(PCIBus *s,
+                                                     uint32_t mmcfg_addr)
+{
+    return pci_find_device(s, PCIE_MMCFG_BUS(mmcfg_addr),
+                           PCIE_MMCFG_DEVFN(mmcfg_addr));
+}
+
+static void pcie_mmcfg_data_write(void *opaque, hwaddr mmcfg_addr,
+                                  uint64_t val, unsigned len)
+{
+    PCIExpressHost *e = opaque;
+    PCIBus *s = e->pci.bus;
+    PCIDevice *pci_dev = pcie_dev_find_by_mmcfg_addr(s, mmcfg_addr);
+    uint32_t addr;
+    uint32_t limit;
+
+    if (!pci_dev) {
+        return;
+    }
+    addr = PCIE_MMCFG_CONFOFFSET(mmcfg_addr);
+    limit = pci_config_size(pci_dev);
+    if (limit <= addr) {
+        /* conventional pci device can be behind pcie-to-pci bridge.
+           256 <= addr < 4K has no effects. */
+        return;
+    }
+    pci_host_config_write_common(pci_dev, addr, limit, val, len);
+}
+
+static uint64_t pcie_mmcfg_data_read(void *opaque,
+                                     hwaddr mmcfg_addr,
+                                     unsigned len)
+{
+    PCIExpressHost *e = opaque;
+    PCIBus *s = e->pci.bus;
+    PCIDevice *pci_dev = pcie_dev_find_by_mmcfg_addr(s, mmcfg_addr);
+    uint32_t addr;
+    uint32_t limit;
+
+    if (!pci_dev) {
+        return ~0x0;
+    }
+    addr = PCIE_MMCFG_CONFOFFSET(mmcfg_addr);
+    limit = pci_config_size(pci_dev);
+    if (limit <= addr) {
+        /* conventional pci device can be behind pcie-to-pci bridge.
+           256 <= addr < 4K has no effects. */
+        return ~0x0;
+    }
+    return pci_host_config_read_common(pci_dev, addr, limit, len);
+}
+
+static const MemoryRegionOps pcie_mmcfg_ops = {
+    .read = pcie_mmcfg_data_read,
+    .write = pcie_mmcfg_data_write,
+    .endianness = DEVICE_NATIVE_ENDIAN,
+};
+
+static void pcie_host_init(Object *obj)
+{
+    PCIExpressHost *e = PCIE_HOST_BRIDGE(obj);
+
+    e->base_addr = PCIE_BASE_ADDR_UNMAPPED;
+    memory_region_init_io(&e->mmio, OBJECT(e), &pcie_mmcfg_ops, e, "pcie-mmcfg-mmio",
+                          PCIE_MMCFG_SIZE_MAX);
+}
+
+void pcie_host_mmcfg_unmap(PCIExpressHost *e)
+{
+    if (e->base_addr != PCIE_BASE_ADDR_UNMAPPED) {
+        memory_region_del_subregion(get_system_memory(), &e->mmio);
+        e->base_addr = PCIE_BASE_ADDR_UNMAPPED;
+    }
+}
+
+void pcie_host_mmcfg_init(PCIExpressHost *e, uint32_t size)
+{
+    assert(!(size & (size - 1)));       /* power of 2 */
+    assert(size >= PCIE_MMCFG_SIZE_MIN);
+    assert(size <= PCIE_MMCFG_SIZE_MAX);
+    e->size = size;
+    memory_region_set_size(&e->mmio, e->size);
+}
+
+void pcie_host_mmcfg_map(PCIExpressHost *e, hwaddr addr,
+                         uint32_t size)
+{
+    pcie_host_mmcfg_init(e, size);
+    e->base_addr = addr;
+    memory_region_add_subregion(get_system_memory(), e->base_addr, &e->mmio);
+}
+
+void pcie_host_mmcfg_update(PCIExpressHost *e,
+                            int enable,
+                            hwaddr addr,
+                            uint32_t size)
+{
+    memory_region_transaction_begin();
+    pcie_host_mmcfg_unmap(e);
+    if (enable) {
+        pcie_host_mmcfg_map(e, addr, size);
+    }
+    memory_region_transaction_commit();
+}
+
+static const TypeInfo pcie_host_type_info = {
+    .name = TYPE_PCIE_HOST_BRIDGE,
+    .parent = TYPE_PCI_HOST_BRIDGE,
+    .abstract = true,
+    .instance_size = sizeof(PCIExpressHost),
+    .instance_init = pcie_host_init,
+};
+
+static void pcie_host_register_types(void)
+{
+    type_register_static(&pcie_host_type_info);
+}
+
+type_init(pcie_host_register_types)
diff --git a/qemu/hw/pci/pcie_port.c b/qemu/hw/pci/pcie_port.c
new file mode 100644
index 000000000..40ca8d5d1
--- /dev/null
+++ b/qemu/hw/pci/pcie_port.c
@@ -0,0 +1,178 @@
+/*
+ * pcie_port.c
+ *
+ * Copyright (c) 2010 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * 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/>.
+ */
+
+#include "hw/pci/pcie_port.h"
+#include "hw/hotplug.h"
+
+void pcie_port_init_reg(PCIDevice *d)
+{
+    /* Unlike pci bridge,
+       66MHz and fast back to back don't apply to pci express port. */
+    pci_set_word(d->config + PCI_STATUS, 0);
+    pci_set_word(d->config + PCI_SEC_STATUS, 0);
+
+    /*
+     * Unlike conventional pci bridge, for some bits the spec states:
+     * Does not apply to PCI Express and must be hardwired to 0.
+     */
+    pci_word_test_and_clear_mask(d->wmask + PCI_BRIDGE_CONTROL,
+                                 PCI_BRIDGE_CTL_MASTER_ABORT |
+                                 PCI_BRIDGE_CTL_FAST_BACK |
+                                 PCI_BRIDGE_CTL_DISCARD |
+                                 PCI_BRIDGE_CTL_SEC_DISCARD |
+                                 PCI_BRIDGE_CTL_DISCARD_STATUS |
+                                 PCI_BRIDGE_CTL_DISCARD_SERR);
+}
+
+/**************************************************************************
+ * (chassis number, pcie physical slot number) -> pcie slot conversion
+ */
+struct PCIEChassis {
+    uint8_t     number;
+
+    QLIST_HEAD(, PCIESlot) slots;
+    QLIST_ENTRY(PCIEChassis) next;
+};
+
+static QLIST_HEAD(, PCIEChassis) chassis = QLIST_HEAD_INITIALIZER(chassis);
+
+static struct PCIEChassis *pcie_chassis_find(uint8_t chassis_number)
+{
+    struct PCIEChassis *c;
+    QLIST_FOREACH(c, &chassis, next) {
+        if (c->number == chassis_number) {
+            break;
+        }
+    }
+    return c;
+}
+
+void pcie_chassis_create(uint8_t chassis_number)
+{
+    struct PCIEChassis *c;
+    c = pcie_chassis_find(chassis_number);
+    if (c) {
+        return;
+    }
+    c = g_malloc0(sizeof(*c));
+    c->number = chassis_number;
+    QLIST_INIT(&c->slots);
+    QLIST_INSERT_HEAD(&chassis, c, next);
+}
+
+static PCIESlot *pcie_chassis_find_slot_with_chassis(struct PCIEChassis *c,
+                                                     uint8_t slot)
+{
+    PCIESlot *s;
+    QLIST_FOREACH(s, &c->slots, next) {
+        if (s->slot == slot) {
+            break;
+        }
+    }
+    return s;
+}
+
+PCIESlot *pcie_chassis_find_slot(uint8_t chassis_number, uint16_t slot)
+{
+    struct PCIEChassis *c;
+    c = pcie_chassis_find(chassis_number);
+    if (!c) {
+        return NULL;
+    }
+    return pcie_chassis_find_slot_with_chassis(c, slot);
+}
+
+int pcie_chassis_add_slot(struct PCIESlot *slot)
+{
+    struct PCIEChassis *c;
+    c = pcie_chassis_find(slot->chassis);
+    if (!c) {
+        return -ENODEV;
+    }
+    if (pcie_chassis_find_slot_with_chassis(c, slot->slot)) {
+        return -EBUSY;
+    }
+    QLIST_INSERT_HEAD(&c->slots, slot, next);
+    return 0;
+}
+
+void pcie_chassis_del_slot(PCIESlot *s)
+{
+    QLIST_REMOVE(s, next);
+}
+
+static Property pcie_port_props[] = {
+    DEFINE_PROP_UINT8("port", PCIEPort, port, 0),
+    DEFINE_PROP_UINT16("aer_log_max", PCIEPort,
+                       parent_obj.parent_obj.exp.aer_log.log_max,
+                       PCIE_AER_LOG_MAX_DEFAULT),
+    DEFINE_PROP_END_OF_LIST()
+};
+
+static void pcie_port_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+
+    dc->props = pcie_port_props;
+}
+
+static const TypeInfo pcie_port_type_info = {
+    .name = TYPE_PCIE_PORT,
+    .parent = TYPE_PCI_BRIDGE,
+    .instance_size = sizeof(PCIEPort),
+    .abstract = true,
+    .class_init = pcie_port_class_init,
+};
+
+static Property pcie_slot_props[] = {
+    DEFINE_PROP_UINT8("chassis", PCIESlot, chassis, 0),
+    DEFINE_PROP_UINT16("slot", PCIESlot, slot, 0),
+    DEFINE_PROP_END_OF_LIST()
+};
+
+static void pcie_slot_class_init(ObjectClass *oc, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(oc);
+    HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(oc);
+
+    dc->props = pcie_slot_props;
+    hc->plug = pcie_cap_slot_hotplug_cb;
+    hc->unplug_request = pcie_cap_slot_hot_unplug_request_cb;
+}
+
+static const TypeInfo pcie_slot_type_info = {
+    .name = TYPE_PCIE_SLOT,
+    .parent = TYPE_PCIE_PORT,
+    .instance_size = sizeof(PCIESlot),
+    .abstract = true,
+    .class_init = pcie_slot_class_init,
+    .interfaces = (InterfaceInfo[]) {
+        { TYPE_HOTPLUG_HANDLER },
+        { }
+    }
+};
+
+static void pcie_port_register_types(void)
+{
+    type_register_static(&pcie_port_type_info);
+    type_register_static(&pcie_slot_type_info);
+}
+
+type_init(pcie_port_register_types)
diff --git a/qemu/hw/pci/shpc.c b/qemu/hw/pci/shpc.c
new file mode 100644
index 000000000..bfb4d31b6
--- /dev/null
+++ b/qemu/hw/pci/shpc.c
@@ -0,0 +1,721 @@
+#include "qemu-common.h"
+#include <strings.h>
+#include <stdint.h>
+#include "qemu/range.h"
+#include "qemu/error-report.h"
+#include "hw/pci/shpc.h"
+#include "hw/pci/pci.h"
+#include "hw/pci/pci_bus.h"
+#include "hw/pci/msi.h"
+
+/* TODO: model power only and disabled slot states. */
+/* TODO: handle SERR and wakeups */
+/* TODO: consider enabling 66MHz support */
+
+/* TODO: remove fully only on state DISABLED and LED off.
+ * track state to properly record this. */
+
+/* SHPC Working Register Set */
+#define SHPC_BASE_OFFSET  0x00 /* 4 bytes */
+#define SHPC_SLOTS_33     0x04 /* 4 bytes. Also encodes PCI-X slots. */
+#define SHPC_SLOTS_66     0x08 /* 4 bytes. */
+#define SHPC_NSLOTS       0x0C /* 1 byte */
+#define SHPC_FIRST_DEV    0x0D /* 1 byte */
+#define SHPC_PHYS_SLOT    0x0E /* 2 byte */
+#define SHPC_PHYS_NUM_MAX 0x7ff
+#define SHPC_PHYS_NUM_UP  0x2000
+#define SHPC_PHYS_MRL     0x4000
+#define SHPC_PHYS_BUTTON  0x8000
+#define SHPC_SEC_BUS      0x10 /* 2 bytes */
+#define SHPC_SEC_BUS_33   0x0
+#define SHPC_SEC_BUS_66   0x1 /* Unused */
+#define SHPC_SEC_BUS_MASK 0x7
+#define SHPC_MSI_CTL      0x12 /* 1 byte */
+#define SHPC_PROG_IFC     0x13 /* 1 byte */
+#define SHPC_PROG_IFC_1_0 0x1
+#define SHPC_CMD_CODE     0x14 /* 1 byte */
+#define SHPC_CMD_TRGT     0x15 /* 1 byte */
+#define SHPC_CMD_TRGT_MIN 0x1
+#define SHPC_CMD_TRGT_MAX 0x1f
+#define SHPC_CMD_STATUS   0x16 /* 2 bytes */
+#define SHPC_CMD_STATUS_BUSY          0x1
+#define SHPC_CMD_STATUS_MRL_OPEN      0x2
+#define SHPC_CMD_STATUS_INVALID_CMD   0x4
+#define SHPC_CMD_STATUS_INVALID_MODE  0x8
+#define SHPC_INT_LOCATOR  0x18 /* 4 bytes */
+#define SHPC_INT_COMMAND  0x1
+#define SHPC_SERR_LOCATOR 0x1C /* 4 bytes */
+#define SHPC_SERR_INT     0x20 /* 4 bytes */
+#define SHPC_INT_DIS      0x1
+#define SHPC_SERR_DIS     0x2
+#define SHPC_CMD_INT_DIS  0x4
+#define SHPC_ARB_SERR_DIS 0x8
+#define SHPC_CMD_DETECTED 0x10000
+#define SHPC_ARB_DETECTED 0x20000
+ /* 4 bytes * slot # (start from 0) */
+#define SHPC_SLOT_REG(s)         (0x24 + (s) * 4)
+ /* 2 bytes */
+#define SHPC_SLOT_STATUS(s)       (0x0 + SHPC_SLOT_REG(s))
+
+/* Same slot state masks are used for command and status registers */
+#define SHPC_SLOT_STATE_MASK     0x03
+#define SHPC_SLOT_STATE_SHIFT \
+    ctz32(SHPC_SLOT_STATE_MASK)
+
+#define SHPC_STATE_NO       0x0
+#define SHPC_STATE_PWRONLY  0x1
+#define SHPC_STATE_ENABLED  0x2
+#define SHPC_STATE_DISABLED 0x3
+
+#define SHPC_SLOT_PWR_LED_MASK   0xC
+#define SHPC_SLOT_PWR_LED_SHIFT \
+    ctz32(SHPC_SLOT_PWR_LED_MASK)
+#define SHPC_SLOT_ATTN_LED_MASK  0x30
+#define SHPC_SLOT_ATTN_LED_SHIFT \
+    ctz32(SHPC_SLOT_ATTN_LED_MASK)
+
+#define SHPC_LED_NO     0x0
+#define SHPC_LED_ON     0x1
+#define SHPC_LED_BLINK  0x2
+#define SHPC_LED_OFF    0x3
+
+#define SHPC_SLOT_STATUS_PWR_FAULT      0x40
+#define SHPC_SLOT_STATUS_BUTTON         0x80
+#define SHPC_SLOT_STATUS_MRL_OPEN       0x100
+#define SHPC_SLOT_STATUS_66             0x200
+#define SHPC_SLOT_STATUS_PRSNT_MASK     0xC00
+#define SHPC_SLOT_STATUS_PRSNT_EMPTY    0x3
+#define SHPC_SLOT_STATUS_PRSNT_25W      0x1
+#define SHPC_SLOT_STATUS_PRSNT_15W      0x2
+#define SHPC_SLOT_STATUS_PRSNT_7_5W     0x0
+
+#define SHPC_SLOT_STATUS_PRSNT_PCIX     0x3000
+
+
+ /* 1 byte */
+#define SHPC_SLOT_EVENT_LATCH(s)        (0x2 + SHPC_SLOT_REG(s))
+ /* 1 byte */
+#define SHPC_SLOT_EVENT_SERR_INT_DIS(d, s) (0x3 + SHPC_SLOT_REG(s))
+#define SHPC_SLOT_EVENT_PRESENCE        0x01
+#define SHPC_SLOT_EVENT_ISOLATED_FAULT  0x02
+#define SHPC_SLOT_EVENT_BUTTON          0x04
+#define SHPC_SLOT_EVENT_MRL             0x08
+#define SHPC_SLOT_EVENT_CONNECTED_FAULT 0x10
+/* Bits below are used for Serr/Int disable only */
+#define SHPC_SLOT_EVENT_MRL_SERR_DIS    0x20
+#define SHPC_SLOT_EVENT_CONNECTED_FAULT_SERR_DIS 0x40
+
+#define SHPC_MIN_SLOTS        1
+#define SHPC_MAX_SLOTS        31
+#define SHPC_SIZEOF(d)    SHPC_SLOT_REG((d)->shpc->nslots)
+
+/* SHPC Slot identifiers */
+
+/* Hotplug supported at 31 slots out of the total 32.  We reserve slot 0,
+   and give the rest of them physical *and* pci numbers starting from 1, so
+   they match logical numbers.  Note: this means that multiple slots must have
+   different chassis number values, to make chassis+physical slot unique.
+   TODO: make this configurable? */
+#define SHPC_IDX_TO_LOGICAL(slot) ((slot) + 1)
+#define SHPC_LOGICAL_TO_IDX(target) ((target) - 1)
+#define SHPC_IDX_TO_PCI(slot) ((slot) + 1)
+#define SHPC_PCI_TO_IDX(pci_slot) ((pci_slot) - 1)
+#define SHPC_IDX_TO_PHYSICAL(slot) ((slot) + 1)
+
+static int roundup_pow_of_two(int x)
+{
+    x |= (x >> 1);
+    x |= (x >> 2);
+    x |= (x >> 4);
+    x |= (x >> 8);
+    x |= (x >> 16);
+    return x + 1;
+}
+
+static uint16_t shpc_get_status(SHPCDevice *shpc, int slot, uint16_t msk)
+{
+    uint8_t *status = shpc->config + SHPC_SLOT_STATUS(slot);
+    return (pci_get_word(status) & msk) >> ctz32(msk);
+}
+
+static void shpc_set_status(SHPCDevice *shpc,
+                            int slot, uint8_t value, uint16_t msk)
+{
+    uint8_t *status = shpc->config + SHPC_SLOT_STATUS(slot);
+    pci_word_test_and_clear_mask(status, msk);
+    pci_word_test_and_set_mask(status, value << ctz32(msk));
+}
+
+static void shpc_interrupt_update(PCIDevice *d)
+{
+    SHPCDevice *shpc = d->shpc;
+    int slot;
+    int level = 0;
+    uint32_t serr_int;
+    uint32_t int_locator = 0;
+
+    /* Update interrupt locator register */
+    for (slot = 0; slot < shpc->nslots; ++slot) {
+        uint8_t event = shpc->config[SHPC_SLOT_EVENT_LATCH(slot)];
+        uint8_t disable = shpc->config[SHPC_SLOT_EVENT_SERR_INT_DIS(d, slot)];
+        uint32_t mask = 1U << SHPC_IDX_TO_LOGICAL(slot);
+        if (event & ~disable) {
+            int_locator |= mask;
+        }
+    }
+    serr_int = pci_get_long(shpc->config + SHPC_SERR_INT);
+    if ((serr_int & SHPC_CMD_DETECTED) && !(serr_int & SHPC_CMD_INT_DIS)) {
+        int_locator |= SHPC_INT_COMMAND;
+    }
+    pci_set_long(shpc->config + SHPC_INT_LOCATOR, int_locator);
+    level = (!(serr_int & SHPC_INT_DIS) && int_locator) ? 1 : 0;
+    if (msi_enabled(d) && shpc->msi_requested != level)
+        msi_notify(d, 0);
+    else
+        pci_set_irq(d, level);
+    shpc->msi_requested = level;
+}
+
+static void shpc_set_sec_bus_speed(SHPCDevice *shpc, uint8_t speed)
+{
+    switch (speed) {
+    case SHPC_SEC_BUS_33:
+        shpc->config[SHPC_SEC_BUS] &= ~SHPC_SEC_BUS_MASK;
+        shpc->config[SHPC_SEC_BUS] |= speed;
+        break;
+    default:
+        pci_word_test_and_set_mask(shpc->config + SHPC_CMD_STATUS,
+                                   SHPC_CMD_STATUS_INVALID_MODE);
+    }
+}
+
+void shpc_reset(PCIDevice *d)
+{
+    SHPCDevice *shpc = d->shpc;
+    int nslots = shpc->nslots;
+    int i;
+    memset(shpc->config, 0, SHPC_SIZEOF(d));
+    pci_set_byte(shpc->config + SHPC_NSLOTS, nslots);
+    pci_set_long(shpc->config + SHPC_SLOTS_33, nslots);
+    pci_set_long(shpc->config + SHPC_SLOTS_66, 0);
+    pci_set_byte(shpc->config + SHPC_FIRST_DEV, SHPC_IDX_TO_PCI(0));
+    pci_set_word(shpc->config + SHPC_PHYS_SLOT,
+                 SHPC_IDX_TO_PHYSICAL(0) |
+                 SHPC_PHYS_NUM_UP |
+                 SHPC_PHYS_MRL |
+                 SHPC_PHYS_BUTTON);
+    pci_set_long(shpc->config + SHPC_SERR_INT, SHPC_INT_DIS |
+                 SHPC_SERR_DIS |
+                 SHPC_CMD_INT_DIS |
+                 SHPC_ARB_SERR_DIS);
+    pci_set_byte(shpc->config + SHPC_PROG_IFC, SHPC_PROG_IFC_1_0);
+    pci_set_word(shpc->config + SHPC_SEC_BUS, SHPC_SEC_BUS_33);
+    for (i = 0; i < shpc->nslots; ++i) {
+        pci_set_byte(shpc->config + SHPC_SLOT_EVENT_SERR_INT_DIS(d, i),
+                     SHPC_SLOT_EVENT_PRESENCE |
+                     SHPC_SLOT_EVENT_ISOLATED_FAULT |
+                     SHPC_SLOT_EVENT_BUTTON |
+                     SHPC_SLOT_EVENT_MRL |
+                     SHPC_SLOT_EVENT_CONNECTED_FAULT |
+                     SHPC_SLOT_EVENT_MRL_SERR_DIS |
+                     SHPC_SLOT_EVENT_CONNECTED_FAULT_SERR_DIS);
+        if (shpc->sec_bus->devices[PCI_DEVFN(SHPC_IDX_TO_PCI(i), 0)]) {
+            shpc_set_status(shpc, i, SHPC_STATE_ENABLED, SHPC_SLOT_STATE_MASK);
+            shpc_set_status(shpc, i, 0, SHPC_SLOT_STATUS_MRL_OPEN);
+            shpc_set_status(shpc, i, SHPC_SLOT_STATUS_PRSNT_7_5W,
+                            SHPC_SLOT_STATUS_PRSNT_MASK);
+            shpc_set_status(shpc, i, SHPC_LED_ON, SHPC_SLOT_PWR_LED_MASK);
+        } else {
+            shpc_set_status(shpc, i, SHPC_STATE_DISABLED, SHPC_SLOT_STATE_MASK);
+            shpc_set_status(shpc, i, 1, SHPC_SLOT_STATUS_MRL_OPEN);
+            shpc_set_status(shpc, i, SHPC_SLOT_STATUS_PRSNT_EMPTY,
+                            SHPC_SLOT_STATUS_PRSNT_MASK);
+            shpc_set_status(shpc, i, SHPC_LED_OFF, SHPC_SLOT_PWR_LED_MASK);
+        }
+        shpc_set_status(shpc, i, 0, SHPC_SLOT_STATUS_66);
+    }
+    shpc_set_sec_bus_speed(shpc, SHPC_SEC_BUS_33);
+    shpc->msi_requested = 0;
+    shpc_interrupt_update(d);
+}
+
+static void shpc_invalid_command(SHPCDevice *shpc)
+{
+    pci_word_test_and_set_mask(shpc->config + SHPC_CMD_STATUS,
+                               SHPC_CMD_STATUS_INVALID_CMD);
+}
+
+static void shpc_free_devices_in_slot(SHPCDevice *shpc, int slot)
+{
+    int devfn;
+    int pci_slot = SHPC_IDX_TO_PCI(slot);
+    for (devfn = PCI_DEVFN(pci_slot, 0);
+         devfn <= PCI_DEVFN(pci_slot, PCI_FUNC_MAX - 1);
+         ++devfn) {
+        PCIDevice *affected_dev = shpc->sec_bus->devices[devfn];
+        if (affected_dev) {
+            object_unparent(OBJECT(affected_dev));
+        }
+    }
+}
+
+static void shpc_slot_command(SHPCDevice *shpc, uint8_t target,
+                              uint8_t state, uint8_t power, uint8_t attn)
+{
+    uint8_t current_state;
+    int slot = SHPC_LOGICAL_TO_IDX(target);
+    if (target < SHPC_CMD_TRGT_MIN || slot >= shpc->nslots) {
+        shpc_invalid_command(shpc);
+        return;
+    }
+    current_state = shpc_get_status(shpc, slot, SHPC_SLOT_STATE_MASK);
+    if (current_state == SHPC_STATE_ENABLED && state == SHPC_STATE_PWRONLY) {
+        shpc_invalid_command(shpc);
+        return;
+    }
+
+    switch (power) {
+    case SHPC_LED_NO:
+        break;
+    default:
+        /* TODO: send event to monitor */
+        shpc_set_status(shpc, slot, power, SHPC_SLOT_PWR_LED_MASK);
+    }
+    switch (attn) {
+    case SHPC_LED_NO:
+        break;
+    default:
+        /* TODO: send event to monitor */
+        shpc_set_status(shpc, slot, attn, SHPC_SLOT_ATTN_LED_MASK);
+    }
+
+    if ((current_state == SHPC_STATE_DISABLED && state == SHPC_STATE_PWRONLY) ||
+        (current_state == SHPC_STATE_DISABLED && state == SHPC_STATE_ENABLED)) {
+        shpc_set_status(shpc, slot, state, SHPC_SLOT_STATE_MASK);
+    } else if ((current_state == SHPC_STATE_ENABLED ||
+                current_state == SHPC_STATE_PWRONLY) &&
+               state == SHPC_STATE_DISABLED) {
+        shpc_set_status(shpc, slot, state, SHPC_SLOT_STATE_MASK);
+        power = shpc_get_status(shpc, slot, SHPC_SLOT_PWR_LED_MASK);
+        /* TODO: track what monitor requested. */
+        /* Look at LED to figure out whether it's ok to remove the device. */
+        if (power == SHPC_LED_OFF) {
+            shpc_free_devices_in_slot(shpc, slot);
+            shpc_set_status(shpc, slot, 1, SHPC_SLOT_STATUS_MRL_OPEN);
+            shpc_set_status(shpc, slot, SHPC_SLOT_STATUS_PRSNT_EMPTY,
+                            SHPC_SLOT_STATUS_PRSNT_MASK);
+            shpc->config[SHPC_SLOT_EVENT_LATCH(slot)] |=
+                SHPC_SLOT_EVENT_BUTTON |
+                SHPC_SLOT_EVENT_MRL |
+                SHPC_SLOT_EVENT_PRESENCE;
+        }
+    }
+}
+
+static void shpc_command(SHPCDevice *shpc)
+{
+    uint8_t code = pci_get_byte(shpc->config + SHPC_CMD_CODE);
+    uint8_t speed;
+    uint8_t target;
+    uint8_t attn;
+    uint8_t power;
+    uint8_t state;
+    int i;
+
+    /* Clear status from the previous command. */
+    pci_word_test_and_clear_mask(shpc->config + SHPC_CMD_STATUS,
+                                 SHPC_CMD_STATUS_BUSY |
+                                 SHPC_CMD_STATUS_MRL_OPEN |
+                                 SHPC_CMD_STATUS_INVALID_CMD |
+                                 SHPC_CMD_STATUS_INVALID_MODE);
+    switch (code) {
+    case 0x00 ... 0x3f:
+        target = shpc->config[SHPC_CMD_TRGT] & SHPC_CMD_TRGT_MAX;
+        state = (code & SHPC_SLOT_STATE_MASK) >> SHPC_SLOT_STATE_SHIFT;
+        power = (code & SHPC_SLOT_PWR_LED_MASK) >> SHPC_SLOT_PWR_LED_SHIFT;
+        attn = (code & SHPC_SLOT_ATTN_LED_MASK) >> SHPC_SLOT_ATTN_LED_SHIFT;
+        shpc_slot_command(shpc, target, state, power, attn);
+        break;
+    case 0x40 ... 0x47:
+        speed = code & SHPC_SEC_BUS_MASK;
+        shpc_set_sec_bus_speed(shpc, speed);
+        break;
+    case 0x48:
+        /* Power only all slots */
+        /* first verify no slots are enabled */
+        for (i = 0; i < shpc->nslots; ++i) {
+            state = shpc_get_status(shpc, i, SHPC_SLOT_STATE_MASK);
+            if (state == SHPC_STATE_ENABLED) {
+                shpc_invalid_command(shpc);
+                goto done;
+            }
+        }
+        for (i = 0; i < shpc->nslots; ++i) {
+            if (!(shpc_get_status(shpc, i, SHPC_SLOT_STATUS_MRL_OPEN))) {
+                shpc_slot_command(shpc, i + SHPC_CMD_TRGT_MIN,
+                                  SHPC_STATE_PWRONLY, SHPC_LED_ON, SHPC_LED_NO);
+            } else {
+                shpc_slot_command(shpc, i + SHPC_CMD_TRGT_MIN,
+                                  SHPC_STATE_NO, SHPC_LED_OFF, SHPC_LED_NO);
+            }
+        }
+        break;
+    case 0x49:
+        /* Enable all slots */
+        /* TODO: Spec says this shall fail if some are already enabled.
+         * This doesn't make sense - why not? a spec bug? */
+        for (i = 0; i < shpc->nslots; ++i) {
+            state = shpc_get_status(shpc, i, SHPC_SLOT_STATE_MASK);
+            if (state == SHPC_STATE_ENABLED) {
+                shpc_invalid_command(shpc);
+                goto done;
+            }
+        }
+        for (i = 0; i < shpc->nslots; ++i) {
+            if (!(shpc_get_status(shpc, i, SHPC_SLOT_STATUS_MRL_OPEN))) {
+                shpc_slot_command(shpc, i + SHPC_CMD_TRGT_MIN,
+                                  SHPC_STATE_ENABLED, SHPC_LED_ON, SHPC_LED_NO);
+            } else {
+                shpc_slot_command(shpc, i + SHPC_CMD_TRGT_MIN,
+                                  SHPC_STATE_NO, SHPC_LED_OFF, SHPC_LED_NO);
+            }
+        }
+        break;
+    default:
+        shpc_invalid_command(shpc);
+        break;
+    }
+done:
+    pci_long_test_and_set_mask(shpc->config + SHPC_SERR_INT, SHPC_CMD_DETECTED);
+}
+
+static void shpc_write(PCIDevice *d, unsigned addr, uint64_t val, int l)
+{
+    SHPCDevice *shpc = d->shpc;
+    int i;
+    if (addr >= SHPC_SIZEOF(d)) {
+        return;
+    }
+    l = MIN(l, SHPC_SIZEOF(d) - addr);
+
+    /* TODO: code duplicated from pci.c */
+    for (i = 0; i < l; val >>= 8, ++i) {
+        unsigned a = addr + i;
+        uint8_t wmask = shpc->wmask[a];
+        uint8_t w1cmask = shpc->w1cmask[a];
+        assert(!(wmask & w1cmask));
+        shpc->config[a] = (shpc->config[a] & ~wmask) | (val & wmask);
+        shpc->config[a] &= ~(val & w1cmask); /* W1C: Write 1 to Clear */
+    }
+    if (ranges_overlap(addr, l, SHPC_CMD_CODE, 2)) {
+        shpc_command(shpc);
+    }
+    shpc_interrupt_update(d);
+}
+
+static uint64_t shpc_read(PCIDevice *d, unsigned addr, int l)
+{
+    uint64_t val = 0x0;
+    if (addr >= SHPC_SIZEOF(d)) {
+        return val;
+    }
+    l = MIN(l, SHPC_SIZEOF(d) - addr);
+    memcpy(&val, d->shpc->config + addr, l);
+    return val;
+}
+
+/* SHPC Bridge Capability */
+#define SHPC_CAP_LENGTH 0x08
+#define SHPC_CAP_DWORD_SELECT 0x2 /* 1 byte */
+#define SHPC_CAP_CxP 0x3 /* 1 byte: CSP, CIP */
+#define SHPC_CAP_DWORD_DATA 0x4 /* 4 bytes */
+#define SHPC_CAP_CSP_MASK 0x4
+#define SHPC_CAP_CIP_MASK 0x8
+
+static uint8_t shpc_cap_dword(PCIDevice *d)
+{
+    return pci_get_byte(d->config + d->shpc->cap + SHPC_CAP_DWORD_SELECT);
+}
+
+/* Update dword data capability register */
+static void shpc_cap_update_dword(PCIDevice *d)
+{
+    unsigned data;
+    data = shpc_read(d, shpc_cap_dword(d) * 4, 4);
+    pci_set_long(d->config  + d->shpc->cap + SHPC_CAP_DWORD_DATA, data);
+}
+
+/* Add SHPC capability to the config space for the device. */
+static int shpc_cap_add_config(PCIDevice *d)
+{
+    uint8_t *config;
+    int config_offset;
+    config_offset = pci_add_capability(d, PCI_CAP_ID_SHPC,
+                                       0, SHPC_CAP_LENGTH);
+    if (config_offset < 0) {
+        return config_offset;
+    }
+    config = d->config + config_offset;
+
+    pci_set_byte(config + SHPC_CAP_DWORD_SELECT, 0);
+    pci_set_byte(config + SHPC_CAP_CxP, 0);
+    pci_set_long(config + SHPC_CAP_DWORD_DATA, 0);
+    d->shpc->cap = config_offset;
+    /* Make dword select and data writeable. */
+    pci_set_byte(d->wmask + config_offset + SHPC_CAP_DWORD_SELECT, 0xff);
+    pci_set_long(d->wmask + config_offset + SHPC_CAP_DWORD_DATA, 0xffffffff);
+    return 0;
+}
+
+static uint64_t shpc_mmio_read(void *opaque, hwaddr addr,
+                               unsigned size)
+{
+    return shpc_read(opaque, addr, size);
+}
+
+static void shpc_mmio_write(void *opaque, hwaddr addr,
+                            uint64_t val, unsigned size)
+{
+    shpc_write(opaque, addr, val, size);
+}
+
+static const MemoryRegionOps shpc_mmio_ops = {
+    .read = shpc_mmio_read,
+    .write = shpc_mmio_write,
+    .endianness = DEVICE_LITTLE_ENDIAN,
+    .valid = {
+        /* SHPC ECN requires dword accesses, but the original 1.0 spec doesn't.
+         * It's easier to suppport all sizes than worry about it. */
+        .min_access_size = 1,
+        .max_access_size = 4,
+    },
+};
+static void shpc_device_hotplug_common(PCIDevice *affected_dev, int *slot,
+                                       SHPCDevice *shpc, Error **errp)
+{
+    int pci_slot = PCI_SLOT(affected_dev->devfn);
+    *slot = SHPC_PCI_TO_IDX(pci_slot);
+
+    if (pci_slot < SHPC_IDX_TO_PCI(0) || *slot >= shpc->nslots) {
+        error_setg(errp, "Unsupported PCI slot %d for standard hotplug "
+                   "controller. Valid slots are between %d and %d.",
+                   pci_slot, SHPC_IDX_TO_PCI(0),
+                   SHPC_IDX_TO_PCI(shpc->nslots) - 1);
+        return;
+    }
+}
+
+void shpc_device_hotplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
+                            Error **errp)
+{
+    Error *local_err = NULL;
+    PCIDevice *pci_hotplug_dev = PCI_DEVICE(hotplug_dev);
+    SHPCDevice *shpc = pci_hotplug_dev->shpc;
+    int slot;
+
+    shpc_device_hotplug_common(PCI_DEVICE(dev), &slot, shpc, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    /* Don't send event when device is enabled during qemu machine creation:
+     * it is present on boot, no hotplug event is necessary. We do send an
+     * event when the device is disabled later. */
+    if (!dev->hotplugged) {
+        shpc_set_status(shpc, slot, 0, SHPC_SLOT_STATUS_MRL_OPEN);
+        shpc_set_status(shpc, slot, SHPC_SLOT_STATUS_PRSNT_7_5W,
+                        SHPC_SLOT_STATUS_PRSNT_MASK);
+        return;
+    }
+
+    /* This could be a cancellation of the previous removal.
+     * We check MRL state to figure out. */
+    if (shpc_get_status(shpc, slot, SHPC_SLOT_STATUS_MRL_OPEN)) {
+        shpc_set_status(shpc, slot, 0, SHPC_SLOT_STATUS_MRL_OPEN);
+        shpc_set_status(shpc, slot, SHPC_SLOT_STATUS_PRSNT_7_5W,
+                        SHPC_SLOT_STATUS_PRSNT_MASK);
+        shpc->config[SHPC_SLOT_EVENT_LATCH(slot)] |=
+            SHPC_SLOT_EVENT_BUTTON |
+            SHPC_SLOT_EVENT_MRL |
+            SHPC_SLOT_EVENT_PRESENCE;
+    } else {
+        /* Press attention button to cancel removal */
+        shpc->config[SHPC_SLOT_EVENT_LATCH(slot)] |=
+            SHPC_SLOT_EVENT_BUTTON;
+    }
+    shpc_set_status(shpc, slot, 0, SHPC_SLOT_STATUS_66);
+    shpc_interrupt_update(pci_hotplug_dev);
+}
+
+void shpc_device_hot_unplug_request_cb(HotplugHandler *hotplug_dev,
+                                       DeviceState *dev, Error **errp)
+{
+    Error *local_err = NULL;
+    PCIDevice *pci_hotplug_dev = PCI_DEVICE(hotplug_dev);
+    SHPCDevice *shpc = pci_hotplug_dev->shpc;
+    uint8_t state;
+    uint8_t led;
+    int slot;
+
+    shpc_device_hotplug_common(PCI_DEVICE(dev), &slot, shpc, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
+
+    shpc->config[SHPC_SLOT_EVENT_LATCH(slot)] |= SHPC_SLOT_EVENT_BUTTON;
+    state = shpc_get_status(shpc, slot, SHPC_SLOT_STATE_MASK);
+    led = shpc_get_status(shpc, slot, SHPC_SLOT_PWR_LED_MASK);
+    if (state == SHPC_STATE_DISABLED && led == SHPC_LED_OFF) {
+        shpc_free_devices_in_slot(shpc, slot);
+        shpc_set_status(shpc, slot, 1, SHPC_SLOT_STATUS_MRL_OPEN);
+        shpc_set_status(shpc, slot, SHPC_SLOT_STATUS_PRSNT_EMPTY,
+                        SHPC_SLOT_STATUS_PRSNT_MASK);
+        shpc->config[SHPC_SLOT_EVENT_LATCH(slot)] |=
+            SHPC_SLOT_EVENT_MRL |
+            SHPC_SLOT_EVENT_PRESENCE;
+    }
+    shpc_set_status(shpc, slot, 0, SHPC_SLOT_STATUS_66);
+    shpc_interrupt_update(pci_hotplug_dev);
+}
+
+/* Initialize the SHPC structure in bridge's BAR. */
+int shpc_init(PCIDevice *d, PCIBus *sec_bus, MemoryRegion *bar, unsigned offset)
+{
+    int i, ret;
+    int nslots = SHPC_MAX_SLOTS; /* TODO: qdev property? */
+    SHPCDevice *shpc = d->shpc = g_malloc0(sizeof(*d->shpc));
+    shpc->sec_bus = sec_bus;
+    ret = shpc_cap_add_config(d);
+    if (ret) {
+        g_free(d->shpc);
+        return ret;
+    }
+    if (nslots < SHPC_MIN_SLOTS) {
+        return 0;
+    }
+    if (nslots > SHPC_MAX_SLOTS ||
+        SHPC_IDX_TO_PCI(nslots) > PCI_SLOT_MAX) {
+        /* TODO: report an error mesage that makes sense. */
+        return -EINVAL;
+    }
+    shpc->nslots = nslots;
+    shpc->config = g_malloc0(SHPC_SIZEOF(d));
+    shpc->cmask = g_malloc0(SHPC_SIZEOF(d));
+    shpc->wmask = g_malloc0(SHPC_SIZEOF(d));
+    shpc->w1cmask = g_malloc0(SHPC_SIZEOF(d));
+
+    shpc_reset(d);
+
+    pci_set_long(shpc->config + SHPC_BASE_OFFSET, offset);
+
+    pci_set_byte(shpc->wmask + SHPC_CMD_CODE, 0xff);
+    pci_set_byte(shpc->wmask + SHPC_CMD_TRGT, SHPC_CMD_TRGT_MAX);
+    pci_set_byte(shpc->wmask + SHPC_CMD_TRGT, SHPC_CMD_TRGT_MAX);
+    pci_set_long(shpc->wmask + SHPC_SERR_INT,
+                 SHPC_INT_DIS |
+                 SHPC_SERR_DIS |
+                 SHPC_CMD_INT_DIS |
+                 SHPC_ARB_SERR_DIS);
+    pci_set_long(shpc->w1cmask + SHPC_SERR_INT,
+                 SHPC_CMD_DETECTED |
+                 SHPC_ARB_DETECTED);
+    for (i = 0; i < nslots; ++i) {
+        pci_set_byte(shpc->wmask +
+                     SHPC_SLOT_EVENT_SERR_INT_DIS(d, i),
+                     SHPC_SLOT_EVENT_PRESENCE |
+                     SHPC_SLOT_EVENT_ISOLATED_FAULT |
+                     SHPC_SLOT_EVENT_BUTTON |
+                     SHPC_SLOT_EVENT_MRL |
+                     SHPC_SLOT_EVENT_CONNECTED_FAULT |
+                     SHPC_SLOT_EVENT_MRL_SERR_DIS |
+                     SHPC_SLOT_EVENT_CONNECTED_FAULT_SERR_DIS);
+        pci_set_byte(shpc->w1cmask +
+                     SHPC_SLOT_EVENT_LATCH(i),
+                     SHPC_SLOT_EVENT_PRESENCE |
+                     SHPC_SLOT_EVENT_ISOLATED_FAULT |
+                     SHPC_SLOT_EVENT_BUTTON |
+                     SHPC_SLOT_EVENT_MRL |
+                     SHPC_SLOT_EVENT_CONNECTED_FAULT);
+    }
+
+    /* TODO: init cmask */
+    memory_region_init_io(&shpc->mmio, OBJECT(d), &shpc_mmio_ops,
+                          d, "shpc-mmio", SHPC_SIZEOF(d));
+    shpc_cap_update_dword(d);
+    memory_region_add_subregion(bar, offset, &shpc->mmio);
+
+    qbus_set_hotplug_handler(BUS(sec_bus), DEVICE(d), NULL);
+
+    d->cap_present |= QEMU_PCI_CAP_SHPC;
+    return 0;
+}
+
+int shpc_bar_size(PCIDevice *d)
+{
+    return roundup_pow_of_two(SHPC_SLOT_REG(SHPC_MAX_SLOTS));
+}
+
+void shpc_cleanup(PCIDevice *d, MemoryRegion *bar)
+{
+    SHPCDevice *shpc = d->shpc;
+    d->cap_present &= ~QEMU_PCI_CAP_SHPC;
+    memory_region_del_subregion(bar, &shpc->mmio);
+    /* TODO: cleanup config space changes? */
+}
+
+void shpc_free(PCIDevice *d)
+{
+    SHPCDevice *shpc = d->shpc;
+    if (!shpc) {
+        return;
+    }
+    object_unparent(OBJECT(&shpc->mmio));
+    g_free(shpc->config);
+    g_free(shpc->cmask);
+    g_free(shpc->wmask);
+    g_free(shpc->w1cmask);
+    g_free(shpc);
+    d->shpc = NULL;
+}
+
+void shpc_cap_write_config(PCIDevice *d, uint32_t addr, uint32_t val, int l)
+{
+    if (!ranges_overlap(addr, l, d->shpc->cap, SHPC_CAP_LENGTH)) {
+        return;
+    }
+    if (ranges_overlap(addr, l, d->shpc->cap + SHPC_CAP_DWORD_DATA, 4)) {
+        unsigned dword_data;
+        dword_data = pci_get_long(d->shpc->config + d->shpc->cap
+                                  + SHPC_CAP_DWORD_DATA);
+        shpc_write(d, shpc_cap_dword(d) * 4, dword_data, 4);
+    }
+    /* Update cap dword data in case guest is going to read it. */
+    shpc_cap_update_dword(d);
+}
+
+static void shpc_save(QEMUFile *f, void *pv, size_t size)
+{
+    PCIDevice *d = container_of(pv, PCIDevice, shpc);
+    qemu_put_buffer(f, d->shpc->config, SHPC_SIZEOF(d));
+}
+
+static int shpc_load(QEMUFile *f, void *pv, size_t size)
+{
+    PCIDevice *d = container_of(pv, PCIDevice, shpc);
+    int ret = qemu_get_buffer(f, d->shpc->config, SHPC_SIZEOF(d));
+    if (ret != SHPC_SIZEOF(d)) {
+        return -EINVAL;
+    }
+    /* Make sure we don't lose notifications. An extra interrupt is harmless. */
+    d->shpc->msi_requested = 0;
+    shpc_interrupt_update(d);
+    return 0;
+}
+
+VMStateInfo shpc_vmstate_info = {
+    .name = "shpc",
+    .get  = shpc_load,
+    .put  = shpc_save,
+};
diff --git a/qemu/hw/pci/slotid_cap.c b/qemu/hw/pci/slotid_cap.c
new file mode 100644
index 000000000..1c01d346c
--- /dev/null
+++ b/qemu/hw/pci/slotid_cap.c
@@ -0,0 +1,45 @@
+#include "hw/pci/slotid_cap.h"
+#include "hw/pci/pci.h"
+#include "qemu/error-report.h"
+
+#define SLOTID_CAP_LENGTH 4
+#define SLOTID_NSLOTS_SHIFT ctz32(PCI_SID_ESR_NSLOTS)
+
+int slotid_cap_init(PCIDevice *d, int nslots,
+                    uint8_t chassis,
+                    unsigned offset)
+{
+    int cap;
+    if (!chassis) {
+        error_report("Bridge chassis not specified. Each bridge is required "
+                     "to be assigned a unique chassis id > 0.");
+        return -EINVAL;
+    }
+    if (nslots < 0 || nslots > (PCI_SID_ESR_NSLOTS >> SLOTID_NSLOTS_SHIFT)) {
+        /* TODO: error report? */
+        return -EINVAL;
+    }
+
+    cap = pci_add_capability(d, PCI_CAP_ID_SLOTID, offset, SLOTID_CAP_LENGTH);
+    if (cap < 0) {
+        return cap;
+    }
+    /* We make each chassis unique, this way each bridge is First in Chassis */
+    d->config[cap + PCI_SID_ESR] = PCI_SID_ESR_FIC |
+        (nslots << SLOTID_NSLOTS_SHIFT);
+    d->cmask[cap + PCI_SID_ESR] = 0xff;
+    d->config[cap + PCI_SID_CHASSIS_NR] = chassis;
+    /* Note: Chassis number register is non-volatile,
+       so we don't reset it. */
+    /* TODO: store in eeprom? */
+    d->wmask[cap + PCI_SID_CHASSIS_NR] = 0xff;
+
+    d->cap_present |= QEMU_PCI_CAP_SLOTID;
+    return 0;
+}
+
+void slotid_cap_cleanup(PCIDevice *d)
+{
+    /* TODO: cleanup config space? */
+    d->cap_present &= ~QEMU_PCI_CAP_SLOTID;
+}