pc, pci, virtio: features, fixes, cleanups

A bunch of fixes, cleanus and new features all over the place.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQEcBAABAgAGBQJaYQZfAAoJECgfDbjSjVRpnwsIAKwqHUL3TaijtxrHhrVc4vCJ
 vkEuO09ZTT5qSvZpqyZjLZ+lTC8MpXIZAbC66PLtYLObGTEq88943BFjmscrjcwt
 gCX3hvcurbulLbyWrIxLSwiPZ4tjzp1ZHRIoxB83wCQ4ipGN5A76n78asY69nuwP
 EDmqzQVDm83FSEkE8uwkO/6Ft5l4z/zUHT6b6Hx5J6JpRkHNNDJSz4QHppPYmaNH
 5tsYECg2ztYryedd45Toh53q21fjz8oK5bSoO02Cfm+dbf3kGtIeZF8eLprqVGxZ
 s8TWUfdXwHLJhqiYTDZZ0glaatZhT0yvedgO0CR1ABco4iEIcZX61Z5mzBVvLOI=
 =B+bl
 -----END PGP SIGNATURE-----

Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

pc, pci, virtio: features, fixes, cleanups

A bunch of fixes, cleanus and new features all over the place.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Thu 18 Jan 2018 20:41:03 GMT
# gpg:                using RSA key 0x281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream: (29 commits)
  vhost: remove assertion to prevent crash
  vhost-user: fix misaligned access to payload
  vhost-user: factor out msg head and payload
  tests: acpi: add comments to fetch_rsdt_referenced_tables/data->tables usage
  tests: acpi: rename test_acpi_tables()/test_dst_table() to reflect its usage
  tests: acpi: init table descriptor in test_dst_table()
  tests: acpi: move tested tables array allocation outside of test_acpi_dsdt_table()
  x86_iommu: check if machine has PCI bus
  x86_iommu: Move machine check to x86_iommu_realize()
  vhost-user-test: use init_virtio_dev in multiqueue test
  vhost-user-test: make features mask an init_virtio_dev() argument
  vhost-user-test: setup virtqueues in all tests
  vhost-user-test: extract read-guest-mem test from main loop
  vhost-user-test: fix features mask
  hw/acpi-build: Make next_base easy to follow
  ACPI/unit-test: Add a testcase for RAM allocation in numa node
  hw/pci-bridge: fix QEMU crash because of pcie-root-port
  intel-iommu: Extend address width to 48 bits
  intel-iommu: Redefine macros to enable supporting 48 bit address width
  vhost-user: fix multiple queue specification
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

.gitignore

@@ -54,6 +54,7 @@
 /module_block.h
 /scsi/qemu-pr-helper
 /vhost-user-scsi
+/vhost-user-blk
 /fsdev/virtfs-proxy-helper
 *.tmp
 *.[1-9]

MAINTAINERS

@@ -852,6 +852,7 @@ X86 Machines
 ------------
 PC
 M: Michael S. Tsirkin <mst@redhat.com>
+M: Marcel Apfelbaum <marcel@redhat.com>
 S: Supported
 F: include/hw/i386/
 F: hw/i386/

Makefile

@@ -334,6 +334,7 @@ dummy := $(call unnest-vars,, \
                 ivshmem-server-obj-y \
                 libvhost-user-obj-y \
                 vhost-user-scsi-obj-y \
+                vhost-user-blk-obj-y \
                 qga-vss-dll-obj-y \
                 block-obj-y \
                 block-obj-m \
@@ -565,6 +566,8 @@ ivshmem-server$(EXESUF): $(ivshmem-server-obj-y) $(COMMON_LDADDS)
 endif
 vhost-user-scsi$(EXESUF): $(vhost-user-scsi-obj-y) libvhost-user.a
 	$(call LINK, $^)
+vhost-user-blk$(EXESUF): $(vhost-user-blk-obj-y) libvhost-user.a
+	$(call LINK, $^)
 
 module_block.h: $(SRC_PATH)/scripts/modules/module_block.py config-host.mak
 	$(call quiet-command,$(PYTHON) $< $@ \

Makefile.objs

@@ -115,6 +115,7 @@ libvhost-user-obj-y = contrib/libvhost-user/
 vhost-user-scsi.o-cflags := $(LIBISCSI_CFLAGS)
 vhost-user-scsi.o-libs := $(LIBISCSI_LIBS)
 vhost-user-scsi-obj-y = contrib/vhost-user-scsi/
+vhost-user-blk-obj-y = contrib/vhost-user-blk/
 
 ######################################################################
 trace-events-subdirs =

accel/kvm/kvm-all.c

@@ -812,6 +812,10 @@ static void kvm_mem_ioeventfd_del(MemoryListener *listener,
     if (r < 0) {
         abort();
     }
+
+    if (e->cleanup) {
+        e->cleanup(e);
+    }
 }
 
 static void kvm_io_ioeventfd_add(MemoryListener *listener,

contrib/libvhost-user/libvhost-user.c

@@ -84,6 +84,8 @@ vu_request_to_string(unsigned int req)
         REQ(VHOST_USER_SET_SLAVE_REQ_FD),
         REQ(VHOST_USER_IOTLB_MSG),
         REQ(VHOST_USER_SET_VRING_ENDIAN),
+        REQ(VHOST_USER_GET_CONFIG),
+        REQ(VHOST_USER_SET_CONFIG),
         REQ(VHOST_USER_MAX),
     };
 #undef REQ
@@ -797,6 +799,42 @@ vu_set_slave_req_fd(VuDev *dev, VhostUserMsg *vmsg)
     return false;
 }
 
+static bool
+vu_get_config(VuDev *dev, VhostUserMsg *vmsg)
+{
+    int ret = -1;
+
+    if (dev->iface->get_config) {
+        ret = dev->iface->get_config(dev, vmsg->payload.config.region,
+                                     vmsg->payload.config.size);
+    }
+
+    if (ret) {
+        /* resize to zero to indicate an error to master */
+        vmsg->size = 0;
+    }
+
+    return true;
+}
+
+static bool
+vu_set_config(VuDev *dev, VhostUserMsg *vmsg)
+{
+    int ret = -1;
+
+    if (dev->iface->set_config) {
+        ret = dev->iface->set_config(dev, vmsg->payload.config.region,
+                                     vmsg->payload.config.offset,
+                                     vmsg->payload.config.size,
+                                     vmsg->payload.config.flags);
+        if (ret) {
+            vu_panic(dev, "Set virtio configuration space failed");
+        }
+    }
+
+    return false;
+}
+
 static bool
 vu_process_message(VuDev *dev, VhostUserMsg *vmsg)
 {
@@ -862,6 +900,10 @@ vu_process_message(VuDev *dev, VhostUserMsg *vmsg)
         return vu_set_vring_enable_exec(dev, vmsg);
     case VHOST_USER_SET_SLAVE_REQ_FD:
         return vu_set_slave_req_fd(dev, vmsg);
+    case VHOST_USER_GET_CONFIG:
+        return vu_get_config(dev, vmsg);
+    case VHOST_USER_SET_CONFIG:
+        return vu_set_config(dev, vmsg);
     case VHOST_USER_NONE:
         break;
     default:

contrib/libvhost-user/libvhost-user.h

@@ -30,6 +30,16 @@
 
 #define VHOST_MEMORY_MAX_NREGIONS 8
 
+typedef enum VhostSetConfigType {
+    VHOST_SET_CONFIG_TYPE_MASTER = 0,
+    VHOST_SET_CONFIG_TYPE_MIGRATION = 1,
+} VhostSetConfigType;
+
+/*
+ * Maximum size of virtio device config space
+ */
+#define VHOST_USER_MAX_CONFIG_SIZE 256
+
 enum VhostUserProtocolFeature {
     VHOST_USER_PROTOCOL_F_MQ = 0,
     VHOST_USER_PROTOCOL_F_LOG_SHMFD = 1,
@@ -69,6 +79,8 @@ typedef enum VhostUserRequest {
     VHOST_USER_SET_SLAVE_REQ_FD = 21,
     VHOST_USER_IOTLB_MSG = 22,
     VHOST_USER_SET_VRING_ENDIAN = 23,
+    VHOST_USER_GET_CONFIG = 24,
+    VHOST_USER_SET_CONFIG = 25,
     VHOST_USER_MAX
 } VhostUserRequest;
 
@@ -90,6 +102,18 @@ typedef struct VhostUserLog {
     uint64_t mmap_offset;
 } VhostUserLog;
 
+typedef struct VhostUserConfig {
+    uint32_t offset;
+    uint32_t size;
+    uint32_t flags;
+    uint8_t region[VHOST_USER_MAX_CONFIG_SIZE];
+} VhostUserConfig;
+
+static VhostUserConfig c __attribute__ ((unused));
+#define VHOST_USER_CONFIG_HDR_SIZE (sizeof(c.offset) \
+                                   + sizeof(c.size) \
+                                   + sizeof(c.flags))
+
 #if defined(_WIN32)
 # define VU_PACKED __attribute__((gcc_struct, packed))
 #else
@@ -112,6 +136,7 @@ typedef struct VhostUserMsg {
         struct vhost_vring_addr addr;
         VhostUserMemory memory;
         VhostUserLog log;
+        VhostUserConfig config;
     } payload;
 
     int fds[VHOST_MEMORY_MAX_NREGIONS];
@@ -140,6 +165,10 @@ typedef int (*vu_process_msg_cb) (VuDev *dev, VhostUserMsg *vmsg,
                                   int *do_reply);
 typedef void (*vu_queue_set_started_cb) (VuDev *dev, int qidx, bool started);
 typedef bool (*vu_queue_is_processed_in_order_cb) (VuDev *dev, int qidx);
+typedef int (*vu_get_config_cb) (VuDev *dev, uint8_t *config, uint32_t len);
+typedef int (*vu_set_config_cb) (VuDev *dev, const uint8_t *data,
+                                 uint32_t offset, uint32_t size,
+                                 uint32_t flags);
 
 typedef struct VuDevIface {
     /* called by VHOST_USER_GET_FEATURES to get the features bitmask */
@@ -162,6 +191,10 @@ typedef struct VuDevIface {
      * on unmanaged exit/crash.
      */
     vu_queue_is_processed_in_order_cb queue_is_processed_in_order;
+    /* get the config space of the device */
+    vu_get_config_cb get_config;
+    /* set the config space of the device */
+    vu_set_config_cb set_config;
 } VuDevIface;
 
 typedef void (*vu_queue_handler_cb) (VuDev *dev, int qidx);

contrib/vhost-user-blk/Makefile.objs

@@ -0,0 +1 @@
+vhost-user-blk-obj-y = vhost-user-blk.o

contrib/vhost-user-blk/vhost-user-blk.c

@@ -0,0 +1,545 @@
+/*
+ * vhost-user-blk sample application
+ *
+ * Copyright (c) 2017 Intel Corporation. All rights reserved.
+ *
+ * Author:
+ *  Changpeng Liu <changpeng.liu@intel.com>
+ *
+ * This work is based on the "vhost-user-scsi" sample and "virtio-blk" driver
+ * implementation by:
+ *  Felipe Franciosi <felipe@nutanix.com>
+ *  Anthony Liguori <aliguori@us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 only.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "standard-headers/linux/virtio_blk.h"
+#include "contrib/libvhost-user/libvhost-user-glib.h"
+#include "contrib/libvhost-user/libvhost-user.h"
+
+#include <glib.h>
+
+struct virtio_blk_inhdr {
+    unsigned char status;
+};
+
+/* vhost user block device */
+typedef struct VubDev {
+    VugDev parent;
+    int blk_fd;
+    struct virtio_blk_config blkcfg;
+    char *blk_name;
+    GMainLoop *loop;
+} VubDev;
+
+typedef struct VubReq {
+    VuVirtqElement *elem;
+    int64_t sector_num;
+    size_t size;
+    struct virtio_blk_inhdr *in;
+    struct virtio_blk_outhdr *out;
+    VubDev *vdev_blk;
+    struct VuVirtq *vq;
+} VubReq;
+
+/* refer util/iov.c */
+static size_t vub_iov_size(const struct iovec *iov,
+                              const unsigned int iov_cnt)
+{
+    size_t len;
+    unsigned int i;
+
+    len = 0;
+    for (i = 0; i < iov_cnt; i++) {
+        len += iov[i].iov_len;
+    }
+    return len;
+}
+
+static void vub_panic_cb(VuDev *vu_dev, const char *buf)
+{
+    VugDev *gdev;
+    VubDev *vdev_blk;
+
+    assert(vu_dev);
+
+    gdev = container_of(vu_dev, VugDev, parent);
+    vdev_blk = container_of(gdev, VubDev, parent);
+    if (buf) {
+        g_warning("vu_panic: %s", buf);
+    }
+
+    g_main_loop_quit(vdev_blk->loop);
+}
+
+static void vub_req_complete(VubReq *req)
+{
+    VugDev *gdev = &req->vdev_blk->parent;
+    VuDev *vu_dev = &gdev->parent;
+
+    /* IO size with 1 extra status byte */
+    vu_queue_push(vu_dev, req->vq, req->elem,
+                  req->size + 1);
+    vu_queue_notify(vu_dev, req->vq);
+
+    if (req->elem) {
+        free(req->elem);
+    }
+
+    g_free(req);
+}
+
+static int vub_open(const char *file_name, bool wce)
+{
+    int fd;
+    int flags = O_RDWR;
+
+    if (!wce) {
+        flags |= O_DIRECT;
+    }
+
+    fd = open(file_name, flags);
+    if (fd < 0) {
+        fprintf(stderr, "Cannot open file %s, %s\n", file_name,
+                strerror(errno));
+        return -1;
+    }
+
+    return fd;
+}
+
+static ssize_t
+vub_readv(VubReq *req, struct iovec *iov, uint32_t iovcnt)
+{
+    VubDev *vdev_blk = req->vdev_blk;
+    ssize_t rc;
+
+    if (!iovcnt) {
+        fprintf(stderr, "Invalid Read IOV count\n");
+        return -1;
+    }
+
+    req->size = vub_iov_size(iov, iovcnt);
+    rc = preadv(vdev_blk->blk_fd, iov, iovcnt, req->sector_num * 512);
+    if (rc < 0) {
+        fprintf(stderr, "%s, Sector %"PRIu64", Size %lu failed with %s\n",
+                vdev_blk->blk_name, req->sector_num, req->size,
+                strerror(errno));
+        return -1;
+    }
+
+    return rc;
+}
+
+static ssize_t
+vub_writev(VubReq *req, struct iovec *iov, uint32_t iovcnt)
+{
+    VubDev *vdev_blk = req->vdev_blk;
+    ssize_t rc;
+
+    if (!iovcnt) {
+        fprintf(stderr, "Invalid Write IOV count\n");
+        return -1;
+    }
+
+    req->size = vub_iov_size(iov, iovcnt);
+    rc = pwritev(vdev_blk->blk_fd, iov, iovcnt, req->sector_num * 512);
+    if (rc < 0) {
+        fprintf(stderr, "%s, Sector %"PRIu64", Size %lu failed with %s\n",
+                vdev_blk->blk_name, req->sector_num, req->size,
+                strerror(errno));
+        return -1;
+    }
+
+    return rc;
+}
+
+static void
+vub_flush(VubReq *req)
+{
+    VubDev *vdev_blk = req->vdev_blk;
+
+    fdatasync(vdev_blk->blk_fd);
+}
+
+static int vub_virtio_process_req(VubDev *vdev_blk,
+                                     VuVirtq *vq)
+{
+    VugDev *gdev = &vdev_blk->parent;
+    VuDev *vu_dev = &gdev->parent;
+    VuVirtqElement *elem;
+    uint32_t type;
+    unsigned in_num;
+    unsigned out_num;
+    VubReq *req;
+
+    elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement) + sizeof(VubReq));
+    if (!elem) {
+        return -1;
+    }
+
+    /* refer to hw/block/virtio_blk.c */
+    if (elem->out_num < 1 || elem->in_num < 1) {
+        fprintf(stderr, "virtio-blk request missing headers\n");
+        free(elem);
+        return -1;
+    }
+
+    req = g_new0(VubReq, 1);
+    req->vdev_blk = vdev_blk;
+    req->vq = vq;
+    req->elem = elem;
+
+    in_num = elem->in_num;
+    out_num = elem->out_num;
+
+    /* don't support VIRTIO_F_ANY_LAYOUT and virtio 1.0 only */
+    if (elem->out_sg[0].iov_len < sizeof(struct virtio_blk_outhdr)) {
+        fprintf(stderr, "Invalid outhdr size\n");
+        goto err;
+    }
+    req->out = (struct virtio_blk_outhdr *)elem->out_sg[0].iov_base;
+    out_num--;
+
+    if (elem->in_sg[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) {
+        fprintf(stderr, "Invalid inhdr size\n");
+        goto err;
+    }
+    req->in = (struct virtio_blk_inhdr *)elem->in_sg[in_num - 1].iov_base;
+    in_num--;
+
+    type = le32toh(req->out->type);
+    switch (type & ~(VIRTIO_BLK_T_OUT | VIRTIO_BLK_T_BARRIER)) {
+        case VIRTIO_BLK_T_IN: {
+            ssize_t ret = 0;
+            bool is_write = type & VIRTIO_BLK_T_OUT;
+            req->sector_num = le64toh(req->out->sector);
+            if (is_write) {
+                ret  = vub_writev(req, &elem->out_sg[1], out_num);
+            } else {
+                ret = vub_readv(req, &elem->in_sg[0], in_num);
+            }
+            if (ret >= 0) {
+                req->in->status = VIRTIO_BLK_S_OK;
+            } else {
+                req->in->status = VIRTIO_BLK_S_IOERR;
+            }
+            vub_req_complete(req);
+            break;
+        }
+        case VIRTIO_BLK_T_FLUSH: {
+            vub_flush(req);
+            req->in->status = VIRTIO_BLK_S_OK;
+            vub_req_complete(req);
+            break;
+        }
+        case VIRTIO_BLK_T_GET_ID: {
+            size_t size = MIN(vub_iov_size(&elem->in_sg[0], in_num),
+                              VIRTIO_BLK_ID_BYTES);
+            snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk");
+            req->in->status = VIRTIO_BLK_S_OK;
+            req->size = elem->in_sg[0].iov_len;
+            vub_req_complete(req);
+            break;
+        }
+        default: {
+            req->in->status = VIRTIO_BLK_S_UNSUPP;
+            vub_req_complete(req);
+            break;
+        }
+    }
+
+    return 0;
+
+err:
+    free(elem);
+    g_free(req);
+    return -1;
+}
+
+static void vub_process_vq(VuDev *vu_dev, int idx)
+{
+    VugDev *gdev;
+    VubDev *vdev_blk;
+    VuVirtq *vq;
+    int ret;
+
+    if ((idx < 0) || (idx >= VHOST_MAX_NR_VIRTQUEUE)) {
+        fprintf(stderr, "VQ Index out of range: %d\n", idx);
+        vub_panic_cb(vu_dev, NULL);
+        return;
+    }
+
+    gdev = container_of(vu_dev, VugDev, parent);
+    vdev_blk = container_of(gdev, VubDev, parent);
+    assert(vdev_blk);
+
+    vq = vu_get_queue(vu_dev, idx);
+    assert(vq);
+
+    while (1) {
+        ret = vub_virtio_process_req(vdev_blk, vq);
+        if (ret) {
+            break;
+        }
+    }
+}
+
+static void vub_queue_set_started(VuDev *vu_dev, int idx, bool started)
+{
+    VuVirtq *vq;
+
+    assert(vu_dev);
+
+    vq = vu_get_queue(vu_dev, idx);
+    vu_set_queue_handler(vu_dev, vq, started ? vub_process_vq : NULL);
+}
+
+static uint64_t
+vub_get_features(VuDev *dev)
+{
+    return 1ull << VIRTIO_BLK_F_SIZE_MAX |
+           1ull << VIRTIO_BLK_F_SEG_MAX |
+           1ull << VIRTIO_BLK_F_TOPOLOGY |
+           1ull << VIRTIO_BLK_F_BLK_SIZE |
+           1ull << VIRTIO_BLK_F_FLUSH |
+           1ull << VIRTIO_BLK_F_CONFIG_WCE |
+           1ull << VIRTIO_F_VERSION_1 |
+           1ull << VHOST_USER_F_PROTOCOL_FEATURES;
+}
+
+static int
+vub_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len)
+{
+    VugDev *gdev;
+    VubDev *vdev_blk;
+
+    gdev = container_of(vu_dev, VugDev, parent);
+    vdev_blk = container_of(gdev, VubDev, parent);
+    memcpy(config, &vdev_blk->blkcfg, len);
+
+    return 0;
+}
+
+static int
+vub_set_config(VuDev *vu_dev, const uint8_t *data,
+               uint32_t offset, uint32_t size, uint32_t flags)
+{
+    VugDev *gdev;
+    VubDev *vdev_blk;
+    uint8_t wce;
+    int fd;
+
+    /* don't support live migration */
+    if (flags != VHOST_SET_CONFIG_TYPE_MASTER) {
+        return -1;
+    }
+
+    gdev = container_of(vu_dev, VugDev, parent);
+    vdev_blk = container_of(gdev, VubDev, parent);
+
+    if (offset != offsetof(struct virtio_blk_config, wce) ||
+        size != 1) {
+        return -1;
+    }
+
+    wce = *data;
+    if (wce == vdev_blk->blkcfg.wce) {
+        /* Do nothing as same with old configuration */
+        return 0;
+    }
+
+    vdev_blk->blkcfg.wce = wce;
+    fprintf(stdout, "Write Cache Policy Changed\n");
+    if (vdev_blk->blk_fd >= 0) {
+        close(vdev_blk->blk_fd);
+        vdev_blk->blk_fd = -1;
+    }
+
+    fd = vub_open(vdev_blk->blk_name, wce);
+    if (fd < 0) {
+        fprintf(stderr, "Error to open block device %s\n", vdev_blk->blk_name);
+        vdev_blk->blk_fd = -1;
+        return -1;
+    }
+    vdev_blk->blk_fd = fd;
+
+    return 0;
+}
+
+static const VuDevIface vub_iface = {
+    .get_features = vub_get_features,
+    .queue_set_started = vub_queue_set_started,
+    .get_config = vub_get_config,
+    .set_config = vub_set_config,
+};
+
+static int unix_sock_new(char *unix_fn)
+{
+    int sock;
+    struct sockaddr_un un;
+    size_t len;
+
+    assert(unix_fn);
+
+    sock = socket(AF_UNIX, SOCK_STREAM, 0);
+    if (sock <= 0) {
+        perror("socket");
+        return -1;
+    }
+
+    un.sun_family = AF_UNIX;
+    (void)snprintf(un.sun_path, sizeof(un.sun_path), "%s", unix_fn);
+    len = sizeof(un.sun_family) + strlen(un.sun_path);
+
+    (void)unlink(unix_fn);
+    if (bind(sock, (struct sockaddr *)&un, len) < 0) {
+        perror("bind");
+        goto fail;
+    }
+
+    if (listen(sock, 1) < 0) {
+        perror("listen");
+        goto fail;
+    }
+
+    return sock;
+
+fail:
+    (void)close(sock);
+
+    return -1;
+}
+
+static void vub_free(struct VubDev *vdev_blk)
+{
+    if (!vdev_blk) {
+        return;
+    }
+
+    g_main_loop_unref(vdev_blk->loop);
+    if (vdev_blk->blk_fd >= 0) {
+        close(vdev_blk->blk_fd);
+    }
+    g_free(vdev_blk);
+}
+
+static uint32_t
+vub_get_blocksize(int fd)
+{
+    uint32_t blocksize = 512;
+
+#if defined(__linux__) && defined(BLKSSZGET)
+    if (ioctl(fd, BLKSSZGET, &blocksize) == 0) {
+        return blocklen;
+    }
+#endif
+
+    return blocksize;
+}
+
+static void
+vub_initialize_config(int fd, struct virtio_blk_config *config)
+{
+    off64_t capacity;
+
+    capacity = lseek64(fd, 0, SEEK_END);
+    config->capacity = capacity >> 9;
+    config->blk_size = vub_get_blocksize(fd);
+    config->size_max = 65536;
+    config->seg_max = 128 - 2;
+    config->min_io_size = 1;
+    config->opt_io_size = 1;
+    config->num_queues = 1;
+}
+
+static VubDev *
+vub_new(char *blk_file)
+{
+    VubDev *vdev_blk;
+
+    vdev_blk = g_new0(VubDev, 1);
+    vdev_blk->loop = g_main_loop_new(NULL, FALSE);
+    vdev_blk->blk_fd = vub_open(blk_file, 0);
+    if (vdev_blk->blk_fd  < 0) {
+        fprintf(stderr, "Error to open block device %s\n", blk_file);
+        vub_free(vdev_blk);
+        return NULL;
+    }
+    vdev_blk->blkcfg.wce = 0;
+    vdev_blk->blk_name = blk_file;
+
+    /* fill virtio_blk_config with block parameters */
+    vub_initialize_config(vdev_blk->blk_fd, &vdev_blk->blkcfg);
+
+    return vdev_blk;
+}
+
+int main(int argc, char **argv)
+{
+    int opt;
+    char *unix_socket = NULL;
+    char *blk_file = NULL;
+    int lsock = -1, csock = -1;
+    VubDev *vdev_blk = NULL;
+
+    while ((opt = getopt(argc, argv, "b:s:h")) != -1) {
+        switch (opt) {
+        case 'b':
+            blk_file = g_strdup(optarg);
+            break;
+        case 's':
+            unix_socket = g_strdup(optarg);
+            break;
+        case 'h':
+        default:
+            printf("Usage: %s [-b block device or file, -s UNIX domain socket]"
+                   " | [ -h ]\n", argv[0]);
+            return 0;
+        }
+    }
+
+    if (!unix_socket || !blk_file) {
+        printf("Usage: %s [-b block device or file, -s UNIX domain socket] |"
+               " [ -h ]\n", argv[0]);
+        return -1;
+    }
+
+    lsock = unix_sock_new(unix_socket);
+    if (lsock < 0) {
+        goto err;
+    }
+
+    csock = accept(lsock, (void *)0, (void *)0);
+    if (csock < 0) {
+        fprintf(stderr, "Accept error %s\n", strerror(errno));
+        goto err;
+    }
+
+    vdev_blk = vub_new(blk_file);
+    if (!vdev_blk) {
+        goto err;
+    }
+
+    vug_init(&vdev_blk->parent, csock, vub_panic_cb, &vub_iface);
+
+    g_main_loop_run(vdev_blk->loop);
+
+    vug_deinit(&vdev_blk->parent);
+
+err:
+    vub_free(vdev_blk);
+    if (csock >= 0) {
+        close(csock);
+    }
+    if (lsock >= 0) {
+        close(lsock);
+    }
+    g_free(unix_socket);
+    g_free(blk_file);
+
+    return 0;
+}

default-configs/pci.mak

@@ -43,3 +43,4 @@ CONFIG_VGA_PCI=y
 CONFIG_IVSHMEM_DEVICE=$(CONFIG_IVSHMEM)
 CONFIG_ROCKER=y
 CONFIG_VHOST_USER_SCSI=$(call land,$(CONFIG_VHOST_USER),$(CONFIG_LINUX))
+CONFIG_VHOST_USER_BLK=$(call land,$(CONFIG_VHOST_USER),$(CONFIG_LINUX))

default-configs/s390x-softmmu.mak

@@ -1,6 +1,7 @@
 CONFIG_PCI=y
 CONFIG_VIRTIO_PCI=$(CONFIG_PCI)
 CONFIG_VHOST_USER_SCSI=$(call land,$(CONFIG_VHOST_USER),$(CONFIG_LINUX))
+CONFIG_VHOST_USER_BLK=$(call land,$(CONFIG_VHOST_USER),$(CONFIG_LINUX))
 CONFIG_VIRTIO=y
 CONFIG_SCLPCONSOLE=y
 CONFIG_TERMINAL3270=y

docs/interop/vhost-user.txt

@@ -119,6 +119,19 @@ Depending on the request type, payload can be:
     - 3: IOTLB invalidate
     - 4: IOTLB access fail
 
+ * Virtio device config space
+   -----------------------------------
+   | offset | size | flags | payload |
+   -----------------------------------
+
+   Offset: a 32-bit offset of virtio device's configuration space
+   Size: a 32-bit configuration space access size in bytes
+   Flags: a 32-bit value:
+    - 0: Vhost master messages used for writeable fields
+    - 1: Vhost master messages used for live migration
+   Payload: Size bytes array holding the contents of the virtio
+       device's configuration space
+
 In QEMU the vhost-user message is implemented with the following struct:
 
 typedef struct VhostUserMsg {
@@ -132,6 +145,7 @@ typedef struct VhostUserMsg {
         VhostUserMemory memory;
         VhostUserLog log;
         struct vhost_iotlb_msg iotlb;
+        VhostUserConfig config;
     };
 } QEMU_PACKED VhostUserMsg;
 
@@ -214,8 +228,8 @@ Multiple queue is treated as a protocol extension, hence the slave has to
 implement protocol features first. The multiple queues feature is supported
 only when the protocol feature VHOST_USER_PROTOCOL_F_MQ (bit 0) is set.
 
-The max number of queues the slave supports can be queried with message
+The max number of queue pairs the slave supports can be queried with message
-VHOST_USER_GET_PROTOCOL_FEATURES. Master should stop when the number of
+VHOST_USER_GET_QUEUE_NUM. Master should stop when the number of
 requested queues is bigger than that.
 
 As all queues share one connection, the master uses a unique index for each
@@ -623,6 +637,32 @@ Master message types
       and expect this message once (per VQ) during device configuration
       (ie. before the master starts the VQ).
 
+ * VHOST_USER_GET_CONFIG
+
+      Id: 24
+      Equivalent ioctl: N/A
+      Master payload: virtio device config space
+      Slave payload: virtio device config space
+
+      Submitted by the vhost-user master to fetch the contents of the virtio
+      device configuration space, vhost-user slave's payload size MUST match
+      master's request, vhost-user slave uses zero length of payload to
+      indicate an error to vhost-user master. The vhost-user master may
+      cache the contents to avoid repeated VHOST_USER_GET_CONFIG calls.
+
+* VHOST_USER_SET_CONFIG
+
+      Id: 25
+      Equivalent ioctl: N/A
+      Master payload: virtio device config space
+      Slave payload: N/A
+
+      Submitted by the vhost-user master when the Guest changes the virtio
+      device configuration space and also can be used for live migration
+      on the destination host. The vhost-user slave must check the flags
+      field, and slaves MUST NOT accept SET_CONFIG for read-only
+      configuration space fields unless the live migration bit is set.
+
 Slave message types
 -------------------
 
@@ -641,6 +681,21 @@ Slave message types
       This request should be send only when VIRTIO_F_IOMMU_PLATFORM feature
       has been successfully negotiated.
 
+* VHOST_USER_SLAVE_CONFIG_CHANGE_MSG
+
+     Id: 2
+     Equivalent ioctl: N/A
+     Slave payload: N/A
+     Master payload: N/A
+
+     Vhost-user slave sends such messages to notify that the virtio device's
+     configuration space has changed, for those host devices which can support
+     such feature, host driver can send VHOST_USER_GET_CONFIG message to slave
+     to get the latest content. If VHOST_USER_PROTOCOL_F_REPLY_ACK is
+     negotiated, and slave set the VHOST_USER_NEED_REPLY flag, master must
+     respond with zero when operation is successfully completed, or non-zero
+     otherwise.
+
 VHOST_USER_PROTOCOL_F_REPLY_ACK:
 -------------------------------
 The original vhost-user specification only demands replies for certain

hw/block/Makefile.objs

@@ -13,3 +13,6 @@ obj-$(CONFIG_SH4) += tc58128.o
 
 obj-$(CONFIG_VIRTIO) += virtio-blk.o
 obj-$(CONFIG_VIRTIO) += dataplane/
+ifeq ($(CONFIG_VIRTIO),y)
+obj-$(CONFIG_VHOST_USER_BLK) += vhost-user-blk.o
+endif

hw/block/vhost-user-blk.c

@@ -0,0 +1,359 @@
+/*
+ * vhost-user-blk host device
+ *
+ * Copyright(C) 2017 Intel Corporation.
+ *
+ * Authors:
+ *  Changpeng Liu <changpeng.liu@intel.com>
+ *
+ * Largely based on the "vhost-user-scsi.c" and "vhost-scsi.c" implemented by:
+ * Felipe Franciosi <felipe@nutanix.com>
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ * Nicholas Bellinger <nab@risingtidesystems.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/typedefs.h"
+#include "qemu/cutils.h"
+#include "qom/object.h"
+#include "hw/qdev-core.h"
+#include "hw/virtio/vhost.h"
+#include "hw/virtio/vhost-user-blk.h"
+#include "hw/virtio/virtio.h"
+#include "hw/virtio/virtio-bus.h"
+#include "hw/virtio/virtio-access.h"
+
+static const int user_feature_bits[] = {
+    VIRTIO_BLK_F_SIZE_MAX,
+    VIRTIO_BLK_F_SEG_MAX,
+    VIRTIO_BLK_F_GEOMETRY,
+    VIRTIO_BLK_F_BLK_SIZE,
+    VIRTIO_BLK_F_TOPOLOGY,
+    VIRTIO_BLK_F_MQ,
+    VIRTIO_BLK_F_RO,
+    VIRTIO_BLK_F_FLUSH,
+    VIRTIO_BLK_F_CONFIG_WCE,
+    VIRTIO_F_VERSION_1,
+    VIRTIO_RING_F_INDIRECT_DESC,
+    VIRTIO_RING_F_EVENT_IDX,
+    VIRTIO_F_NOTIFY_ON_EMPTY,
+    VHOST_INVALID_FEATURE_BIT
+};
+
+static void vhost_user_blk_update_config(VirtIODevice *vdev, uint8_t *config)
+{
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+
+    memcpy(config, &s->blkcfg, sizeof(struct virtio_blk_config));
+}
+
+static void vhost_user_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
+{
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+    struct virtio_blk_config *blkcfg = (struct virtio_blk_config *)config;
+    int ret;
+
+    if (blkcfg->wce == s->blkcfg.wce) {
+        return;
+    }
+
+    ret = vhost_dev_set_config(&s->dev, &blkcfg->wce,
+                               offsetof(struct virtio_blk_config, wce),
+                               sizeof(blkcfg->wce),
+                               VHOST_SET_CONFIG_TYPE_MASTER);
+    if (ret) {
+        error_report("set device config space failed");
+        return;
+    }
+
+    s->blkcfg.wce = blkcfg->wce;
+}
+
+static int vhost_user_blk_handle_config_change(struct vhost_dev *dev)
+{
+    int ret;
+    struct virtio_blk_config blkcfg;
+    VHostUserBlk *s = VHOST_USER_BLK(dev->vdev);
+
+    ret = vhost_dev_get_config(dev, (uint8_t *)&blkcfg,
+                               sizeof(struct virtio_blk_config));
+    if (ret < 0) {
+        error_report("get config space failed");
+        return -1;
+    }
+
+    /* valid for resize only */
+    if (blkcfg.capacity != s->blkcfg.capacity) {
+        s->blkcfg.capacity = blkcfg.capacity;
+        memcpy(dev->vdev->config, &s->blkcfg, sizeof(struct virtio_blk_config));
+        virtio_notify_config(dev->vdev);
+    }
+
+    return 0;
+}
+
+const VhostDevConfigOps blk_ops = {
+    .vhost_dev_config_notifier = vhost_user_blk_handle_config_change,
+};
+
+static void vhost_user_blk_start(VirtIODevice *vdev)
+{
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+    int i, ret;
+
+    if (!k->set_guest_notifiers) {
+        error_report("binding does not support guest notifiers");
+        return;
+    }
+
+    ret = vhost_dev_enable_notifiers(&s->dev, vdev);
+    if (ret < 0) {
+        error_report("Error enabling host notifiers: %d", -ret);
+        return;
+    }
+
+    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
+    if (ret < 0) {
+        error_report("Error binding guest notifier: %d", -ret);
+        goto err_host_notifiers;
+    }
+
+    s->dev.acked_features = vdev->guest_features;
+    ret = vhost_dev_start(&s->dev, vdev);
+    if (ret < 0) {
+        error_report("Error starting vhost: %d", -ret);
+        goto err_guest_notifiers;
+    }
+
+    /* guest_notifier_mask/pending not used yet, so just unmask
+     * everything here. virtio-pci will do the right thing by
+     * enabling/disabling irqfd.
+     */
+    for (i = 0; i < s->dev.nvqs; i++) {
+        vhost_virtqueue_mask(&s->dev, vdev, i, false);
+    }
+
+    return;
+
+err_guest_notifiers:
+    k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
+err_host_notifiers:
+    vhost_dev_disable_notifiers(&s->dev, vdev);
+}
+
+static void vhost_user_blk_stop(VirtIODevice *vdev)
+{
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+    BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+    VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+    int ret;
+
+    if (!k->set_guest_notifiers) {
+        return;
+    }
+
+    vhost_dev_stop(&s->dev, vdev);
+
+    ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
+    if (ret < 0) {
+        error_report("vhost guest notifier cleanup failed: %d", ret);
+        return;
+    }
+
+    vhost_dev_disable_notifiers(&s->dev, vdev);
+}
+
+static void vhost_user_blk_set_status(VirtIODevice *vdev, uint8_t status)
+{
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+    bool should_start = status & VIRTIO_CONFIG_S_DRIVER_OK;
+
+    if (!vdev->vm_running) {
+        should_start = false;
+    }
+
+    if (s->dev.started == should_start) {
+        return;
+    }
+
+    if (should_start) {
+        vhost_user_blk_start(vdev);
+    } else {
+        vhost_user_blk_stop(vdev);
+    }
+
+}
+
+static uint64_t vhost_user_blk_get_features(VirtIODevice *vdev,
+                                            uint64_t features,
+                                            Error **errp)
+{
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+    uint64_t get_features;
+
+    /* Turn on pre-defined features */
+    virtio_add_feature(&features, VIRTIO_BLK_F_SEG_MAX);
+    virtio_add_feature(&features, VIRTIO_BLK_F_GEOMETRY);
+    virtio_add_feature(&features, VIRTIO_BLK_F_TOPOLOGY);
+    virtio_add_feature(&features, VIRTIO_BLK_F_BLK_SIZE);
+    virtio_add_feature(&features, VIRTIO_BLK_F_FLUSH);
+
+    if (s->config_wce) {
+        virtio_add_feature(&features, VIRTIO_BLK_F_CONFIG_WCE);
+    }
+    if (s->config_ro) {
+        virtio_add_feature(&features, VIRTIO_BLK_F_RO);
+    }
+    if (s->num_queues > 1) {
+        virtio_add_feature(&features, VIRTIO_BLK_F_MQ);
+    }
+
+    get_features = vhost_get_features(&s->dev, user_feature_bits, features);
+
+    return get_features;
+}
+
+static void vhost_user_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
+{
+
+}
+
+static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VHostUserBlk *s = VHOST_USER_BLK(vdev);
+    int i, ret;
+
+    if (!s->chardev.chr) {
+        error_setg(errp, "vhost-user-blk: chardev is mandatory");
+        return;
+    }
+
+    if (!s->num_queues || s->num_queues > VIRTIO_QUEUE_MAX) {
+        error_setg(errp, "vhost-user-blk: invalid number of IO queues");
+        return;
+    }
+
+    if (!s->queue_size) {
+        error_setg(errp, "vhost-user-blk: queue size must be non-zero");
+        return;
+    }
+
+    virtio_init(vdev, "virtio-blk", VIRTIO_ID_BLOCK,
+                sizeof(struct virtio_blk_config));
+
+    for (i = 0; i < s->num_queues; i++) {
+        virtio_add_queue(vdev, s->queue_size,
+                         vhost_user_blk_handle_output);
+    }
+
+    s->dev.nvqs = s->num_queues;
+    s->dev.vqs = g_new(struct vhost_virtqueue, s->dev.nvqs);
+    s->dev.vq_index = 0;
+    s->dev.backend_features = 0;
+
+    ret = vhost_dev_init(&s->dev, &s->chardev, VHOST_BACKEND_TYPE_USER, 0);
+    if (ret < 0) {
+        error_setg(errp, "vhost-user-blk: vhost initialization failed: %s",
+                   strerror(-ret));
+        goto virtio_err;
+    }
+
+    ret = vhost_dev_get_config(&s->dev, (uint8_t *)&s->blkcfg,
+                              sizeof(struct virtio_blk_config));
+    if (ret < 0) {
+        error_setg(errp, "vhost-user-blk: get block config failed");
+        goto vhost_err;
+    }
+
+    if (s->blkcfg.num_queues != s->num_queues) {
+        s->blkcfg.num_queues = s->num_queues;
+    }
+
+    vhost_dev_set_config_notifier(&s->dev, &blk_ops);
+
+    return;
+
+vhost_err:
+    vhost_dev_cleanup(&s->dev);
+virtio_err:
+    g_free(s->dev.vqs);
+    virtio_cleanup(vdev);
+}
+
+static void vhost_user_blk_device_unrealize(DeviceState *dev, Error **errp)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+    VHostUserBlk *s = VHOST_USER_BLK(dev);
+
+    vhost_user_blk_set_status(vdev, 0);
+    vhost_dev_cleanup(&s->dev);
+    g_free(s->dev.vqs);
+    virtio_cleanup(vdev);
+}
+
+static void vhost_user_blk_instance_init(Object *obj)
+{
+    VHostUserBlk *s = VHOST_USER_BLK(obj);
+
+    device_add_bootindex_property(obj, &s->bootindex, "bootindex",
+                                  "/disk@0,0", DEVICE(obj), NULL);
+}
+
+static const VMStateDescription vmstate_vhost_user_blk = {
+    .name = "vhost-user-blk",
+    .minimum_version_id = 1,
+    .version_id = 1,
+    .fields = (VMStateField[]) {
+        VMSTATE_VIRTIO_DEVICE,
+        VMSTATE_END_OF_LIST()
+    },
+};
+
+static Property vhost_user_blk_properties[] = {
+    DEFINE_PROP_CHR("chardev", VHostUserBlk, chardev),
+    DEFINE_PROP_UINT16("num-queues", VHostUserBlk, num_queues, 1),
+    DEFINE_PROP_UINT32("queue-size", VHostUserBlk, queue_size, 128),
+    DEFINE_PROP_BIT("config-wce", VHostUserBlk, config_wce, 0, true),
+    DEFINE_PROP_BIT("config-ro", VHostUserBlk, config_ro, 0, false),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void vhost_user_blk_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
+
+    dc->props = vhost_user_blk_properties;
+    dc->vmsd = &vmstate_vhost_user_blk;
+    set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+    vdc->realize = vhost_user_blk_device_realize;
+    vdc->unrealize = vhost_user_blk_device_unrealize;
+    vdc->get_config = vhost_user_blk_update_config;
+    vdc->set_config = vhost_user_blk_set_config;
+    vdc->get_features = vhost_user_blk_get_features;
+    vdc->set_status = vhost_user_blk_set_status;
+}
+
+static const TypeInfo vhost_user_blk_info = {
+    .name = TYPE_VHOST_USER_BLK,
+    .parent = TYPE_VIRTIO_DEVICE,
+    .instance_size = sizeof(VHostUserBlk),
+    .instance_init = vhost_user_blk_instance_init,
+    .class_init = vhost_user_blk_class_init,
+};
+
+static void virtio_register_types(void)
+{
+    type_register_static(&vhost_user_blk_info);
+}
+
+type_init(virtio_register_types)

hw/i386/acpi-build.c

@@ -2394,7 +2394,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
             }
             mem_base = 1ULL << 32;
             mem_len = next_base - pcms->below_4g_mem_size;
-            next_base += (1ULL << 32) - pcms->below_4g_mem_size;
+            next_base = mem_base + mem_len;
         }
         numamem = acpi_data_push(table_data, sizeof *numamem);
         build_srat_memory(numamem, mem_base, mem_len, i - 1,
@@ -2473,6 +2473,7 @@ build_dmar_q35(GArray *table_data, BIOSLinker *linker)
     AcpiDmarDeviceScope *scope = NULL;
     /* Root complex IOAPIC use one path[0] only */
     size_t ioapic_scope_size = sizeof(*scope) + sizeof(scope->path[0]);
+    IntelIOMMUState *intel_iommu = INTEL_IOMMU_DEVICE(iommu);
 
     assert(iommu);
     if (iommu->intr_supported) {
@@ -2480,7 +2481,7 @@ build_dmar_q35(GArray *table_data, BIOSLinker *linker)
     }
 
     dmar = acpi_data_push(table_data, sizeof(*dmar));
-    dmar->host_address_width = VTD_HOST_ADDRESS_WIDTH - 1;
+    dmar->host_address_width = intel_iommu->aw_bits - 1;
     dmar->flags = dmar_flags;
 
     /* DMAR Remapping Hardware Unit Definition structure */

hw/i386/amd_iommu.c

@@ -1144,18 +1144,9 @@ static void amdvi_realize(DeviceState *dev, Error **err)
     AMDVIState *s = AMD_IOMMU_DEVICE(dev);
     X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(dev);
     MachineState *ms = MACHINE(qdev_get_machine());
-    MachineClass *mc = MACHINE_GET_CLASS(ms);
+    PCMachineState *pcms = PC_MACHINE(ms);
-    PCMachineState *pcms =
+    PCIBus *bus = pcms->bus;
-        PC_MACHINE(object_dynamic_cast(OBJECT(ms), TYPE_PC_MACHINE));
-    PCIBus *bus;
 
-    if (!pcms) {
-        error_setg(err, "Machine-type '%s' not supported by amd-iommu",
-                   mc->name);
-        return;
-    }
-
-    bus = pcms->bus;
     s->iotlb = g_hash_table_new_full(amdvi_uint64_hash,
                                      amdvi_uint64_equal, g_free, g_free);
 

hw/i386/intel_iommu.c

@@ -521,9 +521,9 @@ static inline dma_addr_t vtd_ce_get_slpt_base(VTDContextEntry *ce)
     return ce->lo & VTD_CONTEXT_ENTRY_SLPTPTR;
 }
 
-static inline uint64_t vtd_get_slpte_addr(uint64_t slpte)
+static inline uint64_t vtd_get_slpte_addr(uint64_t slpte, uint8_t aw)
 {
-    return slpte & VTD_SL_PT_BASE_ADDR_MASK;
+    return slpte & VTD_SL_PT_BASE_ADDR_MASK(aw);
 }
 
 /* Whether the pte indicates the address of the page frame */
@@ -608,35 +608,29 @@ static inline bool vtd_ce_type_check(X86IOMMUState *x86_iommu,
     return true;
 }
 
-static inline uint64_t vtd_iova_limit(VTDContextEntry *ce)
+static inline uint64_t vtd_iova_limit(VTDContextEntry *ce, uint8_t aw)
 {
     uint32_t ce_agaw = vtd_ce_get_agaw(ce);
-    return 1ULL << MIN(ce_agaw, VTD_MGAW);
+    return 1ULL << MIN(ce_agaw, aw);
 }
 
 /* Return true if IOVA passes range check, otherwise false. */
-static inline bool vtd_iova_range_check(uint64_t iova, VTDContextEntry *ce)
+static inline bool vtd_iova_range_check(uint64_t iova, VTDContextEntry *ce,
+                                        uint8_t aw)
 {
     /*
      * Check if @iova is above 2^X-1, where X is the minimum of MGAW
      * in CAP_REG and AW in context-entry.
      */
-    return !(iova & ~(vtd_iova_limit(ce) - 1));
+    return !(iova & ~(vtd_iova_limit(ce, aw) - 1));
 }
 
-static const uint64_t vtd_paging_entry_rsvd_field[] = {
+/*
-    [0] = ~0ULL,
+ * Rsvd field masks for spte:
-    /* For not large page */
+ *     Index [1] to [4] 4k pages
-    [1] = 0x800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
+ *     Index [5] to [8] large pages
-    [2] = 0x800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
+ */
-    [3] = 0x800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
+static uint64_t vtd_paging_entry_rsvd_field[9];
-    [4] = 0x880ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
-    /* For large page */
-    [5] = 0x800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
-    [6] = 0x1ff800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
-    [7] = 0x3ffff800ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
-    [8] = 0x880ULL | ~(VTD_HAW_MASK | VTD_SL_IGN_COM),
-};
 
 static bool vtd_slpte_nonzero_rsvd(uint64_t slpte, uint32_t level)
 {
@@ -676,7 +670,7 @@ static VTDBus *vtd_find_as_from_bus_num(IntelIOMMUState *s, uint8_t bus_num)
  */
 static int vtd_iova_to_slpte(VTDContextEntry *ce, uint64_t iova, bool is_write,
                              uint64_t *slptep, uint32_t *slpte_level,
-                             bool *reads, bool *writes)
+                             bool *reads, bool *writes, uint8_t aw_bits)
 {
     dma_addr_t addr = vtd_ce_get_slpt_base(ce);
     uint32_t level = vtd_ce_get_level(ce);
@@ -684,7 +678,7 @@ static int vtd_iova_to_slpte(VTDContextEntry *ce, uint64_t iova, bool is_write,
     uint64_t slpte;
     uint64_t access_right_check;
 
-    if (!vtd_iova_range_check(iova, ce)) {
+    if (!vtd_iova_range_check(iova, ce, aw_bits)) {
         trace_vtd_err_dmar_iova_overflow(iova);
         return -VTD_FR_ADDR_BEYOND_MGAW;
     }
@@ -721,7 +715,7 @@ static int vtd_iova_to_slpte(VTDContextEntry *ce, uint64_t iova, bool is_write,
             *slpte_level = level;
             return 0;
         }
-        addr = vtd_get_slpte_addr(slpte);
+        addr = vtd_get_slpte_addr(slpte, aw_bits);
         level--;
     }
 }
@@ -739,11 +733,12 @@ typedef int (*vtd_page_walk_hook)(IOMMUTLBEntry *entry, void *private);
  * @read: whether parent level has read permission
  * @write: whether parent level has write permission
  * @notify_unmap: whether we should notify invalid entries
+ * @aw: maximum address width
  */
 static int vtd_page_walk_level(dma_addr_t addr, uint64_t start,
                                uint64_t end, vtd_page_walk_hook hook_fn,
-                               void *private, uint32_t level,
+                               void *private, uint32_t level, bool read,
-                               bool read, bool write, bool notify_unmap)
+                               bool write, bool notify_unmap, uint8_t aw)
 {
     bool read_cur, write_cur, entry_valid;
     uint32_t offset;
@@ -790,7 +785,7 @@ static int vtd_page_walk_level(dma_addr_t addr, uint64_t start,
             entry.target_as = &address_space_memory;
             entry.iova = iova & subpage_mask;
             /* NOTE: this is only meaningful if entry_valid == true */
-            entry.translated_addr = vtd_get_slpte_addr(slpte);
+            entry.translated_addr = vtd_get_slpte_addr(slpte, aw);
             entry.addr_mask = ~subpage_mask;
             entry.perm = IOMMU_ACCESS_FLAG(read_cur, write_cur);
             if (!entry_valid && !notify_unmap) {
@@ -810,10 +805,10 @@ static int vtd_page_walk_level(dma_addr_t addr, uint64_t start,
                 trace_vtd_page_walk_skip_perm(iova, iova_next);
                 goto next;
             }
-            ret = vtd_page_walk_level(vtd_get_slpte_addr(slpte), iova,
+            ret = vtd_page_walk_level(vtd_get_slpte_addr(slpte, aw), iova,
                                       MIN(iova_next, end), hook_fn, private,
                                       level - 1, read_cur, write_cur,
-                                      notify_unmap);
+                                      notify_unmap, aw);
             if (ret < 0) {
                 return ret;
             }
@@ -834,25 +829,26 @@ next:
  * @end: IOVA range end address (start <= addr < end)
  * @hook_fn: the hook that to be called for each detected area
  * @private: private data for the hook function
+ * @aw: maximum address width
  */
 static int vtd_page_walk(VTDContextEntry *ce, uint64_t start, uint64_t end,
                          vtd_page_walk_hook hook_fn, void *private,
-                         bool notify_unmap)
+                         bool notify_unmap, uint8_t aw)
 {
     dma_addr_t addr = vtd_ce_get_slpt_base(ce);
     uint32_t level = vtd_ce_get_level(ce);
 
-    if (!vtd_iova_range_check(start, ce)) {
+    if (!vtd_iova_range_check(start, ce, aw)) {
         return -VTD_FR_ADDR_BEYOND_MGAW;
     }
 
-    if (!vtd_iova_range_check(end, ce)) {
+    if (!vtd_iova_range_check(end, ce, aw)) {
         /* Fix end so that it reaches the maximum */
-        end = vtd_iova_limit(ce);
+        end = vtd_iova_limit(ce, aw);
     }
 
     return vtd_page_walk_level(addr, start, end, hook_fn, private,
-                               level, true, true, notify_unmap);
+                               level, true, true, notify_unmap, aw);
 }
 
 /* Map a device to its corresponding domain (context-entry) */
@@ -874,7 +870,7 @@ static int vtd_dev_to_context_entry(IntelIOMMUState *s, uint8_t bus_num,
         return -VTD_FR_ROOT_ENTRY_P;
     }
 
-    if (re.rsvd || (re.val & VTD_ROOT_ENTRY_RSVD)) {
+    if (re.rsvd || (re.val & VTD_ROOT_ENTRY_RSVD(s->aw_bits))) {
         trace_vtd_re_invalid(re.rsvd, re.val);
         return -VTD_FR_ROOT_ENTRY_RSVD;
     }
@@ -891,7 +887,7 @@ static int vtd_dev_to_context_entry(IntelIOMMUState *s, uint8_t bus_num,
     }
 
     if ((ce->hi & VTD_CONTEXT_ENTRY_RSVD_HI) ||
-        (ce->lo & VTD_CONTEXT_ENTRY_RSVD_LO)) {
+               (ce->lo & VTD_CONTEXT_ENTRY_RSVD_LO(s->aw_bits))) {
         trace_vtd_ce_invalid(ce->hi, ce->lo);
         return -VTD_FR_CONTEXT_ENTRY_RSVD;
     }
@@ -1173,7 +1169,7 @@ static bool vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus,
     }
 
     ret_fr = vtd_iova_to_slpte(&ce, addr, is_write, &slpte, &level,
-                               &reads, &writes);
+                               &reads, &writes, s->aw_bits);
     if (ret_fr) {
         ret_fr = -ret_fr;
         if (is_fpd_set && vtd_is_qualified_fault(ret_fr)) {
@@ -1190,7 +1186,7 @@ static bool vtd_do_iommu_translate(VTDAddressSpace *vtd_as, PCIBus *bus,
                      access_flags, level);
 out:
     entry->iova = addr & page_mask;
-    entry->translated_addr = vtd_get_slpte_addr(slpte) & page_mask;
+    entry->translated_addr = vtd_get_slpte_addr(slpte, s->aw_bits) & page_mask;
     entry->addr_mask = ~page_mask;
     entry->perm = access_flags;
     return true;
@@ -1207,7 +1203,7 @@ static void vtd_root_table_setup(IntelIOMMUState *s)
 {
     s->root = vtd_get_quad_raw(s, DMAR_RTADDR_REG);
     s->root_extended = s->root & VTD_RTADDR_RTT;
-    s->root &= VTD_RTADDR_ADDR_MASK;
+    s->root &= VTD_RTADDR_ADDR_MASK(s->aw_bits);
 
     trace_vtd_reg_dmar_root(s->root, s->root_extended);
 }
@@ -1223,7 +1219,7 @@ static void vtd_interrupt_remap_table_setup(IntelIOMMUState *s)
     uint64_t value = 0;
     value = vtd_get_quad_raw(s, DMAR_IRTA_REG);
     s->intr_size = 1UL << ((value & VTD_IRTA_SIZE_MASK) + 1);
-    s->intr_root = value & VTD_IRTA_ADDR_MASK;
+    s->intr_root = value & VTD_IRTA_ADDR_MASK(s->aw_bits);
     s->intr_eime = value & VTD_IRTA_EIME;
 
     /* Notify global invalidation */
@@ -1399,7 +1395,7 @@ static void vtd_iotlb_page_invalidate_notify(IntelIOMMUState *s,
         if (!ret && domain_id == VTD_CONTEXT_ENTRY_DID(ce.hi)) {
             vtd_page_walk(&ce, addr, addr + (1 << am) * VTD_PAGE_SIZE,
                           vtd_page_invalidate_notify_hook,
-                          (void *)&vtd_as->iommu, true);
+                          (void *)&vtd_as->iommu, true, s->aw_bits);
         }
     }
 }
@@ -1479,7 +1475,7 @@ static void vtd_handle_gcmd_qie(IntelIOMMUState *s, bool en)
     trace_vtd_inv_qi_enable(en);
 
     if (en) {
-        s->iq = iqa_val & VTD_IQA_IQA_MASK;
+        s->iq = iqa_val & VTD_IQA_IQA_MASK(s->aw_bits);
         /* 2^(x+8) entries */
         s->iq_size = 1UL << ((iqa_val & VTD_IQA_QS) + 8);
         s->qi_enabled = true;
@@ -2410,6 +2406,8 @@ static Property vtd_properties[] = {
     DEFINE_PROP_ON_OFF_AUTO("eim", IntelIOMMUState, intr_eim,
                             ON_OFF_AUTO_AUTO),
     DEFINE_PROP_BOOL("x-buggy-eim", IntelIOMMUState, buggy_eim, false),
+    DEFINE_PROP_UINT8("x-aw-bits", IntelIOMMUState, aw_bits,
+                      VTD_HOST_ADDRESS_WIDTH),
     DEFINE_PROP_BOOL("caching-mode", IntelIOMMUState, caching_mode, FALSE),
     DEFINE_PROP_END_OF_LIST(),
 };
@@ -2765,6 +2763,7 @@ static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n)
     hwaddr size;
     hwaddr start = n->start;
     hwaddr end = n->end;
+    IntelIOMMUState *s = as->iommu_state;
 
     /*
      * Note: all the codes in this function has a assumption that IOVA
@@ -2772,12 +2771,12 @@ static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n)
      * VT-d spec), otherwise we need to consider overflow of 64 bits.
      */
 
-    if (end > VTD_ADDRESS_SIZE) {
+    if (end > VTD_ADDRESS_SIZE(s->aw_bits)) {
         /*
          * Don't need to unmap regions that is bigger than the whole
          * VT-d supported address space size
          */
-        end = VTD_ADDRESS_SIZE;
+        end = VTD_ADDRESS_SIZE(s->aw_bits);
     }
 
     assert(start <= end);
@@ -2789,9 +2788,9 @@ static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n)
          * suite the minimum available mask.
          */
         int n = 64 - clz64(size);
-        if (n > VTD_MGAW) {
+        if (n > s->aw_bits) {
             /* should not happen, but in case it happens, limit it */
-            n = VTD_MGAW;
+            n = s->aw_bits;
         }
         size = 1ULL << n;
     }
@@ -2851,7 +2850,8 @@ static void vtd_iommu_replay(IOMMUMemoryRegion *iommu_mr, IOMMUNotifier *n)
                                   PCI_FUNC(vtd_as->devfn),
                                   VTD_CONTEXT_ENTRY_DID(ce.hi),
                                   ce.hi, ce.lo);
-        vtd_page_walk(&ce, 0, ~0ULL, vtd_replay_hook, (void *)n, false);
+        vtd_page_walk(&ce, 0, ~0ULL, vtd_replay_hook, (void *)n, false,
+                      s->aw_bits);
     } else {
         trace_vtd_replay_ce_invalid(bus_n, PCI_SLOT(vtd_as->devfn),
                                     PCI_FUNC(vtd_as->devfn));
@@ -2882,10 +2882,27 @@ static void vtd_init(IntelIOMMUState *s)
     s->qi_enabled = false;
     s->iq_last_desc_type = VTD_INV_DESC_NONE;
     s->next_frcd_reg = 0;
-    s->cap = VTD_CAP_FRO | VTD_CAP_NFR | VTD_CAP_ND | VTD_CAP_MGAW |
+    s->cap = VTD_CAP_FRO | VTD_CAP_NFR | VTD_CAP_ND |
-             VTD_CAP_SAGAW | VTD_CAP_MAMV | VTD_CAP_PSI | VTD_CAP_SLLPS;
+             VTD_CAP_MAMV | VTD_CAP_PSI | VTD_CAP_SLLPS |
+             VTD_CAP_SAGAW_39bit | VTD_CAP_MGAW(s->aw_bits);
+    if (s->aw_bits == VTD_HOST_AW_48BIT) {
+        s->cap |= VTD_CAP_SAGAW_48bit;
+    }
     s->ecap = VTD_ECAP_QI | VTD_ECAP_IRO;
 
+    /*
+     * Rsvd field masks for spte
+     */
+    vtd_paging_entry_rsvd_field[0] = ~0ULL;
+    vtd_paging_entry_rsvd_field[1] = VTD_SPTE_PAGE_L1_RSVD_MASK(s->aw_bits);
+    vtd_paging_entry_rsvd_field[2] = VTD_SPTE_PAGE_L2_RSVD_MASK(s->aw_bits);
+    vtd_paging_entry_rsvd_field[3] = VTD_SPTE_PAGE_L3_RSVD_MASK(s->aw_bits);
+    vtd_paging_entry_rsvd_field[4] = VTD_SPTE_PAGE_L4_RSVD_MASK(s->aw_bits);
+    vtd_paging_entry_rsvd_field[5] = VTD_SPTE_LPAGE_L1_RSVD_MASK(s->aw_bits);
+    vtd_paging_entry_rsvd_field[6] = VTD_SPTE_LPAGE_L2_RSVD_MASK(s->aw_bits);
+    vtd_paging_entry_rsvd_field[7] = VTD_SPTE_LPAGE_L3_RSVD_MASK(s->aw_bits);
+    vtd_paging_entry_rsvd_field[8] = VTD_SPTE_LPAGE_L4_RSVD_MASK(s->aw_bits);
+
     if (x86_iommu->intr_supported) {
         s->ecap |= VTD_ECAP_IR | VTD_ECAP_MHMV;
         if (s->intr_eim == ON_OFF_AUTO_ON) {
@@ -3021,26 +3038,25 @@ static bool vtd_decide_config(IntelIOMMUState *s, Error **errp)
         }
     }
 
+    /* Currently only address widths supported are 39 and 48 bits */
+    if ((s->aw_bits != VTD_HOST_AW_39BIT) &&
+        (s->aw_bits != VTD_HOST_AW_48BIT)) {
+        error_setg(errp, "Supported values for x-aw-bits are: %d, %d",
+                   VTD_HOST_AW_39BIT, VTD_HOST_AW_48BIT);
+        return false;
+    }
+
     return true;
 }
 
 static void vtd_realize(DeviceState *dev, Error **errp)
 {
     MachineState *ms = MACHINE(qdev_get_machine());
-    MachineClass *mc = MACHINE_GET_CLASS(ms);
+    PCMachineState *pcms = PC_MACHINE(ms);
-    PCMachineState *pcms =
+    PCIBus *bus = pcms->bus;
-        PC_MACHINE(object_dynamic_cast(OBJECT(ms), TYPE_PC_MACHINE));
-    PCIBus *bus;
     IntelIOMMUState *s = INTEL_IOMMU_DEVICE(dev);
     X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(dev);
 
-    if (!pcms) {
-        error_setg(errp, "Machine-type '%s' not supported by intel-iommu",
-                   mc->name);
-        return;
-    }
-
-    bus = pcms->bus;
     x86_iommu->type = TYPE_INTEL;
 
     if (!vtd_decide_config(s, errp)) {

hw/i386/intel_iommu_internal.h

@@ -131,7 +131,7 @@
 #define VTD_TLB_DID(val)            (((val) >> 32) & VTD_DOMAIN_ID_MASK)
 
 /* IVA_REG */
-#define VTD_IVA_ADDR(val)       ((val) & ~0xfffULL & ((1ULL << VTD_MGAW) - 1))
+#define VTD_IVA_ADDR(val)       ((val) & ~0xfffULL)
 #define VTD_IVA_AM(val)         ((val) & 0x3fULL)
 
 /* GCMD_REG */
@@ -172,10 +172,10 @@
 
 /* RTADDR_REG */
 #define VTD_RTADDR_RTT              (1ULL << 11)
-#define VTD_RTADDR_ADDR_MASK        (VTD_HAW_MASK ^ 0xfffULL)
+#define VTD_RTADDR_ADDR_MASK(aw)    (VTD_HAW_MASK(aw) ^ 0xfffULL)
 
 /* IRTA_REG */
-#define VTD_IRTA_ADDR_MASK          (VTD_HAW_MASK ^ 0xfffULL)
+#define VTD_IRTA_ADDR_MASK(aw)      (VTD_HAW_MASK(aw) ^ 0xfffULL)
 #define VTD_IRTA_EIME               (1ULL << 11)
 #define VTD_IRTA_SIZE_MASK          (0xfULL)
 
@@ -197,9 +197,8 @@
 #define VTD_DOMAIN_ID_SHIFT         16  /* 16-bit domain id for 64K domains */
 #define VTD_DOMAIN_ID_MASK          ((1UL << VTD_DOMAIN_ID_SHIFT) - 1)
 #define VTD_CAP_ND                  (((VTD_DOMAIN_ID_SHIFT - 4) / 2) & 7ULL)
-#define VTD_MGAW                    39  /* Maximum Guest Address Width */
+#define VTD_ADDRESS_SIZE(aw)        (1ULL << (aw))
-#define VTD_ADDRESS_SIZE            (1ULL << VTD_MGAW)
+#define VTD_CAP_MGAW(aw)            ((((aw) - 1) & 0x3fULL) << 16)
-#define VTD_CAP_MGAW                (((VTD_MGAW - 1) & 0x3fULL) << 16)
 #define VTD_MAMV                    18ULL
 #define VTD_CAP_MAMV                (VTD_MAMV << 48)
 #define VTD_CAP_PSI                 (1ULL << 39)
@@ -213,13 +212,12 @@
 #define VTD_CAP_SAGAW_39bit         (0x2ULL << VTD_CAP_SAGAW_SHIFT)
  /* 48-bit AGAW, 4-level page-table */
 #define VTD_CAP_SAGAW_48bit         (0x4ULL << VTD_CAP_SAGAW_SHIFT)
-#define VTD_CAP_SAGAW               VTD_CAP_SAGAW_39bit
 
 /* IQT_REG */
 #define VTD_IQT_QT(val)             (((val) >> 4) & 0x7fffULL)
 
 /* IQA_REG */
-#define VTD_IQA_IQA_MASK            (VTD_HAW_MASK ^ 0xfffULL)
+#define VTD_IQA_IQA_MASK(aw)        (VTD_HAW_MASK(aw) ^ 0xfffULL)
 #define VTD_IQA_QS                  0x7ULL
 
 /* IQH_REG */
@@ -252,7 +250,7 @@
 #define VTD_FRCD_SID_MASK       0xffffULL
 #define VTD_FRCD_SID(val)       ((val) & VTD_FRCD_SID_MASK)
 /* For the low 64-bit of 128-bit */
-#define VTD_FRCD_FI(val)        ((val) & (((1ULL << VTD_MGAW) - 1) ^ 0xfffULL))
+#define VTD_FRCD_FI(val)        ((val) & ~0xfffULL)
 
 /* DMA Remapping Fault Conditions */
 typedef enum VTDFaultReason {
@@ -360,8 +358,7 @@ typedef union VTDInvDesc VTDInvDesc;
 #define VTD_INV_DESC_IOTLB_DOMAIN       (2ULL << 4)
 #define VTD_INV_DESC_IOTLB_PAGE         (3ULL << 4)
 #define VTD_INV_DESC_IOTLB_DID(val)     (((val) >> 16) & VTD_DOMAIN_ID_MASK)
-#define VTD_INV_DESC_IOTLB_ADDR(val)    ((val) & ~0xfffULL & \
+#define VTD_INV_DESC_IOTLB_ADDR(val)    ((val) & ~0xfffULL)
-                                         ((1ULL << VTD_MGAW) - 1))
 #define VTD_INV_DESC_IOTLB_AM(val)      ((val) & 0x3fULL)
 #define VTD_INV_DESC_IOTLB_RSVD_LO      0xffffffff0000ff00ULL
 #define VTD_INV_DESC_IOTLB_RSVD_HI      0xf80ULL
@@ -373,6 +370,24 @@ typedef union VTDInvDesc VTDInvDesc;
 #define VTD_INV_DESC_DEVICE_IOTLB_RSVD_HI 0xffeULL
 #define VTD_INV_DESC_DEVICE_IOTLB_RSVD_LO 0xffff0000ffe0fff8
 
+/* Rsvd field masks for spte */
+#define VTD_SPTE_PAGE_L1_RSVD_MASK(aw) \
+        (0x800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
+#define VTD_SPTE_PAGE_L2_RSVD_MASK(aw) \
+        (0x800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
+#define VTD_SPTE_PAGE_L3_RSVD_MASK(aw) \
+        (0x800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
+#define VTD_SPTE_PAGE_L4_RSVD_MASK(aw) \
+        (0x880ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
+#define VTD_SPTE_LPAGE_L1_RSVD_MASK(aw) \
+        (0x800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
+#define VTD_SPTE_LPAGE_L2_RSVD_MASK(aw) \
+        (0x1ff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
+#define VTD_SPTE_LPAGE_L3_RSVD_MASK(aw) \
+        (0x3ffff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
+#define VTD_SPTE_LPAGE_L4_RSVD_MASK(aw) \
+        (0x880ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM))
+
 /* Information about page-selective IOTLB invalidate */
 struct VTDIOTLBPageInvInfo {
     uint16_t domain_id;
@@ -403,7 +418,7 @@ typedef struct VTDRootEntry VTDRootEntry;
 #define VTD_ROOT_ENTRY_CTP          (~0xfffULL)
 
 #define VTD_ROOT_ENTRY_NR           (VTD_PAGE_SIZE / sizeof(VTDRootEntry))
-#define VTD_ROOT_ENTRY_RSVD         (0xffeULL | ~VTD_HAW_MASK)
+#define VTD_ROOT_ENTRY_RSVD(aw)     (0xffeULL | ~VTD_HAW_MASK(aw))
 
 /* Masks for struct VTDContextEntry */
 /* lo */
@@ -415,7 +430,7 @@ typedef struct VTDRootEntry VTDRootEntry;
 #define VTD_CONTEXT_TT_PASS_THROUGH (2ULL << 2)
 /* Second Level Page Translation Pointer*/
 #define VTD_CONTEXT_ENTRY_SLPTPTR   (~0xfffULL)
-#define VTD_CONTEXT_ENTRY_RSVD_LO   (0xff0ULL | ~VTD_HAW_MASK)
+#define VTD_CONTEXT_ENTRY_RSVD_LO(aw) (0xff0ULL | ~VTD_HAW_MASK(aw))
 /* hi */
 #define VTD_CONTEXT_ENTRY_AW        7ULL /* Adjusted guest-address-width */
 #define VTD_CONTEXT_ENTRY_DID(val)  (((val) >> 8) & VTD_DOMAIN_ID_MASK)
@@ -439,7 +454,7 @@ typedef struct VTDRootEntry VTDRootEntry;
 #define VTD_SL_RW_MASK              3ULL
 #define VTD_SL_R                    1ULL
 #define VTD_SL_W                    (1ULL << 1)
-#define VTD_SL_PT_BASE_ADDR_MASK    (~(VTD_PAGE_SIZE - 1) & VTD_HAW_MASK)
+#define VTD_SL_PT_BASE_ADDR_MASK(aw) (~(VTD_PAGE_SIZE - 1) & VTD_HAW_MASK(aw))
 #define VTD_SL_IGN_COM              0xbff0000000000000ULL
 
 #endif

hw/i386/x86-iommu.c

@@ -21,6 +21,8 @@
 #include "hw/sysbus.h"
 #include "hw/boards.h"
 #include "hw/i386/x86-iommu.h"
+#include "hw/i386/pc.h"
+#include "qapi/error.h"
 #include "qemu/error-report.h"
 #include "trace.h"
 
@@ -80,7 +82,18 @@ static void x86_iommu_realize(DeviceState *dev, Error **errp)
 {
     X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(dev);
     X86IOMMUClass *x86_class = X86_IOMMU_GET_CLASS(dev);
+    MachineState *ms = MACHINE(qdev_get_machine());
+    MachineClass *mc = MACHINE_GET_CLASS(ms);
+    PCMachineState *pcms =
+        PC_MACHINE(object_dynamic_cast(OBJECT(ms), TYPE_PC_MACHINE));
     QLIST_INIT(&x86_iommu->iec_notifiers);
+
+    if (!pcms || !pcms->bus) {
+        error_setg(errp, "Machine-type '%s' not supported by IOMMU",
+                   mc->name);
+        return;
+    }
+
     if (x86_class->realize) {
         x86_class->realize(dev, errp);
     }

hw/pci-bridge/gen_pcie_root_port.c

@@ -74,8 +74,13 @@ static void gen_rp_realize(DeviceState *dev, Error **errp)
     PCIDevice *d = PCI_DEVICE(dev);
     GenPCIERootPort *grp = GEN_PCIE_ROOT_PORT(d);
     PCIERootPortClass *rpc = PCIE_ROOT_PORT_GET_CLASS(d);
+    Error *local_err = NULL;
 
-    rpc->parent_realize(dev, errp);
+    rpc->parent_realize(dev, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return;
+    }
 
     int rc = pci_bridge_qemu_reserve_cap_init(d, 0, grp->bus_reserve,
             grp->io_reserve, grp->mem_reserve, grp->pref32_reserve,

hw/pci/shpc.c

@@ -1,6 +1,7 @@
 #include "qemu/osdep.h"
 #include "qapi/error.h"
 #include "qemu-common.h"
+#include "qemu/host-utils.h"
 #include "qemu/range.h"
 #include "qemu/error-report.h"
 #include "hw/pci/shpc.h"
@@ -122,16 +123,6 @@
 #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);
@@ -656,7 +647,7 @@ int shpc_init(PCIDevice *d, PCIBus *sec_bus, MemoryRegion *bar,
 
 int shpc_bar_size(PCIDevice *d)
 {
-    return roundup_pow_of_two(SHPC_SLOT_REG(SHPC_MAX_SLOTS));
+    return pow2roundup32(SHPC_SLOT_REG(SHPC_MAX_SLOTS));
 }
 
 void shpc_cleanup(PCIDevice *d, MemoryRegion *bar)

hw/virtio/vhost-user.c

@@ -26,6 +26,11 @@
 #define VHOST_MEMORY_MAX_NREGIONS    8
 #define VHOST_USER_F_PROTOCOL_FEATURES 30
 
+/*
+ * Maximum size of virtio device config space
+ */
+#define VHOST_USER_MAX_CONFIG_SIZE 256
+
 enum VhostUserProtocolFeature {
     VHOST_USER_PROTOCOL_F_MQ = 0,
     VHOST_USER_PROTOCOL_F_LOG_SHMFD = 1,
@@ -65,12 +70,15 @@ typedef enum VhostUserRequest {
     VHOST_USER_SET_SLAVE_REQ_FD = 21,
     VHOST_USER_IOTLB_MSG = 22,
     VHOST_USER_SET_VRING_ENDIAN = 23,
+    VHOST_USER_GET_CONFIG = 24,
+    VHOST_USER_SET_CONFIG = 25,
     VHOST_USER_MAX
 } VhostUserRequest;
 
 typedef enum VhostUserSlaveRequest {
     VHOST_USER_SLAVE_NONE = 0,
     VHOST_USER_SLAVE_IOTLB_MSG = 1,
+    VHOST_USER_SLAVE_CONFIG_CHANGE_MSG = 2,
     VHOST_USER_SLAVE_MAX
 }  VhostUserSlaveRequest;
 
@@ -92,7 +100,19 @@ typedef struct VhostUserLog {
     uint64_t mmap_offset;
 } VhostUserLog;
 
-typedef struct VhostUserMsg {
+typedef struct VhostUserConfig {
+    uint32_t offset;
+    uint32_t size;
+    uint32_t flags;
+    uint8_t region[VHOST_USER_MAX_CONFIG_SIZE];
+} VhostUserConfig;
+
+static VhostUserConfig c __attribute__ ((unused));
+#define VHOST_USER_CONFIG_HDR_SIZE (sizeof(c.offset) \
+                                   + sizeof(c.size) \
+                                   + sizeof(c.flags))
+
+typedef struct {
     VhostUserRequest request;
 
 #define VHOST_USER_VERSION_MASK     (0x3)
@@ -100,7 +120,9 @@ typedef struct VhostUserMsg {
 #define VHOST_USER_NEED_REPLY_MASK  (0x1 << 3)
     uint32_t flags;
     uint32_t size; /* the following payload size */
-    union {
+} QEMU_PACKED VhostUserHeader;
+
+typedef union {
 #define VHOST_USER_VRING_IDX_MASK   (0xff)
 #define VHOST_USER_VRING_NOFD_MASK  (0x1<<8)
         uint64_t u64;
@@ -109,15 +131,18 @@ typedef struct VhostUserMsg {
         VhostUserMemory memory;
         VhostUserLog log;
         struct vhost_iotlb_msg iotlb;
-    } payload;
+        VhostUserConfig config;
+} VhostUserPayload;
+
+typedef struct VhostUserMsg {
+    VhostUserHeader hdr;
+    VhostUserPayload payload;
 } QEMU_PACKED VhostUserMsg;
 
 static VhostUserMsg m __attribute__ ((unused));
-#define VHOST_USER_HDR_SIZE (sizeof(m.request) \
+#define VHOST_USER_HDR_SIZE (sizeof(VhostUserHeader))
-                            + sizeof(m.flags) \
-                            + sizeof(m.size))
 
-#define VHOST_USER_PAYLOAD_SIZE (sizeof(m) - VHOST_USER_HDR_SIZE)
+#define VHOST_USER_PAYLOAD_SIZE (sizeof(VhostUserPayload))
 
 /* The version of the protocol we support */
 #define VHOST_USER_VERSION    (0x1)
@@ -142,33 +167,33 @@ static int vhost_user_read(struct vhost_dev *dev, VhostUserMsg *msg)
     r = qemu_chr_fe_read_all(chr, p, size);
     if (r != size) {
         error_report("Failed to read msg header. Read %d instead of %d."
-                     " Original request %d.", r, size, msg->request);
+                     " Original request %d.", r, size, msg->hdr.request);
         goto fail;
     }
 
     /* validate received flags */
-    if (msg->flags != (VHOST_USER_REPLY_MASK | VHOST_USER_VERSION)) {
+    if (msg->hdr.flags != (VHOST_USER_REPLY_MASK | VHOST_USER_VERSION)) {
         error_report("Failed to read msg header."
-                " Flags 0x%x instead of 0x%x.", msg->flags,
+                " Flags 0x%x instead of 0x%x.", msg->hdr.flags,
                 VHOST_USER_REPLY_MASK | VHOST_USER_VERSION);
         goto fail;
     }
 
     /* validate message size is sane */
-    if (msg->size > VHOST_USER_PAYLOAD_SIZE) {
+    if (msg->hdr.size > VHOST_USER_PAYLOAD_SIZE) {
         error_report("Failed to read msg header."
-                " Size %d exceeds the maximum %zu.", msg->size,
+                " Size %d exceeds the maximum %zu.", msg->hdr.size,
                 VHOST_USER_PAYLOAD_SIZE);
         goto fail;
     }
 
-    if (msg->size) {
+    if (msg->hdr.size) {
         p += VHOST_USER_HDR_SIZE;
-        size = msg->size;
+        size = msg->hdr.size;
         r = qemu_chr_fe_read_all(chr, p, size);
         if (r != size) {
             error_report("Failed to read msg payload."
-                         " Read %d instead of %d.", r, msg->size);
+                         " Read %d instead of %d.", r, msg->hdr.size);
             goto fail;
         }
     }
@@ -184,7 +209,7 @@ static int process_message_reply(struct vhost_dev *dev,
 {
     VhostUserMsg msg_reply;
 
-    if ((msg->flags & VHOST_USER_NEED_REPLY_MASK) == 0) {
+    if ((msg->hdr.flags & VHOST_USER_NEED_REPLY_MASK) == 0) {
         return 0;
     }
 
@@ -192,10 +217,10 @@ static int process_message_reply(struct vhost_dev *dev,
         return -1;
     }
 
-    if (msg_reply.request != msg->request) {
+    if (msg_reply.hdr.request != msg->hdr.request) {
         error_report("Received unexpected msg type."
                      "Expected %d received %d",
-                     msg->request, msg_reply.request);
+                     msg->hdr.request, msg_reply.hdr.request);
         return -1;
     }
 
@@ -222,15 +247,15 @@ static int vhost_user_write(struct vhost_dev *dev, VhostUserMsg *msg,
 {
     struct vhost_user *u = dev->opaque;
     CharBackend *chr = u->chr;
-    int ret, size = VHOST_USER_HDR_SIZE + msg->size;
+    int ret, size = VHOST_USER_HDR_SIZE + msg->hdr.size;
 
     /*
      * For non-vring specific requests, like VHOST_USER_SET_MEM_TABLE,
      * we just need send it once in the first time. For later such
      * request, we just ignore it.
      */
-    if (vhost_user_one_time_request(msg->request) && dev->vq_index != 0) {
+    if (vhost_user_one_time_request(msg->hdr.request) && dev->vq_index != 0) {
-        msg->flags &= ~VHOST_USER_NEED_REPLY_MASK;
+        msg->hdr.flags &= ~VHOST_USER_NEED_REPLY_MASK;
         return 0;
     }
 
@@ -257,11 +282,11 @@ static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base,
     bool shmfd = virtio_has_feature(dev->protocol_features,
                                     VHOST_USER_PROTOCOL_F_LOG_SHMFD);
     VhostUserMsg msg = {
-        .request = VHOST_USER_SET_LOG_BASE,
+        .hdr.request = VHOST_USER_SET_LOG_BASE,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
         .payload.log.mmap_size = log->size * sizeof(*(log->log)),
         .payload.log.mmap_offset = 0,
-        .size = sizeof(msg.payload.log),
+        .hdr.size = sizeof(msg.payload.log),
     };
 
     if (shmfd && log->fd != -1) {
@@ -273,15 +298,15 @@ static int vhost_user_set_log_base(struct vhost_dev *dev, uint64_t base,
     }
 
     if (shmfd) {
-        msg.size = 0;
+        msg.hdr.size = 0;
         if (vhost_user_read(dev, &msg) < 0) {
             return -1;
         }
 
-        if (msg.request != VHOST_USER_SET_LOG_BASE) {
+        if (msg.hdr.request != VHOST_USER_SET_LOG_BASE) {
             error_report("Received unexpected msg type. "
                          "Expected %d received %d",
-                         VHOST_USER_SET_LOG_BASE, msg.request);
+                         VHOST_USER_SET_LOG_BASE, msg.hdr.request);
             return -1;
         }
     }
@@ -299,12 +324,12 @@ static int vhost_user_set_mem_table(struct vhost_dev *dev,
                                               VHOST_USER_PROTOCOL_F_REPLY_ACK);
 
     VhostUserMsg msg = {
-        .request = VHOST_USER_SET_MEM_TABLE,
+        .hdr.request = VHOST_USER_SET_MEM_TABLE,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
     };
 
     if (reply_supported) {
-        msg.flags |= VHOST_USER_NEED_REPLY_MASK;
+        msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
     }
 
     for (i = 0; i < dev->mem->nregions; ++i) {
@@ -317,11 +342,14 @@ static int vhost_user_set_mem_table(struct vhost_dev *dev,
                                      &offset);
         fd = memory_region_get_fd(mr);
         if (fd > 0) {
+            if (fd_num == VHOST_MEMORY_MAX_NREGIONS) {
+                error_report("Failed preparing vhost-user memory table msg");
+                return -1;
+            }
             msg.payload.memory.regions[fd_num].userspace_addr = reg->userspace_addr;
             msg.payload.memory.regions[fd_num].memory_size  = reg->memory_size;
             msg.payload.memory.regions[fd_num].guest_phys_addr = reg->guest_phys_addr;
             msg.payload.memory.regions[fd_num].mmap_offset = offset;
-            assert(fd_num < VHOST_MEMORY_MAX_NREGIONS);
             fds[fd_num++] = fd;
         }
     }
@@ -334,9 +362,9 @@ static int vhost_user_set_mem_table(struct vhost_dev *dev,
         return -1;
     }
 
-    msg.size = sizeof(msg.payload.memory.nregions);
+    msg.hdr.size = sizeof(msg.payload.memory.nregions);
-    msg.size += sizeof(msg.payload.memory.padding);
+    msg.hdr.size += sizeof(msg.payload.memory.padding);
-    msg.size += fd_num * sizeof(VhostUserMemoryRegion);
+    msg.hdr.size += fd_num * sizeof(VhostUserMemoryRegion);
 
     if (vhost_user_write(dev, &msg, fds, fd_num) < 0) {
         return -1;
@@ -353,10 +381,10 @@ static int vhost_user_set_vring_addr(struct vhost_dev *dev,
                                      struct vhost_vring_addr *addr)
 {
     VhostUserMsg msg = {
-        .request = VHOST_USER_SET_VRING_ADDR,
+        .hdr.request = VHOST_USER_SET_VRING_ADDR,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
         .payload.addr = *addr,
-        .size = sizeof(msg.payload.addr),
+        .hdr.size = sizeof(msg.payload.addr),
     };
 
     if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
@@ -372,10 +400,10 @@ static int vhost_user_set_vring_endian(struct vhost_dev *dev,
     bool cross_endian = virtio_has_feature(dev->protocol_features,
                                            VHOST_USER_PROTOCOL_F_CROSS_ENDIAN);
     VhostUserMsg msg = {
-        .request = VHOST_USER_SET_VRING_ENDIAN,
+        .hdr.request = VHOST_USER_SET_VRING_ENDIAN,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
         .payload.state = *ring,
-        .size = sizeof(msg.payload.state),
+        .hdr.size = sizeof(msg.payload.state),
     };
 
     if (!cross_endian) {
@@ -395,10 +423,10 @@ static int vhost_set_vring(struct vhost_dev *dev,
                            struct vhost_vring_state *ring)
 {
     VhostUserMsg msg = {
-        .request = request,
+        .hdr.request = request,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
         .payload.state = *ring,
-        .size = sizeof(msg.payload.state),
+        .hdr.size = sizeof(msg.payload.state),
     };
 
     if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
@@ -444,10 +472,10 @@ static int vhost_user_get_vring_base(struct vhost_dev *dev,
                                      struct vhost_vring_state *ring)
 {
     VhostUserMsg msg = {
-        .request = VHOST_USER_GET_VRING_BASE,
+        .hdr.request = VHOST_USER_GET_VRING_BASE,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
         .payload.state = *ring,
-        .size = sizeof(msg.payload.state),
+        .hdr.size = sizeof(msg.payload.state),
     };
 
     if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
@@ -458,13 +486,13 @@ static int vhost_user_get_vring_base(struct vhost_dev *dev,
         return -1;
     }
 
-    if (msg.request != VHOST_USER_GET_VRING_BASE) {
+    if (msg.hdr.request != VHOST_USER_GET_VRING_BASE) {
         error_report("Received unexpected msg type. Expected %d received %d",
-                     VHOST_USER_GET_VRING_BASE, msg.request);
+                     VHOST_USER_GET_VRING_BASE, msg.hdr.request);
         return -1;
     }
 
-    if (msg.size != sizeof(msg.payload.state)) {
+    if (msg.hdr.size != sizeof(msg.payload.state)) {
         error_report("Received bad msg size.");
         return -1;
     }
@@ -481,10 +509,10 @@ static int vhost_set_vring_file(struct vhost_dev *dev,
     int fds[VHOST_MEMORY_MAX_NREGIONS];
     size_t fd_num = 0;
     VhostUserMsg msg = {
-        .request = request,
+        .hdr.request = request,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
         .payload.u64 = file->index & VHOST_USER_VRING_IDX_MASK,
-        .size = sizeof(msg.payload.u64),
+        .hdr.size = sizeof(msg.payload.u64),
     };
 
     if (ioeventfd_enabled() && file->fd > 0) {
@@ -515,10 +543,10 @@ static int vhost_user_set_vring_call(struct vhost_dev *dev,
 static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64)
 {
     VhostUserMsg msg = {
-        .request = request,
+        .hdr.request = request,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
         .payload.u64 = u64,
-        .size = sizeof(msg.payload.u64),
+        .hdr.size = sizeof(msg.payload.u64),
     };
 
     if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
@@ -543,8 +571,8 @@ static int vhost_user_set_protocol_features(struct vhost_dev *dev,
 static int vhost_user_get_u64(struct vhost_dev *dev, int request, uint64_t *u64)
 {
     VhostUserMsg msg = {
-        .request = request,
+        .hdr.request = request,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
     };
 
     if (vhost_user_one_time_request(request) && dev->vq_index != 0) {
@@ -559,13 +587,13 @@ static int vhost_user_get_u64(struct vhost_dev *dev, int request, uint64_t *u64)
         return -1;
     }
 
-    if (msg.request != request) {
+    if (msg.hdr.request != request) {
         error_report("Received unexpected msg type. Expected %d received %d",
-                     request, msg.request);
+                     request, msg.hdr.request);
         return -1;
     }
 
-    if (msg.size != sizeof(msg.payload.u64)) {
+    if (msg.hdr.size != sizeof(msg.payload.u64)) {
         error_report("Received bad msg size.");
         return -1;
     }
@@ -583,8 +611,8 @@ static int vhost_user_get_features(struct vhost_dev *dev, uint64_t *features)
 static int vhost_user_set_owner(struct vhost_dev *dev)
 {
     VhostUserMsg msg = {
-        .request = VHOST_USER_SET_OWNER,
+        .hdr.request = VHOST_USER_SET_OWNER,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
     };
 
     if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
@@ -597,8 +625,8 @@ static int vhost_user_set_owner(struct vhost_dev *dev)
 static int vhost_user_reset_device(struct vhost_dev *dev)
 {
     VhostUserMsg msg = {
-        .request = VHOST_USER_RESET_OWNER,
+        .hdr.request = VHOST_USER_RESET_OWNER,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
     };
 
     if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
@@ -608,37 +636,56 @@ static int vhost_user_reset_device(struct vhost_dev *dev)
     return 0;
 }
 
+static int vhost_user_slave_handle_config_change(struct vhost_dev *dev)
+{
+    int ret = -1;
+
+    if (!dev->config_ops) {
+        return -1;
+    }
+
+    if (dev->config_ops->vhost_dev_config_notifier) {
+        ret = dev->config_ops->vhost_dev_config_notifier(dev);
+    }
+
+    return ret;
+}
+
 static void slave_read(void *opaque)
 {
     struct vhost_dev *dev = opaque;
     struct vhost_user *u = dev->opaque;
-    VhostUserMsg msg = { 0, };
+    VhostUserHeader hdr = { 0, };
+    VhostUserPayload payload = { 0, };
     int size, ret = 0;
 
     /* Read header */
-    size = read(u->slave_fd, &msg, VHOST_USER_HDR_SIZE);
+    size = read(u->slave_fd, &hdr, VHOST_USER_HDR_SIZE);
     if (size != VHOST_USER_HDR_SIZE) {
         error_report("Failed to read from slave.");
         goto err;
     }
 
-    if (msg.size > VHOST_USER_PAYLOAD_SIZE) {
+    if (hdr.size > VHOST_USER_PAYLOAD_SIZE) {
         error_report("Failed to read msg header."
-                " Size %d exceeds the maximum %zu.", msg.size,
+                " Size %d exceeds the maximum %zu.", hdr.size,
                 VHOST_USER_PAYLOAD_SIZE);
         goto err;
     }
 
     /* Read payload */
-    size = read(u->slave_fd, &msg.payload, msg.size);
+    size = read(u->slave_fd, &payload, hdr.size);
-    if (size != msg.size) {
+    if (size != hdr.size) {
         error_report("Failed to read payload from slave.");
         goto err;
     }
 
-    switch (msg.request) {
+    switch (hdr.request) {
     case VHOST_USER_SLAVE_IOTLB_MSG:
-        ret = vhost_backend_handle_iotlb_msg(dev, &msg.payload.iotlb);
+        ret = vhost_backend_handle_iotlb_msg(dev, &payload.iotlb);
+        break;
+    case VHOST_USER_SLAVE_CONFIG_CHANGE_MSG :
+        ret = vhost_user_slave_handle_config_change(dev);
         break;
     default:
         error_report("Received unexpected msg type.");
@@ -649,15 +696,23 @@ static void slave_read(void *opaque)
      * REPLY_ACK feature handling. Other reply types has to be managed
      * directly in their request handlers.
      */
-    if (msg.flags & VHOST_USER_NEED_REPLY_MASK) {
+    if (hdr.flags & VHOST_USER_NEED_REPLY_MASK) {
-        msg.flags &= ~VHOST_USER_NEED_REPLY_MASK;
+        struct iovec iovec[2];
-        msg.flags |= VHOST_USER_REPLY_MASK;
 
-        msg.payload.u64 = !!ret;
-        msg.size = sizeof(msg.payload.u64);
 
-        size = write(u->slave_fd, &msg, VHOST_USER_HDR_SIZE + msg.size);
+        hdr.flags &= ~VHOST_USER_NEED_REPLY_MASK;
-        if (size != VHOST_USER_HDR_SIZE + msg.size) {
+        hdr.flags |= VHOST_USER_REPLY_MASK;
+
+        payload.u64 = !!ret;
+        hdr.size = sizeof(payload.u64);
+
+        iovec[0].iov_base = &hdr;
+        iovec[0].iov_len = VHOST_USER_HDR_SIZE;
+        iovec[1].iov_base = &payload;
+        iovec[1].iov_len = hdr.size;
+
+        size = writev(u->slave_fd, iovec, ARRAY_SIZE(iovec));
+        if (size != VHOST_USER_HDR_SIZE + hdr.size) {
             error_report("Failed to send msg reply to slave.");
             goto err;
         }
@@ -675,8 +730,8 @@ err:
 static int vhost_setup_slave_channel(struct vhost_dev *dev)
 {
     VhostUserMsg msg = {
-        .request = VHOST_USER_SET_SLAVE_REQ_FD,
+        .hdr.request = VHOST_USER_SET_SLAVE_REQ_FD,
-        .flags = VHOST_USER_VERSION,
+        .hdr.flags = VHOST_USER_VERSION,
     };
     struct vhost_user *u = dev->opaque;
     int sv[2], ret = 0;
@@ -697,7 +752,7 @@ static int vhost_setup_slave_channel(struct vhost_dev *dev)
     qemu_set_fd_handler(u->slave_fd, slave_read, NULL, dev);
 
     if (reply_supported) {
-        msg.flags |= VHOST_USER_NEED_REPLY_MASK;
+        msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
     }
 
     ret = vhost_user_write(dev, &msg, &sv[1], 1);
@@ -842,10 +897,10 @@ static int vhost_user_migration_done(struct vhost_dev *dev, char* mac_addr)
     /* if backend supports VHOST_USER_PROTOCOL_F_RARP ask it to send the RARP */
     if (virtio_has_feature(dev->protocol_features,
                            VHOST_USER_PROTOCOL_F_RARP)) {
-        msg.request = VHOST_USER_SEND_RARP;
+        msg.hdr.request = VHOST_USER_SEND_RARP;
-        msg.flags = VHOST_USER_VERSION;
+        msg.hdr.flags = VHOST_USER_VERSION;
         memcpy((char *)&msg.payload.u64, mac_addr, 6);
-        msg.size = sizeof(msg.payload.u64);
+        msg.hdr.size = sizeof(msg.payload.u64);
 
         return vhost_user_write(dev, &msg, NULL, 0);
     }
@@ -879,12 +934,12 @@ static int vhost_user_net_set_mtu(struct vhost_dev *dev, uint16_t mtu)
         return 0;
     }
 
-    msg.request = VHOST_USER_NET_SET_MTU;
+    msg.hdr.request = VHOST_USER_NET_SET_MTU;
     msg.payload.u64 = mtu;
-    msg.size = sizeof(msg.payload.u64);
+    msg.hdr.size = sizeof(msg.payload.u64);
-    msg.flags = VHOST_USER_VERSION;
+    msg.hdr.flags = VHOST_USER_VERSION;
     if (reply_supported) {
-        msg.flags |= VHOST_USER_NEED_REPLY_MASK;
+        msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
     }
 
     if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
@@ -903,9 +958,9 @@ static int vhost_user_send_device_iotlb_msg(struct vhost_dev *dev,
                                             struct vhost_iotlb_msg *imsg)
 {
     VhostUserMsg msg = {
-        .request = VHOST_USER_IOTLB_MSG,
+        .hdr.request = VHOST_USER_IOTLB_MSG,
-        .size = sizeof(msg.payload.iotlb),
+        .hdr.size = sizeof(msg.payload.iotlb),
-        .flags = VHOST_USER_VERSION | VHOST_USER_NEED_REPLY_MASK,
+        .hdr.flags = VHOST_USER_VERSION | VHOST_USER_NEED_REPLY_MASK,
         .payload.iotlb = *imsg,
     };
 
@@ -922,6 +977,83 @@ static void vhost_user_set_iotlb_callback(struct vhost_dev *dev, int enabled)
     /* No-op as the receive channel is not dedicated to IOTLB messages. */
 }
 
+static int vhost_user_get_config(struct vhost_dev *dev, uint8_t *config,
+                                 uint32_t config_len)
+{
+    VhostUserMsg msg = {
+        .hdr.request = VHOST_USER_GET_CONFIG,
+        .hdr.flags = VHOST_USER_VERSION,
+        .hdr.size = VHOST_USER_CONFIG_HDR_SIZE + config_len,
+    };
+
+    if (config_len > VHOST_USER_MAX_CONFIG_SIZE) {
+        return -1;
+    }
+
+    msg.payload.config.offset = 0;
+    msg.payload.config.size = config_len;
+    if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+        return -1;
+    }
+
+    if (vhost_user_read(dev, &msg) < 0) {
+        return -1;
+    }
+
+    if (msg.hdr.request != VHOST_USER_GET_CONFIG) {
+        error_report("Received unexpected msg type. Expected %d received %d",
+                     VHOST_USER_GET_CONFIG, msg.hdr.request);
+        return -1;
+    }
+
+    if (msg.hdr.size != VHOST_USER_CONFIG_HDR_SIZE + config_len) {
+        error_report("Received bad msg size.");
+        return -1;
+    }
+
+    memcpy(config, msg.payload.config.region, config_len);
+
+    return 0;
+}
+
+static int vhost_user_set_config(struct vhost_dev *dev, const uint8_t *data,
+                                 uint32_t offset, uint32_t size, uint32_t flags)
+{
+    uint8_t *p;
+    bool reply_supported = virtio_has_feature(dev->protocol_features,
+                                              VHOST_USER_PROTOCOL_F_REPLY_ACK);
+
+    VhostUserMsg msg = {
+        .hdr.request = VHOST_USER_SET_CONFIG,
+        .hdr.flags = VHOST_USER_VERSION,
+        .hdr.size = VHOST_USER_CONFIG_HDR_SIZE + size,
+    };
+
+    if (reply_supported) {
+        msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK;
+    }
+
+    if (size > VHOST_USER_MAX_CONFIG_SIZE) {
+        return -1;
+    }
+
+    msg.payload.config.offset = offset,
+    msg.payload.config.size = size,
+    msg.payload.config.flags = flags,
+    p = msg.payload.config.region;
+    memcpy(p, data, size);
+
+    if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+        return -1;
+    }
+
+    if (reply_supported) {
+        return process_message_reply(dev, &msg);
+    }
+
+    return 0;
+}
+
 const VhostOps user_ops = {
         .backend_type = VHOST_BACKEND_TYPE_USER,
         .vhost_backend_init = vhost_user_init,
@@ -948,4 +1080,6 @@ const VhostOps user_ops = {
         .vhost_net_set_mtu = vhost_user_net_set_mtu,
         .vhost_set_iotlb_callback = vhost_user_set_iotlb_callback,
         .vhost_send_device_iotlb_msg = vhost_user_send_device_iotlb_msg,
+        .vhost_get_config = vhost_user_get_config,
+        .vhost_set_config = vhost_user_set_config,
 };

hw/virtio/vhost.c

@@ -1505,6 +1505,38 @@ void vhost_ack_features(struct vhost_dev *hdev, const int *feature_bits,
     }
 }
 
+int vhost_dev_get_config(struct vhost_dev *hdev, uint8_t *config,
+                         uint32_t config_len)
+{
+    assert(hdev->vhost_ops);
+
+    if (hdev->vhost_ops->vhost_get_config) {
+        return hdev->vhost_ops->vhost_get_config(hdev, config, config_len);
+    }
+
+    return -1;
+}
+
+int vhost_dev_set_config(struct vhost_dev *hdev, const uint8_t *data,
+                         uint32_t offset, uint32_t size, uint32_t flags)
+{
+    assert(hdev->vhost_ops);
+
+    if (hdev->vhost_ops->vhost_set_config) {
+        return hdev->vhost_ops->vhost_set_config(hdev, data, offset,
+                                                 size, flags);
+    }
+
+    return -1;
+}
+
+void vhost_dev_set_config_notifier(struct vhost_dev *hdev,
+                                   const VhostDevConfigOps *ops)
+{
+    assert(hdev->vhost_ops);
+    hdev->config_ops = ops;
+}
+
 /* Host notifiers must be enabled at this point. */
 int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
 {

hw/virtio/virtio-bus.c

@@ -256,6 +256,15 @@ bool virtio_bus_ioeventfd_enabled(VirtioBusState *bus)
     return k->ioeventfd_assign && k->ioeventfd_enabled(proxy);
 }
 
+static void virtio_bus_cleanup_event_notifier(EventNotifier *notifier)
+{
+    /* Test and clear notifier after disabling event,
+     * in case poll callback didn't have time to run.
+     */
+    virtio_queue_host_notifier_read(notifier);
+    event_notifier_cleanup(notifier);
+}
+
 /*
  * This function switches ioeventfd on/off in the device.
  * The caller must set or clear the handlers for the EventNotifier.
@@ -283,19 +292,13 @@ int virtio_bus_set_host_notifier(VirtioBusState *bus, int n, bool assign)
         r = k->ioeventfd_assign(proxy, notifier, n, true);
         if (r < 0) {
             error_report("%s: unable to assign ioeventfd: %d", __func__, r);
-            goto cleanup_event_notifier;
+            virtio_bus_cleanup_event_notifier(notifier);
         }
-        return 0;
     } else {
+        notifier->cleanup = virtio_bus_cleanup_event_notifier;
         k->ioeventfd_assign(proxy, notifier, n, false);
     }
 
-cleanup_event_notifier:
-    /* Test and clear notifier after disabling event,
-     * in case poll callback didn't have time to run.
-     */
-    virtio_queue_host_notifier_read(notifier);
-    event_notifier_cleanup(notifier);
     return r;
 }
 

hw/virtio/virtio-pci.c

@@ -1978,6 +1978,58 @@ static const TypeInfo virtio_blk_pci_info = {
     .class_init    = virtio_blk_pci_class_init,
 };
 
+#if defined(CONFIG_VHOST_USER) && defined(CONFIG_LINUX)
+/* vhost-user-blk */
+
+static Property vhost_user_blk_pci_properties[] = {
+    DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0),
+    DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void vhost_user_blk_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
+{
+    VHostUserBlkPCI *dev = VHOST_USER_BLK_PCI(vpci_dev);
+    DeviceState *vdev = DEVICE(&dev->vdev);
+
+    qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus));
+    object_property_set_bool(OBJECT(vdev), true, "realized", errp);
+}
+
+static void vhost_user_blk_pci_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass);
+    PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass);
+
+    set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+    dc->props = vhost_user_blk_pci_properties;
+    k->realize = vhost_user_blk_pci_realize;
+    pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET;
+    pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_BLOCK;
+    pcidev_k->revision = VIRTIO_PCI_ABI_VERSION;
+    pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI;
+}
+
+static void vhost_user_blk_pci_instance_init(Object *obj)
+{
+    VHostUserBlkPCI *dev = VHOST_USER_BLK_PCI(obj);
+
+    virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev),
+                                TYPE_VHOST_USER_BLK);
+    object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev),
+                              "bootindex", &error_abort);
+}
+
+static const TypeInfo vhost_user_blk_pci_info = {
+    .name           = TYPE_VHOST_USER_BLK_PCI,
+    .parent         = TYPE_VIRTIO_PCI,
+    .instance_size  = sizeof(VHostUserBlkPCI),
+    .instance_init  = vhost_user_blk_pci_instance_init,
+    .class_init     = vhost_user_blk_pci_class_init,
+};
+#endif
+
 /* virtio-scsi-pci */
 
 static Property virtio_scsi_pci_properties[] = {
@@ -2624,6 +2676,9 @@ static void virtio_pci_register_types(void)
     type_register_static(&virtio_9p_pci_info);
 #endif
     type_register_static(&virtio_blk_pci_info);
+#if defined(CONFIG_VHOST_USER) && defined(CONFIG_LINUX)
+    type_register_static(&vhost_user_blk_pci_info);
+#endif
     type_register_static(&virtio_scsi_pci_info);
     type_register_static(&virtio_balloon_pci_info);
     type_register_static(&virtio_serial_pci_info);

hw/virtio/virtio-pci.h

@@ -27,6 +27,9 @@
 #include "hw/virtio/virtio-gpu.h"
 #include "hw/virtio/virtio-crypto.h"
 #include "hw/virtio/vhost-user-scsi.h"
+#if defined(CONFIG_VHOST_USER) && defined(CONFIG_LINUX)
+#include "hw/virtio/vhost-user-blk.h"
+#endif
 
 #ifdef CONFIG_VIRTFS
 #include "hw/9pfs/virtio-9p.h"
@@ -46,6 +49,7 @@ typedef struct VirtIOSerialPCI VirtIOSerialPCI;
 typedef struct VirtIONetPCI VirtIONetPCI;
 typedef struct VHostSCSIPCI VHostSCSIPCI;
 typedef struct VHostUserSCSIPCI VHostUserSCSIPCI;
+typedef struct VHostUserBlkPCI VHostUserBlkPCI;
 typedef struct VirtIORngPCI VirtIORngPCI;
 typedef struct VirtIOInputPCI VirtIOInputPCI;
 typedef struct VirtIOInputHIDPCI VirtIOInputHIDPCI;
@@ -244,6 +248,20 @@ struct VHostUserSCSIPCI {
     VHostUserSCSI vdev;
 };
 
+#if defined(CONFIG_VHOST_USER) && defined(CONFIG_LINUX)
+/*
+ * vhost-user-blk-pci: This extends VirtioPCIProxy.
+ */
+#define TYPE_VHOST_USER_BLK_PCI "vhost-user-blk-pci"
+#define VHOST_USER_BLK_PCI(obj) \
+        OBJECT_CHECK(VHostUserBlkPCI, (obj), TYPE_VHOST_USER_BLK_PCI)
+
+struct VHostUserBlkPCI {
+    VirtIOPCIProxy parent_obj;
+    VHostUserBlk vdev;
+};
+#endif
+
 /*
  * virtio-blk-pci: This extends VirtioPCIProxy.
  */

hw/virtio/virtio.c

@@ -2574,6 +2574,7 @@ static int virtio_device_start_ioeventfd_impl(VirtIODevice *vdev)
     VirtioBusState *qbus = VIRTIO_BUS(qdev_get_parent_bus(DEVICE(vdev)));
     int n, r, err;
 
+    memory_region_transaction_begin();
     for (n = 0; n < VIRTIO_QUEUE_MAX; n++) {
         VirtQueue *vq = &vdev->vq[n];
         if (!virtio_queue_get_num(vdev, n)) {
@@ -2596,6 +2597,7 @@ static int virtio_device_start_ioeventfd_impl(VirtIODevice *vdev)
         }
         event_notifier_set(&vq->host_notifier);
     }
+    memory_region_transaction_commit();
     return 0;
 
 assign_error:
@@ -2609,6 +2611,7 @@ assign_error:
         r = virtio_bus_set_host_notifier(qbus, n, false);
         assert(r >= 0);
     }
+    memory_region_transaction_commit();
     return err;
 }
 
@@ -2625,6 +2628,7 @@ static void virtio_device_stop_ioeventfd_impl(VirtIODevice *vdev)
     VirtioBusState *qbus = VIRTIO_BUS(qdev_get_parent_bus(DEVICE(vdev)));
     int n, r;
 
+    memory_region_transaction_begin();
     for (n = 0; n < VIRTIO_QUEUE_MAX; n++) {
         VirtQueue *vq = &vdev->vq[n];
 
@@ -2635,6 +2639,7 @@ static void virtio_device_stop_ioeventfd_impl(VirtIODevice *vdev)
         r = virtio_bus_set_host_notifier(qbus, n, false);
         assert(r >= 0);
     }
+    memory_region_transaction_commit();
 }
 
 void virtio_device_stop_ioeventfd(VirtIODevice *vdev)

include/hw/i386/intel_iommu.h

@@ -46,8 +46,10 @@
 #define VTD_SID_TO_DEVFN(sid)       ((sid) & 0xff)
 
 #define DMAR_REG_SIZE               0x230
-#define VTD_HOST_ADDRESS_WIDTH      39
+#define VTD_HOST_AW_39BIT           39
-#define VTD_HAW_MASK                ((1ULL << VTD_HOST_ADDRESS_WIDTH) - 1)
+#define VTD_HOST_AW_48BIT           48
+#define VTD_HOST_ADDRESS_WIDTH      VTD_HOST_AW_39BIT
+#define VTD_HAW_MASK(aw)            ((1ULL << (aw)) - 1)
 
 #define DMAR_REPORT_F_INTR          (1)
 
@@ -302,6 +304,7 @@ struct IntelIOMMUState {
     bool intr_eime;                 /* Extended interrupt mode enabled */
     OnOffAuto intr_eim;             /* Toggle for EIM cabability */
     bool buggy_eim;                 /* Force buggy EIM unless eim=off */
+    uint8_t aw_bits;                /* Host/IOVA address width (in bits) */
 };
 
 /* Find the VTD Address space associated with the given bus pointer,

include/hw/virtio/vhost-backend.h

@@ -20,6 +20,11 @@ typedef enum VhostBackendType {
     VHOST_BACKEND_TYPE_MAX = 3,
 } VhostBackendType;
 
+typedef enum VhostSetConfigType {
+    VHOST_SET_CONFIG_TYPE_MASTER = 0,
+    VHOST_SET_CONFIG_TYPE_MIGRATION = 1,
+} VhostSetConfigType;
+
 struct vhost_dev;
 struct vhost_log;
 struct vhost_memory;
@@ -84,6 +89,11 @@ typedef void (*vhost_set_iotlb_callback_op)(struct vhost_dev *dev,
                                            int enabled);
 typedef int (*vhost_send_device_iotlb_msg_op)(struct vhost_dev *dev,
                                               struct vhost_iotlb_msg *imsg);
+typedef int (*vhost_set_config_op)(struct vhost_dev *dev, const uint8_t *data,
+                                   uint32_t offset, uint32_t size,
+                                   uint32_t flags);
+typedef int (*vhost_get_config_op)(struct vhost_dev *dev, uint8_t *config,
+                                   uint32_t config_len);
 
 typedef struct VhostOps {
     VhostBackendType backend_type;
@@ -118,6 +128,8 @@ typedef struct VhostOps {
     vhost_vsock_set_running_op vhost_vsock_set_running;
     vhost_set_iotlb_callback_op vhost_set_iotlb_callback;
     vhost_send_device_iotlb_msg_op vhost_send_device_iotlb_msg;
+    vhost_get_config_op vhost_get_config;
+    vhost_set_config_op vhost_set_config;
 } VhostOps;
 
 extern const VhostOps user_ops;

include/hw/virtio/vhost-user-blk.h

@@ -0,0 +1,41 @@
+/*
+ * vhost-user-blk host device
+ * Copyright(C) 2017 Intel Corporation.
+ *
+ * Authors:
+ *  Changpeng Liu <changpeng.liu@intel.com>
+ *
+ * Based on vhost-scsi.h, Copyright IBM, Corp. 2011
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef VHOST_USER_BLK_H
+#define VHOST_USER_BLK_H
+
+#include "standard-headers/linux/virtio_blk.h"
+#include "qemu-common.h"
+#include "hw/qdev.h"
+#include "hw/block/block.h"
+#include "chardev/char-fe.h"
+#include "hw/virtio/vhost.h"
+
+#define TYPE_VHOST_USER_BLK "vhost-user-blk"
+#define VHOST_USER_BLK(obj) \
+        OBJECT_CHECK(VHostUserBlk, (obj), TYPE_VHOST_USER_BLK)
+
+typedef struct VHostUserBlk {
+    VirtIODevice parent_obj;
+    CharBackend chardev;
+    int32_t bootindex;
+    struct virtio_blk_config blkcfg;
+    uint16_t num_queues;
+    uint32_t queue_size;
+    uint32_t config_wce;
+    uint32_t config_ro;
+    struct vhost_dev dev;
+} VHostUserBlk;
+
+#endif

include/hw/virtio/vhost.h

@@ -46,6 +46,12 @@ struct vhost_iommu {
     QLIST_ENTRY(vhost_iommu) iommu_next;
 };
 
+typedef struct VhostDevConfigOps {
+    /* Vhost device config space changed callback
+     */
+    int (*vhost_dev_config_notifier)(struct vhost_dev *dev);
+} VhostDevConfigOps;
+
 struct vhost_memory;
 struct vhost_dev {
     VirtIODevice *vdev;
@@ -76,6 +82,7 @@ struct vhost_dev {
     QLIST_ENTRY(vhost_dev) entry;
     QLIST_HEAD(, vhost_iommu) iommu_list;
     IOMMUNotifier n;
+    const VhostDevConfigOps *config_ops;
 };
 
 int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
@@ -106,4 +113,12 @@ int vhost_net_set_backend(struct vhost_dev *hdev,
                           struct vhost_vring_file *file);
 
 int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write);
+int vhost_dev_get_config(struct vhost_dev *dev, uint8_t *config,
+                         uint32_t config_len);
+int vhost_dev_set_config(struct vhost_dev *dev, const uint8_t *data,
+                         uint32_t offset, uint32_t size, uint32_t flags);
+/* notifier callback in case vhost device config space changed
+ */
+void vhost_dev_set_config_notifier(struct vhost_dev *dev,
+                                   const VhostDevConfigOps *ops);
 #endif

include/qemu/event_notifier.h

@@ -26,6 +26,7 @@ struct EventNotifier {
     int rfd;
     int wfd;
 #endif
+    void (*cleanup)(EventNotifier *);
 };
 
 typedef void EventNotifierHandler(EventNotifier *);

include/qemu/host-utils.h

@@ -400,6 +400,16 @@ static inline uint64_t pow2ceil(uint64_t value)
     return 0x8000000000000000ull >> (n - 1);
 }
 
+static inline uint32_t pow2roundup32(uint32_t x)
+{
+    x |= (x >> 1);
+    x |= (x >> 2);
+    x |= (x >> 4);
+    x |= (x >> 8);
+    x |= (x >> 16);
+    return x + 1;
+}
+
 /**
  * urshift - 128-bit Unsigned Right Shift.
  * @plow: in/out - lower 64-bit integer.

tests/bios-tables-test.c

@@ -210,10 +210,15 @@ static void test_acpi_facs_table(test_data *data)
     ACPI_ASSERT_CMP(facs_table->signature, "FACS");
 }
 
-static void test_dst_table(AcpiSdtTable *sdt_table, uint32_t addr)
+/** fetch_table
+ *   load ACPI table at @addr into table descriptor @sdt_table
+ *   and check that header checksum matches actual one.
+ */
+static void fetch_table(AcpiSdtTable *sdt_table, uint32_t addr)
 {
     uint8_t checksum;
 
+    memset(sdt_table, 0, sizeof(*sdt_table));
     ACPI_READ_TABLE_HEADER(&sdt_table->header, addr);
 
     sdt_table->aml_len = le32_to_cpu(sdt_table->header.length)
@@ -233,17 +238,15 @@ static void test_acpi_dsdt_table(test_data *data)
     AcpiSdtTable dsdt_table;
     uint32_t addr = le32_to_cpu(data->fadt_table.dsdt);
 
-    memset(&dsdt_table, 0, sizeof(dsdt_table));
+    fetch_table(&dsdt_table, addr);
-    data->tables = g_array_new(false, true, sizeof(AcpiSdtTable));
-
-    test_dst_table(&dsdt_table, addr);
     ACPI_ASSERT_CMP(dsdt_table.header.signature, "DSDT");
 
-    /* Place DSDT first */
+    /* Since DSDT isn't in RSDT, add DSDT to ASL test tables list manually */
     g_array_append_val(data->tables, dsdt_table);
 }
 
-static void test_acpi_tables(test_data *data)
+/* Load all tables and add to test list directly RSDT referenced tables */
+static void fetch_rsdt_referenced_tables(test_data *data)
 {
     int tables_nr = data->rsdt_tables_nr - 1; /* fadt is first */
     int i;
@@ -252,9 +255,10 @@ static void test_acpi_tables(test_data *data)
         AcpiSdtTable ssdt_table;
         uint32_t addr;
 
-        memset(&ssdt_table, 0, sizeof(ssdt_table));
         addr = le32_to_cpu(data->rsdt_tables_addr[i + 1]); /* fadt is first */
-        test_dst_table(&ssdt_table, addr);
+        fetch_table(&ssdt_table, addr);
+
+        /* Add table to ASL test tables list */
         g_array_append_val(data->tables, ssdt_table);
     }
 }
@@ -425,6 +429,7 @@ try_again:
     return exp_tables;
 }
 
+/* test the list of tables in @data->tables against reference tables */
 static void test_acpi_asl(test_data *data)
 {
     int i;
@@ -636,13 +641,14 @@ static void test_acpi_one(const char *params, test_data *data)
 
     boot_sector_test();
 
+    data->tables = g_array_new(false, true, sizeof(AcpiSdtTable));
     test_acpi_rsdp_address(data);
     test_acpi_rsdp_table(data);
     test_acpi_rsdt_table(data);
     test_acpi_fadt_table(data);
     test_acpi_facs_table(data);
     test_acpi_dsdt_table(data);
-    test_acpi_tables(data);
+    fetch_rsdt_referenced_tables(data);
 
     if (iasl) {
         if (getenv(ACPI_REBUILD_EXPECTED_AML)) {
@@ -810,6 +816,28 @@ static void test_acpi_piix4_tcg_memhp(void)
     free_test_data(&data);
 }
 
+static void test_acpi_q35_tcg_numamem(void)
+{
+    test_data data;
+
+    memset(&data, 0, sizeof(data));
+    data.machine = MACHINE_Q35;
+    data.variant = ".numamem";
+    test_acpi_one(" -numa node -numa node,mem=128", &data);
+    free_test_data(&data);
+}
+
+static void test_acpi_piix4_tcg_numamem(void)
+{
+    test_data data;
+
+    memset(&data, 0, sizeof(data));
+    data.machine = MACHINE_PC;
+    data.variant = ".numamem";
+    test_acpi_one(" -numa node -numa node,mem=128", &data);
+    free_test_data(&data);
+}
+
 int main(int argc, char *argv[])
 {
     const char *arch = qtest_get_arch();
@@ -832,6 +860,8 @@ int main(int argc, char *argv[])
         qtest_add_func("acpi/q35/cpuhp", test_acpi_q35_tcg_cphp);
         qtest_add_func("acpi/piix4/memhp", test_acpi_piix4_tcg_memhp);
         qtest_add_func("acpi/q35/memhp", test_acpi_q35_tcg_memhp);
+        qtest_add_func("acpi/piix4/numamem", test_acpi_piix4_tcg_numamem);
+        qtest_add_func("acpi/q35/numamem", test_acpi_q35_tcg_numamem);
     }
     ret = g_test_run();
     boot_sector_cleanup(disk);

tests/vhost-user-test.c

@@ -55,6 +55,7 @@
 /*********** FROM hw/virtio/vhost-user.c *************************************/
 
 #define VHOST_MEMORY_MAX_NREGIONS    8
+#define VHOST_MAX_VIRTQUEUES    0x100
 
 #define VHOST_USER_F_PROTOCOL_FEATURES 30
 #define VHOST_USER_PROTOCOL_F_MQ 0
@@ -141,6 +142,8 @@ enum {
 
 typedef struct TestServer {
     QPCIBus *bus;
+    QVirtioPCIDevice *dev;
+    QVirtQueue *vq[VHOST_MAX_VIRTQUEUES];
     gchar *socket_path;
     gchar *mig_path;
     gchar *chr_name;
@@ -155,33 +158,51 @@ typedef struct TestServer {
     bool test_fail;
     int test_flags;
     int queues;
+    QGuestAllocator *alloc;
 } TestServer;
 
 static const char *tmpfs;
 static const char *root;
 
-static void init_virtio_dev(TestServer *s)
+static void init_virtio_dev(TestServer *s, uint32_t features_mask)
 {
-    QVirtioPCIDevice *dev;
     uint32_t features;
+    int i;
 
     s->bus = qpci_init_pc(NULL);
     g_assert_nonnull(s->bus);
 
-    dev = qvirtio_pci_device_find(s->bus, VIRTIO_ID_NET);
+    s->dev = qvirtio_pci_device_find(s->bus, VIRTIO_ID_NET);
-    g_assert_nonnull(dev);
+    g_assert_nonnull(s->dev);
 
-    qvirtio_pci_device_enable(dev);
+    qvirtio_pci_device_enable(s->dev);
-    qvirtio_reset(&dev->vdev);
+    qvirtio_reset(&s->dev->vdev);
-    qvirtio_set_acknowledge(&dev->vdev);
+    qvirtio_set_acknowledge(&s->dev->vdev);
-    qvirtio_set_driver(&dev->vdev);
+    qvirtio_set_driver(&s->dev->vdev);
 
-    features = qvirtio_get_features(&dev->vdev);
+    s->alloc = pc_alloc_init();
-    features = features & VIRTIO_NET_F_MAC;
-    qvirtio_set_features(&dev->vdev, features);
 
-    qvirtio_set_driver_ok(&dev->vdev);
+    for (i = 0; i < s->queues * 2; i++) {
-    qvirtio_pci_device_free(dev);
+        s->vq[i] = qvirtqueue_setup(&s->dev->vdev, s->alloc, i);
+    }
+
+    features = qvirtio_get_features(&s->dev->vdev);
+    features = features & features_mask;
+    qvirtio_set_features(&s->dev->vdev, features);
+
+    qvirtio_set_driver_ok(&s->dev->vdev);
+}
+
+static void uninit_virtio_dev(TestServer *s)
+{
+    int i;
+
+    for (i = 0; i < s->queues * 2; i++) {
+        qvirtqueue_cleanup(s->dev->vdev.bus, s->vq[i], s->alloc);
+    }
+    pc_alloc_uninit(s->alloc);
+
+    qvirtio_pci_device_free(s->dev);
 }
 
 static void wait_for_fds(TestServer *s)
@@ -617,6 +638,30 @@ GSourceFuncs test_migrate_source_funcs = {
     .check = test_migrate_source_check,
 };
 
+static void test_read_guest_mem(void)
+{
+    TestServer *server = NULL;
+    char *qemu_cmd = NULL;
+    QTestState *s = NULL;
+
+    server = test_server_new("test");
+    test_server_listen(server);
+
+    qemu_cmd = GET_QEMU_CMD(server);
+
+    s = qtest_start(qemu_cmd);
+    g_free(qemu_cmd);
+
+    init_virtio_dev(server, 1u << VIRTIO_NET_F_MAC);
+
+    read_guest_mem(server);
+
+    uninit_virtio_dev(server);
+
+    qtest_quit(s);
+    test_server_free(server);
+}
+
 static void test_migrate(void)
 {
     TestServer *s = test_server_new("src");
@@ -636,7 +681,7 @@ static void test_migrate(void)
     from = qtest_start(cmd);
     g_free(cmd);
 
-    init_virtio_dev(s);
+    init_virtio_dev(s, 1u << VIRTIO_NET_F_MAC);
     wait_for_fds(s);
     size = get_log_size(s);
     g_assert_cmpint(size, ==, (2 * 1024 * 1024) / (VHOST_LOG_PAGE * 8));
@@ -689,6 +734,8 @@ static void test_migrate(void)
 
     read_guest_mem(dest);
 
+    uninit_virtio_dev(s);
+
     g_source_destroy(source);
     g_source_unref(source);
 
@@ -756,7 +803,7 @@ static void test_reconnect_subprocess(void)
     qtest_start(cmd);
     g_free(cmd);
 
-    init_virtio_dev(s);
+    init_virtio_dev(s, 1u << VIRTIO_NET_F_MAC);
     wait_for_fds(s);
     wait_for_rings_started(s, 2);
 
@@ -767,6 +814,8 @@ static void test_reconnect_subprocess(void)
     wait_for_fds(s);
     wait_for_rings_started(s, 2);
 
+    uninit_virtio_dev(s);
+
     qtest_end();
     test_server_free(s);
     return;
@@ -792,10 +841,12 @@ static void test_connect_fail_subprocess(void)
     qtest_start(cmd);
     g_free(cmd);
 
-    init_virtio_dev(s);
+    init_virtio_dev(s, 1u << VIRTIO_NET_F_MAC);
     wait_for_fds(s);
     wait_for_rings_started(s, 2);
 
+    uninit_virtio_dev(s);
+
     qtest_end();
     test_server_free(s);
 }
@@ -820,10 +871,12 @@ static void test_flags_mismatch_subprocess(void)
     qtest_start(cmd);
     g_free(cmd);
 
-    init_virtio_dev(s);
+    init_virtio_dev(s, 1u << VIRTIO_NET_F_MAC);
     wait_for_fds(s);
     wait_for_rings_started(s, 2);
 
+    uninit_virtio_dev(s);
+
     qtest_end();
     test_server_free(s);
 }
@@ -839,79 +892,30 @@ static void test_flags_mismatch(void)
 
 #endif
 
-static QVirtioPCIDevice *virtio_net_pci_init(QPCIBus *bus, int slot)
-{
-    QVirtioPCIDevice *dev;
-
-    dev = qvirtio_pci_device_find(bus, VIRTIO_ID_NET);
-    g_assert(dev != NULL);
-    g_assert_cmphex(dev->vdev.device_type, ==, VIRTIO_ID_NET);
-
-    qvirtio_pci_device_enable(dev);
-    qvirtio_reset(&dev->vdev);
-    qvirtio_set_acknowledge(&dev->vdev);
-    qvirtio_set_driver(&dev->vdev);
-
-    return dev;
-}
-
-static void driver_init(QVirtioDevice *dev)
-{
-    uint32_t features;
-
-    features = qvirtio_get_features(dev);
-    features = features & ~(QVIRTIO_F_BAD_FEATURE |
-                            (1u << VIRTIO_RING_F_INDIRECT_DESC) |
-                            (1u << VIRTIO_RING_F_EVENT_IDX));
-    qvirtio_set_features(dev, features);
-
-    qvirtio_set_driver_ok(dev);
-}
-
-#define PCI_SLOT                0x04
-
 static void test_multiqueue(void)
 {
-    const int queues = 2;
     TestServer *s = test_server_new("mq");
-    QVirtioPCIDevice *dev;
-    QPCIBus *bus;
-    QVirtQueuePCI *vq[queues * 2];
-    QGuestAllocator *alloc;
     char *cmd;
-    int i;
+    uint32_t features_mask = ~(QVIRTIO_F_BAD_FEATURE |
-
+                            (1u << VIRTIO_RING_F_INDIRECT_DESC) |
-    s->queues = queues;
+                            (1u << VIRTIO_RING_F_EVENT_IDX));
+    s->queues = 2;
     test_server_listen(s);
 
     cmd = g_strdup_printf(QEMU_CMD_MEM QEMU_CMD_CHR QEMU_CMD_NETDEV ",queues=%d "
                           "-device virtio-net-pci,netdev=net0,mq=on,vectors=%d",
                           512, 512, root, s->chr_name,
                           s->socket_path, "", s->chr_name,
-                          queues, queues * 2 + 2);
+                          s->queues, s->queues * 2 + 2);
     qtest_start(cmd);
     g_free(cmd);
 
-    bus = qpci_init_pc(NULL);
+    init_virtio_dev(s, features_mask);
-    dev = virtio_net_pci_init(bus, PCI_SLOT);
 
-    alloc = pc_alloc_init();
+    wait_for_rings_started(s, s->queues * 2);
-    for (i = 0; i < queues * 2; i++) {
-        vq[i] = (QVirtQueuePCI *)qvirtqueue_setup(&dev->vdev, alloc, i);
-    }
 
-    driver_init(&dev->vdev);
+    uninit_virtio_dev(s);
-    wait_for_rings_started(s, queues * 2);
 
-    /* End test */
-    for (i = 0; i < queues * 2; i++) {
-        qvirtqueue_cleanup(dev->vdev.bus, &vq[i]->vq, alloc);
-    }
-    pc_alloc_uninit(alloc);
-    qvirtio_pci_device_disable(dev);
-    g_free(dev->pdev);
-    g_free(dev);
-    qpci_free_pc(bus);
     qtest_end();
 
     test_server_free(s);
@@ -919,10 +923,7 @@ static void test_multiqueue(void)
 
 int main(int argc, char **argv)
 {
-    QTestState *s = NULL;
-    TestServer *server = NULL;
     const char *hugefs;
-    char *qemu_cmd = NULL;
     int ret;
     char template[] = "/tmp/vhost-test-XXXXXX";
     GMainLoop *loop;
@@ -947,20 +948,11 @@ int main(int argc, char **argv)
         root = tmpfs;
     }
 
-    server = test_server_new("test");
-    test_server_listen(server);
-
     loop = g_main_loop_new(NULL, FALSE);
     /* run the main loop thread so the chardev may operate */
     thread = g_thread_new(NULL, thread_function, loop);
 
-    qemu_cmd = GET_QEMU_CMD(server);
+    qtest_add_func("/vhost-user/read-guest-mem", test_read_guest_mem);
-
-    s = qtest_start(qemu_cmd);
-    g_free(qemu_cmd);
-    init_virtio_dev(server);
-
-    qtest_add_data_func("/vhost-user/read-guest-mem", server, read_guest_mem);
     qtest_add_func("/vhost-user/migrate", test_migrate);
     qtest_add_func("/vhost-user/multiqueue", test_multiqueue);
 
@@ -978,12 +970,7 @@ int main(int argc, char **argv)
 
     ret = g_test_run();
 
-    if (s) {
-        qtest_quit(s);
-    }
-
     /* cleanup */
-    test_server_free(server);
 
     /* finish the helper thread and dispatch pending sources */
     g_main_loop_quit(loop);

util/event_notifier-posix.c

@@ -29,6 +29,7 @@ void event_notifier_init_fd(EventNotifier *e, int fd)
 {
     e->rfd = fd;
     e->wfd = fd;
+    e->cleanup = NULL;
 }
 #endif
 
@@ -65,6 +66,7 @@ int event_notifier_init(EventNotifier *e, int active)
         e->rfd = fds[0];
         e->wfd = fds[1];
     }
+    e->cleanup = NULL;
     if (active) {
         event_notifier_set(e);
     }
@@ -80,10 +82,11 @@ void event_notifier_cleanup(EventNotifier *e)
 {
     if (e->rfd != e->wfd) {
         close(e->rfd);
-        e->rfd = -1;
     }
     close(e->wfd);
+    e->rfd = -1;
     e->wfd = -1;
+    e->cleanup = NULL;
 }
 
 int event_notifier_get_fd(const EventNotifier *e)

util/event_notifier-win32.c

@@ -19,6 +19,7 @@ int event_notifier_init(EventNotifier *e, int active)
 {
     e->event = CreateEvent(NULL, TRUE, FALSE, NULL);
     assert(e->event);
+    e->cleanup = NULL;
     return 0;
 }
 
@@ -26,6 +27,7 @@ void event_notifier_cleanup(EventNotifier *e)
 {
     CloseHandle(e->event);
     e->event = NULL;
+    e->cleanup = NULL;
 }
 
 HANDLE event_notifier_get_handle(EventNotifier *e)