diff mbox series

[v2,09/23] vfio-user: define socket send functions

Message ID 1bb359101a9396f480463cda3269fbd9851a114a.1675228037.git.john.g.johnson@oracle.com (mailing list archive)
State New, archived
Headers show
Series vfio-user client | expand

Commit Message

John Johnson Feb. 2, 2023, 5:55 a.m. UTC
Also negotiate protocol version with remote server

Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
---
 hw/vfio/user-protocol.h |  62 ++++++
 hw/vfio/user.h          |   9 +
 hw/vfio/user-pci.c      |  16 ++
 hw/vfio/user.c          | 512 ++++++++++++++++++++++++++++++++++++++++++++++++
 hw/vfio/trace-events    |   2 +
 5 files changed, 601 insertions(+)
diff mbox series

Patch

diff --git a/hw/vfio/user-protocol.h b/hw/vfio/user-protocol.h
index d23877c..5de5b20 100644
--- a/hw/vfio/user-protocol.h
+++ b/hw/vfio/user-protocol.h
@@ -51,4 +51,66 @@  enum vfio_user_command {
 #define VFIO_USER_NO_REPLY      0x10
 #define VFIO_USER_ERROR         0x20
 
+
+/*
+ * VFIO_USER_VERSION
+ */
+typedef struct {
+    VFIOUserHdr hdr;
+    uint16_t major;
+    uint16_t minor;
+    char capabilities[];
+} VFIOUserVersion;
+
+#define VFIO_USER_MAJOR_VER     0
+#define VFIO_USER_MINOR_VER     0
+
+#define VFIO_USER_CAP           "capabilities"
+
+/* "capabilities" members */
+#define VFIO_USER_CAP_MAX_FDS   "max_msg_fds"
+#define VFIO_USER_CAP_MAX_XFER  "max_data_xfer_size"
+#define VFIO_USER_CAP_PGSIZES   "pgsizes"
+#define VFIO_USER_CAP_MAP_MAX   "max_dma_maps"
+#define VFIO_USER_CAP_MIGR      "migration"
+
+/* "migration" members */
+#define VFIO_USER_CAP_PGSIZE            "pgsize"
+#define VFIO_USER_CAP_MAX_BITMAP        "max_bitmap_size"
+
+/*
+ * Max FDs mainly comes into play when a device supports multiple interrupts
+ * where each ones uses an eventfd to inject it into the guest.
+ * It is clamped by the the number of FDs the qio channel supports in a
+ * single message.
+ */
+#define VFIO_USER_DEF_MAX_FDS   8
+#define VFIO_USER_MAX_MAX_FDS   16
+
+/*
+ * Max transfer limits the amount of data in region and DMA messages.
+ * Region R/W will be very small (limited by how much a single instruction
+ * can process) so just use a reasonable limit here.
+ */
+#define VFIO_USER_DEF_MAX_XFER  (1024 * 1024)
+#define VFIO_USER_MAX_MAX_XFER  (64 * 1024 * 1024)
+
+/*
+ * Default pagesizes supported is 4k.
+ */
+#define VFIO_USER_DEF_PGSIZE    4096
+
+/*
+ * Default max number of DMA mappings is stolen from the
+ * linux kernel "dma_entry_limit"
+ */
+#define VFIO_USER_DEF_MAP_MAX   65535
+
+/*
+ * Default max bitmap size is also take from the linux kernel,
+ * where usage of signed ints limits the VA range to 2^31 bytes.
+ * Dividing that by the number of bits per byte yields 256MB
+ */
+#define VFIO_USER_DEF_MAX_BITMAP (256 * 1024 * 1024)
+
 #endif /* VFIO_USER_PROTOCOL_H */
diff --git a/hw/vfio/user.h b/hw/vfio/user.h
index 5259a30..038e5e3 100644
--- a/hw/vfio/user.h
+++ b/hw/vfio/user.h
@@ -35,6 +35,7 @@  typedef struct VFIOUserMsg {
     uint32_t id;
     QemuCond cv;
     bool complete;
+    bool pending;
     enum msg_type type;
 } VFIOUserMsg;
 
@@ -54,6 +55,12 @@  typedef struct VFIOUserProxy {
     struct QIOChannel *ioc;
     void (*request)(void *opaque, VFIOUserMsg *msg);
     void *req_arg;
+    uint64_t max_xfer_size;
+    uint64_t max_send_fds;
+    uint64_t max_dma;
+    uint64_t dma_pgsizes;
+    uint64_t max_bitmap;
+    uint64_t migr_pgsize;
     int flags;
     QemuCond close_cv;
     AioContext *ctx;
@@ -76,11 +83,13 @@  typedef struct VFIOUserProxy {
 
 /* VFIOProxy flags */
 #define VFIO_PROXY_CLIENT        0x1
+#define VFIO_PROXY_FORCE_QUEUED  0x4
 
 VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp);
 void vfio_user_disconnect(VFIOUserProxy *proxy);
 void vfio_user_set_handler(VFIODevice *vbasedev,
                            void (*handler)(void *opaque, VFIOUserMsg *msg),
                            void *reqarg);
+int vfio_user_validate_version(VFIOUserProxy *proxy, Error **errp);
 
 #endif /* VFIO_USER_H */
diff --git a/hw/vfio/user-pci.c b/hw/vfio/user-pci.c
index 8b4e3ea..0fe2593 100644
--- a/hw/vfio/user-pci.c
+++ b/hw/vfio/user-pci.c
@@ -40,6 +40,7 @@  OBJECT_DECLARE_SIMPLE_TYPE(VFIOUserPCIDevice, VFIO_USER_PCI)
 struct VFIOUserPCIDevice {
     VFIOPCIDevice device;
     char *sock_name;
+    bool send_queued;   /* all sends are queued */
 };
 
 /*
@@ -100,11 +101,25 @@  static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
     vbasedev->proxy = proxy;
     vfio_user_set_handler(vbasedev, vfio_user_pci_process_req, vdev);
 
+    if (udev->send_queued) {
+        proxy->flags |= VFIO_PROXY_FORCE_QUEUED;
+    }
+
+    vfio_user_validate_version(proxy, &err);
+    if (err != NULL) {
+        error_propagate(errp, err);
+        goto error;
+    }
+
     vbasedev->name = g_strdup_printf("VFIO user <%s>", udev->sock_name);
     vbasedev->ops = &vfio_user_pci_ops;
     vbasedev->type = VFIO_DEVICE_TYPE_PCI;
     vbasedev->dev = DEVICE(vdev);
 
+    return;
+
+error:
+    error_prepend(errp, VFIO_MSG_PREFIX, vdev->vbasedev.name);
 }
 
 static void vfio_user_instance_finalize(Object *obj)
@@ -121,6 +136,7 @@  static void vfio_user_instance_finalize(Object *obj)
 
 static Property vfio_user_pci_dev_properties[] = {
     DEFINE_PROP_STRING("socket", VFIOUserPCIDevice, sock_name),
+    DEFINE_PROP_BOOL("x-send-queued", VFIOUserPCIDevice, send_queued, false),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/vfio/user.c b/hw/vfio/user.c
index f20e196..2d60f99 100644
--- a/hw/vfio/user.c
+++ b/hw/vfio/user.c
@@ -23,12 +23,20 @@ 
 #include "io/channel-socket.h"
 #include "io/channel-util.h"
 #include "sysemu/iothread.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qjson.h"
+#include "qapi/qmp/qnull.h"
+#include "qapi/qmp/qstring.h"
+#include "qapi/qmp/qnum.h"
+#include "qapi/qmp/qbool.h"
 #include "user.h"
 #include "trace.h"
 
+static int wait_time = 5000;   /* wait up to 5 sec for busy servers */
 static IOThread *vfio_user_iothread;
 
 static void vfio_user_shutdown(VFIOUserProxy *proxy);
+static int vfio_user_send_qio(VFIOUserProxy *proxy, VFIOUserMsg *msg);
 static VFIOUserMsg *vfio_user_getmsg(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
                                      VFIOUserFDs *fds);
 static VFIOUserFDs *vfio_user_getfds(int numfds);
@@ -36,9 +44,16 @@  static void vfio_user_recycle(VFIOUserProxy *proxy, VFIOUserMsg *msg);
 
 static void vfio_user_recv(void *opaque);
 static int vfio_user_recv_one(VFIOUserProxy *proxy);
+static void vfio_user_send(void *opaque);
+static int vfio_user_send_one(VFIOUserProxy *proxy);
 static void vfio_user_cb(void *opaque);
 
 static void vfio_user_request(void *opaque);
+static int vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg);
+static void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+                                VFIOUserFDs *fds, int rsize, bool nobql);
+static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
+                                  uint32_t size, uint32_t flags);
 
 static inline void vfio_user_set_error(VFIOUserHdr *hdr, uint32_t err)
 {
@@ -56,6 +71,35 @@  static void vfio_user_shutdown(VFIOUserProxy *proxy)
     qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx, NULL, NULL, NULL);
 }
 
+static int vfio_user_send_qio(VFIOUserProxy *proxy, VFIOUserMsg *msg)
+{
+    VFIOUserFDs *fds =  msg->fds;
+    struct iovec iov = {
+        .iov_base = msg->hdr,
+        .iov_len = msg->hdr->size,
+    };
+    size_t numfds = 0;
+    int ret, *fdp = NULL;
+    Error *local_err = NULL;
+
+    if (fds != NULL && fds->send_fds != 0) {
+        numfds = fds->send_fds;
+        fdp = fds->fds;
+    }
+
+    ret = qio_channel_writev_full(proxy->ioc, &iov, 1, fdp, numfds, 0,
+                                  &local_err);
+
+    if (ret == -1) {
+        vfio_user_set_error(msg->hdr, EIO);
+        vfio_user_shutdown(proxy);
+        error_report_err(local_err);
+    }
+    trace_vfio_user_send_write(msg->hdr->id, ret);
+
+    return ret;
+}
+
 static VFIOUserMsg *vfio_user_getmsg(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
                                      VFIOUserFDs *fds)
 {
@@ -96,6 +140,7 @@  static void vfio_user_recycle(VFIOUserProxy *proxy, VFIOUserMsg *msg)
     msg->hdr = NULL;
     msg->fds = NULL;
     msg->complete = false;
+    msg->pending = false;
     QTAILQ_INSERT_HEAD(&proxy->free, msg, next);
 }
 
@@ -390,6 +435,54 @@  err:
     return -1;
 }
 
+/*
+ * Send messages from outgoing queue when the socket buffer has space.
+ * If we deplete 'outgoing', remove ourselves from the poll list.
+ */
+static void vfio_user_send(void *opaque)
+{
+    VFIOUserProxy *proxy = opaque;
+
+    QEMU_LOCK_GUARD(&proxy->lock);
+
+    if (proxy->state == VFIO_PROXY_CONNECTED) {
+        while (!QTAILQ_EMPTY(&proxy->outgoing)) {
+            if (vfio_user_send_one(proxy) < 0) {
+                return;
+            }
+        }
+        qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx,
+                                       vfio_user_recv, NULL, proxy);
+    }
+}
+
+/*
+ * Send a single message.
+ *
+ * Sent async messages are freed, others are moved to pending queue.
+ */
+static int vfio_user_send_one(VFIOUserProxy *proxy)
+{
+    VFIOUserMsg *msg;
+    int ret;
+
+    msg = QTAILQ_FIRST(&proxy->outgoing);
+    ret = vfio_user_send_qio(proxy, msg);
+    if (ret < 0) {
+        return ret;
+    }
+
+    QTAILQ_REMOVE(&proxy->outgoing, msg, next);
+    if (msg->type == VFIO_MSG_ASYNC) {
+        vfio_user_recycle(proxy, msg);
+    } else {
+        QTAILQ_INSERT_TAIL(&proxy->pending, msg, next);
+        msg->pending = true;
+    }
+
+    return 0;
+}
+
 static void vfio_user_cb(void *opaque)
 {
     VFIOUserProxy *proxy = opaque;
@@ -451,6 +544,134 @@  static void vfio_user_request(void *opaque)
     }
 }
 
+/*
+ * Messages are queued onto the proxy's outgoing list.
+ *
+ * It handles 3 types of messages:
+ *
+ * async messages - replies and posted writes
+ *
+ * There will be no reply from the server, so message
+ * buffers are freed after they're sent.
+ *
+ * nowait messages - map/unmap during address space transactions
+ *
+ * These are also sent async, but a reply is expected so that
+ * vfio_wait_reqs() can wait for the youngest nowait request.
+ * They transition from the outgoing list to the pending list
+ * when sent, and are freed when the reply is received.
+ *
+ * wait messages - all other requests
+ *
+ * The reply to these messages is waited for by their caller.
+ * They also transition from outgoing to pending when sent, but
+ * the message buffer is returned to the caller with the reply
+ * contents.  The caller is responsible for freeing these messages.
+ *
+ * As an optimization, if the outgoing list and the socket send
+ * buffer are empty, the message is sent inline instead of being
+ * added to the outgoing list.  The rest of the transitions are
+ * unchanged.
+ *
+ * returns 0 if the message was sent or queued
+ * returns -1 on send error
+ */
+static int vfio_user_send_queued(VFIOUserProxy *proxy, VFIOUserMsg *msg)
+{
+    int ret;
+
+    /*
+     * Unsent outgoing msgs - add to tail
+     */
+    if (!QTAILQ_EMPTY(&proxy->outgoing)) {
+        QTAILQ_INSERT_TAIL(&proxy->outgoing, msg, next);
+        return 0;
+    }
+
+    /*
+     * Try inline - if blocked, queue it and kick send poller
+     */
+    if (proxy->flags & VFIO_PROXY_FORCE_QUEUED) {
+        ret = QIO_CHANNEL_ERR_BLOCK;
+    } else {
+        ret = vfio_user_send_qio(proxy, msg);
+    }
+    if (ret == QIO_CHANNEL_ERR_BLOCK) {
+        QTAILQ_INSERT_HEAD(&proxy->outgoing, msg, next);
+        qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx,
+                                       vfio_user_recv, vfio_user_send,
+                                       proxy);
+        return 0;
+    }
+    if (ret == -1) {
+        return ret;
+    }
+
+    /*
+     * Sent - free async, add others to pending
+     */
+    if (msg->type == VFIO_MSG_ASYNC) {
+        vfio_user_recycle(proxy, msg);
+    } else {
+        QTAILQ_INSERT_TAIL(&proxy->pending, msg, next);
+        msg->pending = true;
+    }
+
+    return 0;
+}
+
+static void vfio_user_send_wait(VFIOUserProxy *proxy, VFIOUserHdr *hdr,
+                                VFIOUserFDs *fds, int rsize, bool nobql)
+{
+    VFIOUserMsg *msg;
+    bool iolock = false;
+    int ret;
+
+    if (hdr->flags & VFIO_USER_NO_REPLY) {
+        error_printf("vfio_user_send_wait on async message\n");
+        vfio_user_set_error(hdr, EINVAL);
+        return;
+    }
+
+    /*
+     * We may block later, so use a per-proxy lock and drop
+     * BQL while we sleep unless 'nobql' says not to.
+     */
+    qemu_mutex_lock(&proxy->lock);
+    if (!nobql) {
+        iolock = qemu_mutex_iothread_locked();
+        if (iolock) {
+            qemu_mutex_unlock_iothread();
+        }
+    }
+
+    msg = vfio_user_getmsg(proxy, hdr, fds);
+    msg->id = hdr->id;
+    msg->rsize = rsize ? rsize : hdr->size;
+    msg->type = VFIO_MSG_WAIT;
+
+    ret = vfio_user_send_queued(proxy, msg);
+
+    if (ret == 0) {
+        while (!msg->complete) {
+            if (!qemu_cond_timedwait(&msg->cv, &proxy->lock, wait_time)) {
+                VFIOUserMsgQ *list;
+
+                list = msg->pending ? &proxy->pending : &proxy->outgoing;
+                QTAILQ_REMOVE(list, msg, next);
+                vfio_user_set_error(hdr, ETIMEDOUT);
+                break;
+            }
+        }
+    }
+    vfio_user_recycle(proxy, msg);
+
+    /* lock order is BQL->proxy - don't hold proxy when getting BQL */
+    qemu_mutex_unlock(&proxy->lock);
+    if (iolock) {
+        qemu_mutex_lock_iothread();
+    }
+}
 
 static QLIST_HEAD(, VFIOUserProxy) vfio_user_sockets =
     QLIST_HEAD_INITIALIZER(vfio_user_sockets);
@@ -479,6 +700,15 @@  VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp)
     proxy = g_malloc0(sizeof(VFIOUserProxy));
     proxy->sockname = g_strdup_printf("unix:%s", sockname);
     proxy->ioc = ioc;
+
+    /* init defaults */
+    proxy->max_xfer_size = VFIO_USER_DEF_MAX_XFER;
+    proxy->max_send_fds = VFIO_USER_DEF_MAX_FDS;
+    proxy->max_dma = VFIO_USER_DEF_MAP_MAX;
+    proxy->dma_pgsizes = VFIO_USER_DEF_PGSIZE;
+    proxy->max_bitmap = VFIO_USER_DEF_MAX_BITMAP;
+    proxy->migr_pgsize = VFIO_USER_DEF_PGSIZE;
+
     proxy->flags = VFIO_PROXY_CLIENT;
     proxy->state = VFIO_PROXY_CONNECTED;
 
@@ -576,3 +806,285 @@  void vfio_user_disconnect(VFIOUserProxy *proxy)
     g_free(proxy->sockname);
     g_free(proxy);
 }
+
+static void vfio_user_request_msg(VFIOUserHdr *hdr, uint16_t cmd,
+                                  uint32_t size, uint32_t flags)
+{
+    static uint16_t next_id;
+
+    hdr->id = qatomic_fetch_inc(&next_id);
+    hdr->command = cmd;
+    hdr->size = size;
+    hdr->flags = (flags & ~VFIO_USER_TYPE) | VFIO_USER_REQUEST;
+    hdr->error_reply = 0;
+}
+
+struct cap_entry {
+    const char *name;
+    int (*check)(VFIOUserProxy *proxy, QObject *qobj, Error **errp);
+};
+
+static int caps_parse(VFIOUserProxy *proxy, QDict *qdict,
+                      struct cap_entry caps[], Error **errp)
+{
+    QObject *qobj;
+    struct cap_entry *p;
+
+    for (p = caps; p->name != NULL; p++) {
+        qobj = qdict_get(qdict, p->name);
+        if (qobj != NULL) {
+            if (p->check(proxy, qobj, errp)) {
+                return -1;
+            }
+            qdict_del(qdict, p->name);
+        }
+    }
+
+    /* warning, for now */
+    if (qdict_size(qdict) != 0) {
+        warn_report("spurious capabilities");
+    }
+    return 0;
+}
+
+static int check_migr_pgsize(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+    QNum *qn = qobject_to(QNum, qobj);
+    uint64_t pgsize;
+
+    if (qn == NULL || !qnum_get_try_uint(qn, &pgsize)) {
+        error_setg(errp, "malformed %s", VFIO_USER_CAP_PGSIZE);
+        return -1;
+    }
+
+    /* must be larger than default */
+    if (pgsize & (VFIO_USER_DEF_PGSIZE - 1)) {
+        error_setg(errp, "pgsize 0x%"PRIx64" too small", pgsize);
+        return -1;
+    }
+
+    proxy->migr_pgsize = pgsize;
+    return 0;
+}
+
+static int check_bitmap(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+    QNum *qn = qobject_to(QNum, qobj);
+    uint64_t bitmap_size;
+
+    if (qn == NULL || !qnum_get_try_uint(qn, &bitmap_size)) {
+        error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_BITMAP);
+        return -1;
+    }
+
+    /* can only lower it */
+    if (bitmap_size > VFIO_USER_DEF_MAX_BITMAP) {
+        error_setg(errp, "%s too large", VFIO_USER_CAP_MAX_BITMAP);
+        return -1;
+    }
+
+    proxy->max_bitmap = bitmap_size;
+    return 0;
+}
+
+static struct cap_entry caps_migr[] = {
+    { VFIO_USER_CAP_PGSIZE, check_migr_pgsize },
+    { VFIO_USER_CAP_MAX_BITMAP, check_bitmap },
+    { NULL }
+};
+
+static int check_max_fds(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+    QNum *qn = qobject_to(QNum, qobj);
+    uint64_t max_send_fds;
+
+    if (qn == NULL || !qnum_get_try_uint(qn, &max_send_fds) ||
+        max_send_fds > VFIO_USER_MAX_MAX_FDS) {
+        error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_FDS);
+        return -1;
+    }
+    proxy->max_send_fds = max_send_fds;
+    return 0;
+}
+
+static int check_max_xfer(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+    QNum *qn = qobject_to(QNum, qobj);
+    uint64_t max_xfer_size;
+
+    if (qn == NULL || !qnum_get_try_uint(qn, &max_xfer_size) ||
+        max_xfer_size > VFIO_USER_MAX_MAX_XFER) {
+        error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_XFER);
+        return -1;
+    }
+    proxy->max_xfer_size = max_xfer_size;
+    return 0;
+}
+
+static int check_pgsizes(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+    QNum *qn = qobject_to(QNum, qobj);
+    uint64_t pgsizes;
+
+    if (qn == NULL || !qnum_get_try_uint(qn, &pgsizes)) {
+        error_setg(errp, "malformed %s", VFIO_USER_CAP_PGSIZES);
+        return -1;
+    }
+
+    /* must be larger than default */
+    if (pgsizes & (VFIO_USER_DEF_PGSIZE - 1)) {
+        error_setg(errp, "pgsize 0x%"PRIx64" too small", pgsizes);
+        return -1;
+    }
+
+    proxy->dma_pgsizes = pgsizes;
+    return 0;
+}
+
+static int check_max_dma(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+    QNum *qn = qobject_to(QNum, qobj);
+    uint64_t max_dma;
+
+    if (qn == NULL || !qnum_get_try_uint(qn, &max_dma)) {
+        error_setg(errp, "malformed %s", VFIO_USER_CAP_MAP_MAX);
+        return -1;
+    }
+
+    /* can only lower it */
+    if (max_dma > VFIO_USER_DEF_MAP_MAX) {
+        error_setg(errp, "%s too large", VFIO_USER_CAP_MAP_MAX);
+        return -1;
+    }
+
+    proxy->max_dma = max_dma;
+    return 0;
+}
+
+static int check_migr(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+    QDict *qdict = qobject_to(QDict, qobj);
+
+    if (qdict == NULL) {
+        error_setg(errp, "malformed %s", VFIO_USER_CAP_MAX_FDS);
+        return -1;
+    }
+    return caps_parse(proxy, qdict, caps_migr, errp);
+}
+
+static struct cap_entry caps_cap[] = {
+    { VFIO_USER_CAP_MAX_FDS, check_max_fds },
+    { VFIO_USER_CAP_MAX_XFER, check_max_xfer },
+    { VFIO_USER_CAP_PGSIZES, check_pgsizes },
+    { VFIO_USER_CAP_MAP_MAX, check_max_dma },
+    { VFIO_USER_CAP_MIGR, check_migr },
+    { NULL }
+};
+
+static int check_cap(VFIOUserProxy *proxy, QObject *qobj, Error **errp)
+{
+   QDict *qdict = qobject_to(QDict, qobj);
+
+    if (qdict == NULL) {
+        error_setg(errp, "malformed %s", VFIO_USER_CAP);
+        return -1;
+    }
+    return caps_parse(proxy, qdict, caps_cap, errp);
+}
+
+static struct cap_entry ver_0_0[] = {
+    { VFIO_USER_CAP, check_cap },
+    { NULL }
+};
+
+static int caps_check(VFIOUserProxy *proxy, int minor, const char *caps,
+                      Error **errp)
+{
+    QObject *qobj;
+    QDict *qdict;
+    int ret;
+
+    qobj = qobject_from_json(caps, NULL);
+    if (qobj == NULL) {
+        error_setg(errp, "malformed capabilities %s", caps);
+        return -1;
+    }
+    qdict = qobject_to(QDict, qobj);
+    if (qdict == NULL) {
+        error_setg(errp, "capabilities %s not an object", caps);
+        qobject_unref(qobj);
+        return -1;
+    }
+    ret = caps_parse(proxy, qdict, ver_0_0, errp);
+
+    qobject_unref(qobj);
+    return ret;
+}
+
+static GString *caps_json(void)
+{
+    QDict *dict = qdict_new();
+    QDict *capdict = qdict_new();
+    QDict *migdict = qdict_new();
+    GString *str;
+
+    qdict_put_int(migdict, VFIO_USER_CAP_PGSIZE, VFIO_USER_DEF_PGSIZE);
+    qdict_put_int(migdict, VFIO_USER_CAP_MAX_BITMAP, VFIO_USER_DEF_MAX_BITMAP);
+    qdict_put_obj(capdict, VFIO_USER_CAP_MIGR, QOBJECT(migdict));
+
+    qdict_put_int(capdict, VFIO_USER_CAP_MAX_FDS, VFIO_USER_MAX_MAX_FDS);
+    qdict_put_int(capdict, VFIO_USER_CAP_MAX_XFER, VFIO_USER_DEF_MAX_XFER);
+    qdict_put_int(capdict, VFIO_USER_CAP_PGSIZES, VFIO_USER_DEF_PGSIZE);
+    qdict_put_int(capdict, VFIO_USER_CAP_MAP_MAX, VFIO_USER_DEF_MAP_MAX);
+
+    qdict_put_obj(dict, VFIO_USER_CAP, QOBJECT(capdict));
+
+    str = qobject_to_json(QOBJECT(dict));
+    qobject_unref(dict);
+    return str;
+}
+
+int vfio_user_validate_version(VFIOUserProxy *proxy, Error **errp)
+{
+    g_autofree VFIOUserVersion *msgp;
+    GString *caps;
+    char *reply;
+    int size, caplen;
+
+    caps = caps_json();
+    caplen = caps->len + 1;
+    size = sizeof(*msgp) + caplen;
+    msgp = g_malloc0(size);
+
+    vfio_user_request_msg(&msgp->hdr, VFIO_USER_VERSION, size, 0);
+    msgp->major = VFIO_USER_MAJOR_VER;
+    msgp->minor = VFIO_USER_MINOR_VER;
+    memcpy(&msgp->capabilities, caps->str, caplen);
+    g_string_free(caps, true);
+    trace_vfio_user_version(msgp->major, msgp->minor, msgp->capabilities);
+
+    vfio_user_send_wait(proxy, &msgp->hdr, NULL, 0, false);
+    if (msgp->hdr.flags & VFIO_USER_ERROR) {
+        error_setg_errno(errp, msgp->hdr.error_reply, "version reply");
+        return -1;
+    }
+
+    if (msgp->major != VFIO_USER_MAJOR_VER ||
+        msgp->minor > VFIO_USER_MINOR_VER) {
+        error_setg(errp, "incompatible server version");
+        return -1;
+    }
+
+    reply = msgp->capabilities;
+    if (reply[msgp->hdr.size - sizeof(*msgp) - 1] != '\0') {
+        error_setg(errp, "corrupt version reply");
+        return -1;
+    }
+
+    if (caps_check(proxy, msgp->minor, reply, errp) != 0) {
+        return -1;
+    }
+
+    trace_vfio_user_version(msgp->major, msgp->minor, msgp->capabilities);
+    return 0;
+}
diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events
index 73cc121..e3640bc 100644
--- a/hw/vfio/trace-events
+++ b/hw/vfio/trace-events
@@ -171,3 +171,5 @@  vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu dirty
 vfio_user_recv_hdr(const char *name, uint16_t id, uint16_t cmd, uint32_t size, uint32_t flags) " (%s) id 0x%x cmd 0x%x size 0x%x flags 0x%x"
 vfio_user_recv_read(uint16_t id, int read) " id 0x%x read 0x%x"
 vfio_user_recv_request(uint16_t cmd) " command 0x%x"
+vfio_user_send_write(uint16_t id, int wrote) " id 0x%x wrote 0x%x"
+vfio_user_version(uint16_t major, uint16_t minor, const char *caps) " major %d minor %d caps: %s"