[PATCH RFC v2 04/16] vfio-user: connect vfio proxy to remote server

[Elena Ufimtseva <elena.ufimtseva@oracle.com>]

From: John Johnson <john.g.johnson@oracle.com>

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
---
 hw/vfio/user.h                |  66 ++++++++++++++
 include/hw/vfio/vfio-common.h |   2 +
 hw/vfio/pci.c                 |  29 ++++++
 hw/vfio/user.c                | 160 ++++++++++++++++++++++++++++++++++
 MAINTAINERS                   |   4 +
 hw/vfio/meson.build           |   1 +
 6 files changed, 262 insertions(+)
 create mode 100644 hw/vfio/user.h
 create mode 100644 hw/vfio/user.c

diff --git a/hw/vfio/user.h b/hw/vfio/user.h
new file mode 100644
index 0000000000..62b2d03d56
--- /dev/null
+++ b/hw/vfio/user.h
@@ -0,0 +1,66 @@
+#ifndef VFIO_USER_H
+#define VFIO_USER_H
+
+/*
+ * vfio protocol over a UNIX socket.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+typedef struct {
+    int send_fds;
+    int recv_fds;
+    int *fds;
+} VFIOUserFDs;
+
+typedef struct VFIOUserReply {
+    QTAILQ_ENTRY(VFIOUserReply) next;
+    VFIOUserFDs *fds;
+    uint32_t rsize;
+    uint32_t id;
+    QemuCond cv;
+    bool complete;
+    bool nowait;
+} VFIOUserReply;
+
+
+enum proxy_state {
+    VFIO_PROXY_CONNECTED = 1,
+    VFIO_PROXY_RECV_ERROR = 2,
+    VFIO_PROXY_CLOSING = 3,
+    VFIO_PROXY_CLOSED = 4,
+};
+
+typedef struct VFIOProxy {
+    QLIST_ENTRY(VFIOProxy) next;
+    char *sockname;
+    struct QIOChannel *ioc;
+    int (*request)(void *opaque, char *buf, VFIOUserFDs *fds);
+    void *reqarg;
+    int flags;
+    QemuCond close_cv;
+
+    /*
+     * above only changed when BQL is held
+     * below are protected by per-proxy lock
+     */
+    QemuMutex lock;
+    QTAILQ_HEAD(, VFIOUserReply) free;
+    QTAILQ_HEAD(, VFIOUserReply) pending;
+    VFIOUserReply *last_nowait;
+    enum proxy_state state;
+    bool close_wait;
+} VFIOProxy;
+
+/* VFIOProxy flags */
+#define VFIO_PROXY_CLIENT       0x1
+#define VFIO_PROXY_SECURE       0x2
+
+VFIOProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp);
+void vfio_user_disconnect(VFIOProxy *proxy);
+
+#endif /* VFIO_USER_H */
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index 8af11b0a76..f43dc6e5d0 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -75,6 +75,7 @@ typedef struct VFIOAddressSpace {
 } VFIOAddressSpace;
 
 struct VFIOGroup;
+typedef struct VFIOProxy VFIOProxy;
 
 typedef struct VFIOContainer {
     VFIOAddressSpace *space;
@@ -143,6 +144,7 @@ typedef struct VFIODevice {
     VFIOMigration *migration;
     Error *migration_blocker;
     OnOffAuto pre_copy_dirty_page_tracking;
+    VFIOProxy *proxy;
 } VFIODevice;
 
 struct VFIODeviceOps {
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index d642aafb7f..7c2d245ca5 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -42,6 +42,7 @@
 #include "qapi/error.h"
 #include "migration/blocker.h"
 #include "migration/qemu-file.h"
+#include "hw/vfio/user.h"
 
 #define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug"
 
@@ -3361,13 +3362,35 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
     VFIOUserPCIDevice *udev = VFIO_USER_PCI(pdev);
     VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
     VFIODevice *vbasedev = &vdev->vbasedev;
+    SocketAddress addr;
+    VFIOProxy *proxy;
+    Error *err = NULL;
 
+    /*
+     * TODO: make option parser understand SocketAddress
+     * and use that instead of having scaler options
+     * for each socket type.
+     */
     if (!udev->sock_name) {
         error_setg(errp, "No socket specified");
         error_append_hint(errp, "Use -device vfio-user-pci,socket=<name>\n");
         return;
     }
 
+    memset(&addr, 0, sizeof(addr));
+    addr.type = SOCKET_ADDRESS_TYPE_UNIX;
+    addr.u.q_unix.path = udev->sock_name;
+    proxy = vfio_user_connect_dev(&addr, &err);
+    if (!proxy) {
+        error_setg(errp, "Remote proxy not found");
+        return;
+    }
+    vbasedev->proxy = proxy;
+
+    if (udev->secure_dma) {
+        proxy->flags |= VFIO_PROXY_SECURE;
+    }
+
     vbasedev->name = g_strdup_printf("VFIO user <%s>", udev->sock_name);
     vbasedev->dev = DEVICE(vdev);
     vbasedev->fd = -1;
@@ -3379,6 +3402,12 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
 
 static void vfio_user_instance_finalize(Object *obj)
 {
+    VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
+    VFIODevice *vbasedev = &vdev->vbasedev;
+
+    vfio_put_device(vdev);
+
+    vfio_user_disconnect(vbasedev->proxy);
 }
 
 static Property vfio_user_pci_dev_properties[] = {
diff --git a/hw/vfio/user.c b/hw/vfio/user.c
new file mode 100644
index 0000000000..3bd304e036
--- /dev/null
+++ b/hw/vfio/user.c
@@ -0,0 +1,160 @@
+/*
+ * vfio protocol over a UNIX socket.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include <linux/vfio.h>
+#include <sys/ioctl.h>
+
+#include "qemu/error-report.h"
+#include "qapi/error.h"
+#include "qemu/main-loop.h"
+#include "hw/hw.h"
+#include "hw/vfio/vfio-common.h"
+#include "hw/vfio/vfio.h"
+#include "qemu/sockets.h"
+#include "io/channel.h"
+#include "io/channel-socket.h"
+#include "io/channel-util.h"
+#include "sysemu/iothread.h"
+#include "user.h"
+
+static IOThread *vfio_user_iothread;
+static void vfio_user_shutdown(VFIOProxy *proxy);
+
+
+/*
+ * Functions called by main, CPU, or iothread threads
+ */
+
+static void vfio_user_shutdown(VFIOProxy *proxy)
+{
+    qio_channel_shutdown(proxy->ioc, QIO_CHANNEL_SHUTDOWN_READ, NULL);
+}
+
+
+/*
+ * Functions only called by iothread
+ */
+
+static void vfio_user_cb(void *opaque)
+{
+    VFIOProxy *proxy = opaque;
+
+    qemu_mutex_lock(&proxy->lock);
+    proxy->state = VFIO_PROXY_CLOSED;
+    qemu_mutex_unlock(&proxy->lock);
+    qemu_cond_signal(&proxy->close_cv);
+}
+
+
+/*
+ * Functions called by main or CPU threads
+ */
+
+static QLIST_HEAD(, VFIOProxy) vfio_user_sockets =
+    QLIST_HEAD_INITIALIZER(vfio_user_sockets);
+
+VFIOProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp)
+{
+    VFIOProxy *proxy;
+    QIOChannelSocket *sioc;
+    QIOChannel *ioc;
+    char *sockname;
+
+    if (addr->type != SOCKET_ADDRESS_TYPE_UNIX) {
+        error_setg(errp, "vfio_user_connect - bad address family");
+        return NULL;
+    }
+    sockname = addr->u.q_unix.path;
+
+    sioc = qio_channel_socket_new();
+    ioc = QIO_CHANNEL(sioc);
+    if (qio_channel_socket_connect_sync(sioc, addr, errp)) {
+        object_unref(OBJECT(ioc));
+        return NULL;
+    }
+    qio_channel_set_blocking(ioc, true, NULL);
+
+    proxy = g_malloc0(sizeof(VFIOProxy));
+    proxy->sockname = sockname;
+    proxy->ioc = ioc;
+    proxy->flags = VFIO_PROXY_CLIENT;
+    proxy->state = VFIO_PROXY_CONNECTED;
+    qemu_cond_init(&proxy->close_cv);
+
+    if (vfio_user_iothread == NULL) {
+        vfio_user_iothread = iothread_create("VFIO user", errp);
+    }
+
+    qemu_mutex_init(&proxy->lock);
+    QTAILQ_INIT(&proxy->free);
+    QTAILQ_INIT(&proxy->pending);
+    QLIST_INSERT_HEAD(&vfio_user_sockets, proxy, next);
+
+    return proxy;
+}
+
+void vfio_user_disconnect(VFIOProxy *proxy)
+{
+    VFIOUserReply *r1, *r2;
+
+    qemu_mutex_lock(&proxy->lock);
+
+    /* our side is quitting */
+    if (proxy->state == VFIO_PROXY_CONNECTED) {
+        vfio_user_shutdown(proxy);
+        if (!QTAILQ_EMPTY(&proxy->pending)) {
+            error_printf("vfio_user_disconnect: outstanding requests\n");
+        }
+    }
+    object_unref(OBJECT(proxy->ioc));
+    proxy->ioc = NULL;
+
+    proxy->state = VFIO_PROXY_CLOSING;
+    QTAILQ_FOREACH_SAFE(r1, &proxy->pending, next, r2) {
+        qemu_cond_destroy(&r1->cv);
+        QTAILQ_REMOVE(&proxy->pending, r1, next);
+        g_free(r1);
+    }
+    QTAILQ_FOREACH_SAFE(r1, &proxy->free, next, r2) {
+        qemu_cond_destroy(&r1->cv);
+        QTAILQ_REMOVE(&proxy->free, r1, next);
+        g_free(r1);
+    }
+
+    /*
+     * Make sure the iothread isn't blocking anywhere
+     * with a ref to this proxy by waiting for a BH
+     * handler to run after the proxy fd handlers were
+     * deleted above.
+     */
+    proxy->close_wait = 1;
+    aio_bh_schedule_oneshot(iothread_get_aio_context(vfio_user_iothread),
+                            vfio_user_cb, proxy);
+
+    /* drop locks so the iothread can make progress */
+    qemu_mutex_unlock_iothread();
+    qemu_cond_wait(&proxy->close_cv, &proxy->lock);
+
+    /* we now hold the only ref to proxy */
+    qemu_mutex_unlock(&proxy->lock);
+    qemu_cond_destroy(&proxy->close_cv);
+    qemu_mutex_destroy(&proxy->lock);
+
+    qemu_mutex_lock_iothread();
+
+    QLIST_REMOVE(proxy, next);
+    if (QLIST_EMPTY(&vfio_user_sockets)) {
+        iothread_destroy(vfio_user_iothread);
+        vfio_user_iothread = NULL;
+    }
+
+    g_free(proxy);
+}
diff --git a/MAINTAINERS b/MAINTAINERS
index d838b9e3f2..f429bab391 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1882,8 +1882,12 @@ L: qemu-s390x@nongnu.org
 vfio-user
 M: John G Johnson <john.g.johnson@oracle.com>
 M: Thanos Makatos <thanos.makatos@nutanix.com>
+M: Elena Ufimtseva <elena.ufimtseva@oracle.com>
+M: Jagannathan Raman <jag.raman@oracle.com>
 S: Supported
 F: docs/devel/vfio-user.rst
+F: hw/vfio/user.c
+F: hw/vfio/user.h
 
 vhost
 M: Michael S. Tsirkin <mst@redhat.com>
diff --git a/hw/vfio/meson.build b/hw/vfio/meson.build
index da9af297a0..739b30be73 100644
--- a/hw/vfio/meson.build
+++ b/hw/vfio/meson.build
@@ -8,6 +8,7 @@ vfio_ss.add(when: 'CONFIG_VFIO_PCI', if_true: files(
   'display.c',
   'pci-quirks.c',
   'pci.c',
+  'user.c',
 ))
 vfio_ss.add(when: 'CONFIG_VFIO_CCW', if_true: files('ccw.c'))
 vfio_ss.add(when: 'CONFIG_VFIO_PLATFORM', if_true: files('platform.c'))
-- 
2.25.1