qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Cédric Le Goater" <clg@redhat.com>
To: qemu-devel@nongnu.org
Cc: "Alex Williamson" <alex.williamson@redhat.com>,
	"John Levon" <john.levon@nutanix.com>,
	"John Johnson" <john.g.johnson@oracle.com>,
	"Elena Ufimtseva" <elena.ufimtseva@oracle.com>,
	"Jagannathan Raman" <jag.raman@oracle.com>,
	"Cédric Le Goater" <clg@redhat.com>
Subject: [PULL 08/25] vfio-user: connect vfio proxy to remote server
Date: Thu, 26 Jun 2025 09:45:12 +0200	[thread overview]
Message-ID: <20250626074529.1384114-9-clg@redhat.com> (raw)
In-Reply-To: <20250626074529.1384114-1-clg@redhat.com>

From: John Levon <john.levon@nutanix.com>

Introduce the vfio-user "proxy": this is the client code responsible for
sending and receiving vfio-user messages across the control socket.

The new files hw/vfio-user/proxy.[ch] contain some basic plumbing for
managing the proxy; initialize the proxy during realization of the
VFIOUserPCIDevice instance.

Originally-by: John Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
Signed-off-by: John Levon <john.levon@nutanix.com>
Reviewed-by: Cédric Le Goater <clg@redhat.com>
Link: https://lore.kernel.org/qemu-devel/20250625193012.2316242-3-john.levon@nutanix.com
Signed-off-by: Cédric Le Goater <clg@redhat.com>
---
 hw/vfio-user/proxy.h          |  79 +++++++++++++++++
 include/hw/vfio/vfio-device.h |   2 +
 hw/vfio-user/pci.c            |  22 +++++
 hw/vfio-user/proxy.c          | 162 ++++++++++++++++++++++++++++++++++
 hw/vfio-user/meson.build      |   1 +
 5 files changed, 266 insertions(+)
 create mode 100644 hw/vfio-user/proxy.h
 create mode 100644 hw/vfio-user/proxy.c

diff --git a/hw/vfio-user/proxy.h b/hw/vfio-user/proxy.h
new file mode 100644
index 0000000000000000000000000000000000000000..a9bce82239d0e9dc40a892e1542488cfffc4f3da
--- /dev/null
+++ b/hw/vfio-user/proxy.h
@@ -0,0 +1,79 @@
+#ifndef VFIO_USER_PROXY_H
+#define VFIO_USER_PROXY_H
+
+/*
+ * vfio protocol over a UNIX socket.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "io/channel.h"
+#include "io/channel-socket.h"
+
+typedef struct {
+    int send_fds;
+    int recv_fds;
+    int *fds;
+} VFIOUserFDs;
+
+enum msg_type {
+    VFIO_MSG_NONE,
+    VFIO_MSG_ASYNC,
+    VFIO_MSG_WAIT,
+    VFIO_MSG_NOWAIT,
+    VFIO_MSG_REQ,
+};
+
+typedef struct VFIOUserMsg {
+    QTAILQ_ENTRY(VFIOUserMsg) next;
+    VFIOUserFDs *fds;
+    uint32_t rsize;
+    uint32_t id;
+    QemuCond cv;
+    bool complete;
+    enum msg_type type;
+} VFIOUserMsg;
+
+
+enum proxy_state {
+    VFIO_PROXY_CONNECTED = 1,
+    VFIO_PROXY_ERROR = 2,
+    VFIO_PROXY_CLOSING = 3,
+    VFIO_PROXY_CLOSED = 4,
+};
+
+typedef QTAILQ_HEAD(VFIOUserMsgQ, VFIOUserMsg) VFIOUserMsgQ;
+
+typedef struct VFIOUserProxy {
+    QLIST_ENTRY(VFIOUserProxy) next;
+    char *sockname;
+    struct QIOChannel *ioc;
+    void (*request)(void *opaque, VFIOUserMsg *msg);
+    void *req_arg;
+    int flags;
+    QemuCond close_cv;
+    AioContext *ctx;
+    QEMUBH *req_bh;
+
+    /*
+     * above only changed when BQL is held
+     * below are protected by per-proxy lock
+     */
+    QemuMutex lock;
+    VFIOUserMsgQ free;
+    VFIOUserMsgQ pending;
+    VFIOUserMsgQ incoming;
+    VFIOUserMsgQ outgoing;
+    VFIOUserMsg *last_nowait;
+    enum proxy_state state;
+} VFIOUserProxy;
+
+/* VFIOProxy flags */
+#define VFIO_PROXY_CLIENT        0x1
+
+VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp);
+void vfio_user_disconnect(VFIOUserProxy *proxy);
+
+#endif /* VFIO_USER_PROXY_H */
diff --git a/include/hw/vfio/vfio-device.h b/include/hw/vfio/vfio-device.h
index 959e458d7f7e9facd8216fbd3695d9d97dbc667a..c616652ee72265c637cb5136fdffb4444639e0b7 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -47,6 +47,7 @@ typedef struct VFIOMigration VFIOMigration;
 
 typedef struct IOMMUFDBackend IOMMUFDBackend;
 typedef struct VFIOIOASHwpt VFIOIOASHwpt;
+typedef struct VFIOUserProxy VFIOUserProxy;
 
 typedef struct VFIODevice {
     QLIST_ENTRY(VFIODevice) next;
@@ -88,6 +89,7 @@ typedef struct VFIODevice {
     struct vfio_region_info **reginfo;
     int *region_fds;
     VFIODeviceCPR cpr;
+    VFIOUserProxy *proxy;
 } VFIODevice;
 
 struct VFIODeviceOps {
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index 86d705574736586a893feb529a057e799ae610c8..642421e7916aad01a894ee390c43453dd5297356 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -12,6 +12,7 @@
 
 #include "hw/qdev-properties.h"
 #include "hw/vfio/pci.h"
+#include "hw/vfio-user/proxy.h"
 
 #define TYPE_VFIO_USER_PCI "vfio-user-pci"
 OBJECT_DECLARE_SIMPLE_TYPE(VFIOUserPCIDevice, VFIO_USER_PCI)
@@ -54,6 +55,8 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
     VFIODevice *vbasedev = &vdev->vbasedev;
     const char *sock_name;
     AddressSpace *as;
+    SocketAddress addr;
+    VFIOUserProxy *proxy;
 
     if (!udev->socket) {
         error_setg(errp, "No socket specified");
@@ -69,6 +72,15 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
 
     vbasedev->name = g_strdup_printf("vfio-user:%s", sock_name);
 
+    memset(&addr, 0, sizeof(addr));
+    addr.type = SOCKET_ADDRESS_TYPE_UNIX;
+    addr.u.q_unix.path = (char *)sock_name;
+    proxy = vfio_user_connect_dev(&addr, errp);
+    if (!proxy) {
+        return;
+    }
+    vbasedev->proxy = proxy;
+
     /*
      * vfio-user devices are effectively mdevs (don't use a host iommu).
      */
@@ -112,8 +124,13 @@ static void vfio_user_instance_init(Object *obj)
 static void vfio_user_instance_finalize(Object *obj)
 {
     VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj);
+    VFIODevice *vbasedev = &vdev->vbasedev;
 
     vfio_pci_put_device(vdev);
+
+    if (vbasedev->proxy != NULL) {
+        vfio_user_disconnect(vbasedev->proxy);
+    }
 }
 
 static const Property vfio_user_pci_dev_properties[] = {
@@ -133,6 +150,11 @@ static void vfio_user_pci_set_socket(Object *obj, Visitor *v, const char *name,
     VFIOUserPCIDevice *udev = VFIO_USER_PCI(obj);
     bool success;
 
+    if (udev->device.vbasedev.proxy) {
+        error_setg(errp, "Proxy is connected");
+        return;
+    }
+
     qapi_free_SocketAddress(udev->socket);
 
     udev->socket = NULL;
diff --git a/hw/vfio-user/proxy.c b/hw/vfio-user/proxy.c
new file mode 100644
index 0000000000000000000000000000000000000000..bb436c9db91b6ebd90542b4121b62d56bbbdf4ab
--- /dev/null
+++ b/hw/vfio-user/proxy.c
@@ -0,0 +1,162 @@
+/*
+ * vfio protocol over a UNIX socket.
+ *
+ * Copyright © 2018, 2021 Oracle and/or its affiliates.
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+
+#include "qemu/osdep.h"
+#include <sys/ioctl.h>
+
+#include "hw/vfio/vfio-device.h"
+#include "hw/vfio-user/proxy.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/lockable.h"
+#include "system/iothread.h"
+
+static IOThread *vfio_user_iothread;
+
+static void vfio_user_shutdown(VFIOUserProxy *proxy);
+
+
+/*
+ * Functions called by main, CPU, or iothread threads
+ */
+
+static void vfio_user_shutdown(VFIOUserProxy *proxy)
+{
+    qio_channel_shutdown(proxy->ioc, QIO_CHANNEL_SHUTDOWN_READ, NULL);
+    qio_channel_set_aio_fd_handler(proxy->ioc, proxy->ctx, NULL,
+                                   proxy->ctx, NULL, NULL);
+}
+
+/*
+ * Functions only called by iothread
+ */
+
+static void vfio_user_cb(void *opaque)
+{
+    VFIOUserProxy *proxy = opaque;
+
+    QEMU_LOCK_GUARD(&proxy->lock);
+
+    proxy->state = VFIO_PROXY_CLOSED;
+    qemu_cond_signal(&proxy->close_cv);
+}
+
+
+/*
+ * Functions called by main or CPU threads
+ */
+
+static QLIST_HEAD(, VFIOUserProxy) vfio_user_sockets =
+    QLIST_HEAD_INITIALIZER(vfio_user_sockets);
+
+VFIOUserProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp)
+{
+    VFIOUserProxy *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, false, NULL);
+
+    proxy = g_malloc0(sizeof(VFIOUserProxy));
+    proxy->sockname = g_strdup_printf("unix:%s", sockname);
+    proxy->ioc = ioc;
+    proxy->flags = VFIO_PROXY_CLIENT;
+    proxy->state = VFIO_PROXY_CONNECTED;
+
+    qemu_mutex_init(&proxy->lock);
+    qemu_cond_init(&proxy->close_cv);
+
+    if (vfio_user_iothread == NULL) {
+        vfio_user_iothread = iothread_create("VFIO user", errp);
+    }
+
+    proxy->ctx = iothread_get_aio_context(vfio_user_iothread);
+
+    QTAILQ_INIT(&proxy->outgoing);
+    QTAILQ_INIT(&proxy->incoming);
+    QTAILQ_INIT(&proxy->free);
+    QTAILQ_INIT(&proxy->pending);
+    QLIST_INSERT_HEAD(&vfio_user_sockets, proxy, next);
+
+    return proxy;
+}
+
+void vfio_user_disconnect(VFIOUserProxy *proxy)
+{
+    VFIOUserMsg *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->outgoing, next, r2) {
+        qemu_cond_destroy(&r1->cv);
+        QTAILQ_REMOVE(&proxy->outgoing, r1, next);
+        g_free(r1);
+    }
+    QTAILQ_FOREACH_SAFE(r1, &proxy->incoming, next, r2) {
+        qemu_cond_destroy(&r1->cv);
+        QTAILQ_REMOVE(&proxy->incoming, r1, next);
+        g_free(r1);
+    }
+    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.
+     */
+    aio_bh_schedule_oneshot(proxy->ctx, vfio_user_cb, proxy);
+    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);
+
+    QLIST_REMOVE(proxy, next);
+    if (QLIST_EMPTY(&vfio_user_sockets)) {
+        iothread_destroy(vfio_user_iothread);
+        vfio_user_iothread = NULL;
+    }
+
+    g_free(proxy->sockname);
+    g_free(proxy);
+}
diff --git a/hw/vfio-user/meson.build b/hw/vfio-user/meson.build
index b82c558252e82d0f492bd68ab6c8b657d5b6b08c..9e85a8ea51c3402d828df0b78d534a4adde193a2 100644
--- a/hw/vfio-user/meson.build
+++ b/hw/vfio-user/meson.build
@@ -4,6 +4,7 @@ vfio_user_ss = ss.source_set()
 vfio_user_ss.add(files(
   'container.c',
   'pci.c',
+  'proxy.c',
 ))
 
 system_ss.add_all(when: 'CONFIG_VFIO_USER', if_true: vfio_user_ss)
-- 
2.49.0



  parent reply	other threads:[~2025-06-26  7:50 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-26  7:45 [PULL 00/25] vfio queue Cédric Le Goater
2025-06-26  7:45 ` [PULL 01/25] hw/vfio/ap: attribute constructor for cfg_chg_events_lock Cédric Le Goater
2025-06-26  7:45 ` [PULL 02/25] vfio: add vfio_device_get_region_fd() Cédric Le Goater
2025-06-26  7:45 ` [PULL 03/25] vfio: add documentation for posted write argument Cédric Le Goater
2025-06-26  7:45 ` [PULL 04/25] vfio: add license tag to some files Cédric Le Goater
2025-06-26  7:45 ` [PULL 05/25] vfio/container: Fix SIGSEGV when open container file fails Cédric Le Goater
2025-06-26  7:45 ` [PULL 06/25] vfio/container: fails mdev hotplug if add migration blocker failed Cédric Le Goater
2025-06-26  7:45 ` [PULL 07/25] vfio-user: add vfio-user class and container Cédric Le Goater
2025-06-26  7:45 ` Cédric Le Goater [this message]
2025-07-10 12:33   ` [PULL 08/25] vfio-user: connect vfio proxy to remote server Peter Maydell
2025-07-10 12:56     ` John Levon
2025-06-26  7:45 ` [PULL 09/25] vfio-user: implement message receive infrastructure Cédric Le Goater
2025-07-10 12:44   ` Peter Maydell
2025-06-26  7:45 ` [PULL 10/25] vfio-user: implement message send infrastructure Cédric Le Goater
2025-06-26  7:45 ` [PULL 11/25] vfio-user: implement VFIO_USER_DEVICE_GET_INFO Cédric Le Goater
2025-06-26  7:45 ` [PULL 12/25] vfio-user: implement VFIO_USER_DEVICE_GET_REGION_INFO Cédric Le Goater
2025-06-26  7:45 ` [PULL 13/25] vfio-user: implement VFIO_USER_REGION_READ/WRITE Cédric Le Goater
2025-06-26  7:45 ` [PULL 14/25] vfio-user: set up PCI in vfio_user_pci_realize() Cédric Le Goater
2025-06-26  7:45 ` [PULL 15/25] vfio-user: implement VFIO_USER_DEVICE_GET/SET_IRQ* Cédric Le Goater
2025-06-26  7:45 ` [PULL 16/25] vfio-user: forward MSI-X PBA BAR accesses to server Cédric Le Goater
2025-06-26  7:45 ` [PULL 17/25] vfio-user: set up container access to the proxy Cédric Le Goater
2025-06-26  7:45 ` [PULL 18/25] vfio-user: implement VFIO_USER_DEVICE_RESET Cédric Le Goater
2025-06-26  7:45 ` [PULL 19/25] vfio-user: implement VFIO_USER_DMA_MAP/UNMAP Cédric Le Goater
2025-06-26  7:45 ` [PULL 20/25] vfio-user: implement VFIO_USER_DMA_READ/WRITE Cédric Le Goater
2025-06-26  7:45 ` [PULL 21/25] vfio-user: add 'x-msg-timeout' option Cédric Le Goater
2025-06-26  7:45 ` [PULL 22/25] vfio-user: support posted writes Cédric Le Goater
2025-06-26  7:45 ` [PULL 23/25] vfio-user: add coalesced " Cédric Le Goater
2025-06-26  7:45 ` [PULL 24/25] docs: add vfio-user documentation Cédric Le Goater
2025-06-26  7:45 ` [PULL 25/25] vfio-user: introduce vfio-user protocol specification Cédric Le Goater
2025-06-27 18:30 ` [PULL 00/25] vfio queue Stefan Hajnoczi

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250626074529.1384114-9-clg@redhat.com \
    --to=clg@redhat.com \
    --cc=alex.williamson@redhat.com \
    --cc=elena.ufimtseva@oracle.com \
    --cc=jag.raman@oracle.com \
    --cc=john.g.johnson@oracle.com \
    --cc=john.levon@nutanix.com \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).