qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: John Levon <john.levon@nutanix.com>
To: qemu-devel@nongnu.org
Cc: "Marc-André Lureau" <marcandre.lureau@redhat.com>,
	"Thanos Makatos" <thanos.makatos@nutanix.com>,
	"Daniel P. Berrangé" <berrange@redhat.com>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Peter Xu" <peterx@redhat.com>,
	"David Hildenbrand" <david@redhat.com>,
	"Cédric Le Goater" <clg@redhat.com>,
	"Stefano Garzarella" <sgarzare@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>,
	"Alex Williamson" <alex.williamson@redhat.com>,
	"Philippe Mathieu-Daudé" <philmd@linaro.org>,
	"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>
Subject: [PATCH 11/27] vfio-user: connect vfio proxy to remote server
Date: Thu, 15 May 2025 16:43:56 +0100	[thread overview]
Message-ID: <20250515154413.210315-12-john.levon@nutanix.com> (raw)
In-Reply-To: <20250515154413.210315-1-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>
---
 hw/vfio-user/proxy.h          |  82 +++++++++++++++++
 include/hw/vfio/vfio-device.h |   2 +
 hw/vfio-user/pci.c            |  17 ++++
 hw/vfio-user/proxy.c          | 165 ++++++++++++++++++++++++++++++++++
 hw/vfio-user/meson.build      |   1 +
 5 files changed, 267 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 0000000000..60fe3e0b6d
--- /dev/null
+++ b/hw/vfio-user/proxy.h
@@ -0,0 +1,82 @@
+#ifndef VFIO_USER_PROXY_H
+#define VFIO_USER_PROXY_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.
+ *
+ * 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 a23ef4ea13..09f1a21bf8 100644
--- a/include/hw/vfio/vfio-device.h
+++ b/include/hw/vfio/vfio-device.h
@@ -46,6 +46,7 @@ typedef struct VFIOMigration VFIOMigration;
 
 typedef struct IOMMUFDBackend IOMMUFDBackend;
 typedef struct VFIOIOASHwpt VFIOIOASHwpt;
+typedef struct VFIOUserProxy VFIOUserProxy;
 
 typedef struct VFIODevice {
     QLIST_ENTRY(VFIODevice) next;
@@ -86,6 +87,7 @@ typedef struct VFIODevice {
     QLIST_ENTRY(VFIODevice) hwpt_next;
     struct vfio_region_info **reginfo;
     int *region_fds;
+    VFIOUserProxy *proxy;
 } VFIODevice;
 
 struct VFIODeviceOps {
diff --git a/hw/vfio-user/pci.c b/hw/vfio-user/pci.c
index 0525becb33..593104d15e 100644
--- a/hw/vfio-user/pci.c
+++ b/hw/vfio-user/pci.c
@@ -14,6 +14,7 @@
 
 #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)
@@ -46,6 +47,8 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
     VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev);
     VFIODevice *vbasedev = &vdev->vbasedev;
     AddressSpace *as;
+    SocketAddress addr;
+    VFIOUserProxy *proxy;
 
     /*
      * TODO: make option parser understand SocketAddress
@@ -58,6 +61,15 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)
         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, errp);
+    if (!proxy) {
+        return;
+    }
+    vbasedev->proxy = proxy;
+
     vbasedev->name = g_strdup_printf("VFIO user <%s>", udev->sock_name);
 
     /*
@@ -103,8 +115,13 @@ 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[] = {
diff --git a/hw/vfio-user/proxy.c b/hw/vfio-user/proxy.c
new file mode 100644
index 0000000000..ac481553ba
--- /dev/null
+++ b/hw/vfio-user/proxy.c
@@ -0,0 +1,165 @@
+/*
+ * 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.
+ *
+ * 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 f1fee70c85..695b341547 100644
--- a/hw/vfio-user/meson.build
+++ b/hw/vfio-user/meson.build
@@ -2,6 +2,7 @@ vfio_user_ss = ss.source_set()
 vfio_user_ss.add(files(
   'container.c',
   'pci.c',
+  'proxy.c',
 ))
 
 if get_option('vfio_user_client').enabled()
-- 
2.43.0



  parent reply	other threads:[~2025-05-15 15:48 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-05-15 15:43 [PATCH 00/27] vfio-user client John Levon
2025-05-15 15:43 ` [PATCH 01/27] vfio: return mr from vfio_get_xlat_addr John Levon
2025-05-15 15:46   ` John Levon
2025-05-15 15:43 ` [PATCH 02/27] vfio/container: pass MemoryRegion to DMA operations John Levon
2025-05-16 15:11   ` Cédric Le Goater
2025-05-18 17:00     ` John Levon
2025-05-19  8:17       ` Cédric Le Goater
2025-05-15 15:43 ` [PATCH 03/27] vfio: move more cleanup into vfio_pci_put_device() John Levon
2025-05-16 15:21   ` Cédric Le Goater
2025-05-15 15:43 ` [PATCH 04/27] vfio: move config space read into vfio_pci_config_setup() John Levon
2025-05-16 15:26   ` Cédric Le Goater
2025-05-15 15:43 ` [PATCH 05/27] vfio: refactor out IRQ signalling setup John Levon
2025-05-16 15:27   ` Cédric Le Goater
2025-05-15 15:43 ` [PATCH 06/27] vfio: enable per-IRQ MSI-X masking John Levon
2025-05-15 15:43 ` [PATCH 07/27] vfio: add per-region fd support John Levon
2025-05-15 15:43 ` [PATCH 08/27] vfio: mark posted writes in region write callbacks John Levon
2025-05-15 15:43 ` [PATCH 09/27] vfio-user: introduce vfio-user protocol specification John Levon
2025-05-15 15:43 ` [PATCH 10/27] vfio-user: add vfio-user class and container John Levon
2025-05-15 15:43 ` John Levon [this message]
2025-05-15 15:43 ` [PATCH 12/27] vfio-user: implement message receive infrastructure John Levon
2025-05-15 15:43 ` [PATCH 13/27] vfio-user: implement message send infrastructure John Levon
2025-05-15 15:43 ` [PATCH 14/27] vfio-user: implement VFIO_USER_DEVICE_GET_INFO John Levon
2025-05-15 15:44 ` [PATCH 15/27] vfio-user: implement VFIO_USER_DEVICE_GET_REGION_INFO John Levon
2025-05-15 15:44 ` [PATCH 16/27] vfio-user: implement VFIO_USER_REGION_READ/WRITE John Levon
2025-05-15 15:44 ` [PATCH 17/27] vfio-user: set up PCI in vfio_user_pci_realize() John Levon
2025-05-15 15:44 ` [PATCH 18/27] vfio-user: implement VFIO_USER_DEVICE_GET/SET_IRQ* John Levon
2025-05-15 15:44 ` [PATCH 19/27] vfio-user: forward MSI-X PBA BAR accesses to server John Levon
2025-05-15 15:44 ` [PATCH 20/27] vfio-user: set up container access to the proxy John Levon
2025-05-15 15:44 ` [PATCH 21/27] vfio-user: implement VFIO_USER_DEVICE_RESET John Levon
2025-05-15 15:44 ` [PATCH 22/27] vfio-user: implement VFIO_USER_DMA_MAP/UNMAP John Levon
2025-05-15 15:44 ` [PATCH 23/27] vfio-user: implement VFIO_USER_DMA_READ/WRITE John Levon
2025-05-15 15:44 ` [PATCH 24/27] vfio-user: add 'x-msg-timeout' option John Levon
2025-05-15 15:44 ` [PATCH 25/27] vfio-user: support posted writes John Levon
2025-05-15 15:44 ` [PATCH 26/27] vfio-user: add coalesced " John Levon
2025-05-15 15:44 ` [PATCH 27/27] docs: add vfio-user documentation John Levon
2025-05-19 12:40 ` [PATCH 00/27] vfio-user client Cédric Le Goater
2025-05-19 13:29   ` John Levon
2025-05-20  5:59     ` Cédric Le Goater
2025-05-20 15:05       ` John Levon

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=20250515154413.210315-12-john.levon@nutanix.com \
    --to=john.levon@nutanix.com \
    --cc=alex.williamson@redhat.com \
    --cc=berrange@redhat.com \
    --cc=clg@redhat.com \
    --cc=david@redhat.com \
    --cc=elena.ufimtseva@oracle.com \
    --cc=jag.raman@oracle.com \
    --cc=john.g.johnson@oracle.com \
    --cc=marcandre.lureau@redhat.com \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peterx@redhat.com \
    --cc=philmd@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=sgarzare@redhat.com \
    --cc=thanos.makatos@nutanix.com \
    /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).