[Qemu-devel] [PATCH v3 2/7] Decouple vhost from kernel interface

[Antonios Motakis <a.motakis@virtualopensystems.com>]

We introduce the concept of vhost-backend, which can be either vhost-kernel
or vhost-user. The existing vhost interface to the kernel is abstracted
behind the vhost-kernel backend.

We replace all direct ioctls to the kernel with a vhost_call to the backend.
vhost dev->control is referenced only in the vhost-backend (ioctl, open, close).

Signed-off-by: Antonios Motakis <a.motakis@virtualopensystems.com>
Signed-off-by: Nikolay Nikolaev <n.nikolaev@virtualopensystems.com>
---
 hw/net/vhost_net.c                | 13 +++++---
 hw/scsi/vhost-scsi.c              | 13 +++++---
 hw/virtio/Makefile.objs           |  2 +-
 hw/virtio/vhost-backend.c         | 64 +++++++++++++++++++++++++++++++++++++++
 hw/virtio/vhost.c                 | 47 ++++++++++++++--------------
 include/hw/virtio/vhost-backend.h | 37 ++++++++++++++++++++++
 include/hw/virtio/vhost.h         |  4 ++-
 7 files changed, 147 insertions(+), 33 deletions(-)
 create mode 100644 hw/virtio/vhost-backend.c
 create mode 100644 include/hw/virtio/vhost-backend.h

diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index 006576d..4aaf0b4 100644
--- a/hw/net/vhost_net.c
+++ b/hw/net/vhost_net.c
@@ -27,7 +27,6 @@
 #include <sys/socket.h>
 #include <linux/kvm.h>
 #include <fcntl.h>
-#include <sys/ioctl.h>
 #include <linux/virtio_ring.h>
 #include <netpacket/packet.h>
 #include <net/ethernet.h>
@@ -113,7 +112,8 @@ struct vhost_net *vhost_net_init(NetClientState *backend, int devfd,
     net->dev.nvqs = 2;
     net->dev.vqs = net->vqs;
 
-    r = vhost_dev_init(&net->dev, devfd, "/dev/vhost-net", force);
+    r = vhost_dev_init(&net->dev, devfd, "/dev/vhost-net",
+                       VHOST_BACKEND_TYPE_KERNEL, force);
     if (r < 0) {
         goto fail;
     }
@@ -170,7 +170,8 @@ static int vhost_net_start_one(struct vhost_net *net,
     qemu_set_fd_handler(net->backend, NULL, NULL, NULL);
     file.fd = net->backend;
     for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
-        r = ioctl(net->dev.control, VHOST_NET_SET_BACKEND, &file);
+        const VhostOps *vhost_ops = net->dev.vhost_ops;
+        r = vhost_ops->vhost_call(&net->dev, VHOST_NET_SET_BACKEND, &file);
         if (r < 0) {
             r = -errno;
             goto fail;
@@ -180,7 +181,8 @@ static int vhost_net_start_one(struct vhost_net *net,
 fail:
     file.fd = -1;
     while (file.index-- > 0) {
-        int r = ioctl(net->dev.control, VHOST_NET_SET_BACKEND, &file);
+        const VhostOps *vhost_ops = net->dev.vhost_ops;
+        int r = vhost_ops->vhost_call(&net->dev, VHOST_NET_SET_BACKEND, &file);
         assert(r >= 0);
     }
     net->nc->info->poll(net->nc, true);
@@ -201,7 +203,8 @@ static void vhost_net_stop_one(struct vhost_net *net,
     }
 
     for (file.index = 0; file.index < net->dev.nvqs; ++file.index) {
-        int r = ioctl(net->dev.control, VHOST_NET_SET_BACKEND, &file);
+        const VhostOps *vhost_ops = net->dev.vhost_ops;
+        int r = vhost_ops->vhost_call(&net->dev, VHOST_NET_SET_BACKEND, &file);
         assert(r >= 0);
     }
     net->nc->info->poll(net->nc, true);
diff --git a/hw/scsi/vhost-scsi.c b/hw/scsi/vhost-scsi.c
index 9e770fb..b074b65 100644
--- a/hw/scsi/vhost-scsi.c
+++ b/hw/scsi/vhost-scsi.c
@@ -27,12 +27,13 @@
 static int vhost_scsi_set_endpoint(VHostSCSI *s)
 {
     VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s);
+    const VhostOps *vhost_ops = s->dev.vhost_ops;
     struct vhost_scsi_target backend;
     int ret;
 
     memset(&backend, 0, sizeof(backend));
     pstrcpy(backend.vhost_wwpn, sizeof(backend.vhost_wwpn), vs->conf.wwpn);
-    ret = ioctl(s->dev.control, VHOST_SCSI_SET_ENDPOINT, &backend);
+    ret = vhost_ops->vhost_call(&s->dev, VHOST_SCSI_SET_ENDPOINT, &backend);
     if (ret < 0) {
         return -errno;
     }
@@ -43,10 +44,11 @@ static void vhost_scsi_clear_endpoint(VHostSCSI *s)
 {
     VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(s);
     struct vhost_scsi_target backend;
+    const VhostOps *vhost_ops = s->dev.vhost_ops;
 
     memset(&backend, 0, sizeof(backend));
     pstrcpy(backend.vhost_wwpn, sizeof(backend.vhost_wwpn), vs->conf.wwpn);
-    ioctl(s->dev.control, VHOST_SCSI_CLEAR_ENDPOINT, &backend);
+    vhost_ops->vhost_call(&s->dev, VHOST_SCSI_CLEAR_ENDPOINT, &backend);
 }
 
 static int vhost_scsi_start(VHostSCSI *s)
@@ -55,13 +57,15 @@ static int vhost_scsi_start(VHostSCSI *s)
     VirtIODevice *vdev = VIRTIO_DEVICE(s);
     BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
     VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+    const VhostOps *vhost_ops = s->dev.vhost_ops;
 
     if (!k->set_guest_notifiers) {
         error_report("binding does not support guest notifiers");
         return -ENOSYS;
     }
 
-    ret = ioctl(s->dev.control, VHOST_SCSI_GET_ABI_VERSION, &abi_version);
+    ret = vhost_ops->vhost_call(&s->dev,
+                                VHOST_SCSI_GET_ABI_VERSION, &abi_version);
     if (ret < 0) {
         return -errno;
     }
@@ -225,7 +229,8 @@ static int vhost_scsi_init(VirtIODevice *vdev)
     s->dev.vqs = g_new(struct vhost_virtqueue, s->dev.nvqs);
     s->dev.vq_index = 0;
 
-    ret = vhost_dev_init(&s->dev, vhostfd, "/dev/vhost-scsi", true);
+    ret = vhost_dev_init(&s->dev, vhostfd, "/dev/vhost-scsi",
+                         VHOST_BACKEND_TYPE_KERNEL, true);
     if (ret < 0) {
         error_report("vhost-scsi: vhost initialization failed: %s\n",
                 strerror(-ret));
diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs
index 1ba53d9..51e5bdb 100644
--- a/hw/virtio/Makefile.objs
+++ b/hw/virtio/Makefile.objs
@@ -5,4 +5,4 @@ common-obj-y += virtio-mmio.o
 common-obj-$(CONFIG_VIRTIO_BLK_DATA_PLANE) += dataplane/
 
 obj-y += virtio.o virtio-balloon.o 
-obj-$(CONFIG_LINUX) += vhost.o
+obj-$(CONFIG_LINUX) += vhost.o vhost-backend.o
diff --git a/hw/virtio/vhost-backend.c b/hw/virtio/vhost-backend.c
new file mode 100644
index 0000000..2a9a1ec
--- /dev/null
+++ b/hw/virtio/vhost-backend.c
@@ -0,0 +1,64 @@
+/*
+ * vhost-backend
+ *
+ * Copyright (c) 2013 Virtual Open Systems Sarl.
+ *
+ * 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 "hw/virtio/vhost.h"
+#include "hw/virtio/vhost-backend.h"
+
+#include <fcntl.h>
+#include <unistd.h>
+#include <sys/ioctl.h>
+
+static int vhost_kernel_call(struct vhost_dev *dev, unsigned long int request,
+                             void *arg)
+{
+    int fd = dev->control;
+
+    assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_KERNEL);
+
+    return ioctl(fd, request, arg);
+}
+
+static int vhost_kernel_init(struct vhost_dev *dev, const char *devpath)
+{
+    assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_KERNEL);
+
+    dev->control = open(devpath, O_RDWR);
+    return dev->control;
+}
+
+static int vhost_kernel_cleanup(struct vhost_dev *dev)
+{
+    assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_KERNEL);
+
+    return close(dev->control);
+}
+
+static const VhostOps kernel_ops = {
+        .backend_type = VHOST_BACKEND_TYPE_KERNEL,
+        .vhost_call = vhost_kernel_call,
+        .vhost_backend_init = vhost_kernel_init,
+        .vhost_backend_cleanup = vhost_kernel_cleanup
+};
+
+int vhost_set_backend_type(struct vhost_dev *dev, VhostBackendType backend_type)
+{
+    int r = 0;
+
+    switch (backend_type) {
+    case VHOST_BACKEND_TYPE_KERNEL:
+        dev->vhost_ops = &kernel_ops;
+        break;
+    default:
+        fprintf(stderr, "Unknown vhost backend type\n");
+        r = -1;
+    }
+
+    return r;
+}
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 9e336ad..a1137e1 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -13,8 +13,8 @@
  * GNU GPL, version 2 or (at your option) any later version.
  */
 
-#include <sys/ioctl.h>
 #include "hw/virtio/vhost.h"
+#include "hw/virtio/vhost-backend.h"
 #include "hw/hw.h"
 #include "qemu/atomic.h"
 #include "qemu/range.h"
@@ -291,7 +291,7 @@ static inline void vhost_dev_log_resize(struct vhost_dev* dev, uint64_t size)
 
     log = g_malloc0(size * sizeof *log);
     log_base = (uint64_t)(unsigned long)log;
-    r = ioctl(dev->control, VHOST_SET_LOG_BASE, &log_base);
+    r = dev->vhost_ops->vhost_call(dev, VHOST_SET_LOG_BASE, &log_base);
     assert(r >= 0);
     /* Sync only the range covered by the old log */
     if (dev->log_size) {
@@ -460,7 +460,7 @@ static void vhost_commit(MemoryListener *listener)
     }
 
     if (!dev->log_enabled) {
-        r = ioctl(dev->control, VHOST_SET_MEM_TABLE, dev->mem);
+        r = dev->vhost_ops->vhost_call(dev, VHOST_SET_MEM_TABLE, dev->mem);
         assert(r >= 0);
         dev->memory_changed = false;
         return;
@@ -473,7 +473,7 @@ static void vhost_commit(MemoryListener *listener)
     if (dev->log_size < log_size) {
         vhost_dev_log_resize(dev, log_size + VHOST_LOG_BUFFER);
     }
-    r = ioctl(dev->control, VHOST_SET_MEM_TABLE, dev->mem);
+    r = dev->vhost_ops->vhost_call(dev, VHOST_SET_MEM_TABLE, dev->mem);
     assert(r >= 0);
     /* To log less, can only decrease log size after table update. */
     if (dev->log_size > log_size + VHOST_LOG_BUFFER) {
@@ -541,7 +541,7 @@ static int vhost_virtqueue_set_addr(struct vhost_dev *dev,
         .log_guest_addr = vq->used_phys,
         .flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0,
     };
-    int r = ioctl(dev->control, VHOST_SET_VRING_ADDR, &addr);
+    int r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_ADDR, &addr);
     if (r < 0) {
         return -errno;
     }
@@ -555,7 +555,7 @@ static int vhost_dev_set_features(struct vhost_dev *dev, bool enable_log)
     if (enable_log) {
         features |= 0x1 << VHOST_F_LOG_ALL;
     }
-    r = ioctl(dev->control, VHOST_SET_FEATURES, &features);
+    r = dev->vhost_ops->vhost_call(dev, VHOST_SET_FEATURES, &features);
     return r < 0 ? -errno : 0;
 }
 
@@ -670,13 +670,13 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
     assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs);
 
     vq->num = state.num = virtio_queue_get_num(vdev, idx);
-    r = ioctl(dev->control, VHOST_SET_VRING_NUM, &state);
+    r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_NUM, &state);
     if (r) {
         return -errno;
     }
 
     state.num = virtio_queue_get_last_avail_idx(vdev, idx);
-    r = ioctl(dev->control, VHOST_SET_VRING_BASE, &state);
+    r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_BASE, &state);
     if (r) {
         return -errno;
     }
@@ -718,7 +718,7 @@ static int vhost_virtqueue_start(struct vhost_dev *dev,
     }
 
     file.fd = event_notifier_get_fd(virtio_queue_get_host_notifier(vvq));
-    r = ioctl(dev->control, VHOST_SET_VRING_KICK, &file);
+    r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_KICK, &file);
     if (r) {
         r = -errno;
         goto fail_kick;
@@ -756,7 +756,7 @@ static void vhost_virtqueue_stop(struct vhost_dev *dev,
     };
     int r;
     assert(idx >= dev->vq_index && idx < dev->vq_index + dev->nvqs);
-    r = ioctl(dev->control, VHOST_GET_VRING_BASE, &state);
+    r = dev->vhost_ops->vhost_call(dev, VHOST_GET_VRING_BASE, &state);
     if (r < 0) {
         fprintf(stderr, "vhost VQ %d ring restore failed: %d\n", idx, r);
         fflush(stderr);
@@ -798,7 +798,7 @@ static int vhost_virtqueue_init(struct vhost_dev *dev,
     }
 
     file.fd = event_notifier_get_fd(&vq->masked_notifier);
-    r = ioctl(dev->control, VHOST_SET_VRING_CALL, &file);
+    r = dev->vhost_ops->vhost_call(dev, VHOST_SET_VRING_CALL, &file);
     if (r) {
         r = -errno;
         goto fail_call;
@@ -815,24 +815,28 @@ static void vhost_virtqueue_cleanup(struct vhost_virtqueue *vq)
 }
 
 int vhost_dev_init(struct vhost_dev *hdev, int devfd, const char *devpath,
-                   bool force)
+                   VhostBackendType backend_type, bool force)
 {
     uint64_t features;
     int i, r;
+
+    if (vhost_set_backend_type(hdev, backend_type) < 0) {
+        return -1;
+    }
+
     if (devfd >= 0) {
         hdev->control = devfd;
     } else {
-        hdev->control = open(devpath, O_RDWR);
-        if (hdev->control < 0) {
+        if (hdev->vhost_ops->vhost_backend_init(hdev, devpath) < 0) {
             return -errno;
         }
     }
-    r = ioctl(hdev->control, VHOST_SET_OWNER, NULL);
+    r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_OWNER, NULL);
     if (r < 0) {
         goto fail;
     }
 
-    r = ioctl(hdev->control, VHOST_GET_FEATURES, &features);
+    r = hdev->vhost_ops->vhost_call(hdev, VHOST_GET_FEATURES, &features);
     if (r < 0) {
         goto fail;
     }
@@ -877,7 +881,7 @@ fail_vq:
     }
 fail:
     r = -errno;
-    close(hdev->control);
+    hdev->vhost_ops->vhost_backend_cleanup(hdev);
     return r;
 }
 
@@ -890,7 +894,7 @@ void vhost_dev_cleanup(struct vhost_dev *hdev)
     memory_listener_unregister(&hdev->memory_listener);
     g_free(hdev->mem);
     g_free(hdev->mem_sections);
-    close(hdev->control);
+    hdev->vhost_ops->vhost_backend_cleanup(hdev);
 }
 
 bool vhost_dev_query(struct vhost_dev *hdev, VirtIODevice *vdev)
@@ -992,7 +996,7 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n,
     } else {
         file.fd = event_notifier_get_fd(virtio_queue_get_guest_notifier(vvq));
     }
-    r = ioctl(hdev->control, VHOST_SET_VRING_CALL, &file);
+    r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_VRING_CALL, &file);
     assert(r >= 0);
 }
 
@@ -1007,7 +1011,7 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
     if (r < 0) {
         goto fail_features;
     }
-    r = ioctl(hdev->control, VHOST_SET_MEM_TABLE, hdev->mem);
+    r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_MEM_TABLE, hdev->mem);
     if (r < 0) {
         r = -errno;
         goto fail_mem;
@@ -1026,8 +1030,7 @@ int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
         hdev->log_size = vhost_get_log_size(hdev);
         hdev->log = hdev->log_size ?
             g_malloc0(hdev->log_size * sizeof *hdev->log) : NULL;
-        r = ioctl(hdev->control, VHOST_SET_LOG_BASE,
-                  (uint64_t)(unsigned long)hdev->log);
+        r = hdev->vhost_ops->vhost_call(hdev, VHOST_SET_LOG_BASE, hdev->log);
         if (r < 0) {
             r = -errno;
             goto fail_log;
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
new file mode 100644
index 0000000..93fc55b
--- /dev/null
+++ b/include/hw/virtio/vhost-backend.h
@@ -0,0 +1,37 @@
+/*
+ * vhost-backend
+ *
+ * Copyright (c) 2013 Virtual Open Systems Sarl.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef VHOST_BACKEND_H_
+#define VHOST_BACKEND_H_
+
+typedef enum VhostBackendType {
+    VHOST_BACKEND_TYPE_NONE = 0,
+    VHOST_BACKEND_TYPE_KERNEL = 1,
+    VHOST_BACKEND_TYPE_MAX = 2,
+} VhostBackendType;
+
+struct vhost_dev;
+
+typedef int (*vhost_call)(struct vhost_dev *dev, unsigned long int request,
+             void *arg);
+typedef int (*vhost_backend_init)(struct vhost_dev *dev, const char *devpath);
+typedef int (*vhost_backend_cleanup)(struct vhost_dev *dev);
+
+typedef struct VhostOps {
+    VhostBackendType backend_type;
+    vhost_call vhost_call;
+    vhost_backend_init vhost_backend_init;
+    vhost_backend_cleanup vhost_backend_cleanup;
+} VhostOps;
+
+int vhost_set_backend_type(struct vhost_dev *dev,
+                           VhostBackendType backend_type);
+
+#endif /* VHOST_BACKEND_H_ */
diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index de24746..bd650a5 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -2,6 +2,7 @@
 #define VHOST_H
 
 #include "hw/hw.h"
+#include "hw/virtio/vhost-backend.h"
 #include "hw/virtio/virtio.h"
 #include "exec/memory.h"
 
@@ -48,10 +49,11 @@ struct vhost_dev {
     bool memory_changed;
     hwaddr mem_changed_start_addr;
     hwaddr mem_changed_end_addr;
+    const VhostOps *vhost_ops;
 };
 
 int vhost_dev_init(struct vhost_dev *hdev, int devfd, const char *devpath,
-                   bool force);
+                   VhostBackendType backend_type, bool force);
 void vhost_dev_cleanup(struct vhost_dev *hdev);
 bool vhost_dev_query(struct vhost_dev *hdev, VirtIODevice *vdev);
 int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev);
-- 
1.8.3.2