[Qemu-devel] [PULL v2 052/106] Add vhost_ops to vhost_dev struct and replace all relevant ioctls

[Michael S. Tsirkin]

From: Nikolay Nikolaev <address@hidden>

Decouple vhost from the Linux kernel by introducing vhost_ops. The
intention is to provide different backends - a 'kernel' backend based on
the ioctl interface, and an 'user' backend based on a UNIX domain socket
and shared memory interface.

Signed-off-by: Antonios Motakis <address@hidden>
Signed-off-by: Nikolay Nikolaev <address@hidden>
Reviewed-by: Michael S. Tsirkin <address@hidden>
Signed-off-by: Michael S. Tsirkin <address@hidden>
---
 include/hw/virtio/vhost-backend.h | 27 ++++++++++++++++++++++++++
 include/hw/virtio/vhost.h         |  2 ++
 hw/net/vhost_net.c                | 10 ++++++----
 hw/scsi/vhost-scsi.c              | 10 +++++++---
 hw/virtio/vhost.c                 | 41 ++++++++++++++++++++-------------------
 5 files changed, 63 insertions(+), 27 deletions(-)
 create mode 100644 include/hw/virtio/vhost-backend.h

diff --git a/include/hw/virtio/vhost-backend.h 
b/include/hw/virtio/vhost-backend.h
new file mode 100644
index 0000000..14e5878
--- /dev/null
+++ b/include/hw/virtio/vhost-backend.h
@@ -0,0 +1,27 @@
+/*
+ * 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_
+
+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, void *opaque);
+typedef int (*vhost_backend_cleanup)(struct vhost_dev *dev);
+
+typedef struct VhostOps {
+    vhost_call vhost_call;
+    vhost_backend_init vhost_backend_init;
+    vhost_backend_cleanup vhost_backend_cleanup;
+} VhostOps;
+
+#endif /* VHOST_BACKEND_H_ */
diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index 8afc6f9..4714277 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"
 
@@ -49,6 +50,7 @@ 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, void *opaque,
diff --git a/hw/net/vhost_net.c b/hw/net/vhost_net.c
index 7a5523f..402f37e 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>
@@ -177,7 +176,8 @@ 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;
@@ -187,7 +187,8 @@ 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);
     }
     if (net->nc->info->poll) {
@@ -210,7 +211,8 @@ 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);
     }
     if (net->nc->info->poll) {
diff --git a/hw/scsi/vhost-scsi.c b/hw/scsi/vhost-scsi.c
index e4c98b4..ed564bc 100644
--- a/hw/scsi/vhost-scsi.c
+++ b/hw/scsi/vhost-scsi.c
@@ -36,12 +36,13 @@ static const int kernel_feature_bits[] = {
 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;
     }
@@ -52,10 +53,11 @@ 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)
@@ -64,13 +66,15 @@ 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;
     }
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 0d3b7bb..8584101 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -13,7 +13,6 @@
  * GNU GPL, version 2 or (at your option) any later version.
  */
 
-#include <sys/ioctl.h>
 #include "hw/virtio/vhost.h"
 #include "hw/hw.h"
 #include "qemu/atomic.h"
@@ -289,7 +288,7 @@ 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) {
@@ -456,7 +455,7 @@ 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;
@@ -469,7 +468,7 @@ 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) {
@@ -537,7 +536,7 @@ 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;
     }
@@ -551,7 +550,7 @@ 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;
 }
 
@@ -664,13 +663,13 @@ 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;
     }
@@ -712,7 +711,7 @@ 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;
@@ -750,7 +749,7 @@ 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);
@@ -792,7 +791,7 @@ 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;
@@ -813,14 +812,17 @@ int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
 {
     uint64_t features;
     int i, r;
-    hdev->control = (uintptr_t) opaque;;
 
-    r = ioctl(hdev->control, VHOST_SET_OWNER, NULL);
+    if (hdev->vhost_ops->vhost_backend_init(hdev, opaque) < 0) {
+        return -errno;
+    }
+
+    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;
     }
@@ -865,7 +867,7 @@ fail_vq:
     }
 fail:
     r = -errno;
-    close(hdev->control);
+    hdev->vhost_ops->vhost_backend_cleanup(hdev);
     return r;
 }
 
@@ -878,7 +880,7 @@ 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)
@@ -980,7 +982,7 @@ 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);
 }
 
@@ -1022,7 +1024,7 @@ 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;
@@ -1041,8 +1043,7 @@ 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;
-- 
MST