* Re: [Qemu-devel] [PATCH v3 0/4] *** Introduce a new vhost-user-blk host device to Qemu ***
2017-09-12 7:56 [Qemu-devel] [PATCH v3 0/4] *** Introduce a new vhost-user-blk host device to Qemu *** Changpeng Liu
@ 2017-09-11 17:25 ` Eric Blake
2017-09-12 7:56 ` [Qemu-devel] [PATCH v3 1/4] vhost-user: add new vhost user messages to support virtio config space Changpeng Liu
` (3 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Eric Blake @ 2017-09-11 17:25 UTC (permalink / raw)
To: Changpeng Liu, qemu-devel
Cc: james.r.harris, mst, stefanha, pbonzini, felipe, marcandre.lureau
[-- Attachment #1: Type: text/plain, Size: 704 bytes --]
On 09/12/2017 02:56 AM, Changpeng Liu wrote:
^^^^^^^^^^^^^^^^^^^
Wow, your system clock is off. According to the mail headers:
> Received: from orsmga004.jf.intel.com ([10.7.209.38])
> by fmsmga105.fm.intel.com with ESMTP; 11 Sep 2017 00:36:13 -0700
...
> Date: Tue, 12 Sep 2017 15:56:12 +0800
the intel.com machine received it at 7:36 UTC Monday, even though your
computer sent it at 9:56 UTC Tuesday, 26 hours in the future. Sending
mail from the future messes with clients that like to display mail
sorted by date of last activity in the thread.
--
Eric Blake, Principal Software Engineer
Red Hat, Inc. +1-919-301-3266
Virtualization: qemu.org | libvirt.org
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 619 bytes --]
^ permalink raw reply [flat|nested] 6+ messages in thread* [Qemu-devel] [PATCH v3 1/4] vhost-user: add new vhost user messages to support virtio config space
2017-09-12 7:56 [Qemu-devel] [PATCH v3 0/4] *** Introduce a new vhost-user-blk host device to Qemu *** Changpeng Liu
2017-09-11 17:25 ` Eric Blake
@ 2017-09-12 7:56 ` Changpeng Liu
2017-09-12 7:56 ` [Qemu-devel] [PATCH v3 2/4] vhost-user-blk: introduce a new vhost-user-blk host device Changpeng Liu
` (2 subsequent siblings)
4 siblings, 0 replies; 6+ messages in thread
From: Changpeng Liu @ 2017-09-12 7:56 UTC (permalink / raw)
To: changpeng.liu, qemu-devel
Cc: stefanha, pbonzini, mst, marcandre.lureau, felipe, james.r.harris
Add VHOST_USER_GET_CONFIG/VHOST_USER_SET_CONFIG messages which can be
used for live migration for vhost user devices, also vhost user devices
can benefit from the messages to get/set virtio config space from/to the
I/O target besides Qemu. For the purpose to support virtio config space
change, VHOST_USER_SET_CONFIG_FD message is added as the event notifier
in case virtio config space change.
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
---
docs/interop/vhost-user.txt | 32 +++++++++++++
hw/virtio/vhost-user.c | 97 +++++++++++++++++++++++++++++++++++++++
hw/virtio/vhost.c | 63 +++++++++++++++++++++++++
include/hw/virtio/vhost-backend.h | 8 ++++
include/hw/virtio/vhost.h | 16 +++++++
5 files changed, 216 insertions(+)
diff --git a/docs/interop/vhost-user.txt b/docs/interop/vhost-user.txt
index 954771d..a953299 100644
--- a/docs/interop/vhost-user.txt
+++ b/docs/interop/vhost-user.txt
@@ -116,6 +116,10 @@ Depending on the request type, payload can be:
- 3: IOTLB invalidate
- 4: IOTLB access fail
+ * Virtio device config space
+
+ 256 Bytes static virito config space
+
In QEMU the vhost-user message is implemented with the following struct:
typedef struct VhostUserMsg {
@@ -129,6 +133,7 @@ typedef struct VhostUserMsg {
VhostUserMemory memory;
VhostUserLog log;
struct vhost_iotlb_msg iotlb;
+ uint8_t config[256];
};
} QEMU_PACKED VhostUserMsg;
@@ -596,6 +601,33 @@ Master message types
and expect this message once (per VQ) during device configuration
(ie. before the master starts the VQ).
+ * VHOST_USER_GET_CONFIG
+ Id: 24
+ Equivalent ioctl: N/A
+ Master payload: virtio device config space
+
+ Submitted by the vhost-user master to fetch the contents of the virtio
+ config space. The vhost-user master may cache the contents to avoid
+ repeated VHOST_USER_GET_CONFIG calls.
+
+* VHOST_USER_SET_CONFIG
+ Id: 25
+ Equivalent ioctl: N/A
+ Master payload: virtio device config space
+
+ Submitted by the vhost-user master when the guest writes to virtio
+ config space and also after live migration on the destination host.
+
+* VHOST_USER_SET_CONFIG_FD
+ Id: 26
+ Equivalent ioctl: N/A
+ Master payload: N/A
+
+ Sets the notifier file descriptor, which is passed as ancillary data.
+ Vhost-user slave uses the file descriptor to notify vhost-user master
+ when the virtio config space changed. The vhost-user master can read
+ the virtio config space to get the update.
+
Slave message types
-------------------
diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c
index 093675e..4e7bafc 100644
--- a/hw/virtio/vhost-user.c
+++ b/hw/virtio/vhost-user.c
@@ -26,6 +26,11 @@
#define VHOST_MEMORY_MAX_NREGIONS 8
#define VHOST_USER_F_PROTOCOL_FEATURES 30
+/*
+ * Maximum size of virtio device config space
+ */
+#define VHOST_USER_MAX_CONFIG_SIZE 256
+
enum VhostUserProtocolFeature {
VHOST_USER_PROTOCOL_F_MQ = 0,
VHOST_USER_PROTOCOL_F_LOG_SHMFD = 1,
@@ -65,6 +70,9 @@ typedef enum VhostUserRequest {
VHOST_USER_SET_SLAVE_REQ_FD = 21,
VHOST_USER_IOTLB_MSG = 22,
VHOST_USER_SET_VRING_ENDIAN = 23,
+ VHOST_USER_GET_CONFIG = 24,
+ VHOST_USER_SET_CONFIG = 25,
+ VHOST_USER_SET_CONFIG_FD = 26,
VHOST_USER_MAX
} VhostUserRequest;
@@ -109,6 +117,7 @@ typedef struct VhostUserMsg {
VhostUserMemory memory;
VhostUserLog log;
struct vhost_iotlb_msg iotlb;
+ uint8_t config[VHOST_USER_MAX_CONFIG_SIZE];
} payload;
} QEMU_PACKED VhostUserMsg;
@@ -922,6 +931,91 @@ static void vhost_user_set_iotlb_callback(struct vhost_dev *dev, int enabled)
/* No-op as the receive channel is not dedicated to IOTLB messages. */
}
+static int vhost_user_get_config(struct vhost_dev *dev, uint8_t *config,
+ size_t config_len)
+{
+ VhostUserMsg msg = {
+ .request = VHOST_USER_GET_CONFIG,
+ .flags = VHOST_USER_VERSION,
+ .size = config_len,
+ };
+
+ if (config_len == 0 || config_len > VHOST_USER_PAYLOAD_SIZE) {
+ error_report("bad config length");
+ return -1;
+ }
+
+ if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+ return -1;
+ }
+
+ if (vhost_user_read(dev, &msg) < 0) {
+ return -1;
+ }
+
+ if (msg.request != VHOST_USER_GET_CONFIG) {
+ error_report("Received unexpected msg type. Expected %d received %d",
+ VHOST_USER_GET_CONFIG, msg.request);
+ return -1;
+ }
+
+ if (msg.size != config_len) {
+ error_report("Received bad msg size.");
+ return -1;
+ }
+
+ memcpy(config, &msg.payload.config, config_len);
+
+ return 0;
+}
+
+static int vhost_user_set_config(struct vhost_dev *dev, const uint8_t *config,
+ size_t config_len)
+{
+ bool reply_supported = virtio_has_feature(dev->protocol_features,
+ VHOST_USER_PROTOCOL_F_REPLY_ACK);
+
+ VhostUserMsg msg = {
+ .request = VHOST_USER_SET_CONFIG,
+ .flags = VHOST_USER_VERSION,
+ .size = config_len,
+ };
+
+ if (reply_supported) {
+ msg.flags |= VHOST_USER_NEED_REPLY_MASK;
+ }
+
+ if (config_len == 0 || config_len > VHOST_USER_PAYLOAD_SIZE) {
+ error_report("bad config length");
+ return -1;
+ }
+
+ memcpy(&msg.payload.config, config, config_len);
+ if (vhost_user_write(dev, &msg, NULL, 0) < 0) {
+ return -1;
+ }
+
+ if (reply_supported) {
+ return process_message_reply(dev, &msg);
+ }
+
+ return 0;
+}
+
+static int vhost_user_set_config_fd(struct vhost_dev *dev, int fd)
+{
+ VhostUserMsg msg = {
+ .request = VHOST_USER_SET_CONFIG_FD,
+ .flags = VHOST_USER_VERSION,
+ };
+
+ if (vhost_user_write(dev, &msg, &fd, 1) < 0) {
+ return -1;
+ }
+
+ return 0;
+}
+
const VhostOps user_ops = {
.backend_type = VHOST_BACKEND_TYPE_USER,
.vhost_backend_init = vhost_user_init,
@@ -948,4 +1042,7 @@ const VhostOps user_ops = {
.vhost_net_set_mtu = vhost_user_net_set_mtu,
.vhost_set_iotlb_callback = vhost_user_set_iotlb_callback,
.vhost_send_device_iotlb_msg = vhost_user_send_device_iotlb_msg,
+ .vhost_get_config = vhost_user_get_config,
+ .vhost_set_config = vhost_user_set_config,
+ .vhost_set_config_fd = vhost_user_set_config_fd,
};
diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c
index 5fd69f0..ddc3395 100644
--- a/hw/virtio/vhost.c
+++ b/hw/virtio/vhost.c
@@ -1353,6 +1353,9 @@ void vhost_dev_cleanup(struct vhost_dev *hdev)
for (i = 0; i < hdev->nvqs; ++i) {
vhost_virtqueue_cleanup(hdev->vqs + i);
}
+ if (hdev->config_ops) {
+ event_notifier_cleanup(&hdev->config_notifier);
+ }
if (hdev->mem) {
/* those are only safe after successful init */
memory_listener_unregister(&hdev->memory_listener);
@@ -1500,6 +1503,66 @@ void vhost_ack_features(struct vhost_dev *hdev, const int *feature_bits,
}
}
+int vhost_dev_get_config(struct vhost_dev *hdev, uint8_t *config,
+ size_t config_len)
+{
+ assert(hdev->vhost_ops);
+
+ if (hdev->vhost_ops->vhost_get_config) {
+ return hdev->vhost_ops->vhost_get_config(hdev, config, config_len);
+ }
+
+ return 0;
+}
+
+int vhost_dev_set_config(struct vhost_dev *hdev, const uint8_t *config,
+ size_t config_len)
+{
+ assert(hdev->vhost_ops);
+
+ if (hdev->vhost_ops->vhost_set_config) {
+ return hdev->vhost_ops->vhost_set_config(hdev, config, config_len);
+ }
+
+ return 0;
+}
+
+static void vhost_dev_config_notifier_read(EventNotifier *n)
+{
+ struct vhost_dev *hdev = container_of(n, struct vhost_dev,
+ config_notifier);
+
+ if (event_notifier_test_and_clear(n)) {
+ if (hdev->config_ops) {
+ hdev->config_ops->vhost_dev_config_notifier(hdev);
+ }
+ }
+}
+
+int vhost_dev_set_config_notifier(struct vhost_dev *hdev,
+ const VhostDevConfigOps *ops)
+{
+ int r, fd;
+
+ assert(hdev->vhost_ops);
+
+ r = event_notifier_init(&hdev->config_notifier, 0);
+ if (r < 0) {
+ return r;
+ }
+
+ hdev->config_ops = ops;
+ event_notifier_set_handler(&hdev->config_notifier,
+ vhost_dev_config_notifier_read);
+
+ if (hdev->vhost_ops->vhost_set_config_fd) {
+ fd = event_notifier_get_fd(&hdev->config_notifier);
+ return hdev->vhost_ops->vhost_set_config_fd(hdev, fd);
+ }
+
+ return 0;
+}
+
/* Host notifiers must be enabled at this point. */
int vhost_dev_start(struct vhost_dev *hdev, VirtIODevice *vdev)
{
diff --git a/include/hw/virtio/vhost-backend.h b/include/hw/virtio/vhost-backend.h
index a7a5f22..df6769e 100644
--- a/include/hw/virtio/vhost-backend.h
+++ b/include/hw/virtio/vhost-backend.h
@@ -84,6 +84,11 @@ typedef void (*vhost_set_iotlb_callback_op)(struct vhost_dev *dev,
int enabled);
typedef int (*vhost_send_device_iotlb_msg_op)(struct vhost_dev *dev,
struct vhost_iotlb_msg *imsg);
+typedef int (*vhost_set_config_op)(struct vhost_dev *dev, const uint8_t *config,
+ size_t config_len);
+typedef int (*vhost_get_config_op)(struct vhost_dev *dev, uint8_t *config,
+ size_t config_len);
+typedef int (*vhost_set_config_fd_op)(struct vhost_dev *dev, int fd);
typedef struct VhostOps {
VhostBackendType backend_type;
@@ -118,6 +123,9 @@ typedef struct VhostOps {
vhost_vsock_set_running_op vhost_vsock_set_running;
vhost_set_iotlb_callback_op vhost_set_iotlb_callback;
vhost_send_device_iotlb_msg_op vhost_send_device_iotlb_msg;
+ vhost_get_config_op vhost_get_config;
+ vhost_set_config_op vhost_set_config;
+ vhost_set_config_fd_op vhost_set_config_fd;
} VhostOps;
extern const VhostOps user_ops;
diff --git a/include/hw/virtio/vhost.h b/include/hw/virtio/vhost.h
index 467dc77..ff172f2 100644
--- a/include/hw/virtio/vhost.h
+++ b/include/hw/virtio/vhost.h
@@ -46,6 +46,12 @@ struct vhost_iommu {
QLIST_ENTRY(vhost_iommu) iommu_next;
};
+typedef struct VhostDevConfigOps {
+ /* Vhost device config space changed callback
+ */
+ void (*vhost_dev_config_notifier)(struct vhost_dev *dev);
+} VhostDevConfigOps;
+
struct vhost_memory;
struct vhost_dev {
VirtIODevice *vdev;
@@ -76,6 +82,8 @@ struct vhost_dev {
QLIST_ENTRY(vhost_dev) entry;
QLIST_HEAD(, vhost_iommu) iommu_list;
IOMMUNotifier n;
+ EventNotifier config_notifier;
+ const VhostDevConfigOps *config_ops;
};
int vhost_dev_init(struct vhost_dev *hdev, void *opaque,
@@ -106,4 +114,12 @@ int vhost_net_set_backend(struct vhost_dev *hdev,
struct vhost_vring_file *file);
int vhost_device_iotlb_miss(struct vhost_dev *dev, uint64_t iova, int write);
+int vhost_dev_get_config(struct vhost_dev *dev, uint8_t *config,
+ size_t config_len);
+int vhost_dev_set_config(struct vhost_dev *dev, const uint8_t *config,
+ size_t config_len);
+/* notifier callback in case vhost device config space changed
+ */
+int vhost_dev_set_config_notifier(struct vhost_dev *dev,
+ const VhostDevConfigOps *ops);
#endif
--
1.9.3
^ permalink raw reply related [flat|nested] 6+ messages in thread* [Qemu-devel] [PATCH v3 2/4] vhost-user-blk: introduce a new vhost-user-blk host device
2017-09-12 7:56 [Qemu-devel] [PATCH v3 0/4] *** Introduce a new vhost-user-blk host device to Qemu *** Changpeng Liu
2017-09-11 17:25 ` Eric Blake
2017-09-12 7:56 ` [Qemu-devel] [PATCH v3 1/4] vhost-user: add new vhost user messages to support virtio config space Changpeng Liu
@ 2017-09-12 7:56 ` Changpeng Liu
2017-09-12 7:56 ` [Qemu-devel] [PATCH v3 3/4] contrib/libvhost-user: enable virtio config space messages Changpeng Liu
2017-09-12 7:56 ` [Qemu-devel] [PATCH v3 4/4] contrib/vhost-user-blk: introduce a vhost-user-blk sample application Changpeng Liu
4 siblings, 0 replies; 6+ messages in thread
From: Changpeng Liu @ 2017-09-12 7:56 UTC (permalink / raw)
To: changpeng.liu, qemu-devel
Cc: stefanha, pbonzini, mst, marcandre.lureau, felipe, james.r.harris
This commit introduces a new vhost-user device for block, it uses a
chardev to connect with the backend, same with Qemu virito-blk device,
Guest OS still uses the virtio-blk frontend driver.
To use it, start Qemu with command line like this:
qemu-system-x86_64 \
-chardev socket,id=char0,path=/path/vhost.socket \
-device vhost-user-blk-pci,chardev=char0,num_queues=1, \
bootindex=2... \
Users can use different parameters for `num_queues` and `bootindex`.
Different with exist Qemu virtio-blk host device, it makes more easy
for users to implement their own I/O processing logic, such as all
user space I/O stack against hardware block device. It uses the new
vhost messages(VHOST_USER_GET_CONFIG) to get block virtio config
information from backend process.
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
---
configure | 11 ++
hw/block/Makefile.objs | 3 +
hw/block/vhost-user-blk.c | 360 +++++++++++++++++++++++++++++++++++++
hw/virtio/virtio-pci.c | 55 ++++++
hw/virtio/virtio-pci.h | 18 ++
include/hw/virtio/vhost-user-blk.h | 40 +++++
6 files changed, 487 insertions(+)
create mode 100644 hw/block/vhost-user-blk.c
create mode 100644 include/hw/virtio/vhost-user-blk.h
diff --git a/configure b/configure
index fd7e3a5..4259833 100755
--- a/configure
+++ b/configure
@@ -310,6 +310,7 @@ tcg="yes"
vhost_net="no"
vhost_scsi="no"
+vhost_user_blk="no"
vhost_vsock="no"
vhost_user=""
kvm="no"
@@ -774,6 +775,7 @@ Linux)
kvm="yes"
vhost_net="yes"
vhost_scsi="yes"
+ vhost_user_blk="yes"
vhost_vsock="yes"
QEMU_INCLUDES="-I\$(SRC_PATH)/linux-headers -I$(pwd)/linux-headers $QEMU_INCLUDES"
supported_os="yes"
@@ -1131,6 +1133,10 @@ for opt do
;;
--enable-vhost-scsi) vhost_scsi="yes"
;;
+ --disable-vhost-user-blk) vhost_user_blk="no"
+ ;;
+ --enable-vhost-user-blk) vhost_user_blk="yes"
+ ;;
--disable-vhost-vsock) vhost_vsock="no"
;;
--enable-vhost-vsock) vhost_vsock="yes"
@@ -1501,6 +1507,7 @@ disabled with --disable-FEATURE, default is enabled if available:
cap-ng libcap-ng support
attr attr and xattr support
vhost-net vhost-net acceleration support
+ vhost-user-blk VM virtio-blk acceleration in user space
spice spice
rbd rados block device (rbd)
libiscsi iscsi support
@@ -5360,6 +5367,7 @@ echo "posix_madvise $posix_madvise"
echo "libcap-ng support $cap_ng"
echo "vhost-net support $vhost_net"
echo "vhost-scsi support $vhost_scsi"
+echo "vhost-user-blk support $vhost_user_blk"
echo "vhost-vsock support $vhost_vsock"
echo "vhost-user support $vhost_user"
echo "Trace backends $trace_backends"
@@ -5767,6 +5775,9 @@ fi
if test "$vhost_scsi" = "yes" ; then
echo "CONFIG_VHOST_SCSI=y" >> $config_host_mak
fi
+if test "$vhost_user_blk" = "yes" -a "$vhost_user" = "yes"; then
+ echo "CONFIG_VHOST_USER_BLK=y" >> $config_host_mak
+fi
if test "$vhost_net" = "yes" -a "$vhost_user" = "yes"; then
echo "CONFIG_VHOST_NET_USED=y" >> $config_host_mak
fi
diff --git a/hw/block/Makefile.objs b/hw/block/Makefile.objs
index e0ed980..4c19a58 100644
--- a/hw/block/Makefile.objs
+++ b/hw/block/Makefile.objs
@@ -13,3 +13,6 @@ obj-$(CONFIG_SH4) += tc58128.o
obj-$(CONFIG_VIRTIO) += virtio-blk.o
obj-$(CONFIG_VIRTIO) += dataplane/
+ifeq ($(CONFIG_VIRTIO),y)
+obj-$(CONFIG_VHOST_USER_BLK) += vhost-user-blk.o
+endif
diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c
new file mode 100644
index 0000000..8aa9fa9
--- /dev/null
+++ b/hw/block/vhost-user-blk.c
@@ -0,0 +1,360 @@
+/*
+ * vhost-user-blk host device
+ *
+ * Copyright IBM, Corp. 2011
+ * Copyright(C) 2017 Intel Corporation.
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ * Changpeng Liu <changpeng.liu@intel.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qemu/error-report.h"
+#include "qemu/typedefs.h"
+#include "qemu/cutils.h"
+#include "qom/object.h"
+#include "hw/qdev-core.h"
+#include "hw/virtio/vhost.h"
+#include "hw/virtio/vhost-user-blk.h"
+#include "hw/virtio/virtio.h"
+#include "hw/virtio/virtio-bus.h"
+#include "hw/virtio/virtio-access.h"
+
+static const int user_feature_bits[] = {
+ VIRTIO_BLK_F_SIZE_MAX,
+ VIRTIO_BLK_F_SEG_MAX,
+ VIRTIO_BLK_F_GEOMETRY,
+ VIRTIO_BLK_F_BLK_SIZE,
+ VIRTIO_BLK_F_TOPOLOGY,
+ VIRTIO_BLK_F_SCSI,
+ VIRTIO_BLK_F_MQ,
+ VIRTIO_BLK_F_RO,
+ VIRTIO_BLK_F_FLUSH,
+ VIRTIO_BLK_F_BARRIER,
+ VIRTIO_BLK_F_WCE,
+ VIRTIO_F_VERSION_1,
+ VIRTIO_RING_F_INDIRECT_DESC,
+ VIRTIO_RING_F_EVENT_IDX,
+ VIRTIO_F_NOTIFY_ON_EMPTY,
+ VHOST_INVALID_FEATURE_BIT
+};
+
+static void vhost_user_blk_update_config(VirtIODevice *vdev, uint8_t *config)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+
+ memcpy(config, &s->blkcfg, sizeof(struct virtio_blk_config));
+}
+
+static void vhost_user_blk_set_config(VirtIODevice *vdev, const uint8_t *config)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ struct virtio_blk_config *blkcfg = (struct virtio_blk_config *)config;
+ int ret;
+
+ if (blkcfg->wce == s->blkcfg.wce) {
+ return;
+ }
+
+ ret = vhost_dev_set_config(&s->dev, config,
+ sizeof(struct virtio_blk_config));
+ if (ret) {
+ error_report("set device config space failed");
+ return;
+ }
+
+ s->blkcfg.wce = blkcfg->wce;
+}
+
+static void vhost_user_blk_handle_config_change(struct vhost_dev *dev)
+{
+ int ret;
+ struct virtio_blk_config blkcfg;
+ VHostUserBlk *s = VHOST_USER_BLK(dev->vdev);
+
+ ret = vhost_dev_get_config(dev, (uint8_t *)&blkcfg,
+ sizeof(struct virtio_blk_config));
+ if (ret < 0) {
+ error_report("get config space failed");
+ return;
+ }
+
+ memcpy(&s->blkcfg, &blkcfg, sizeof(struct virtio_blk_config));
+ memcpy(dev->vdev->config, &blkcfg, sizeof(struct virtio_blk_config));
+
+ virtio_notify_config(dev->vdev);
+}
+
+const VhostDevConfigOps blk_ops = {
+ .vhost_dev_config_notifier = vhost_user_blk_handle_config_change,
+};
+
+static void vhost_user_blk_start(VirtIODevice *vdev)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+ VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+ int i, ret;
+
+ if (!k->set_guest_notifiers) {
+ error_report("binding does not support guest notifiers");
+ return;
+ }
+
+ ret = vhost_dev_enable_notifiers(&s->dev, vdev);
+ if (ret < 0) {
+ error_report("Error enabling host notifiers: %d", -ret);
+ return;
+ }
+
+ ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, true);
+ if (ret < 0) {
+ error_report("Error binding guest notifier: %d", -ret);
+ goto err_host_notifiers;
+ }
+
+ s->dev.acked_features = vdev->guest_features;
+ ret = vhost_dev_start(&s->dev, vdev);
+ if (ret < 0) {
+ error_report("Error starting vhost: %d", -ret);
+ goto err_guest_notifiers;
+ }
+
+ /* guest_notifier_mask/pending not used yet, so just unmask
+ * everything here. virtio-pci will do the right thing by
+ * enabling/disabling irqfd.
+ */
+ for (i = 0; i < s->dev.nvqs; i++) {
+ vhost_virtqueue_mask(&s->dev, vdev, i, false);
+ }
+
+ return;
+
+err_guest_notifiers:
+ k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
+err_host_notifiers:
+ vhost_dev_disable_notifiers(&s->dev, vdev);
+}
+
+static void vhost_user_blk_stop(VirtIODevice *vdev)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
+ VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
+ int ret;
+
+ if (!k->set_guest_notifiers) {
+ return;
+ }
+
+ vhost_dev_stop(&s->dev, vdev);
+
+ ret = k->set_guest_notifiers(qbus->parent, s->dev.nvqs, false);
+ if (ret < 0) {
+ error_report("vhost guest notifier cleanup failed: %d", ret);
+ return;
+ }
+
+ vhost_dev_disable_notifiers(&s->dev, vdev);
+}
+
+static void vhost_user_blk_set_status(VirtIODevice *vdev, uint8_t status)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ bool should_start = status & VIRTIO_CONFIG_S_DRIVER_OK;
+
+ if (!vdev->vm_running) {
+ should_start = false;
+ }
+
+ if (s->dev.started == should_start) {
+ return;
+ }
+
+ if (should_start) {
+ vhost_user_blk_start(vdev);
+ } else {
+ vhost_user_blk_stop(vdev);
+ }
+
+}
+
+static uint64_t vhost_user_blk_get_features(VirtIODevice *vdev,
+ uint64_t features,
+ Error **errp)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ uint64_t get_features;
+
+ /* Turn on pre-defined features */
+ features |= s->host_features;
+
+ get_features = vhost_get_features(&s->dev, user_feature_bits, features);
+
+ return get_features;
+}
+
+static void vhost_user_blk_handle_output(VirtIODevice *vdev, VirtQueue *vq)
+{
+
+}
+
+static void vhost_user_blk_device_realize(DeviceState *dev, Error **errp)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+ VHostUserBlk *s = VHOST_USER_BLK(vdev);
+ int i, ret;
+
+ if (!s->chardev.chr) {
+ error_setg(errp, "vhost-user-blk: chardev is mandatory");
+ return;
+ }
+
+ if (!s->num_queues || s->num_queues > VIRTIO_QUEUE_MAX) {
+ error_setg(errp, "vhost-user-blk: invalid number of IO queues");
+ return;
+ }
+
+ if (!s->queue_size) {
+ error_setg(errp, "vhost-user-blk: queue size must be non-zero");
+ return;
+ }
+
+ virtio_init(vdev, "virtio-blk", VIRTIO_ID_BLOCK,
+ sizeof(struct virtio_blk_config));
+
+ for (i = 0; i < s->num_queues; i++) {
+ virtio_add_queue(vdev, s->queue_size,
+ vhost_user_blk_handle_output);
+ }
+
+ s->dev.nvqs = s->num_queues;
+ s->dev.vqs = g_new(struct vhost_virtqueue, s->dev.nvqs);
+ s->dev.vq_index = 0;
+ s->dev.backend_features = 0;
+
+ ret = vhost_dev_init(&s->dev, &s->chardev, VHOST_BACKEND_TYPE_USER, 0);
+ if (ret < 0) {
+ error_setg(errp, "vhost-user-blk: vhost initialization failed: %s",
+ strerror(-ret));
+ goto virtio_err;
+ }
+
+ ret = vhost_dev_get_config(&s->dev, (uint8_t *)&s->blkcfg,
+ sizeof(struct virtio_blk_config));
+ if (ret < 0) {
+ error_setg(errp, "vhost-user-blk: get block config failed");
+ goto vhost_err;
+ }
+
+ if (s->blkcfg.num_queues != s->num_queues) {
+ s->blkcfg.num_queues = s->num_queues;
+ }
+
+ vhost_dev_set_config_notifier(&s->dev, &blk_ops);
+
+ return;
+
+vhost_err:
+ vhost_dev_cleanup(&s->dev);
+virtio_err:
+ g_free(s->dev.vqs);
+ virtio_cleanup(vdev);
+}
+
+static void vhost_user_blk_device_unrealize(DeviceState *dev, Error **errp)
+{
+ VirtIODevice *vdev = VIRTIO_DEVICE(dev);
+ VHostUserBlk *s = VHOST_USER_BLK(dev);
+
+ vhost_user_blk_set_status(vdev, 0);
+ vhost_dev_cleanup(&s->dev);
+ g_free(s->dev.vqs);
+ virtio_cleanup(vdev);
+}
+
+static void vhost_user_blk_instance_init(Object *obj)
+{
+ VHostUserBlk *s = VHOST_USER_BLK(obj);
+
+ device_add_bootindex_property(obj, &s->bootindex, "bootindex",
+ "/disk@0,0", DEVICE(obj), NULL);
+}
+
+static const VMStateDescription vmstate_vhost_user_blk = {
+ .name = "vhost-user-blk",
+ .minimum_version_id = 1,
+ .version_id = 1,
+ .fields = (VMStateField[]) {
+ VMSTATE_VIRTIO_DEVICE,
+ VMSTATE_END_OF_LIST()
+ },
+};
+
+static Property vhost_user_blk_properties[] = {
+ DEFINE_PROP_CHR("chardev", VHostUserBlk, chardev),
+ DEFINE_PROP_UINT16("num_queues", VHostUserBlk, num_queues, 1),
+ DEFINE_PROP_UINT32("queue_size", VHostUserBlk, queue_size, 128),
+ DEFINE_PROP_BIT64("f_size_max", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_SIZE_MAX, true),
+ DEFINE_PROP_BIT64("f_sizemax", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_SIZE_MAX, true),
+ DEFINE_PROP_BIT64("f_segmax", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_SEG_MAX, true),
+ DEFINE_PROP_BIT64("f_geometry", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_GEOMETRY, true),
+ DEFINE_PROP_BIT64("f_readonly", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_RO, false),
+ DEFINE_PROP_BIT64("f_blocksize", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_BLK_SIZE, true),
+ DEFINE_PROP_BIT64("f_topology", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_TOPOLOGY, true),
+ DEFINE_PROP_BIT64("f_multiqueue", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_MQ, true),
+ DEFINE_PROP_BIT64("f_flush", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_FLUSH, true),
+ DEFINE_PROP_BIT64("f_barrier", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_BARRIER, false),
+ DEFINE_PROP_BIT64("f_scsi", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_SCSI, false),
+ DEFINE_PROP_BIT64("f_wce", VHostUserBlk, host_features,
+ VIRTIO_BLK_F_WCE, false),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void vhost_user_blk_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+ VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
+
+ dc->props = vhost_user_blk_properties;
+ dc->vmsd = &vmstate_vhost_user_blk;
+ set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+ vdc->realize = vhost_user_blk_device_realize;
+ vdc->unrealize = vhost_user_blk_device_unrealize;
+ vdc->get_config = vhost_user_blk_update_config;
+ vdc->set_config = vhost_user_blk_set_config;
+ vdc->get_features = vhost_user_blk_get_features;
+ vdc->set_status = vhost_user_blk_set_status;
+}
+
+static const TypeInfo vhost_user_blk_info = {
+ .name = TYPE_VHOST_USER_BLK,
+ .parent = TYPE_VIRTIO_DEVICE,
+ .instance_size = sizeof(VHostUserBlk),
+ .instance_init = vhost_user_blk_instance_init,
+ .class_init = vhost_user_blk_class_init,
+};
+
+static void virtio_register_types(void)
+{
+ type_register_static(&vhost_user_blk_info);
+}
+
+type_init(virtio_register_types)
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index 8b0d6b6..be9a992 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -2012,6 +2012,58 @@ static const TypeInfo virtio_blk_pci_info = {
.class_init = virtio_blk_pci_class_init,
};
+#ifdef CONFIG_VHOST_USER_BLK
+/* vhost-user-blk */
+
+static Property vhost_user_blk_pci_properties[] = {
+ DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0),
+ DEFINE_PROP_UINT32("vectors", VirtIOPCIProxy, nvectors, 2),
+ DEFINE_PROP_END_OF_LIST(),
+};
+
+static void vhost_user_blk_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
+{
+ VHostUserBlkPCI *dev = VHOST_USER_BLK_PCI(vpci_dev);
+ DeviceState *vdev = DEVICE(&dev->vdev);
+
+ qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus));
+ object_property_set_bool(OBJECT(vdev), true, "realized", errp);
+}
+
+static void vhost_user_blk_pci_class_init(ObjectClass *klass, void *data)
+{
+ DeviceClass *dc = DEVICE_CLASS(klass);
+ VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass);
+ PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass);
+
+ set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+ dc->props = vhost_user_blk_pci_properties;
+ k->realize = vhost_user_blk_pci_realize;
+ pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET;
+ pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_BLOCK;
+ pcidev_k->revision = VIRTIO_PCI_ABI_VERSION;
+ pcidev_k->class_id = PCI_CLASS_STORAGE_SCSI;
+}
+
+static void vhost_user_blk_pci_instance_init(Object *obj)
+{
+ VHostUserBlkPCI *dev = VHOST_USER_BLK_PCI(obj);
+
+ virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev),
+ TYPE_VHOST_USER_BLK);
+ object_property_add_alias(obj, "bootindex", OBJECT(&dev->vdev),
+ "bootindex", &error_abort);
+}
+
+static const TypeInfo vhost_user_blk_pci_info = {
+ .name = TYPE_VHOST_USER_BLK_PCI,
+ .parent = TYPE_VIRTIO_PCI,
+ .instance_size = sizeof(VHostUserBlkPCI),
+ .instance_init = vhost_user_blk_pci_instance_init,
+ .class_init = vhost_user_blk_pci_class_init,
+};
+#endif
+
/* virtio-scsi-pci */
static Property virtio_scsi_pci_properties[] = {
@@ -2658,6 +2710,9 @@ static void virtio_pci_register_types(void)
type_register_static(&virtio_9p_pci_info);
#endif
type_register_static(&virtio_blk_pci_info);
+#ifdef CONFIG_VHOST_USER_BLK
+ type_register_static(&vhost_user_blk_pci_info);
+#endif
type_register_static(&virtio_scsi_pci_info);
type_register_static(&virtio_balloon_pci_info);
type_register_static(&virtio_serial_pci_info);
diff --git a/hw/virtio/virtio-pci.h b/hw/virtio/virtio-pci.h
index 69f5959..19a0d01 100644
--- a/hw/virtio/virtio-pci.h
+++ b/hw/virtio/virtio-pci.h
@@ -27,6 +27,9 @@
#include "hw/virtio/virtio-gpu.h"
#include "hw/virtio/virtio-crypto.h"
#include "hw/virtio/vhost-user-scsi.h"
+#ifdef CONFIG_VHOST_USER_BLK
+#include "hw/virtio/vhost-user-blk.h"
+#endif
#ifdef CONFIG_VIRTFS
#include "hw/9pfs/virtio-9p.h"
@@ -46,6 +49,7 @@ typedef struct VirtIOSerialPCI VirtIOSerialPCI;
typedef struct VirtIONetPCI VirtIONetPCI;
typedef struct VHostSCSIPCI VHostSCSIPCI;
typedef struct VHostUserSCSIPCI VHostUserSCSIPCI;
+typedef struct VHostUserBlkPCI VHostUserBlkPCI;
typedef struct VirtIORngPCI VirtIORngPCI;
typedef struct VirtIOInputPCI VirtIOInputPCI;
typedef struct VirtIOInputHIDPCI VirtIOInputHIDPCI;
@@ -241,6 +245,20 @@ struct VHostUserSCSIPCI {
VHostUserSCSI vdev;
};
+#ifdef CONFIG_VHOST_USER_BLK
+/*
+ * vhost-user-blk-pci: This extends VirtioPCIProxy.
+ */
+#define TYPE_VHOST_USER_BLK_PCI "vhost-user-blk-pci"
+#define VHOST_USER_BLK_PCI(obj) \
+ OBJECT_CHECK(VHostUserBlkPCI, (obj), TYPE_VHOST_USER_BLK_PCI)
+
+struct VHostUserBlkPCI {
+ VirtIOPCIProxy parent_obj;
+ VHostUserBlk vdev;
+};
+#endif
+
/*
* virtio-blk-pci: This extends VirtioPCIProxy.
*/
diff --git a/include/hw/virtio/vhost-user-blk.h b/include/hw/virtio/vhost-user-blk.h
new file mode 100644
index 0000000..77d20f0
--- /dev/null
+++ b/include/hw/virtio/vhost-user-blk.h
@@ -0,0 +1,40 @@
+/*
+ * vhost-user-blk host device
+ * Copyright IBM, Corp. 2011
+ * Copyright(C) 2017 Intel Corporation.
+ *
+ * Authors:
+ * Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
+ * Changpeng Liu <changpeng.liu@intel.com>
+ *
+ * This work is licensed under the terms of the GNU LGPL, version 2 or later.
+ * See the COPYING.LIB file in the top-level directory.
+ *
+ */
+
+#ifndef VHOST_USER_BLK_H
+#define VHOST_USER_BLK_H
+
+#include "standard-headers/linux/virtio_blk.h"
+#include "qemu-common.h"
+#include "hw/qdev.h"
+#include "hw/block/block.h"
+#include "chardev/char-fe.h"
+#include "hw/virtio/vhost.h"
+
+#define TYPE_VHOST_USER_BLK "vhost-user-blk"
+#define VHOST_USER_BLK(obj) \
+ OBJECT_CHECK(VHostUserBlk, (obj), TYPE_VHOST_USER_BLK)
+
+typedef struct VHostUserBlk {
+ VirtIODevice parent_obj;
+ CharBackend chardev;
+ int32_t bootindex;
+ uint64_t host_features;
+ struct virtio_blk_config blkcfg;
+ uint16_t num_queues;
+ uint32_t queue_size;
+ struct vhost_dev dev;
+} VHostUserBlk;
+
+#endif
--
1.9.3
^ permalink raw reply related [flat|nested] 6+ messages in thread* [Qemu-devel] [PATCH v3 3/4] contrib/libvhost-user: enable virtio config space messages
2017-09-12 7:56 [Qemu-devel] [PATCH v3 0/4] *** Introduce a new vhost-user-blk host device to Qemu *** Changpeng Liu
` (2 preceding siblings ...)
2017-09-12 7:56 ` [Qemu-devel] [PATCH v3 2/4] vhost-user-blk: introduce a new vhost-user-blk host device Changpeng Liu
@ 2017-09-12 7:56 ` Changpeng Liu
2017-09-12 7:56 ` [Qemu-devel] [PATCH v3 4/4] contrib/vhost-user-blk: introduce a vhost-user-blk sample application Changpeng Liu
4 siblings, 0 replies; 6+ messages in thread
From: Changpeng Liu @ 2017-09-12 7:56 UTC (permalink / raw)
To: changpeng.liu, qemu-devel
Cc: stefanha, pbonzini, mst, marcandre.lureau, felipe, james.r.harris
Enable VHOST_USER_GET_CONFIG/VHOST_USER_SET_CONFIG/VHOST_USER_SET_CONFIG_FD
messages in libvhost-user library, users can implement their own I/O target
based on the library. This enable the virtio config space delivered between
Qemu host device and the I/O target, also event notifier is added in case
of virtio config space changed.
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
---
contrib/libvhost-user/libvhost-user.c | 74 +++++++++++++++++++++++++++++++++++
contrib/libvhost-user/libvhost-user.h | 15 +++++++
2 files changed, 89 insertions(+)
diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c
index d27d630..ff37d6b 100644
--- a/contrib/libvhost-user/libvhost-user.c
+++ b/contrib/libvhost-user/libvhost-user.c
@@ -63,6 +63,9 @@ vu_request_to_string(int req)
REQ(VHOST_USER_SET_VRING_ENABLE),
REQ(VHOST_USER_SEND_RARP),
REQ(VHOST_USER_INPUT_GET_CONFIG),
+ REQ(VHOST_USER_GET_CONFIG),
+ REQ(VHOST_USER_SET_CONFIG),
+ REQ(VHOST_USER_SET_CONFIG_FD),
REQ(VHOST_USER_MAX),
};
#undef REQ
@@ -757,6 +760,66 @@ vu_set_vring_enable_exec(VuDev *dev, VhostUserMsg *vmsg)
}
static bool
+vu_get_config(VuDev *dev, VhostUserMsg *vmsg)
+{
+ int ret = -1;
+
+ if (dev->iface->get_config) {
+ ret = dev->iface->get_config(dev, vmsg->payload.config, vmsg->size);
+ }
+
+ if (ret) {
+ /* resize to zero to indicate an error to master */
+ vmsg->size = 0;
+ }
+
+ return true;
+}
+
+static bool
+vu_set_config(VuDev *dev, VhostUserMsg *vmsg)
+{
+ int ret = -1;
+ bool reply_supported = !!(dev->protocol_features &
+ (1ULL << VHOST_USER_PROTOCOL_F_REPLY_ACK));
+
+ if (dev->iface->set_config) {
+ ret = dev->iface->set_config(dev, vmsg->payload.config, vmsg->size);
+ }
+
+ vmsg->size = sizeof(vmsg->payload.u64);
+ if (!ret) {
+ vmsg->payload.u64 = 0;
+ } else {
+ /* indicate an error in case reply supported */
+ vmsg->payload.u64 = 1;
+ }
+
+ if (reply_supported) {
+ return true;
+ }
+
+ return false;
+}
+
+static bool
+vu_set_config_fd(VuDev *dev, VhostUserMsg *vmsg)
+{
+ if (vmsg->fd_num != 1) {
+ vu_panic(dev, "Invalid config_fd message");
+ return false;
+ }
+
+ if (dev->config_fd != -1) {
+ close(dev->config_fd);
+ }
+ dev->config_fd = vmsg->fds[0];
+ DPRINT("Got config_fd: %d\n", vmsg->fds[0]);
+
+ return false;
+}
+
+static bool
vu_process_message(VuDev *dev, VhostUserMsg *vmsg)
{
int do_reply = 0;
@@ -819,6 +882,12 @@ vu_process_message(VuDev *dev, VhostUserMsg *vmsg)
return vu_get_queue_num_exec(dev, vmsg);
case VHOST_USER_SET_VRING_ENABLE:
return vu_set_vring_enable_exec(dev, vmsg);
+ case VHOST_USER_GET_CONFIG:
+ return vu_get_config(dev, vmsg);
+ case VHOST_USER_SET_CONFIG:
+ return vu_set_config(dev, vmsg);
+ case VHOST_USER_SET_CONFIG_FD:
+ return vu_set_config_fd(dev, vmsg);
case VHOST_USER_NONE:
break;
default:
@@ -893,6 +962,10 @@ vu_deinit(VuDev *dev)
vu_close_log(dev);
+ if (dev->config_fd != -1) {
+ close(dev->config_fd);
+ }
+
if (dev->sock != -1) {
close(dev->sock);
}
@@ -922,6 +995,7 @@ vu_init(VuDev *dev,
dev->remove_watch = remove_watch;
dev->iface = iface;
dev->log_call_fd = -1;
+ dev->config_fd = -1;
for (i = 0; i < VHOST_MAX_NR_VIRTQUEUE; i++) {
dev->vq[i] = (VuVirtq) {
.call_fd = -1, .kick_fd = -1, .err_fd = -1,
diff --git a/contrib/libvhost-user/libvhost-user.h b/contrib/libvhost-user/libvhost-user.h
index 4021f11..15167b8 100644
--- a/contrib/libvhost-user/libvhost-user.h
+++ b/contrib/libvhost-user/libvhost-user.h
@@ -30,10 +30,13 @@
#define VHOST_MEMORY_MAX_NREGIONS 8
+#define VHOST_USER_MAX_CONFIG_SIZE 256
+
enum VhostUserProtocolFeature {
VHOST_USER_PROTOCOL_F_MQ = 0,
VHOST_USER_PROTOCOL_F_LOG_SHMFD = 1,
VHOST_USER_PROTOCOL_F_RARP = 2,
+ VHOST_USER_PROTOCOL_F_REPLY_ACK = 3,
VHOST_USER_PROTOCOL_F_MAX
};
@@ -62,6 +65,9 @@ typedef enum VhostUserRequest {
VHOST_USER_SET_VRING_ENABLE = 18,
VHOST_USER_SEND_RARP = 19,
VHOST_USER_INPUT_GET_CONFIG = 20,
+ VHOST_USER_GET_CONFIG = 24,
+ VHOST_USER_SET_CONFIG = 25,
+ VHOST_USER_SET_CONFIG_FD = 26,
VHOST_USER_MAX
} VhostUserRequest;
@@ -105,6 +111,7 @@ typedef struct VhostUserMsg {
struct vhost_vring_addr addr;
VhostUserMemory memory;
VhostUserLog log;
+ uint8_t config[VHOST_USER_MAX_CONFIG_SIZE];
} payload;
int fds[VHOST_MEMORY_MAX_NREGIONS];
@@ -133,6 +140,9 @@ typedef int (*vu_process_msg_cb) (VuDev *dev, VhostUserMsg *vmsg,
int *do_reply);
typedef void (*vu_queue_set_started_cb) (VuDev *dev, int qidx, bool started);
typedef bool (*vu_queue_is_processed_in_order_cb) (VuDev *dev, int qidx);
+typedef int (*vu_get_config_cb) (VuDev *dev, uint8_t *config, size_t len);
+typedef int (*vu_set_config_cb) (VuDev *dev, const uint8_t *config,
+ size_t len);
typedef struct VuDevIface {
/* called by VHOST_USER_GET_FEATURES to get the features bitmask */
@@ -155,6 +165,10 @@ typedef struct VuDevIface {
* on unmanaged exit/crash.
*/
vu_queue_is_processed_in_order_cb queue_is_processed_in_order;
+ /* get the config space of the device */
+ vu_get_config_cb get_config;
+ /* set the config space of the device */
+ vu_set_config_cb set_config;
} VuDevIface;
typedef void (*vu_queue_handler_cb) (VuDev *dev, int qidx);
@@ -219,6 +233,7 @@ struct VuDev {
VuDevRegion regions[VHOST_MEMORY_MAX_NREGIONS];
VuVirtq vq[VHOST_MAX_NR_VIRTQUEUE];
int log_call_fd;
+ int config_fd;
uint64_t log_size;
uint8_t *log_table;
uint64_t features;
--
1.9.3
^ permalink raw reply related [flat|nested] 6+ messages in thread* [Qemu-devel] [PATCH v3 4/4] contrib/vhost-user-blk: introduce a vhost-user-blk sample application
2017-09-12 7:56 [Qemu-devel] [PATCH v3 0/4] *** Introduce a new vhost-user-blk host device to Qemu *** Changpeng Liu
` (3 preceding siblings ...)
2017-09-12 7:56 ` [Qemu-devel] [PATCH v3 3/4] contrib/libvhost-user: enable virtio config space messages Changpeng Liu
@ 2017-09-12 7:56 ` Changpeng Liu
4 siblings, 0 replies; 6+ messages in thread
From: Changpeng Liu @ 2017-09-12 7:56 UTC (permalink / raw)
To: changpeng.liu, qemu-devel
Cc: stefanha, pbonzini, mst, marcandre.lureau, felipe, james.r.harris
This commit introcudes a vhost-user-blk backend device, it uses UNIX
domain socket to communicate with Qemu. The vhost-user-blk sample
application should be used with Qemu vhost-user-blk-pci device.
To use it, complie with:
make vhost-user-blk
and start like this:
vhost-user-blk -b /dev/sdb -s /path/vhost.socket
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
---
.gitignore | 1 +
Makefile | 3 +
Makefile.objs | 2 +
contrib/vhost-user-blk/Makefile.objs | 1 +
contrib/vhost-user-blk/vhost-user-blk.c | 735 ++++++++++++++++++++++++++++++++
5 files changed, 742 insertions(+)
create mode 100644 contrib/vhost-user-blk/Makefile.objs
create mode 100644 contrib/vhost-user-blk/vhost-user-blk.c
diff --git a/.gitignore b/.gitignore
index cf65316..dbe5c13 100644
--- a/.gitignore
+++ b/.gitignore
@@ -51,6 +51,7 @@
/module_block.h
/vscclient
/vhost-user-scsi
+/vhost-user-blk
/fsdev/virtfs-proxy-helper
*.[1-9]
*.a
diff --git a/Makefile b/Makefile
index 337a1f6..91782b0 100644
--- a/Makefile
+++ b/Makefile
@@ -270,6 +270,7 @@ dummy := $(call unnest-vars,, \
ivshmem-server-obj-y \
libvhost-user-obj-y \
vhost-user-scsi-obj-y \
+ vhost-user-blk-obj-y \
qga-vss-dll-obj-y \
block-obj-y \
block-obj-m \
@@ -485,6 +486,8 @@ ivshmem-server$(EXESUF): $(ivshmem-server-obj-y) $(COMMON_LDADDS)
endif
vhost-user-scsi$(EXESUF): $(vhost-user-scsi-obj-y)
$(call LINK, $^)
+vhost-user-blk$(EXESUF): $(vhost-user-blk-obj-y)
+ $(call LINK, $^)
module_block.h: $(SRC_PATH)/scripts/modules/module_block.py config-host.mak
$(call quiet-command,$(PYTHON) $< $@ \
diff --git a/Makefile.objs b/Makefile.objs
index 24a4ea0..6b81548 100644
--- a/Makefile.objs
+++ b/Makefile.objs
@@ -114,6 +114,8 @@ vhost-user-scsi.o-cflags := $(LIBISCSI_CFLAGS)
vhost-user-scsi.o-libs := $(LIBISCSI_LIBS)
vhost-user-scsi-obj-y = contrib/vhost-user-scsi/
vhost-user-scsi-obj-y += contrib/libvhost-user/libvhost-user.o
+vhost-user-blk-obj-y = contrib/vhost-user-blk/
+vhost-user-blk-obj-y += contrib/libvhost-user/libvhost-user.o
######################################################################
trace-events-subdirs =
diff --git a/contrib/vhost-user-blk/Makefile.objs b/contrib/vhost-user-blk/Makefile.objs
new file mode 100644
index 0000000..72e2cdc
--- /dev/null
+++ b/contrib/vhost-user-blk/Makefile.objs
@@ -0,0 +1 @@
+vhost-user-blk-obj-y = vhost-user-blk.o
diff --git a/contrib/vhost-user-blk/vhost-user-blk.c b/contrib/vhost-user-blk/vhost-user-blk.c
new file mode 100644
index 0000000..9b90164
--- /dev/null
+++ b/contrib/vhost-user-blk/vhost-user-blk.c
@@ -0,0 +1,735 @@
+/*
+ * vhost-user-blk sample application
+ *
+ * Copyright IBM, Corp. 2007
+ * Copyright (c) 2016 Nutanix Inc. All rights reserved.
+ * Copyright (c) 2017 Intel Corporation. All rights reserved.
+ *
+ * Author:
+ * Anthony Liguori <aliguori@us.ibm.com>
+ * Felipe Franciosi <felipe@nutanix.com>
+ * Changpeng Liu <changpeng.liu@intel.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 only.
+ * See the COPYING file in the top-level directory.
+ */
+
+#include "qemu/osdep.h"
+#include "hw/virtio/virtio-blk.h"
+#include "contrib/libvhost-user/libvhost-user.h"
+
+#include <glib.h>
+
+/* Small compat shim from glib 2.32 */
+#ifndef G_SOURCE_CONTINUE
+#define G_SOURCE_CONTINUE TRUE
+#endif
+#ifndef G_SOURCE_REMOVE
+#define G_SOURCE_REMOVE FALSE
+#endif
+
+/* And this is the final byte of request*/
+#define VIRTIO_BLK_S_OK 0
+#define VIRTIO_BLK_S_IOERR 1
+#define VIRTIO_BLK_S_UNSUPP 2
+
+typedef struct vhost_blk_dev {
+ VuDev vu_dev;
+ int server_sock;
+ int blk_fd;
+ struct virtio_blk_config blkcfg;
+ char *blk_name;
+ GMainLoop *loop;
+ GTree *fdmap; /* fd -> gsource context id */
+} vhost_blk_dev_t;
+
+typedef struct vhost_blk_request {
+ VuVirtqElement *elem;
+ int64_t sector_num;
+ size_t size;
+ struct virtio_blk_inhdr *in;
+ struct virtio_blk_outhdr *out;
+ vhost_blk_dev_t *vdev_blk;
+ struct VuVirtq *vq;
+} vhost_blk_request_t;
+
+/** refer util/iov.c **/
+static size_t vu_blk_iov_size(const struct iovec *iov,
+ const unsigned int iov_cnt)
+{
+ size_t len;
+ unsigned int i;
+
+ len = 0;
+ for (i = 0; i < iov_cnt; i++) {
+ len += iov[i].iov_len;
+ }
+ return len;
+}
+
+/** glib event loop integration for libvhost-user and misc callbacks **/
+
+QEMU_BUILD_BUG_ON((int)G_IO_IN != (int)VU_WATCH_IN);
+QEMU_BUILD_BUG_ON((int)G_IO_OUT != (int)VU_WATCH_OUT);
+QEMU_BUILD_BUG_ON((int)G_IO_PRI != (int)VU_WATCH_PRI);
+QEMU_BUILD_BUG_ON((int)G_IO_ERR != (int)VU_WATCH_ERR);
+QEMU_BUILD_BUG_ON((int)G_IO_HUP != (int)VU_WATCH_HUP);
+
+typedef struct vu_blk_gsrc {
+ GSource parent;
+ vhost_blk_dev_t *vdev_blk;
+ GPollFD gfd;
+ vu_watch_cb vu_cb;
+} vu_blk_gsrc_t;
+
+static gint vu_blk_fdmap_compare(gconstpointer a, gconstpointer b)
+{
+ return (b > a) - (b < a);
+}
+
+static gboolean vu_blk_gsrc_prepare(GSource *src, gint *timeout)
+{
+ assert(timeout);
+
+ *timeout = -1;
+ return FALSE;
+}
+
+static gboolean vu_blk_gsrc_check(GSource *src)
+{
+ vu_blk_gsrc_t *vu_blk_src = (vu_blk_gsrc_t *)src;
+
+ assert(vu_blk_src);
+
+ return vu_blk_src->gfd.revents & vu_blk_src->gfd.events;
+}
+
+static gboolean vu_blk_gsrc_dispatch(GSource *src,
+ GSourceFunc cb, gpointer data)
+{
+ vhost_blk_dev_t *vdev_blk;
+ vu_blk_gsrc_t *vu_blk_src = (vu_blk_gsrc_t *)src;
+
+ assert(vu_blk_src);
+ assert(!(vu_blk_src->vu_cb && cb));
+
+ vdev_blk = vu_blk_src->vdev_blk;
+
+ assert(vdev_blk);
+
+ if (cb) {
+ return cb(data);
+ }
+ if (vu_blk_src->vu_cb) {
+ vu_blk_src->vu_cb(&vdev_blk->vu_dev, vu_blk_src->gfd.revents, data);
+ }
+ return G_SOURCE_CONTINUE;
+}
+
+static GSourceFuncs vu_blk_gsrc_funcs = {
+ vu_blk_gsrc_prepare,
+ vu_blk_gsrc_check,
+ vu_blk_gsrc_dispatch,
+ NULL
+};
+
+static int vu_blk_gsrc_new(vhost_blk_dev_t *vdev_blk, int fd,
+ GIOCondition cond, vu_watch_cb vu_cb,
+ GSourceFunc gsrc_cb, gpointer data)
+{
+ GSource *vu_blk_gsrc;
+ vu_blk_gsrc_t *vu_blk_src;
+ guint id;
+
+ assert(vdev_blk);
+ assert(fd >= 0);
+ assert(vu_cb || gsrc_cb);
+ assert(!(vu_cb && gsrc_cb));
+
+ vu_blk_gsrc = g_source_new(&vu_blk_gsrc_funcs, sizeof(vu_blk_gsrc_t));
+ if (!vu_blk_gsrc) {
+ fprintf(stderr, "Error creating GSource for new watch\n");
+ return -1;
+ }
+ vu_blk_src = (vu_blk_gsrc_t *)vu_blk_gsrc;
+
+ vu_blk_src->vdev_blk = vdev_blk;
+ vu_blk_src->gfd.fd = fd;
+ vu_blk_src->gfd.events = cond;
+ vu_blk_src->vu_cb = vu_cb;
+
+ g_source_add_poll(vu_blk_gsrc, &vu_blk_src->gfd);
+ g_source_set_callback(vu_blk_gsrc, gsrc_cb, data, NULL);
+ id = g_source_attach(vu_blk_gsrc, NULL);
+ assert(id);
+ g_source_unref(vu_blk_gsrc);
+
+ g_tree_insert(vdev_blk->fdmap, (gpointer)(uintptr_t)fd,
+ (gpointer)(uintptr_t)id);
+
+ return 0;
+}
+
+static void vu_blk_panic_cb(VuDev *vu_dev, const char *buf)
+{
+ vhost_blk_dev_t *vdev_blk;
+
+ assert(vu_dev);
+
+ vdev_blk = container_of(vu_dev, vhost_blk_dev_t, vu_dev);
+
+ if (buf) {
+ fprintf(stderr, "vu_blk_panic_cb: %s\n", buf);
+ }
+
+ if (vdev_blk) {
+ assert(vdev_blk->loop);
+ g_main_loop_quit(vdev_blk->loop);
+ }
+}
+
+static void vu_blk_add_watch_cb(VuDev *vu_dev, int fd, int vu_evt,
+ vu_watch_cb cb, void *pvt) {
+ vhost_blk_dev_t *vdev_blk;
+ guint id;
+
+ assert(vu_dev);
+ assert(fd >= 0);
+ assert(cb);
+
+ vdev_blk = container_of(vu_dev, vhost_blk_dev_t, vu_dev);
+ if (!vdev_blk) {
+ vu_blk_panic_cb(vu_dev, NULL);
+ return;
+ }
+
+ id = (guint)(uintptr_t)g_tree_lookup(vdev_blk->fdmap,
+ (gpointer)(uintptr_t)fd);
+ if (id) {
+ GSource *vu_blk_src = g_main_context_find_source_by_id(NULL, id);
+ assert(vu_blk_src);
+ g_source_destroy(vu_blk_src);
+ (void)g_tree_remove(vdev_blk->fdmap, (gpointer)(uintptr_t)fd);
+ }
+
+ if (vu_blk_gsrc_new(vdev_blk, fd, vu_evt, cb, NULL, pvt)) {
+ vu_blk_panic_cb(vu_dev, NULL);
+ }
+}
+
+static void vu_blk_del_watch_cb(VuDev *vu_dev, int fd)
+{
+ vhost_blk_dev_t *vdev_blk;
+ guint id;
+
+ assert(vu_dev);
+ assert(fd >= 0);
+
+ vdev_blk = container_of(vu_dev, vhost_blk_dev_t, vu_dev);
+ if (!vdev_blk) {
+ vu_blk_panic_cb(vu_dev, NULL);
+ return;
+ }
+
+ id = (guint)(uintptr_t)g_tree_lookup(vdev_blk->fdmap,
+ (gpointer)(uintptr_t)fd);
+ if (id) {
+ GSource *vu_blk_src = g_main_context_find_source_by_id(NULL, id);
+ assert(vu_blk_src);
+ g_source_destroy(vu_blk_src);
+ (void)g_tree_remove(vdev_blk->fdmap, (gpointer)(uintptr_t)fd);
+ }
+}
+
+static void vu_blk_req_complete(vhost_blk_request_t *req)
+{
+ VuDev *vu_dev = &req->vdev_blk->vu_dev;
+
+ /* IO size with 1 extra status byte */
+ vu_queue_push(vu_dev, req->vq, req->elem,
+ req->size + 1);
+ vu_queue_notify(vu_dev, req->vq);
+
+ if (req->elem) {
+ free(req->elem);
+ }
+ if (req) {
+ free(req);
+ }
+}
+
+static int vu_blk_open(const char *file_name)
+{
+ int fd;
+
+ fd = open(file_name, O_RDWR | O_DIRECT);
+ if (fd < 0) {
+ fprintf(stderr, "Cannot open file %s, %s\n", file_name,
+ strerror(errno));
+ return -1;
+ }
+
+ return fd;
+}
+
+static void vu_blk_close(int fd)
+{
+ if (fd >= 0) {
+ close(fd);
+ }
+}
+
+static ssize_t
+vu_blk_readv(vhost_blk_request_t *req, struct iovec *iov, uint32_t iovcnt)
+{
+ vhost_blk_dev_t *vdev_blk = req->vdev_blk;
+ ssize_t rc;
+
+ if (!iovcnt) {
+ fprintf(stderr, "Invalid Read IOV count\n");
+ return -1;
+ }
+
+ req->size = vu_blk_iov_size(iov, iovcnt);
+ rc = preadv(vdev_blk->blk_fd, iov, iovcnt, req->sector_num * 512);
+ if (rc < 0) {
+ fprintf(stderr, "Block %s, Sector %"PRIu64", Size %lu Read Failed\n",
+ vdev_blk->blk_name, req->sector_num, req->size);
+ return -1;
+ }
+
+ return rc;
+}
+
+static ssize_t
+vu_blk_writev(vhost_blk_request_t *req, struct iovec *iov, uint32_t iovcnt)
+{
+ vhost_blk_dev_t *vdev_blk = req->vdev_blk;
+ ssize_t rc;
+
+ if (!iovcnt) {
+ fprintf(stderr, "Invalid Write IOV count\n");
+ return -1;
+ }
+
+ req->size = vu_blk_iov_size(iov, iovcnt);
+ rc = pwritev(vdev_blk->blk_fd, iov, iovcnt, req->sector_num * 512);
+ if (rc < 0) {
+ fprintf(stderr, "Block %s, Sector %"PRIu64", Size %lu Write Failed\n",
+ vdev_blk->blk_name, req->sector_num, req->size);
+ return -1;
+ }
+
+ return rc;
+}
+
+static void
+vu_blk_flush(vhost_blk_request_t *req)
+{
+ vhost_blk_dev_t *vdev_blk = req->vdev_blk;
+
+ if (vdev_blk->blk_fd) {
+ fsync(vdev_blk->blk_fd);
+ }
+}
+
+
+static int vu_virtio_blk_process_req(vhost_blk_dev_t *vdev_blk,
+ VuVirtq *vq)
+{
+ VuVirtqElement *elem;
+ uint32_t type;
+ unsigned in_num;
+ unsigned out_num;
+ vhost_blk_request_t *req;
+
+ elem = vu_queue_pop(&vdev_blk->vu_dev, vq, sizeof(VuVirtqElement));
+ if (!elem) {
+ return -1;
+ }
+
+ /* refer to hw/block/virtio_blk.c */
+ if (elem->out_num < 1 || elem->in_num < 1) {
+ fprintf(stderr, "virtio-blk request missing headers\n");
+ free(elem);
+ return -1;
+ }
+
+ req = calloc(1, sizeof(*req));
+ assert(req);
+ req->vdev_blk = vdev_blk;
+ req->vq = vq;
+ req->elem = elem;
+
+ in_num = elem->in_num;
+ out_num = elem->out_num;
+
+ /* don't support VIRTIO_F_ANY_LAYOUT and virtio 1.0 only */
+ if (elem->out_sg[0].iov_len < sizeof(struct virtio_blk_outhdr)) {
+ fprintf(stderr, "Invalid outhdr size\n");
+ goto err;
+ }
+ req->out = (struct virtio_blk_outhdr *)elem->out_sg[0].iov_base;
+ out_num--;
+
+ if (elem->in_sg[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) {
+ fprintf(stderr, "Invalid inhdr size\n");
+ goto err;
+ }
+ req->in = (struct virtio_blk_inhdr *)elem->in_sg[in_num - 1].iov_base;
+ in_num--;
+
+ type = le32_to_cpu(req->out->type);
+ switch (type & ~(VIRTIO_BLK_T_OUT | VIRTIO_BLK_T_BARRIER)) {
+ case VIRTIO_BLK_T_IN: {
+ ssize_t ret = 0;
+ bool is_write = type & VIRTIO_BLK_T_OUT;
+ req->sector_num = le64_to_cpu(req->out->sector);
+ if (is_write) {
+ ret = vu_blk_writev(req, &elem->out_sg[1], out_num);
+ } else {
+ ret = vu_blk_readv(req, &elem->in_sg[0], in_num);
+ }
+ if (ret >= 0) {
+ req->in->status = VIRTIO_BLK_S_OK;
+ } else {
+ req->in->status = VIRTIO_BLK_S_IOERR;
+ }
+ vu_blk_req_complete(req);
+ break;
+ }
+ case VIRTIO_BLK_T_FLUSH: {
+ vu_blk_flush(req);
+ req->in->status = VIRTIO_BLK_S_OK;
+ vu_blk_req_complete(req);
+ break;
+ }
+ case VIRTIO_BLK_T_GET_ID: {
+ size_t size = MIN(vu_blk_iov_size(&elem->in_sg[0], in_num),
+ VIRTIO_BLK_ID_BYTES);
+ snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk");
+ req->in->status = VIRTIO_BLK_S_OK;
+ req->size = elem->in_sg[0].iov_len;
+ vu_blk_req_complete(req);
+ break;
+ }
+ default: {
+ req->in->status = VIRTIO_BLK_S_UNSUPP;
+ vu_blk_req_complete(req);
+ break;
+ }
+ }
+
+ return 0;
+
+err:
+ free(elem);
+ free(req);
+ return -1;
+}
+
+static void vu_blk_process_vq(VuDev *vu_dev, int idx)
+{
+ vhost_blk_dev_t *vdev_blk;
+ VuVirtq *vq;
+ int ret;
+
+ if ((idx < 0) || (idx >= VHOST_MAX_NR_VIRTQUEUE)) {
+ fprintf(stderr, "VQ Index out of range: %d\n", idx);
+ vu_blk_panic_cb(vu_dev, NULL);
+ return;
+ }
+
+ vdev_blk = container_of(vu_dev, vhost_blk_dev_t, vu_dev);
+ assert(vdev_blk);
+
+ vq = vu_get_queue(vu_dev, idx);
+ assert(vq);
+
+ while (1) {
+ ret = vu_virtio_blk_process_req(vdev_blk, vq);
+ if (ret) {
+ break;
+ }
+ }
+}
+
+static void vu_blk_queue_set_started(VuDev *vu_dev, int idx, bool started)
+{
+ VuVirtq *vq;
+
+ assert(vu_dev);
+
+ if ((idx < 0) || (idx >= VHOST_MAX_NR_VIRTQUEUE)) {
+ fprintf(stderr, "VQ Index out of range: %d\n", idx);
+ vu_blk_panic_cb(vu_dev, NULL);
+ return;
+ }
+
+ vq = vu_get_queue(vu_dev, idx);
+ vu_set_queue_handler(vu_dev, vq, started ? vu_blk_process_vq : NULL);
+}
+
+static uint64_t
+vu_blk_get_features(VuDev *dev)
+{
+ return 1ull << VIRTIO_BLK_F_SIZE_MAX |
+ 1ull << VIRTIO_BLK_F_SEG_MAX |
+ 1ull << VIRTIO_BLK_F_TOPOLOGY |
+ 1ull << VIRTIO_BLK_F_BLK_SIZE |
+ 1ull << VIRTIO_F_VERSION_1 |
+ 1ull << VHOST_USER_F_PROTOCOL_FEATURES;
+}
+
+static int
+vu_blk_get_config(VuDev *vu_dev, uint8_t *config, size_t len)
+{
+ vhost_blk_dev_t *vdev_blk;
+
+ if (len != sizeof(struct virtio_blk_config)) {
+ return -1;
+ }
+ vdev_blk = container_of(vu_dev, vhost_blk_dev_t, vu_dev);
+ memcpy(config, &vdev_blk->blkcfg, len);
+
+ return 0;
+}
+
+static const VuDevIface vu_blk_iface = {
+ .get_features = vu_blk_get_features,
+ .queue_set_started = vu_blk_queue_set_started,
+ .get_config = vu_blk_get_config,
+};
+
+static gboolean vu_blk_vhost_cb(gpointer data)
+{
+ VuDev *vu_dev = (VuDev *)data;
+
+ assert(vu_dev);
+
+ if (!vu_dispatch(vu_dev) != 0) {
+ fprintf(stderr, "Error processing vhost message\n");
+ vu_blk_panic_cb(vu_dev, NULL);
+ return G_SOURCE_REMOVE;
+ }
+
+ return G_SOURCE_CONTINUE;
+}
+
+static int unix_sock_new(char *unix_fn)
+{
+ int sock;
+ struct sockaddr_un un;
+ size_t len;
+
+ assert(unix_fn);
+
+ sock = socket(AF_UNIX, SOCK_STREAM, 0);
+ if (sock <= 0) {
+ perror("socket");
+ return -1;
+ }
+
+ un.sun_family = AF_UNIX;
+ (void)snprintf(un.sun_path, sizeof(un.sun_path), "%s", unix_fn);
+ len = sizeof(un.sun_family) + strlen(un.sun_path);
+
+ (void)unlink(unix_fn);
+ if (bind(sock, (struct sockaddr *)&un, len) < 0) {
+ perror("bind");
+ goto fail;
+ }
+
+ if (listen(sock, 1) < 0) {
+ perror("listen");
+ goto fail;
+ }
+
+ return sock;
+
+fail:
+ (void)close(sock);
+
+ return -1;
+}
+
+static int vdev_blk_run(struct vhost_blk_dev *vdev_blk)
+{
+ int cli_sock;
+ int ret = 0;
+
+ assert(vdev_blk);
+ assert(vdev_blk->server_sock >= 0);
+ assert(vdev_blk->loop);
+
+ cli_sock = accept(vdev_blk->server_sock, (void *)0, (void *)0);
+ if (cli_sock < 0) {
+ perror("accept");
+ return -1;
+ }
+
+ vu_init(&vdev_blk->vu_dev,
+ cli_sock,
+ vu_blk_panic_cb,
+ vu_blk_add_watch_cb,
+ vu_blk_del_watch_cb,
+ &vu_blk_iface);
+
+ if (vu_blk_gsrc_new(vdev_blk, cli_sock, G_IO_IN, NULL, vu_blk_vhost_cb,
+ &vdev_blk->vu_dev)) {
+ ret = -1;
+ goto out;
+ }
+
+ g_main_loop_run(vdev_blk->loop);
+
+out:
+ vu_deinit(&vdev_blk->vu_dev);
+ return ret;
+}
+
+static void vdev_blk_deinit(struct vhost_blk_dev *vdev_blk)
+{
+ if (!vdev_blk) {
+ return;
+ }
+
+ if (vdev_blk->server_sock >= 0) {
+ struct sockaddr_storage ss;
+ socklen_t sslen = sizeof(ss);
+
+ if (getsockname(vdev_blk->server_sock, (struct sockaddr *)&ss,
+ &sslen) == 0) {
+ struct sockaddr_un *su = (struct sockaddr_un *)&ss;
+ (void)unlink(su->sun_path);
+ }
+
+ (void)close(vdev_blk->server_sock);
+ vdev_blk->server_sock = -1;
+ }
+
+ if (vdev_blk->loop) {
+ g_main_loop_unref(vdev_blk->loop);
+ vdev_blk->loop = NULL;
+ }
+
+ if (vdev_blk->blk_fd) {
+ vu_blk_close(vdev_blk->blk_fd);
+ }
+}
+
+static void
+vu_blk_initialize_config(int fd, struct virtio_blk_config *config)
+{
+ off64_t capacity;
+
+ capacity = lseek64(fd, 0, SEEK_END);
+ config->capacity = capacity >> 9;
+ config->blk_size = 512;
+ config->size_max = 65536;
+ config->seg_max = 128 - 2;
+ config->min_io_size = 1;
+ config->opt_io_size = 1;
+ config->num_queues = 1;
+}
+
+static vhost_blk_dev_t *
+vdev_blk_new(char *unix_fn, char *blk_file)
+{
+ vhost_blk_dev_t *vdev_blk = NULL;
+
+ vdev_blk = calloc(1, sizeof(struct vhost_blk_dev));
+ if (!vdev_blk) {
+ fprintf(stderr, "calloc: %s", strerror(errno));
+ return NULL;
+ }
+
+ vdev_blk->server_sock = unix_sock_new(unix_fn);
+ if (vdev_blk->server_sock < 0) {
+ goto err;
+ }
+
+ vdev_blk->loop = g_main_loop_new(NULL, FALSE);
+ if (!vdev_blk->loop) {
+ fprintf(stderr, "Error creating glib event loop");
+ goto err;
+ }
+
+ vdev_blk->fdmap = g_tree_new(vu_blk_fdmap_compare);
+ if (!vdev_blk->fdmap) {
+ fprintf(stderr, "Error creating glib tree for fdmap");
+ goto err;
+ }
+
+ vdev_blk->blk_fd = vu_blk_open(blk_file);
+ if (vdev_blk->blk_fd < 0) {
+ fprintf(stderr, "Error open block device %s\n", blk_file);
+ goto err;
+ }
+ vdev_blk->blk_name = blk_file;
+
+ /* fill virtio_blk_config with block parameters */
+ vu_blk_initialize_config(vdev_blk->blk_fd, &vdev_blk->blkcfg);
+
+ return vdev_blk;
+
+err:
+ vdev_blk_deinit(vdev_blk);
+ free(vdev_blk);
+
+ return NULL;
+}
+
+int main(int argc, char **argv)
+{
+ int opt;
+ char *unix_socket = NULL;
+ char *blk_file = NULL;
+ vhost_blk_dev_t *vdev_blk = NULL;
+
+ while ((opt = getopt(argc, argv, "b:h:s:")) != -1) {
+ switch (opt) {
+ case 'b':
+ blk_file = strdup(optarg);
+ break;
+ case 's':
+ unix_socket = strdup(optarg);
+ break;
+ case 'h':
+ default:
+ printf("Usage: %s [-b block device or file, -s UNIX domain socket]"
+ " | [ -h ]\n", argv[0]);
+ break;
+ }
+ }
+
+ if (!unix_socket || !blk_file) {
+ printf("Usage: %s [-b block device or file, -s UNIX domain socket] |"
+ " [ -h ]\n", argv[0]);
+ return -1;
+ }
+
+ vdev_blk = vdev_blk_new(unix_socket, blk_file);
+ if (!vdev_blk) {
+ goto err;
+ }
+
+ if (vdev_blk_run(vdev_blk) != 0) {
+ goto err;
+ }
+
+err:
+ if (vdev_blk) {
+ vdev_blk_deinit(vdev_blk);
+ free(vdev_blk);
+ }
+ if (unix_socket) {
+ free(unix_socket);
+ }
+ if (blk_file) {
+ free(blk_file);
+ }
+
+ return 0;
+}
+
--
1.9.3
^ permalink raw reply related [flat|nested] 6+ messages in thread