* [PATCH v10 1/7] libvhost-user: Allow vu_message_read to be replaced
2020-09-18 8:09 [PATCH v10 0/7] vhost-user block device backend implementation Coiby Xu
@ 2020-09-18 8:09 ` Coiby Xu
2020-09-18 10:14 ` Stefan Hajnoczi
2020-09-18 8:09 ` [PATCH v10 2/7] libvhost-user: remove watch for kick_fd when de-initialize vu-dev Coiby Xu
` (9 subsequent siblings)
10 siblings, 1 reply; 20+ messages in thread
From: Coiby Xu @ 2020-09-18 8:09 UTC (permalink / raw)
To: qemu-devel
Cc: kwolf, bharatlkmlkvm, Dr. David Alan Gilbert, stefanha,
Marc-André Lureau
Allow vu_message_read to be replaced by one which will make use of the
QIOChannel functions. Thus reading vhost-user message won't stall the
guest. For slave channel, we still use the default vu_message_read.
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Signed-off-by: Coiby Xu <coiby.xu@gmail.com>
---
contrib/libvhost-user/libvhost-user-glib.c | 2 +-
contrib/libvhost-user/libvhost-user.c | 14 +++++++-------
contrib/libvhost-user/libvhost-user.h | 21 +++++++++++++++++++++
tests/vhost-user-bridge.c | 2 ++
tools/virtiofsd/fuse_virtio.c | 4 ++--
5 files changed, 33 insertions(+), 10 deletions(-)
diff --git a/contrib/libvhost-user/libvhost-user-glib.c b/contrib/libvhost-user/libvhost-user-glib.c
index 53f1ca4cdd..0df2ec9271 100644
--- a/contrib/libvhost-user/libvhost-user-glib.c
+++ b/contrib/libvhost-user/libvhost-user-glib.c
@@ -147,7 +147,7 @@ vug_init(VugDev *dev, uint16_t max_queues, int socket,
g_assert(dev);
g_assert(iface);
- if (!vu_init(&dev->parent, max_queues, socket, panic, set_watch,
+ if (!vu_init(&dev->parent, max_queues, socket, panic, NULL, set_watch,
remove_watch, iface)) {
return false;
}
diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c
index 53f16bdf08..73732b928f 100644
--- a/contrib/libvhost-user/libvhost-user.c
+++ b/contrib/libvhost-user/libvhost-user.c
@@ -67,8 +67,6 @@
/* The version of inflight buffer */
#define INFLIGHT_VERSION 1
-#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64)
-
/* The version of the protocol we support */
#define VHOST_USER_VERSION 1
#define LIBVHOST_USER_DEBUG 0
@@ -267,7 +265,7 @@ have_userfault(void)
}
static bool
-vu_message_read(VuDev *dev, int conn_fd, VhostUserMsg *vmsg)
+vu_message_read_default(VuDev *dev, int conn_fd, VhostUserMsg *vmsg)
{
char control[CMSG_SPACE(VHOST_MEMORY_BASELINE_NREGIONS * sizeof(int))] = {};
struct iovec iov = {
@@ -415,7 +413,7 @@ vu_process_message_reply(VuDev *dev, const VhostUserMsg *vmsg)
goto out;
}
- if (!vu_message_read(dev, dev->slave_fd, &msg_reply)) {
+ if (!vu_message_read_default(dev, dev->slave_fd, &msg_reply)) {
goto out;
}
@@ -898,7 +896,7 @@ vu_set_mem_table_exec_postcopy(VuDev *dev, VhostUserMsg *vmsg)
/* Wait for QEMU to confirm that it's registered the handler for the
* faults.
*/
- if (!vu_message_read(dev, dev->sock, vmsg) ||
+ if (!dev->read_msg(dev, dev->sock, vmsg) ||
vmsg->size != sizeof(vmsg->payload.u64) ||
vmsg->payload.u64 != 0) {
vu_panic(dev, "failed to receive valid ack for postcopy set-mem-table");
@@ -1860,7 +1858,7 @@ vu_dispatch(VuDev *dev)
int reply_requested;
bool need_reply, success = false;
- if (!vu_message_read(dev, dev->sock, &vmsg)) {
+ if (!dev->read_msg(dev, dev->sock, &vmsg)) {
goto end;
}
@@ -1958,6 +1956,7 @@ vu_init(VuDev *dev,
uint16_t max_queues,
int socket,
vu_panic_cb panic,
+ vu_read_msg_cb read_msg,
vu_set_watch_cb set_watch,
vu_remove_watch_cb remove_watch,
const VuDevIface *iface)
@@ -1975,6 +1974,7 @@ vu_init(VuDev *dev,
dev->sock = socket;
dev->panic = panic;
+ dev->read_msg = read_msg ? read_msg : vu_message_read_default;
dev->set_watch = set_watch;
dev->remove_watch = remove_watch;
dev->iface = iface;
@@ -2340,7 +2340,7 @@ static void _vu_queue_notify(VuDev *dev, VuVirtq *vq, bool sync)
vu_message_write(dev, dev->slave_fd, &vmsg);
if (ack) {
- vu_message_read(dev, dev->slave_fd, &vmsg);
+ vu_message_read_default(dev, dev->slave_fd, &vmsg);
}
return;
}
diff --git a/contrib/libvhost-user/libvhost-user.h b/contrib/libvhost-user/libvhost-user.h
index 844c37c648..fe27831395 100644
--- a/contrib/libvhost-user/libvhost-user.h
+++ b/contrib/libvhost-user/libvhost-user.h
@@ -36,6 +36,8 @@
*/
#define VHOST_USER_MAX_RAM_SLOTS 32
+#define VHOST_USER_HDR_SIZE offsetof(VhostUserMsg, payload.u64)
+
typedef enum VhostSetConfigType {
VHOST_SET_CONFIG_TYPE_MASTER = 0,
VHOST_SET_CONFIG_TYPE_MIGRATION = 1,
@@ -221,6 +223,7 @@ typedef uint64_t (*vu_get_features_cb) (VuDev *dev);
typedef void (*vu_set_features_cb) (VuDev *dev, uint64_t features);
typedef int (*vu_process_msg_cb) (VuDev *dev, VhostUserMsg *vmsg,
int *do_reply);
+typedef bool (*vu_read_msg_cb) (VuDev *dev, int sock, VhostUserMsg *vmsg);
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, uint32_t len);
@@ -389,6 +392,23 @@ struct VuDev {
bool broken;
uint16_t max_queues;
+ /* @read_msg: custom method to read vhost-user message
+ *
+ * Read data from vhost_user socket fd and fill up
+ * the passed VhostUserMsg *vmsg struct.
+ *
+ * If reading fails, it should close the received set of file
+ * descriptors as socket message's auxiliary data.
+ *
+ * For the details, please refer to vu_message_read in libvhost-user.c
+ * which will be used by default if not custom method is provided when
+ * calling vu_init
+ *
+ * Returns: true if vhost-user message successfully received,
+ * otherwise return false.
+ *
+ */
+ vu_read_msg_cb read_msg;
/* @set_watch: add or update the given fd to the watch set,
* call cb when condition is met */
vu_set_watch_cb set_watch;
@@ -432,6 +452,7 @@ bool vu_init(VuDev *dev,
uint16_t max_queues,
int socket,
vu_panic_cb panic,
+ vu_read_msg_cb read_msg,
vu_set_watch_cb set_watch,
vu_remove_watch_cb remove_watch,
const VuDevIface *iface);
diff --git a/tests/vhost-user-bridge.c b/tests/vhost-user-bridge.c
index 6c3d490611..bd43607a4d 100644
--- a/tests/vhost-user-bridge.c
+++ b/tests/vhost-user-bridge.c
@@ -520,6 +520,7 @@ vubr_accept_cb(int sock, void *ctx)
VHOST_USER_BRIDGE_MAX_QUEUES,
conn_fd,
vubr_panic,
+ NULL,
vubr_set_watch,
vubr_remove_watch,
&vuiface)) {
@@ -573,6 +574,7 @@ vubr_new(const char *path, bool client)
VHOST_USER_BRIDGE_MAX_QUEUES,
dev->sock,
vubr_panic,
+ NULL,
vubr_set_watch,
vubr_remove_watch,
&vuiface)) {
diff --git a/tools/virtiofsd/fuse_virtio.c b/tools/virtiofsd/fuse_virtio.c
index 9e5537506c..f7da358d4a 100644
--- a/tools/virtiofsd/fuse_virtio.c
+++ b/tools/virtiofsd/fuse_virtio.c
@@ -996,8 +996,8 @@ int virtio_session_mount(struct fuse_session *se)
se->vu_socketfd = data_sock;
se->virtio_dev->se = se;
pthread_rwlock_init(&se->virtio_dev->vu_dispatch_rwlock, NULL);
- vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, fv_set_watch,
- fv_remove_watch, &fv_iface);
+ vu_init(&se->virtio_dev->dev, 2, se->vu_socketfd, fv_panic, NULL,
+ fv_set_watch, fv_remove_watch, &fv_iface);
return 0;
}
--
2.28.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* Re: [PATCH v10 1/7] libvhost-user: Allow vu_message_read to be replaced
2020-09-18 8:09 ` [PATCH v10 1/7] libvhost-user: Allow vu_message_read to be replaced Coiby Xu
@ 2020-09-18 10:14 ` Stefan Hajnoczi
0 siblings, 0 replies; 20+ messages in thread
From: Stefan Hajnoczi @ 2020-09-18 10:14 UTC (permalink / raw)
To: Coiby Xu
Cc: kwolf, bharatlkmlkvm, qemu-devel, Dr. David Alan Gilbert,
Marc-André Lureau
[-- Attachment #1: Type: text/plain, Size: 817 bytes --]
On Fri, Sep 18, 2020 at 04:09:06PM +0800, Coiby Xu wrote:
> Allow vu_message_read to be replaced by one which will make use of the
> QIOChannel functions. Thus reading vhost-user message won't stall the
> guest. For slave channel, we still use the default vu_message_read.
>
> Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
> Signed-off-by: Coiby Xu <coiby.xu@gmail.com>
> ---
> contrib/libvhost-user/libvhost-user-glib.c | 2 +-
> contrib/libvhost-user/libvhost-user.c | 14 +++++++-------
> contrib/libvhost-user/libvhost-user.h | 21 +++++++++++++++++++++
> tests/vhost-user-bridge.c | 2 ++
> tools/virtiofsd/fuse_virtio.c | 4 ++--
> 5 files changed, 33 insertions(+), 10 deletions(-)
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 20+ messages in thread
* [PATCH v10 2/7] libvhost-user: remove watch for kick_fd when de-initialize vu-dev
2020-09-18 8:09 [PATCH v10 0/7] vhost-user block device backend implementation Coiby Xu
2020-09-18 8:09 ` [PATCH v10 1/7] libvhost-user: Allow vu_message_read to be replaced Coiby Xu
@ 2020-09-18 8:09 ` Coiby Xu
2020-09-18 10:28 ` Stefan Hajnoczi
2020-09-18 8:09 ` [PATCH v10 3/7] util/vhost-user-server: generic vhost user server Coiby Xu
` (8 subsequent siblings)
10 siblings, 1 reply; 20+ messages in thread
From: Coiby Xu @ 2020-09-18 8:09 UTC (permalink / raw)
To: qemu-devel; +Cc: kwolf, bharatlkmlkvm, stefanha
When the client is running in gdb and quit command is run in gdb,
QEMU will still dispatch the event which will cause segment fault in
the callback function.
Signed-off-by: Coiby Xu <coiby.xu@gmail.com>
---
contrib/libvhost-user/libvhost-user.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/contrib/libvhost-user/libvhost-user.c b/contrib/libvhost-user/libvhost-user.c
index 73732b928f..5fdfa64294 100644
--- a/contrib/libvhost-user/libvhost-user.c
+++ b/contrib/libvhost-user/libvhost-user.c
@@ -1909,6 +1909,7 @@ vu_deinit(VuDev *dev)
}
if (vq->kick_fd != -1) {
+ dev->remove_watch(dev, vq->kick_fd);
close(vq->kick_fd);
vq->kick_fd = -1;
}
--
2.28.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* Re: [PATCH v10 2/7] libvhost-user: remove watch for kick_fd when de-initialize vu-dev
2020-09-18 8:09 ` [PATCH v10 2/7] libvhost-user: remove watch for kick_fd when de-initialize vu-dev Coiby Xu
@ 2020-09-18 10:28 ` Stefan Hajnoczi
0 siblings, 0 replies; 20+ messages in thread
From: Stefan Hajnoczi @ 2020-09-18 10:28 UTC (permalink / raw)
To: Coiby Xu; +Cc: kwolf, bharatlkmlkvm, qemu-devel
[-- Attachment #1: Type: text/plain, Size: 422 bytes --]
On Fri, Sep 18, 2020 at 04:09:07PM +0800, Coiby Xu wrote:
> When the client is running in gdb and quit command is run in gdb,
> QEMU will still dispatch the event which will cause segment fault in
> the callback function.
>
> Signed-off-by: Coiby Xu <coiby.xu@gmail.com>
> ---
> contrib/libvhost-user/libvhost-user.c | 1 +
> 1 file changed, 1 insertion(+)
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 20+ messages in thread
* [PATCH v10 3/7] util/vhost-user-server: generic vhost user server
2020-09-18 8:09 [PATCH v10 0/7] vhost-user block device backend implementation Coiby Xu
2020-09-18 8:09 ` [PATCH v10 1/7] libvhost-user: Allow vu_message_read to be replaced Coiby Xu
2020-09-18 8:09 ` [PATCH v10 2/7] libvhost-user: remove watch for kick_fd when de-initialize vu-dev Coiby Xu
@ 2020-09-18 8:09 ` Coiby Xu
2020-09-18 8:09 ` [PATCH v10 4/7] block: move logical block size check function to a common utility function Coiby Xu
` (7 subsequent siblings)
10 siblings, 0 replies; 20+ messages in thread
From: Coiby Xu @ 2020-09-18 8:09 UTC (permalink / raw)
To: qemu-devel; +Cc: kwolf, bharatlkmlkvm, Coiby Xu, stefanha
Sharing QEMU devices via vhost-user protocol.
Only one vhost-user client can connect to the server one time.
Suggested-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Coiby Xu <coiby.xu@gmail.com>
---
util/meson.build | 1 +
util/vhost-user-server.c | 428 +++++++++++++++++++++++++++++++++++++++
util/vhost-user-server.h | 65 ++++++
3 files changed, 494 insertions(+)
create mode 100644 util/vhost-user-server.c
create mode 100644 util/vhost-user-server.h
diff --git a/util/meson.build b/util/meson.build
index e6b207a99e..3921981ccf 100644
--- a/util/meson.build
+++ b/util/meson.build
@@ -66,6 +66,7 @@ if have_block
util_ss.add(files('main-loop.c'))
util_ss.add(files('nvdimm-utils.c'))
util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c'))
+ util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c'))
util_ss.add(files('qemu-coroutine-sleep.c'))
util_ss.add(files('qemu-co-shared-resource.c'))
util_ss.add(files('thread-pool.c', 'qemu-timer.c'))
diff --git a/util/vhost-user-server.c b/util/vhost-user-server.c
new file mode 100644
index 0000000000..7b50a2b1fd
--- /dev/null
+++ b/util/vhost-user-server.c
@@ -0,0 +1,428 @@
+/*
+ * Sharing QEMU devices via vhost-user protocol
+ *
+ * Copyright (c) Coiby Xu <coiby.xu@gmail.com>.
+ * Copyright (c) 2020 Red Hat, Inc.
+ *
+ * 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 "qemu/osdep.h"
+#include "qemu/main-loop.h"
+#include "vhost-user-server.h"
+
+static void vmsg_close_fds(VhostUserMsg *vmsg)
+{
+ int i;
+ for (i = 0; i < vmsg->fd_num; i++) {
+ close(vmsg->fds[i]);
+ }
+}
+
+static void vmsg_unblock_fds(VhostUserMsg *vmsg)
+{
+ int i;
+ for (i = 0; i < vmsg->fd_num; i++) {
+ qemu_set_nonblock(vmsg->fds[i]);
+ }
+}
+
+static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc,
+ gpointer opaque);
+
+static void close_client(VuServer *server)
+{
+ /*
+ * Before closing the client
+ *
+ * 1. Let vu_client_trip stop processing new vhost-user msg
+ *
+ * 2. remove kick_handler
+ *
+ * 3. wait for the kick handler to be finished
+ *
+ * 4. wait for the current vhost-user msg to be finished processing
+ */
+
+ QIOChannelSocket *sioc = server->sioc;
+ /* When this is set vu_client_trip will stop new processing vhost-user message */
+ server->sioc = NULL;
+
+ VuFdWatch *vu_fd_watch, *next;
+ QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) {
+ aio_set_fd_handler(server->ioc->ctx, vu_fd_watch->fd, true, NULL,
+ NULL, NULL, NULL);
+ }
+
+ while (!QTAILQ_EMPTY(&server->vu_fd_watches)) {
+ QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) {
+ if (!vu_fd_watch->processing) {
+ QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next);
+ g_free(vu_fd_watch);
+ }
+ }
+ }
+
+ while (server->processing_msg) {
+ if (server->ioc->read_coroutine) {
+ server->ioc->read_coroutine = NULL;
+ qio_channel_set_aio_fd_handler(server->ioc, server->ioc->ctx, NULL,
+ NULL, server->ioc);
+ server->processing_msg = false;
+ }
+ }
+
+ vu_deinit(&server->vu_dev);
+ object_unref(OBJECT(sioc));
+ object_unref(OBJECT(server->ioc));
+}
+
+static void panic_cb(VuDev *vu_dev, const char *buf)
+{
+ VuServer *server = container_of(vu_dev, VuServer, vu_dev);
+
+ /* avoid while loop in close_client */
+ server->processing_msg = false;
+
+ if (buf) {
+ error_report("vu_panic: %s", buf);
+ }
+
+ if (server->sioc) {
+ close_client(server);
+ }
+
+ if (server->device_panic_notifier) {
+ server->device_panic_notifier(server);
+ }
+
+ /*
+ * Set the callback function for network listener so another
+ * vhost-user client can connect to this server
+ */
+ qio_net_listener_set_client_func(server->listener,
+ vu_accept,
+ server,
+ NULL);
+}
+
+static bool coroutine_fn
+vu_message_read(VuDev *vu_dev, int conn_fd, VhostUserMsg *vmsg)
+{
+ struct iovec iov = {
+ .iov_base = (char *)vmsg,
+ .iov_len = VHOST_USER_HDR_SIZE,
+ };
+ int rc, read_bytes = 0;
+ Error *local_err = NULL;
+ /*
+ * Store fds/nfds returned from qio_channel_readv_full into
+ * temporary variables.
+ *
+ * VhostUserMsg is a packed structure, gcc will complain about passing
+ * pointer to a packed structure member if we pass &VhostUserMsg.fd_num
+ * and &VhostUserMsg.fds directly when calling qio_channel_readv_full,
+ * thus two temporary variables nfds and fds are used here.
+ */
+ size_t nfds = 0, nfds_t = 0;
+ const size_t max_fds = G_N_ELEMENTS(vmsg->fds);
+ int *fds_t = NULL;
+ VuServer *server = container_of(vu_dev, VuServer, vu_dev);
+ QIOChannel *ioc = server->ioc;
+
+ if (!ioc) {
+ error_report_err(local_err);
+ goto fail;
+ }
+
+ assert(qemu_in_coroutine());
+ do {
+ /*
+ * qio_channel_readv_full may have short reads, keeping calling it
+ * until getting VHOST_USER_HDR_SIZE or 0 bytes in total
+ */
+ rc = qio_channel_readv_full(ioc, &iov, 1, &fds_t, &nfds_t, &local_err);
+ if (rc < 0) {
+ if (rc == QIO_CHANNEL_ERR_BLOCK) {
+ qio_channel_yield(ioc, G_IO_IN);
+ continue;
+ } else {
+ error_report_err(local_err);
+ return false;
+ }
+ }
+ read_bytes += rc;
+ if (nfds_t > 0) {
+ if (nfds + nfds_t > max_fds) {
+ error_report("A maximum of %zu fds are allowed, "
+ "however got %lu fds now",
+ max_fds, nfds + nfds_t);
+ goto fail;
+ }
+ memcpy(vmsg->fds + nfds, fds_t,
+ nfds_t *sizeof(vmsg->fds[0]));
+ nfds += nfds_t;
+ g_free(fds_t);
+ }
+ if (read_bytes == VHOST_USER_HDR_SIZE || rc == 0) {
+ break;
+ }
+ iov.iov_base = (char *)vmsg + read_bytes;
+ iov.iov_len = VHOST_USER_HDR_SIZE - read_bytes;
+ } while (true);
+
+ vmsg->fd_num = nfds;
+ /* qio_channel_readv_full will make socket fds blocking, unblock them */
+ vmsg_unblock_fds(vmsg);
+ if (vmsg->size > sizeof(vmsg->payload)) {
+ error_report("Error: too big message request: %d, "
+ "size: vmsg->size: %u, "
+ "while sizeof(vmsg->payload) = %zu",
+ vmsg->request, vmsg->size, sizeof(vmsg->payload));
+ goto fail;
+ }
+
+ struct iovec iov_payload = {
+ .iov_base = (char *)&vmsg->payload,
+ .iov_len = vmsg->size,
+ };
+ if (vmsg->size) {
+ rc = qio_channel_readv_all_eof(ioc, &iov_payload, 1, &local_err);
+ if (rc == -1) {
+ error_report_err(local_err);
+ goto fail;
+ }
+ }
+
+ return true;
+
+fail:
+ vmsg_close_fds(vmsg);
+
+ return false;
+}
+
+
+static void vu_client_start(VuServer *server);
+static coroutine_fn void vu_client_trip(void *opaque)
+{
+ VuServer *server = opaque;
+
+ while (!server->aio_context_changed && server->sioc) {
+ server->processing_msg = true;
+ vu_dispatch(&server->vu_dev);
+ server->processing_msg = false;
+ }
+
+ if (server->aio_context_changed && server->sioc) {
+ server->aio_context_changed = false;
+ vu_client_start(server);
+ }
+}
+
+static void vu_client_start(VuServer *server)
+{
+ server->co_trip = qemu_coroutine_create(vu_client_trip, server);
+ aio_co_enter(server->ctx, server->co_trip);
+}
+
+/*
+ * a wrapper for vu_kick_cb
+ *
+ * since aio_dispatch can only pass one user data pointer to the
+ * callback function, pack VuDev and pvt into a struct. Then unpack it
+ * and pass them to vu_kick_cb
+ */
+static void kick_handler(void *opaque)
+{
+ VuFdWatch *vu_fd_watch = opaque;
+ vu_fd_watch->processing = true;
+ vu_fd_watch->cb(vu_fd_watch->vu_dev, 0, vu_fd_watch->pvt);
+ vu_fd_watch->processing = false;
+}
+
+
+static VuFdWatch *find_vu_fd_watch(VuServer *server, int fd)
+{
+
+ VuFdWatch *vu_fd_watch, *next;
+ QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) {
+ if (vu_fd_watch->fd == fd) {
+ return vu_fd_watch;
+ }
+ }
+ return NULL;
+}
+
+static void
+set_watch(VuDev *vu_dev, int fd, int vu_evt,
+ vu_watch_cb cb, void *pvt)
+{
+
+ VuServer *server = container_of(vu_dev, VuServer, vu_dev);
+ g_assert(vu_dev);
+ g_assert(fd >= 0);
+ g_assert(cb);
+
+ VuFdWatch *vu_fd_watch = find_vu_fd_watch(server, fd);
+
+ if (!vu_fd_watch) {
+ VuFdWatch *vu_fd_watch = g_new0(VuFdWatch, 1);
+
+ QTAILQ_INSERT_TAIL(&server->vu_fd_watches, vu_fd_watch, next);
+
+ vu_fd_watch->fd = fd;
+ vu_fd_watch->cb = cb;
+ qemu_set_nonblock(fd);
+ aio_set_fd_handler(server->ioc->ctx, fd, true, kick_handler,
+ NULL, NULL, vu_fd_watch);
+ vu_fd_watch->vu_dev = vu_dev;
+ vu_fd_watch->pvt = pvt;
+ }
+}
+
+
+static void remove_watch(VuDev *vu_dev, int fd)
+{
+ VuServer *server;
+ g_assert(vu_dev);
+ g_assert(fd >= 0);
+
+ server = container_of(vu_dev, VuServer, vu_dev);
+
+ VuFdWatch *vu_fd_watch = find_vu_fd_watch(server, fd);
+
+ if (!vu_fd_watch) {
+ return;
+ }
+ aio_set_fd_handler(server->ioc->ctx, fd, true, NULL, NULL, NULL, NULL);
+
+ QTAILQ_REMOVE(&server->vu_fd_watches, vu_fd_watch, next);
+ g_free(vu_fd_watch);
+}
+
+
+static void vu_accept(QIONetListener *listener, QIOChannelSocket *sioc,
+ gpointer opaque)
+{
+ VuServer *server = opaque;
+
+ if (server->sioc) {
+ warn_report("Only one vhost-user client is allowed to "
+ "connect the server one time");
+ return;
+ }
+
+ if (!vu_init(&server->vu_dev, server->max_queues, sioc->fd, panic_cb,
+ vu_message_read, set_watch, remove_watch, server->vu_iface)) {
+ error_report("Failed to initialize libvhost-user");
+ return;
+ }
+
+ /*
+ * Unset the callback function for network listener to make another
+ * vhost-user client keeping waiting until this client disconnects
+ */
+ qio_net_listener_set_client_func(server->listener,
+ NULL,
+ NULL,
+ NULL);
+ server->sioc = sioc;
+ /*
+ * Increase the object reference, so sioc will not freed by
+ * qio_net_listener_channel_func which will call object_unref(OBJECT(sioc))
+ */
+ object_ref(OBJECT(server->sioc));
+ qio_channel_set_name(QIO_CHANNEL(sioc), "vhost-user client");
+ server->ioc = QIO_CHANNEL(sioc);
+ object_ref(OBJECT(server->ioc));
+ qio_channel_attach_aio_context(server->ioc, server->ctx);
+ qio_channel_set_blocking(QIO_CHANNEL(server->sioc), false, NULL);
+ vu_client_start(server);
+}
+
+
+void vhost_user_server_stop(VuServer *server)
+{
+ if (server->sioc) {
+ close_client(server);
+ }
+
+ if (server->listener) {
+ qio_net_listener_disconnect(server->listener);
+ object_unref(OBJECT(server->listener));
+ }
+
+}
+
+void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx)
+{
+ VuFdWatch *vu_fd_watch, *next;
+ void *opaque = NULL;
+ IOHandler *io_read = NULL;
+ bool attach;
+
+ server->ctx = ctx ? ctx : qemu_get_aio_context();
+
+ if (!server->sioc) {
+ /* not yet serving any client*/
+ return;
+ }
+
+ if (ctx) {
+ qio_channel_attach_aio_context(server->ioc, ctx);
+ server->aio_context_changed = true;
+ io_read = kick_handler;
+ attach = true;
+ } else {
+ qio_channel_detach_aio_context(server->ioc);
+ /* server->ioc->ctx keeps the old AioConext */
+ ctx = server->ioc->ctx;
+ attach = false;
+ }
+
+ QTAILQ_FOREACH_SAFE(vu_fd_watch, &server->vu_fd_watches, next, next) {
+ if (vu_fd_watch->cb) {
+ opaque = attach ? vu_fd_watch : NULL;
+ aio_set_fd_handler(ctx, vu_fd_watch->fd, true,
+ io_read, NULL, NULL,
+ opaque);
+ }
+ }
+}
+
+
+bool vhost_user_server_start(VuServer *server,
+ SocketAddress *socket_addr,
+ AioContext *ctx,
+ uint16_t max_queues,
+ DevicePanicNotifierFn *device_panic_notifier,
+ const VuDevIface *vu_iface,
+ Error **errp)
+{
+ QIONetListener *listener = qio_net_listener_new();
+ if (qio_net_listener_open_sync(listener, socket_addr, 1,
+ errp) < 0) {
+ object_unref(OBJECT(listener));
+ return false;
+ }
+
+ /* zero out unspecified fileds */
+ *server = (VuServer) {
+ .listener = listener,
+ .vu_iface = vu_iface,
+ .max_queues = max_queues,
+ .ctx = ctx,
+ .device_panic_notifier = device_panic_notifier,
+ };
+
+ qio_net_listener_set_name(server->listener, "vhost-user-backend-listener");
+
+ qio_net_listener_set_client_func(server->listener,
+ vu_accept,
+ server,
+ NULL);
+
+ QTAILQ_INIT(&server->vu_fd_watches);
+ return true;
+}
diff --git a/util/vhost-user-server.h b/util/vhost-user-server.h
new file mode 100644
index 0000000000..5232f96718
--- /dev/null
+++ b/util/vhost-user-server.h
@@ -0,0 +1,65 @@
+/*
+ * Sharing QEMU devices via vhost-user protocol
+ *
+ * Copyright (c) Coiby Xu <coiby.xu@gmail.com>.
+ * Copyright (c) 2020 Red Hat, Inc.
+ *
+ * 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_USER_SERVER_H
+#define VHOST_USER_SERVER_H
+
+#include "contrib/libvhost-user/libvhost-user.h"
+#include "io/channel-socket.h"
+#include "io/channel-file.h"
+#include "io/net-listener.h"
+#include "qemu/error-report.h"
+#include "qapi/error.h"
+#include "standard-headers/linux/virtio_blk.h"
+
+typedef struct VuFdWatch {
+ VuDev *vu_dev;
+ int fd; /*kick fd*/
+ void *pvt;
+ vu_watch_cb cb;
+ bool processing;
+ QTAILQ_ENTRY(VuFdWatch) next;
+} VuFdWatch;
+
+typedef struct VuServer VuServer;
+typedef void DevicePanicNotifierFn(VuServer *server);
+
+struct VuServer {
+ QIONetListener *listener;
+ AioContext *ctx;
+ DevicePanicNotifierFn *device_panic_notifier;
+ int max_queues;
+ const VuDevIface *vu_iface;
+ VuDev vu_dev;
+ QIOChannel *ioc; /* The I/O channel with the client */
+ QIOChannelSocket *sioc; /* The underlying data channel with the client */
+ /* IOChannel for fd provided via VHOST_USER_SET_SLAVE_REQ_FD */
+ QIOChannel *ioc_slave;
+ QIOChannelSocket *sioc_slave;
+ Coroutine *co_trip; /* coroutine for processing VhostUserMsg */
+ QTAILQ_HEAD(, VuFdWatch) vu_fd_watches;
+ /* restart coroutine co_trip if AIOContext is changed */
+ bool aio_context_changed;
+ bool processing_msg;
+};
+
+bool vhost_user_server_start(VuServer *server,
+ SocketAddress *unix_socket,
+ AioContext *ctx,
+ uint16_t max_queues,
+ DevicePanicNotifierFn *device_panic_notifier,
+ const VuDevIface *vu_iface,
+ Error **errp);
+
+void vhost_user_server_stop(VuServer *server);
+
+void vhost_user_server_set_aio_context(VuServer *server, AioContext *ctx);
+
+#endif /* VHOST_USER_SERVER_H */
--
2.28.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v10 4/7] block: move logical block size check function to a common utility function
2020-09-18 8:09 [PATCH v10 0/7] vhost-user block device backend implementation Coiby Xu
` (2 preceding siblings ...)
2020-09-18 8:09 ` [PATCH v10 3/7] util/vhost-user-server: generic vhost user server Coiby Xu
@ 2020-09-18 8:09 ` Coiby Xu
2020-09-18 17:56 ` Eduardo Habkost
2020-09-18 8:09 ` [PATCH v10 5/7] block/export: vhost-user block device backend server Coiby Xu
` (6 subsequent siblings)
10 siblings, 1 reply; 20+ messages in thread
From: Coiby Xu @ 2020-09-18 8:09 UTC (permalink / raw)
To: qemu-devel
Cc: kwolf, Daniel P. Berrangé,
Eduardo Habkost, bharatlkmlkvm, stefanha, Paolo Bonzini
Move the constants from hw/core/qdev-properties.c to
util/block-helpers.h so that knowledge of the min/max values is
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Coiby Xu <coiby.xu@gmail.com>
---
hw/core/qdev-properties.c | 31 +++++---------------------
util/block-helpers.c | 46 +++++++++++++++++++++++++++++++++++++++
util/block-helpers.h | 19 ++++++++++++++++
util/meson.build | 1 +
4 files changed, 71 insertions(+), 26 deletions(-)
create mode 100644 util/block-helpers.c
create mode 100644 util/block-helpers.h
diff --git a/hw/core/qdev-properties.c b/hw/core/qdev-properties.c
index 098298c78e..e6ffd80b36 100644
--- a/hw/core/qdev-properties.c
+++ b/hw/core/qdev-properties.c
@@ -16,6 +16,7 @@
#include "qemu/uuid.h"
#include "qemu/units.h"
#include "qemu/cutils.h"
+#include "util/block-helpers.h"
void qdev_prop_set_after_realize(DeviceState *dev, const char *name,
Error **errp)
@@ -851,16 +852,6 @@ const PropertyInfo qdev_prop_size32 = {
/* --- blocksize --- */
-/* lower limit is sector size */
-#define MIN_BLOCK_SIZE 512
-#define MIN_BLOCK_SIZE_STR "512 B"
-/*
- * upper limit is arbitrary, 2 MiB looks sufficient for all sensible uses, and
- * matches qcow2 cluster size limit
- */
-#define MAX_BLOCK_SIZE (2 * MiB)
-#define MAX_BLOCK_SIZE_STR "2 MiB"
-
static void set_blocksize(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
@@ -868,6 +859,7 @@ static void set_blocksize(Object *obj, Visitor *v, const char *name,
Property *prop = opaque;
uint32_t *ptr = qdev_get_prop_ptr(dev, prop);
uint64_t value;
+ Error *local_err = NULL;
if (dev->realized) {
qdev_prop_set_after_realize(dev, name, errp);
@@ -877,24 +869,11 @@ static void set_blocksize(Object *obj, Visitor *v, const char *name,
if (!visit_type_size(v, name, &value, errp)) {
return;
}
- /* value of 0 means "unset" */
- if (value && (value < MIN_BLOCK_SIZE || value > MAX_BLOCK_SIZE)) {
- error_setg(errp,
- "Property %s.%s doesn't take value %" PRIu64
- " (minimum: " MIN_BLOCK_SIZE_STR
- ", maximum: " MAX_BLOCK_SIZE_STR ")",
- dev->id ? : "", name, value);
- return;
- }
-
- /* We rely on power-of-2 blocksizes for bitmasks */
- if ((value & (value - 1)) != 0) {
- error_setg(errp,
- "Property %s.%s doesn't take value '%" PRId64 "', it's not a power of 2",
- dev->id ?: "", name, (int64_t)value);
+ check_block_size(dev->id ? : "", name, value, &local_err);
+ if (local_err) {
+ error_propagate(errp, local_err);
return;
}
-
*ptr = value;
}
diff --git a/util/block-helpers.c b/util/block-helpers.c
new file mode 100644
index 0000000000..c4851432f5
--- /dev/null
+++ b/util/block-helpers.c
@@ -0,0 +1,46 @@
+/*
+ * Block utility functions
+ *
+ * Copyright IBM, Corp. 2011
+ * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.com>
+ *
+ * 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 "qemu/osdep.h"
+#include "qapi/error.h"
+#include "qapi/qmp/qerror.h"
+#include "block-helpers.h"
+
+/**
+ * check_block_size:
+ * @id: The unique ID of the object
+ * @name: The name of the property being validated
+ * @value: The block size in bytes
+ * @errp: A pointer to an area to store an error
+ *
+ * This function checks that the block size meets the following conditions:
+ * 1. At least MIN_BLOCK_SIZE
+ * 2. No larger than MAX_BLOCK_SIZE
+ * 3. A power of 2
+ */
+void check_block_size(const char *id, const char *name, int64_t value,
+ Error **errp)
+{
+ /* value of 0 means "unset" */
+ if (value && (value < MIN_BLOCK_SIZE || value > MAX_BLOCK_SIZE)) {
+ error_setg(errp, QERR_PROPERTY_VALUE_OUT_OF_RANGE,
+ id, name, value, MIN_BLOCK_SIZE, MAX_BLOCK_SIZE);
+ return;
+ }
+
+ /* We rely on power-of-2 blocksizes for bitmasks */
+ if ((value & (value - 1)) != 0) {
+ error_setg(errp,
+ "Property %s.%s doesn't take value '%" PRId64
+ "', it's not a power of 2",
+ id, name, value);
+ return;
+ }
+}
diff --git a/util/block-helpers.h b/util/block-helpers.h
new file mode 100644
index 0000000000..b53295a529
--- /dev/null
+++ b/util/block-helpers.h
@@ -0,0 +1,19 @@
+#ifndef BLOCK_HELPERS_H
+#define BLOCK_HELPERS_H
+
+#include "qemu/units.h"
+
+/* lower limit is sector size */
+#define MIN_BLOCK_SIZE INT64_C(512)
+#define MIN_BLOCK_SIZE_STR "512 B"
+/*
+ * upper limit is arbitrary, 2 MiB looks sufficient for all sensible uses, and
+ * matches qcow2 cluster size limit
+ */
+#define MAX_BLOCK_SIZE (2 * MiB)
+#define MAX_BLOCK_SIZE_STR "2 MiB"
+
+void check_block_size(const char *id, const char *name, int64_t value,
+ Error **errp);
+
+#endif /* BLOCK_HELPERS_H */
diff --git a/util/meson.build b/util/meson.build
index 3921981ccf..2296e81b34 100644
--- a/util/meson.build
+++ b/util/meson.build
@@ -67,6 +67,7 @@ if have_block
util_ss.add(files('nvdimm-utils.c'))
util_ss.add(files('qemu-coroutine.c', 'qemu-coroutine-lock.c', 'qemu-coroutine-io.c'))
util_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-server.c'))
+ util_ss.add(files('block-helpers.c'))
util_ss.add(files('qemu-coroutine-sleep.c'))
util_ss.add(files('qemu-co-shared-resource.c'))
util_ss.add(files('thread-pool.c', 'qemu-timer.c'))
--
2.28.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* [PATCH v10 5/7] block/export: vhost-user block device backend server
2020-09-18 8:09 [PATCH v10 0/7] vhost-user block device backend implementation Coiby Xu
` (3 preceding siblings ...)
2020-09-18 8:09 ` [PATCH v10 4/7] block: move logical block size check function to a common utility function Coiby Xu
@ 2020-09-18 8:09 ` Coiby Xu
2020-09-18 9:44 ` Stefan Hajnoczi
2020-09-18 8:09 ` [PATCH v10 6/7] test: new qTest case to test the vhost-user-blk-server Coiby Xu
` (5 subsequent siblings)
10 siblings, 1 reply; 20+ messages in thread
From: Coiby Xu @ 2020-09-18 8:09 UTC (permalink / raw)
To: qemu-devel
Cc: kwolf, open list:Block layer core, Coiby Xu, Max Reitz,
bharatlkmlkvm, stefanha, Paolo Bonzini
By making use of libvhost-user, block device drive can be shared to
the connected vhost-user client. Only one client can connect to the
server one time.
Since vhost-user-server needs a block drive to be created first, delay
the creation of this object.
Suggested-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Coiby Xu <coiby.xu@gmail.com>
---
block/export/vhost-user-blk-server.c | 661 +++++++++++++++++++++++++++
block/export/vhost-user-blk-server.h | 36 ++
block/meson.build | 1 +
softmmu/vl.c | 4 +
4 files changed, 702 insertions(+)
create mode 100644 block/export/vhost-user-blk-server.c
create mode 100644 block/export/vhost-user-blk-server.h
diff --git a/block/export/vhost-user-blk-server.c b/block/export/vhost-user-blk-server.c
new file mode 100644
index 0000000000..ec78130f09
--- /dev/null
+++ b/block/export/vhost-user-blk-server.c
@@ -0,0 +1,661 @@
+/*
+ * Sharing QEMU block devices via vhost-user protocal
+ *
+ * Parts of the code based on nbd/server.c.
+ *
+ * Copyright (c) Coiby Xu <coiby.xu@gmail.com>.
+ * Copyright (c) 2020 Red Hat, Inc.
+ *
+ * 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 "qemu/osdep.h"
+#include "block/block.h"
+#include "vhost-user-blk-server.h"
+#include "qapi/error.h"
+#include "qom/object_interfaces.h"
+#include "sysemu/block-backend.h"
+#include "util/block-helpers.h"
+
+enum {
+ VHOST_USER_BLK_MAX_QUEUES = 1,
+};
+struct virtio_blk_inhdr {
+ unsigned char status;
+};
+
+typedef struct VuBlockReq {
+ VuVirtqElement *elem;
+ int64_t sector_num;
+ size_t size;
+ struct virtio_blk_inhdr *in;
+ struct virtio_blk_outhdr out;
+ VuServer *server;
+ struct VuVirtq *vq;
+} VuBlockReq;
+
+static void vu_block_req_complete(VuBlockReq *req)
+{
+ VuDev *vu_dev = &req->server->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);
+ }
+
+ g_free(req);
+}
+
+static VuBlockDev *get_vu_block_device_by_server(VuServer *server)
+{
+ return container_of(server, VuBlockDev, vu_server);
+}
+
+static int coroutine_fn
+vu_block_discard_write_zeroes(VuBlockReq *req, struct iovec *iov,
+ uint32_t iovcnt, uint32_t type)
+{
+ struct virtio_blk_discard_write_zeroes desc;
+ ssize_t size = iov_to_buf(iov, iovcnt, 0, &desc, sizeof(desc));
+ if (unlikely(size != sizeof(desc))) {
+ error_report("Invalid size %ld, expect %ld", size, sizeof(desc));
+ return -EINVAL;
+ }
+
+ VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server);
+ uint64_t range[2] = { le64_to_cpu(desc.sector) << 9,
+ le32_to_cpu(desc.num_sectors) << 9 };
+ if (type == VIRTIO_BLK_T_DISCARD) {
+ if (blk_co_pdiscard(vdev_blk->backend, range[0], range[1]) == 0) {
+ return 0;
+ }
+ } else if (type == VIRTIO_BLK_T_WRITE_ZEROES) {
+ if (blk_co_pwrite_zeroes(vdev_blk->backend,
+ range[0], range[1], 0) == 0) {
+ return 0;
+ }
+ }
+
+ return -EINVAL;
+}
+
+static void coroutine_fn vu_block_flush(VuBlockReq *req)
+{
+ VuBlockDev *vdev_blk = get_vu_block_device_by_server(req->server);
+ BlockBackend *backend = vdev_blk->backend;
+ blk_co_flush(backend);
+}
+
+struct req_data {
+ VuServer *server;
+ VuVirtq *vq;
+ VuVirtqElement *elem;
+};
+
+static void coroutine_fn vu_block_virtio_process_req(void *opaque)
+{
+ struct req_data *data = opaque;
+ VuServer *server = data->server;
+ VuVirtq *vq = data->vq;
+ VuVirtqElement *elem = data->elem;
+ uint32_t type;
+ VuBlockReq *req;
+
+ VuBlockDev *vdev_blk = get_vu_block_device_by_server(server);
+ BlockBackend *backend = vdev_blk->backend;
+
+ struct iovec *in_iov = elem->in_sg;
+ struct iovec *out_iov = elem->out_sg;
+ unsigned in_num = elem->in_num;
+ unsigned out_num = elem->out_num;
+ /* refer to hw/block/virtio_blk.c */
+ if (elem->out_num < 1 || elem->in_num < 1) {
+ error_report("virtio-blk request missing headers");
+ free(elem);
+ return;
+ }
+
+ req = g_new0(VuBlockReq, 1);
+ req->server = server;
+ req->vq = vq;
+ req->elem = elem;
+
+ if (unlikely(iov_to_buf(out_iov, out_num, 0, &req->out,
+ sizeof(req->out)) != sizeof(req->out))) {
+ error_report("virtio-blk request outhdr too short");
+ goto err;
+ }
+
+ iov_discard_front(&out_iov, &out_num, sizeof(req->out));
+
+ if (in_iov[in_num - 1].iov_len < sizeof(struct virtio_blk_inhdr)) {
+ error_report("virtio-blk request inhdr too short");
+ goto err;
+ }
+
+ /* We always touch the last byte, so just see how big in_iov is. */
+ req->in = (void *)in_iov[in_num - 1].iov_base
+ + in_iov[in_num - 1].iov_len
+ - sizeof(struct virtio_blk_inhdr);
+ iov_discard_back(in_iov, &in_num, sizeof(struct virtio_blk_inhdr));
+
+ type = le32_to_cpu(req->out.type);
+ switch (type & ~VIRTIO_BLK_T_BARRIER) {
+ case VIRTIO_BLK_T_IN:
+ case VIRTIO_BLK_T_OUT: {
+ ssize_t ret = 0;
+ bool is_write = type & VIRTIO_BLK_T_OUT;
+ req->sector_num = le64_to_cpu(req->out.sector);
+
+ int64_t offset = req->sector_num * vdev_blk->blk_size;
+ QEMUIOVector qiov;
+ if (is_write) {
+ qemu_iovec_init_external(&qiov, out_iov, out_num);
+ ret = blk_co_pwritev(backend, offset, qiov.size,
+ &qiov, 0);
+ } else {
+ qemu_iovec_init_external(&qiov, in_iov, in_num);
+ ret = blk_co_preadv(backend, offset, qiov.size,
+ &qiov, 0);
+ }
+ if (ret >= 0) {
+ req->in->status = VIRTIO_BLK_S_OK;
+ } else {
+ req->in->status = VIRTIO_BLK_S_IOERR;
+ }
+ break;
+ }
+ case VIRTIO_BLK_T_FLUSH:
+ vu_block_flush(req);
+ req->in->status = VIRTIO_BLK_S_OK;
+ break;
+ case VIRTIO_BLK_T_GET_ID: {
+ size_t size = MIN(iov_size(&elem->in_sg[0], in_num),
+ VIRTIO_BLK_ID_BYTES);
+ snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk_server");
+ req->in->status = VIRTIO_BLK_S_OK;
+ req->size = elem->in_sg[0].iov_len;
+ break;
+ }
+ case VIRTIO_BLK_T_DISCARD:
+ case VIRTIO_BLK_T_WRITE_ZEROES: {
+ int rc;
+ rc = vu_block_discard_write_zeroes(req, &elem->out_sg[1],
+ out_num, type);
+ if (rc == 0) {
+ req->in->status = VIRTIO_BLK_S_OK;
+ } else {
+ req->in->status = VIRTIO_BLK_S_IOERR;
+ }
+ break;
+ }
+ default:
+ req->in->status = VIRTIO_BLK_S_UNSUPP;
+ break;
+ }
+
+ vu_block_req_complete(req);
+ return;
+
+err:
+ free(elem);
+ g_free(req);
+ return;
+}
+
+static void vu_block_process_vq(VuDev *vu_dev, int idx)
+{
+ VuServer *server;
+ VuVirtq *vq;
+ struct req_data *req_data;
+
+ server = container_of(vu_dev, VuServer, vu_dev);
+ assert(server);
+
+ vq = vu_get_queue(vu_dev, idx);
+ assert(vq);
+ VuVirtqElement *elem;
+ while (1) {
+ elem = vu_queue_pop(vu_dev, vq, sizeof(VuVirtqElement) +
+ sizeof(VuBlockReq));
+ if (elem) {
+ req_data = g_new0(struct req_data, 1);
+ req_data->server = server;
+ req_data->vq = vq;
+ req_data->elem = elem;
+ Coroutine *co = qemu_coroutine_create(vu_block_virtio_process_req,
+ req_data);
+ aio_co_enter(server->ioc->ctx, co);
+ } else {
+ break;
+ }
+ }
+}
+
+static void vu_block_queue_set_started(VuDev *vu_dev, int idx, bool started)
+{
+ VuVirtq *vq;
+
+ assert(vu_dev);
+
+ vq = vu_get_queue(vu_dev, idx);
+ vu_set_queue_handler(vu_dev, vq, started ? vu_block_process_vq : NULL);
+}
+
+static uint64_t vu_block_get_features(VuDev *dev)
+{
+ uint64_t features;
+ VuServer *server = container_of(dev, VuServer, vu_dev);
+ VuBlockDev *vdev_blk = get_vu_block_device_by_server(server);
+ features = 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_BLK_F_FLUSH |
+ 1ull << VIRTIO_BLK_F_DISCARD |
+ 1ull << VIRTIO_BLK_F_WRITE_ZEROES |
+ 1ull << VIRTIO_BLK_F_CONFIG_WCE |
+ 1ull << VIRTIO_F_VERSION_1 |
+ 1ull << VIRTIO_RING_F_INDIRECT_DESC |
+ 1ull << VIRTIO_RING_F_EVENT_IDX |
+ 1ull << VHOST_USER_F_PROTOCOL_FEATURES;
+
+ if (!vdev_blk->writable) {
+ features |= 1ull << VIRTIO_BLK_F_RO;
+ }
+
+ return features;
+}
+
+static uint64_t vu_block_get_protocol_features(VuDev *dev)
+{
+ return 1ull << VHOST_USER_PROTOCOL_F_CONFIG |
+ 1ull << VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD;
+}
+
+static int
+vu_block_get_config(VuDev *vu_dev, uint8_t *config, uint32_t len)
+{
+ VuServer *server = container_of(vu_dev, VuServer, vu_dev);
+ VuBlockDev *vdev_blk = get_vu_block_device_by_server(server);
+ memcpy(config, &vdev_blk->blkcfg, len);
+
+ return 0;
+}
+
+static int
+vu_block_set_config(VuDev *vu_dev, const uint8_t *data,
+ uint32_t offset, uint32_t size, uint32_t flags)
+{
+ VuServer *server = container_of(vu_dev, VuServer, vu_dev);
+ VuBlockDev *vdev_blk = get_vu_block_device_by_server(server);
+ uint8_t wce;
+
+ /* don't support live migration */
+ if (flags != VHOST_SET_CONFIG_TYPE_MASTER) {
+ return -EINVAL;
+ }
+
+ if (offset != offsetof(struct virtio_blk_config, wce) ||
+ size != 1) {
+ return -EINVAL;
+ }
+
+ wce = *data;
+ vdev_blk->blkcfg.wce = wce;
+ blk_set_enable_write_cache(vdev_blk->backend, wce);
+ return 0;
+}
+
+/*
+ * When the client disconnects, it sends a VHOST_USER_NONE request
+ * and vu_process_message will simple call exit which cause the VM
+ * to exit abruptly.
+ * To avoid this issue, process VHOST_USER_NONE request ahead
+ * of vu_process_message.
+ *
+ */
+static int vu_block_process_msg(VuDev *dev, VhostUserMsg *vmsg, int *do_reply)
+{
+ if (vmsg->request == VHOST_USER_NONE) {
+ dev->panic(dev, "disconnect");
+ return true;
+ }
+ return false;
+}
+
+static const VuDevIface vu_block_iface = {
+ .get_features = vu_block_get_features,
+ .queue_set_started = vu_block_queue_set_started,
+ .get_protocol_features = vu_block_get_protocol_features,
+ .get_config = vu_block_get_config,
+ .set_config = vu_block_set_config,
+ .process_msg = vu_block_process_msg,
+};
+
+static void blk_aio_attached(AioContext *ctx, void *opaque)
+{
+ VuBlockDev *vub_dev = opaque;
+ aio_context_acquire(ctx);
+ vhost_user_server_set_aio_context(&vub_dev->vu_server, ctx);
+ aio_context_release(ctx);
+}
+
+static void blk_aio_detach(void *opaque)
+{
+ VuBlockDev *vub_dev = opaque;
+ AioContext *ctx = vub_dev->vu_server.ctx;
+ aio_context_acquire(ctx);
+ vhost_user_server_set_aio_context(&vub_dev->vu_server, NULL);
+ aio_context_release(ctx);
+}
+
+static void
+vu_block_initialize_config(BlockDriverState *bs,
+ struct virtio_blk_config *config, uint32_t blk_size)
+{
+ config->capacity = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
+ config->blk_size = blk_size;
+ config->size_max = 0;
+ config->seg_max = 128 - 2;
+ config->min_io_size = 1;
+ config->opt_io_size = 1;
+ config->num_queues = VHOST_USER_BLK_MAX_QUEUES;
+ config->max_discard_sectors = 32768;
+ config->max_discard_seg = 1;
+ config->discard_sector_alignment = config->blk_size >> 9;
+ config->max_write_zeroes_sectors = 32768;
+ config->max_write_zeroes_seg = 1;
+}
+
+static VuBlockDev *vu_block_init(VuBlockDev *vu_block_device, Error **errp)
+{
+
+ BlockBackend *blk;
+ Error *local_error = NULL;
+ const char *node_name = vu_block_device->node_name;
+ bool writable = vu_block_device->writable;
+ uint64_t perm = BLK_PERM_CONSISTENT_READ;
+ int ret;
+
+ AioContext *ctx;
+
+ BlockDriverState *bs = bdrv_lookup_bs(node_name, node_name, &local_error);
+
+ if (!bs) {
+ error_propagate(errp, local_error);
+ return NULL;
+ }
+
+ if (bdrv_is_read_only(bs)) {
+ writable = false;
+ }
+
+ if (writable) {
+ perm |= BLK_PERM_WRITE;
+ }
+
+ ctx = bdrv_get_aio_context(bs);
+ aio_context_acquire(ctx);
+ bdrv_invalidate_cache(bs, NULL);
+ aio_context_release(ctx);
+
+ /*
+ * Don't allow resize while the vhost user server is running,
+ * otherwise we don't care what happens with the node.
+ */
+ blk = blk_new(bdrv_get_aio_context(bs), perm,
+ BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE_UNCHANGED |
+ BLK_PERM_WRITE | BLK_PERM_GRAPH_MOD);
+ ret = blk_insert_bs(blk, bs, errp);
+
+ if (ret < 0) {
+ goto fail;
+ }
+
+ blk_set_enable_write_cache(blk, false);
+
+ blk_set_allow_aio_context_change(blk, true);
+
+ vu_block_device->blkcfg.wce = 0;
+ vu_block_device->backend = blk;
+ if (!vu_block_device->blk_size) {
+ vu_block_device->blk_size = BDRV_SECTOR_SIZE;
+ }
+ vu_block_device->blkcfg.blk_size = vu_block_device->blk_size;
+ blk_set_guest_block_size(blk, vu_block_device->blk_size);
+ vu_block_initialize_config(bs, &vu_block_device->blkcfg,
+ vu_block_device->blk_size);
+ return vu_block_device;
+
+fail:
+ blk_unref(blk);
+ return NULL;
+}
+
+static void vu_block_deinit(VuBlockDev *vu_block_device)
+{
+ if (vu_block_device->backend) {
+ blk_remove_aio_context_notifier(vu_block_device->backend, blk_aio_attached,
+ blk_aio_detach, vu_block_device);
+ }
+
+ blk_unref(vu_block_device->backend);
+}
+
+static void vhost_user_blk_server_stop(VuBlockDev *vu_block_device)
+{
+ vhost_user_server_stop(&vu_block_device->vu_server);
+ vu_block_deinit(vu_block_device);
+}
+
+static void vhost_user_blk_server_start(VuBlockDev *vu_block_device,
+ Error **errp)
+{
+ AioContext *ctx;
+ SocketAddress *addr = vu_block_device->addr;
+
+ if (!vu_block_init(vu_block_device, errp)) {
+ return;
+ }
+
+ ctx = bdrv_get_aio_context(blk_bs(vu_block_device->backend));
+
+ if (!vhost_user_server_start(&vu_block_device->vu_server, addr, ctx,
+ VHOST_USER_BLK_MAX_QUEUES,
+ NULL, &vu_block_iface,
+ errp)) {
+ goto error;
+ }
+
+ blk_add_aio_context_notifier(vu_block_device->backend, blk_aio_attached,
+ blk_aio_detach, vu_block_device);
+ vu_block_device->running = true;
+ return;
+
+ error:
+ vu_block_deinit(vu_block_device);
+}
+
+static bool vu_prop_modifiable(VuBlockDev *vus, Error **errp)
+{
+ if (vus->running) {
+ error_setg(errp, "The property can't be modified "
+ "while the server is running");
+ return false;
+ }
+ return true;
+}
+
+static void vu_set_node_name(Object *obj, const char *value, Error **errp)
+{
+ VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
+
+ if (!vu_prop_modifiable(vus, errp)) {
+ return;
+ }
+
+ if (vus->node_name) {
+ g_free(vus->node_name);
+ }
+
+ vus->node_name = g_strdup(value);
+}
+
+static char *vu_get_node_name(Object *obj, Error **errp)
+{
+ VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
+ return g_strdup(vus->node_name);
+}
+
+static void free_socket_addr(SocketAddress *addr)
+{
+ g_free(addr->u.q_unix.path);
+ g_free(addr);
+}
+
+static void vu_set_unix_socket(Object *obj, const char *value,
+ Error **errp)
+{
+ VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
+
+ if (!vu_prop_modifiable(vus, errp)) {
+ return;
+ }
+
+ if (vus->addr) {
+ free_socket_addr(vus->addr);
+ }
+
+ SocketAddress *addr = g_new0(SocketAddress, 1);
+ addr->type = SOCKET_ADDRESS_TYPE_UNIX;
+ addr->u.q_unix.path = g_strdup(value);
+ vus->addr = addr;
+}
+
+static char *vu_get_unix_socket(Object *obj, Error **errp)
+{
+ VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
+ return g_strdup(vus->addr->u.q_unix.path);
+}
+
+static bool vu_get_block_writable(Object *obj, Error **errp)
+{
+ VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
+ return vus->writable;
+}
+
+static void vu_set_block_writable(Object *obj, bool value, Error **errp)
+{
+ VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
+
+ if (!vu_prop_modifiable(vus, errp)) {
+ return;
+ }
+
+ vus->writable = value;
+}
+
+static void vu_get_blk_size(Object *obj, Visitor *v, const char *name,
+ void *opaque, Error **errp)
+{
+ VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
+ uint32_t value = vus->blk_size;
+
+ visit_type_uint32(v, name, &value, errp);
+}
+
+static void vu_set_blk_size(Object *obj, Visitor *v, const char *name,
+ void *opaque, Error **errp)
+{
+ VuBlockDev *vus = VHOST_USER_BLK_SERVER(obj);
+
+ Error *local_err = NULL;
+ uint32_t value;
+
+ if (!vu_prop_modifiable(vus, errp)) {
+ return;
+ }
+
+ visit_type_uint32(v, name, &value, &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ check_block_size(object_get_typename(obj), name, value, &local_err);
+ if (local_err) {
+ goto out;
+ }
+
+ vus->blk_size = value;
+
+out:
+ error_propagate(errp, local_err);
+}
+
+static void vhost_user_blk_server_instance_finalize(Object *obj)
+{
+ VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj);
+
+ vhost_user_blk_server_stop(vub);
+
+ /*
+ * Unlike object_property_add_str, object_class_property_add_str
+ * doesn't have a release method. Thus manual memory freeing is
+ * needed.
+ */
+ free_socket_addr(vub->addr);
+ g_free(vub->node_name);
+}
+
+static void vhost_user_blk_server_complete(UserCreatable *obj, Error **errp)
+{
+ VuBlockDev *vub = VHOST_USER_BLK_SERVER(obj);
+
+ vhost_user_blk_server_start(vub, errp);
+}
+
+static void vhost_user_blk_server_class_init(ObjectClass *klass,
+ void *class_data)
+{
+ UserCreatableClass *ucc = USER_CREATABLE_CLASS(klass);
+ ucc->complete = vhost_user_blk_server_complete;
+
+ object_class_property_add_bool(klass, "writable",
+ vu_get_block_writable,
+ vu_set_block_writable);
+
+ object_class_property_add_str(klass, "node-name",
+ vu_get_node_name,
+ vu_set_node_name);
+
+ object_class_property_add_str(klass, "unix-socket",
+ vu_get_unix_socket,
+ vu_set_unix_socket);
+
+ object_class_property_add(klass, "logical-block-size", "uint32",
+ vu_get_blk_size, vu_set_blk_size,
+ NULL, NULL);
+}
+
+static const TypeInfo vhost_user_blk_server_info = {
+ .name = TYPE_VHOST_USER_BLK_SERVER,
+ .parent = TYPE_OBJECT,
+ .instance_size = sizeof(VuBlockDev),
+ .instance_finalize = vhost_user_blk_server_instance_finalize,
+ .class_init = vhost_user_blk_server_class_init,
+ .interfaces = (InterfaceInfo[]) {
+ {TYPE_USER_CREATABLE},
+ {}
+ },
+};
+
+static void vhost_user_blk_server_register_types(void)
+{
+ type_register_static(&vhost_user_blk_server_info);
+}
+
+type_init(vhost_user_blk_server_register_types)
diff --git a/block/export/vhost-user-blk-server.h b/block/export/vhost-user-blk-server.h
new file mode 100644
index 0000000000..f06f37c4c8
--- /dev/null
+++ b/block/export/vhost-user-blk-server.h
@@ -0,0 +1,36 @@
+/*
+ * Sharing QEMU block devices via vhost-user protocal
+ *
+ * Copyright (c) Coiby Xu <coiby.xu@gmail.com>.
+ * Copyright (c) 2020 Red Hat, Inc.
+ *
+ * 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_USER_BLK_SERVER_H
+#define VHOST_USER_BLK_SERVER_H
+#include "util/vhost-user-server.h"
+
+typedef struct VuBlockDev VuBlockDev;
+#define TYPE_VHOST_USER_BLK_SERVER "vhost-user-blk-server"
+#define VHOST_USER_BLK_SERVER(obj) \
+ OBJECT_CHECK(VuBlockDev, obj, TYPE_VHOST_USER_BLK_SERVER)
+
+/* vhost user block device */
+struct VuBlockDev {
+ Object parent_obj;
+ char *node_name;
+ SocketAddress *addr;
+ AioContext *ctx;
+ VuServer vu_server;
+ bool running;
+ uint32_t blk_size;
+ BlockBackend *backend;
+ QIOChannelSocket *sioc;
+ QTAILQ_ENTRY(VuBlockDev) next;
+ struct virtio_blk_config blkcfg;
+ bool writable;
+};
+
+#endif /* VHOST_USER_BLK_SERVER_H */
diff --git a/block/meson.build b/block/meson.build
index a3e56b7cd1..6c7d9400e4 100644
--- a/block/meson.build
+++ b/block/meson.build
@@ -60,6 +60,7 @@ block_ss.add(when: 'CONFIG_WIN32', if_true: files('file-win32.c', 'win32-aio.c')
block_ss.add(when: 'CONFIG_POSIX', if_true: [files('file-posix.c'), coref, iokit])
block_ss.add(when: 'CONFIG_LIBISCSI', if_true: files('iscsi-opts.c'))
block_ss.add(when: 'CONFIG_LINUX', if_true: files('nvme.c'))
+block_ss.add(when: 'CONFIG_LINUX', if_true: files('export/vhost-user-blk-server.c', '../contrib/libvhost-user/libvhost-user.c'))
block_ss.add(when: 'CONFIG_REPLICATION', if_true: files('replication.c'))
block_ss.add(when: 'CONFIG_SHEEPDOG', if_true: files('sheepdog.c'))
block_ss.add(when: ['CONFIG_LINUX_AIO', libaio], if_true: files('linux-aio.c'))
diff --git a/softmmu/vl.c b/softmmu/vl.c
index f7b103467c..5128b81d40 100644
--- a/softmmu/vl.c
+++ b/softmmu/vl.c
@@ -2537,6 +2537,10 @@ static bool object_create_initial(const char *type, QemuOpts *opts)
}
#endif
+ /* Reason: vhost-user-blk-server property "node-name" */
+ if (g_str_equal(type, "vhost-user-blk-server")) {
+ return false;
+ }
/*
* Reason: filter-* property "netdev" etc.
*/
--
2.28.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* Re: [PATCH v10 5/7] block/export: vhost-user block device backend server
2020-09-18 8:09 ` [PATCH v10 5/7] block/export: vhost-user block device backend server Coiby Xu
@ 2020-09-18 9:44 ` Stefan Hajnoczi
0 siblings, 0 replies; 20+ messages in thread
From: Stefan Hajnoczi @ 2020-09-18 9:44 UTC (permalink / raw)
To: Coiby Xu
Cc: kwolf, open list:Block layer core, qemu-devel, Max Reitz,
bharatlkmlkvm, Paolo Bonzini
[-- Attachment #1: Type: text/plain, Size: 735 bytes --]
On Fri, Sep 18, 2020 at 04:09:10PM +0800, Coiby Xu wrote:
> + case VIRTIO_BLK_T_GET_ID: {
> + size_t size = MIN(iov_size(&elem->in_sg[0], in_num),
> + VIRTIO_BLK_ID_BYTES);
> + snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk_server");
gcc (GCC) 10.2.1 says:
../block/export/vhost-user-blk-server.c:178:50: error: ‘%s’ directive output truncated writing 21 bytes into a region of size 20 [-Werror=format-truncation=]
178 | snprintf(elem->in_sg[0].iov_base, size, "%s", "vhost_user_blk_server");
| ^~ ~~~~~~~~~~~~~~~~~~~~~~~
I suggest changing this string constant to "vhost_user_blk" for now.
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 20+ messages in thread
* [PATCH v10 6/7] test: new qTest case to test the vhost-user-blk-server
2020-09-18 8:09 [PATCH v10 0/7] vhost-user block device backend implementation Coiby Xu
` (4 preceding siblings ...)
2020-09-18 8:09 ` [PATCH v10 5/7] block/export: vhost-user block device backend server Coiby Xu
@ 2020-09-18 8:09 ` Coiby Xu
2020-09-23 12:36 ` Stefan Hajnoczi
2020-09-18 8:09 ` [PATCH v10 7/7] MAINTAINERS: Add vhost-user block device backend server maintainer Coiby Xu
` (4 subsequent siblings)
10 siblings, 1 reply; 20+ messages in thread
From: Coiby Xu @ 2020-09-18 8:09 UTC (permalink / raw)
To: qemu-devel
Cc: kwolf, Laurent Vivier, Thomas Huth, Coiby Xu, bharatlkmlkvm,
stefanha, Paolo Bonzini
This test case has the same tests as tests/virtio-blk-test.c except for
tests have block_resize. Since vhost-user server can only server one
client one time, two instances of vhost-user-blk-server are started by
qemu-storage-daemon for the hotplug test.
In order to not block scripts/tap-driver.pl, vhost-user-blk-server will
send "quit" command to qemu-storage-daemon's QMP monitor. So a function
is added to libqtest.c to establish socket connection with socket
server.
Suggested-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Coiby Xu <coiby.xu@gmail.com>
---
tests/qtest/libqos/libqtest.h | 17 +
tests/qtest/libqos/meson.build | 1 +
tests/qtest/libqos/vhost-user-blk.c | 129 +++++
tests/qtest/libqos/vhost-user-blk.h | 48 ++
tests/qtest/libqtest.c | 36 +-
tests/qtest/meson.build | 4 +-
tests/qtest/vhost-user-blk-test.c | 751 ++++++++++++++++++++++++++++
7 files changed, 983 insertions(+), 3 deletions(-)
create mode 100644 tests/qtest/libqos/vhost-user-blk.c
create mode 100644 tests/qtest/libqos/vhost-user-blk.h
create mode 100644 tests/qtest/vhost-user-blk-test.c
diff --git a/tests/qtest/libqos/libqtest.h b/tests/qtest/libqos/libqtest.h
index a6ee1654f2..2c20381cee 100644
--- a/tests/qtest/libqos/libqtest.h
+++ b/tests/qtest/libqos/libqtest.h
@@ -132,6 +132,23 @@ void qtest_qmp_send(QTestState *s, const char *fmt, ...)
void qtest_qmp_send_raw(QTestState *s, const char *fmt, ...)
GCC_FMT_ATTR(2, 3);
+/**
+ * qtest_socket_client:
+ * @server_socket_path: the socket server's path
+ *
+ * Connect to a socket server.
+ */
+int qtest_socket_client(char *server_socket_path);
+
+/**
+ * qtest_create_state_with_qmp_fd:
+ * @fd: socket fd
+ *
+ * Wrap socket fd in QTestState to make use of qtest_qmp*
+ * functions
+ */
+QTestState *qtest_create_state_with_qmp_fd(int fd);
+
/**
* qtest_vqmp_fds:
* @s: #QTestState instance to operate on.
diff --git a/tests/qtest/libqos/meson.build b/tests/qtest/libqos/meson.build
index 1cddf5bdaa..1f5c8f1053 100644
--- a/tests/qtest/libqos/meson.build
+++ b/tests/qtest/libqos/meson.build
@@ -32,6 +32,7 @@ libqos_srcs = files('../libqtest.c',
'virtio-9p.c',
'virtio-balloon.c',
'virtio-blk.c',
+ 'vhost-user-blk.c',
'virtio-mmio.c',
'virtio-net.c',
'virtio-pci.c',
diff --git a/tests/qtest/libqos/vhost-user-blk.c b/tests/qtest/libqos/vhost-user-blk.c
new file mode 100644
index 0000000000..58c7e1eb69
--- /dev/null
+++ b/tests/qtest/libqos/vhost-user-blk.c
@@ -0,0 +1,129 @@
+/*
+ * libqos driver framework
+ *
+ * Based on tests/qtest/libqos/virtio-blk.c
+ *
+ * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.com>
+ *
+ * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com>
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License version 2.1 as published by the Free Software Foundation.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>
+ */
+
+#include "qemu/osdep.h"
+#include "libqtest.h"
+#include "qemu/module.h"
+#include "standard-headers/linux/virtio_blk.h"
+#include "vhost-user-blk.h"
+
+#define PCI_SLOT 0x04
+#define PCI_FN 0x00
+
+/* virtio-blk-device */
+static void *qvhost_user_blk_get_driver(QVhostUserBlk *v_blk,
+ const char *interface)
+{
+ if (!g_strcmp0(interface, "vhost-user-blk")) {
+ return v_blk;
+ }
+ if (!g_strcmp0(interface, "virtio")) {
+ return v_blk->vdev;
+ }
+
+ fprintf(stderr, "%s not present in vhost-user-blk-device\n", interface);
+ g_assert_not_reached();
+}
+
+static void *qvhost_user_blk_device_get_driver(void *object,
+ const char *interface)
+{
+ QVhostUserBlkDevice *v_blk = object;
+ return qvhost_user_blk_get_driver(&v_blk->blk, interface);
+}
+
+static void *vhost_user_blk_device_create(void *virtio_dev,
+ QGuestAllocator *t_alloc,
+ void *addr)
+{
+ QVhostUserBlkDevice *vhost_user_blk = g_new0(QVhostUserBlkDevice, 1);
+ QVhostUserBlk *interface = &vhost_user_blk->blk;
+
+ interface->vdev = virtio_dev;
+
+ vhost_user_blk->obj.get_driver = qvhost_user_blk_device_get_driver;
+
+ return &vhost_user_blk->obj;
+}
+
+/* virtio-blk-pci */
+static void *qvhost_user_blk_pci_get_driver(void *object, const char *interface)
+{
+ QVhostUserBlkPCI *v_blk = object;
+ if (!g_strcmp0(interface, "pci-device")) {
+ return v_blk->pci_vdev.pdev;
+ }
+ return qvhost_user_blk_get_driver(&v_blk->blk, interface);
+}
+
+static void *vhost_user_blk_pci_create(void *pci_bus, QGuestAllocator *t_alloc,
+ void *addr)
+{
+ QVhostUserBlkPCI *vhost_user_blk = g_new0(QVhostUserBlkPCI, 1);
+ QVhostUserBlk *interface = &vhost_user_blk->blk;
+ QOSGraphObject *obj = &vhost_user_blk->pci_vdev.obj;
+
+ virtio_pci_init(&vhost_user_blk->pci_vdev, pci_bus, addr);
+ interface->vdev = &vhost_user_blk->pci_vdev.vdev;
+
+ g_assert_cmphex(interface->vdev->device_type, ==, VIRTIO_ID_BLOCK);
+
+ obj->get_driver = qvhost_user_blk_pci_get_driver;
+
+ return obj;
+}
+
+static void vhost_user_blk_register_nodes(void)
+{
+ /*
+ * FIXME: every test using these two nodes needs to setup a
+ * -drive,id=drive0 otherwise QEMU is not going to start.
+ * Therefore, we do not include "produces" edge for virtio
+ * and pci-device yet.
+ */
+
+ char *arg = g_strdup_printf("id=drv0,chardev=char1,addr=%x.%x",
+ PCI_SLOT, PCI_FN);
+
+ QPCIAddress addr = {
+ .devfn = QPCI_DEVFN(PCI_SLOT, PCI_FN),
+ };
+
+ QOSGraphEdgeOptions opts = { };
+
+ /* virtio-blk-device */
+ /** opts.extra_device_opts = "drive=drive0"; */
+ qos_node_create_driver("vhost-user-blk-device", vhost_user_blk_device_create);
+ qos_node_consumes("vhost-user-blk-device", "virtio-bus", &opts);
+ qos_node_produces("vhost-user-blk-device", "vhost-user-blk");
+
+ /* virtio-blk-pci */
+ opts.extra_device_opts = arg;
+ add_qpci_address(&opts, &addr);
+ qos_node_create_driver("vhost-user-blk-pci", vhost_user_blk_pci_create);
+ qos_node_consumes("vhost-user-blk-pci", "pci-bus", &opts);
+ qos_node_produces("vhost-user-blk-pci", "vhost-user-blk");
+
+ g_free(arg);
+}
+
+libqos_init(vhost_user_blk_register_nodes);
diff --git a/tests/qtest/libqos/vhost-user-blk.h b/tests/qtest/libqos/vhost-user-blk.h
new file mode 100644
index 0000000000..2a03456a45
--- /dev/null
+++ b/tests/qtest/libqos/vhost-user-blk.h
@@ -0,0 +1,48 @@
+/*
+ * libqos driver framework
+ *
+ * Based on tests/qtest/libqos/virtio-blk.c
+ *
+ * Copyright (c) 2020 Coiby Xu <coiby.xu@gmail.com>
+ *
+ * Copyright (c) 2018 Emanuele Giuseppe Esposito <e.emanuelegiuseppe@gmail.com>
+ *
+ * This library is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License version 2 as published by the Free Software Foundation.
+ *
+ * This library is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>
+ */
+
+#ifndef TESTS_LIBQOS_VHOST_USER_BLK_H
+#define TESTS_LIBQOS_VHOST_USER_BLK_H
+
+#include "qgraph.h"
+#include "virtio.h"
+#include "virtio-pci.h"
+
+typedef struct QVhostUserBlk QVhostUserBlk;
+typedef struct QVhostUserBlkPCI QVhostUserBlkPCI;
+typedef struct QVhostUserBlkDevice QVhostUserBlkDevice;
+
+struct QVhostUserBlk {
+ QVirtioDevice *vdev;
+};
+
+struct QVhostUserBlkPCI {
+ QVirtioPCIDevice pci_vdev;
+ QVhostUserBlk blk;
+};
+
+struct QVhostUserBlkDevice {
+ QOSGraphObject obj;
+ QVhostUserBlk blk;
+};
+
+#endif
diff --git a/tests/qtest/libqtest.c b/tests/qtest/libqtest.c
index 58f58e1ece..ba19011737 100644
--- a/tests/qtest/libqtest.c
+++ b/tests/qtest/libqtest.c
@@ -4,11 +4,13 @@
* Copyright IBM, Corp. 2012
* Copyright Red Hat, Inc. 2012
* Copyright SUSE LINUX Products GmbH 2013
+ * Copyright Copyright (c) Coiby Xu
*
* Authors:
* Anthony Liguori <aliguori@us.ibm.com>
* Paolo Bonzini <pbonzini@redhat.com>
* Andreas Färber <afaerber@suse.de>
+ * Coiby Xu <coiby.xu@gmail.com>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
@@ -52,8 +54,7 @@ typedef struct QTestClientTransportOps {
QTestRecvFn recv_line; /* for receiving qtest command responses */
} QTestTransportOps;
-struct QTestState
-{
+struct QTestState {
int fd;
int qmp_fd;
pid_t qemu_pid; /* our child QEMU process */
@@ -608,6 +609,37 @@ QDict *qtest_qmp_receive(QTestState *s)
return qmp_fd_receive(s->qmp_fd);
}
+QTestState *qtest_create_state_with_qmp_fd(int fd)
+{
+ QTestState *qmp_test_state = g_new0(QTestState, 1);
+ qmp_test_state->qmp_fd = fd;
+ return qmp_test_state;
+}
+
+int qtest_socket_client(char *server_socket_path)
+{
+ struct sockaddr_un serv_addr;
+ int sock;
+ int ret;
+ int retries = 0;
+ sock = socket(PF_UNIX, SOCK_STREAM, 0);
+ g_assert_cmpint(sock, !=, -1);
+ serv_addr.sun_family = AF_UNIX;
+ snprintf(serv_addr.sun_path, sizeof(serv_addr.sun_path), "%s",
+ server_socket_path);
+
+ for (retries = 0; retries < 3; retries++) {
+ ret = connect(sock, (struct sockaddr *)&serv_addr, sizeof(serv_addr));
+ if (ret == 0) {
+ break;
+ }
+ g_usleep(G_USEC_PER_SEC);
+ }
+
+ g_assert_cmpint(ret, ==, 0);
+ return sock;
+}
+
/**
* Allow users to send a message without waiting for the reply,
* in the case that they choose to discard all replies up until
diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build
index 874b5be62b..c72821b09a 100644
--- a/tests/qtest/meson.build
+++ b/tests/qtest/meson.build
@@ -191,6 +191,7 @@ qos_test_ss.add(
)
qos_test_ss.add(when: 'CONFIG_VIRTFS', if_true: files('virtio-9p-test.c'))
qos_test_ss.add(when: 'CONFIG_VHOST_USER', if_true: files('vhost-user-test.c'))
+qos_test_ss.add(when: 'CONFIG_LINUX', if_true: files('vhost-user-blk-test.c'))
extra_qtest_deps = {
'bios-tables-test': [io],
@@ -234,7 +235,8 @@ foreach dir : target_dirs
qtest_env.set('QTEST_QEMU_IMG', './qemu-img')
qtest_env.set('G_TEST_DBUS_DAEMON', meson.source_root() / 'tests/dbus-vmstate-daemon.sh')
qtest_env.set('QTEST_QEMU_BINARY', './qemu-system-' + target_base)
-
+ qtest_env.set('QTEST_QEMU_STORAGE_DAEMON_BINARY', './storage-daemon/qemu-storage-daemon')
+
foreach test : qtests
# Executables are shared across targets, declare them only the first time we
# encounter them
diff --git a/tests/qtest/vhost-user-blk-test.c b/tests/qtest/vhost-user-blk-test.c
new file mode 100644
index 0000000000..d4ccac6b54
--- /dev/null
+++ b/tests/qtest/vhost-user-blk-test.c
@@ -0,0 +1,751 @@
+/*
+ * QTest testcase for Vhost-user Block Device
+ *
+ * Based on tests/qtest//virtio-blk-test.c
+
+ * Copyright (c) 2014 SUSE LINUX Products GmbH
+ * Copyright (c) 2014 Marc Marí
+ * Copyright (c) 2020 Coiby Xu
+ *
+ * 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 "qemu/osdep.h"
+#include "libqtest-single.h"
+#include "qemu/bswap.h"
+#include "qemu/module.h"
+#include "standard-headers/linux/virtio_blk.h"
+#include "standard-headers/linux/virtio_pci.h"
+#include "libqos/qgraph.h"
+#include "libqos/vhost-user-blk.h"
+#include "libqos/libqos-pc.h"
+
+#define TEST_IMAGE_SIZE (64 * 1024 * 1024)
+#define QVIRTIO_BLK_TIMEOUT_US (30 * 1000 * 1000)
+#define PCI_SLOT_HP 0x06
+
+typedef struct QVirtioBlkReq {
+ uint32_t type;
+ uint32_t ioprio;
+ uint64_t sector;
+ char *data;
+ uint8_t status;
+} QVirtioBlkReq;
+
+#ifdef HOST_WORDS_BIGENDIAN
+static const bool host_is_big_endian = true;
+#else
+static const bool host_is_big_endian; /* false */
+#endif
+
+static inline void virtio_blk_fix_request(QVirtioDevice *d, QVirtioBlkReq *req)
+{
+ if (qvirtio_is_big_endian(d) != host_is_big_endian) {
+ req->type = bswap32(req->type);
+ req->ioprio = bswap32(req->ioprio);
+ req->sector = bswap64(req->sector);
+ }
+}
+
+static inline void virtio_blk_fix_dwz_hdr(QVirtioDevice *d,
+ struct virtio_blk_discard_write_zeroes *dwz_hdr)
+{
+ if (qvirtio_is_big_endian(d) != host_is_big_endian) {
+ dwz_hdr->sector = bswap64(dwz_hdr->sector);
+ dwz_hdr->num_sectors = bswap32(dwz_hdr->num_sectors);
+ dwz_hdr->flags = bswap32(dwz_hdr->flags);
+ }
+}
+
+static uint64_t virtio_blk_request(QGuestAllocator *alloc, QVirtioDevice *d,
+ QVirtioBlkReq *req, uint64_t data_size)
+{
+ uint64_t addr;
+ uint8_t status = 0xFF;
+ QTestState *qts = global_qtest;
+
+ switch (req->type) {
+ case VIRTIO_BLK_T_IN:
+ case VIRTIO_BLK_T_OUT:
+ g_assert_cmpuint(data_size % 512, ==, 0);
+ break;
+ case VIRTIO_BLK_T_DISCARD:
+ case VIRTIO_BLK_T_WRITE_ZEROES:
+ g_assert_cmpuint(data_size %
+ sizeof(struct virtio_blk_discard_write_zeroes), ==, 0);
+ break;
+ default:
+ g_assert_cmpuint(data_size, ==, 0);
+ }
+
+ addr = guest_alloc(alloc, sizeof(*req) + data_size);
+
+ virtio_blk_fix_request(d, req);
+
+ qtest_memwrite(qts, addr, req, 16);
+ qtest_memwrite(qts, addr + 16, req->data, data_size);
+ qtest_memwrite(qts, addr + 16 + data_size, &status, sizeof(status));
+
+ return addr;
+}
+
+/* Returns the request virtqueue so the caller can perform further tests */
+static QVirtQueue *test_basic(QVirtioDevice *dev, QGuestAllocator *alloc)
+{
+ QVirtioBlkReq req;
+ uint64_t req_addr;
+ uint64_t capacity;
+ uint64_t features;
+ uint32_t free_head;
+ uint8_t status;
+ char *data;
+ QTestState *qts = global_qtest;
+ QVirtQueue *vq;
+
+ features = qvirtio_get_features(dev);
+ features = features & ~(QVIRTIO_F_BAD_FEATURE |
+ (1u << VIRTIO_RING_F_INDIRECT_DESC) |
+ (1u << VIRTIO_RING_F_EVENT_IDX) |
+ (1u << VIRTIO_BLK_F_SCSI));
+ qvirtio_set_features(dev, features);
+
+ capacity = qvirtio_config_readq(dev, 0);
+ g_assert_cmpint(capacity, ==, TEST_IMAGE_SIZE / 512);
+
+ vq = qvirtqueue_setup(dev, alloc, 0);
+
+ qvirtio_set_driver_ok(dev);
+
+ /* Write and read with 3 descriptor layout */
+ /* Write request */
+ req.type = VIRTIO_BLK_T_OUT;
+ req.ioprio = 1;
+ req.sector = 0;
+ req.data = g_malloc0(512);
+ strcpy(req.data, "TEST");
+
+ req_addr = virtio_blk_request(alloc, dev, &req, 512);
+
+ g_free(req.data);
+
+ free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 16, 512, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false);
+
+ qvirtqueue_kick(qts, dev, vq, free_head);
+
+ qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL,
+ QVIRTIO_BLK_TIMEOUT_US);
+ status = readb(req_addr + 528);
+ g_assert_cmpint(status, ==, 0);
+
+ guest_free(alloc, req_addr);
+
+ /* Read request */
+ req.type = VIRTIO_BLK_T_IN;
+ req.ioprio = 1;
+ req.sector = 0;
+ req.data = g_malloc0(512);
+
+ req_addr = virtio_blk_request(alloc, dev, &req, 512);
+
+ g_free(req.data);
+
+ free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 16, 512, true, true);
+ qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false);
+
+ qvirtqueue_kick(qts, dev, vq, free_head);
+
+ qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL,
+ QVIRTIO_BLK_TIMEOUT_US);
+ status = readb(req_addr + 528);
+ g_assert_cmpint(status, ==, 0);
+
+ data = g_malloc0(512);
+ qtest_memread(qts, req_addr + 16, data, 512);
+ g_assert_cmpstr(data, ==, "TEST");
+ g_free(data);
+
+ guest_free(alloc, req_addr);
+
+ if (features & (1u << VIRTIO_BLK_F_WRITE_ZEROES)) {
+ struct virtio_blk_discard_write_zeroes dwz_hdr;
+ void *expected;
+
+ /*
+ * WRITE_ZEROES request on the same sector of previous test where
+ * we wrote "TEST".
+ */
+ req.type = VIRTIO_BLK_T_WRITE_ZEROES;
+ req.data = (char *) &dwz_hdr;
+ dwz_hdr.sector = 0;
+ dwz_hdr.num_sectors = 1;
+ dwz_hdr.flags = 0;
+
+ virtio_blk_fix_dwz_hdr(dev, &dwz_hdr);
+
+ req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr));
+
+ free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 16, sizeof(dwz_hdr), false, true);
+ qvirtqueue_add(qts, vq, req_addr + 16 + sizeof(dwz_hdr), 1, true,
+ false);
+
+ qvirtqueue_kick(qts, dev, vq, free_head);
+
+ qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL,
+ QVIRTIO_BLK_TIMEOUT_US);
+ status = readb(req_addr + 16 + sizeof(dwz_hdr));
+ g_assert_cmpint(status, ==, 0);
+
+ guest_free(alloc, req_addr);
+
+ /* Read request to check if the sector contains all zeroes */
+ req.type = VIRTIO_BLK_T_IN;
+ req.ioprio = 1;
+ req.sector = 0;
+ req.data = g_malloc0(512);
+
+ req_addr = virtio_blk_request(alloc, dev, &req, 512);
+
+ g_free(req.data);
+
+ free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 16, 512, true, true);
+ qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false);
+
+ qvirtqueue_kick(qts, dev, vq, free_head);
+
+ qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL,
+ QVIRTIO_BLK_TIMEOUT_US);
+ status = readb(req_addr + 528);
+ g_assert_cmpint(status, ==, 0);
+
+ data = g_malloc(512);
+ expected = g_malloc0(512);
+ qtest_memread(qts, req_addr + 16, data, 512);
+ g_assert_cmpmem(data, 512, expected, 512);
+ g_free(expected);
+ g_free(data);
+
+ guest_free(alloc, req_addr);
+ }
+
+ if (features & (1u << VIRTIO_BLK_F_DISCARD)) {
+ struct virtio_blk_discard_write_zeroes dwz_hdr;
+
+ req.type = VIRTIO_BLK_T_DISCARD;
+ req.data = (char *) &dwz_hdr;
+ dwz_hdr.sector = 0;
+ dwz_hdr.num_sectors = 1;
+ dwz_hdr.flags = 0;
+
+ virtio_blk_fix_dwz_hdr(dev, &dwz_hdr);
+
+ req_addr = virtio_blk_request(alloc, dev, &req, sizeof(dwz_hdr));
+
+ free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 16, sizeof(dwz_hdr), false, true);
+ qvirtqueue_add(qts, vq, req_addr + 16 + sizeof(dwz_hdr),
+ 1, true, false);
+
+ qvirtqueue_kick(qts, dev, vq, free_head);
+
+ qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL,
+ QVIRTIO_BLK_TIMEOUT_US);
+ status = readb(req_addr + 16 + sizeof(dwz_hdr));
+ g_assert_cmpint(status, ==, 0);
+
+ guest_free(alloc, req_addr);
+ }
+
+ if (features & (1u << VIRTIO_F_ANY_LAYOUT)) {
+ /* Write and read with 2 descriptor layout */
+ /* Write request */
+ req.type = VIRTIO_BLK_T_OUT;
+ req.ioprio = 1;
+ req.sector = 1;
+ req.data = g_malloc0(512);
+ strcpy(req.data, "TEST");
+
+ req_addr = virtio_blk_request(alloc, dev, &req, 512);
+
+ g_free(req.data);
+
+ free_head = qvirtqueue_add(qts, vq, req_addr, 528, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false);
+ qvirtqueue_kick(qts, dev, vq, free_head);
+
+ qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL,
+ QVIRTIO_BLK_TIMEOUT_US);
+ status = readb(req_addr + 528);
+ g_assert_cmpint(status, ==, 0);
+
+ guest_free(alloc, req_addr);
+
+ /* Read request */
+ req.type = VIRTIO_BLK_T_IN;
+ req.ioprio = 1;
+ req.sector = 1;
+ req.data = g_malloc0(512);
+
+ req_addr = virtio_blk_request(alloc, dev, &req, 512);
+
+ g_free(req.data);
+
+ free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 16, 513, true, false);
+
+ qvirtqueue_kick(qts, dev, vq, free_head);
+
+ qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL,
+ QVIRTIO_BLK_TIMEOUT_US);
+ status = readb(req_addr + 528);
+ g_assert_cmpint(status, ==, 0);
+
+ data = g_malloc0(512);
+ qtest_memread(qts, req_addr + 16, data, 512);
+ g_assert_cmpstr(data, ==, "TEST");
+ g_free(data);
+
+ guest_free(alloc, req_addr);
+ }
+
+ return vq;
+}
+
+static void basic(void *obj, void *data, QGuestAllocator *t_alloc)
+{
+ QVhostUserBlk *blk_if = obj;
+ QVirtQueue *vq;
+
+ vq = test_basic(blk_if->vdev, t_alloc);
+ qvirtqueue_cleanup(blk_if->vdev->bus, vq, t_alloc);
+
+}
+
+static void indirect(void *obj, void *u_data, QGuestAllocator *t_alloc)
+{
+ QVirtQueue *vq;
+ QVhostUserBlk *blk_if = obj;
+ QVirtioDevice *dev = blk_if->vdev;
+ QVirtioBlkReq req;
+ QVRingIndirectDesc *indirect;
+ uint64_t req_addr;
+ uint64_t capacity;
+ uint64_t features;
+ uint32_t free_head;
+ uint8_t status;
+ char *data;
+ QTestState *qts = global_qtest;
+
+ features = qvirtio_get_features(dev);
+ g_assert_cmphex(features & (1u << VIRTIO_RING_F_INDIRECT_DESC), !=, 0);
+ features = features & ~(QVIRTIO_F_BAD_FEATURE |
+ (1u << VIRTIO_RING_F_EVENT_IDX) |
+ (1u << VIRTIO_BLK_F_SCSI));
+ qvirtio_set_features(dev, features);
+
+ capacity = qvirtio_config_readq(dev, 0);
+ g_assert_cmpint(capacity, ==, TEST_IMAGE_SIZE / 512);
+
+ vq = qvirtqueue_setup(dev, t_alloc, 0);
+ qvirtio_set_driver_ok(dev);
+
+ /* Write request */
+ req.type = VIRTIO_BLK_T_OUT;
+ req.ioprio = 1;
+ req.sector = 0;
+ req.data = g_malloc0(512);
+ strcpy(req.data, "TEST");
+
+ req_addr = virtio_blk_request(t_alloc, dev, &req, 512);
+
+ g_free(req.data);
+
+ indirect = qvring_indirect_desc_setup(qts, dev, t_alloc, 2);
+ qvring_indirect_desc_add(dev, qts, indirect, req_addr, 528, false);
+ qvring_indirect_desc_add(dev, qts, indirect, req_addr + 528, 1, true);
+ free_head = qvirtqueue_add_indirect(qts, vq, indirect);
+ qvirtqueue_kick(qts, dev, vq, free_head);
+
+ qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL,
+ QVIRTIO_BLK_TIMEOUT_US);
+ status = readb(req_addr + 528);
+ g_assert_cmpint(status, ==, 0);
+
+ g_free(indirect);
+ guest_free(t_alloc, req_addr);
+
+ /* Read request */
+ req.type = VIRTIO_BLK_T_IN;
+ req.ioprio = 1;
+ req.sector = 0;
+ req.data = g_malloc0(512);
+ strcpy(req.data, "TEST");
+
+ req_addr = virtio_blk_request(t_alloc, dev, &req, 512);
+
+ g_free(req.data);
+
+ indirect = qvring_indirect_desc_setup(qts, dev, t_alloc, 2);
+ qvring_indirect_desc_add(dev, qts, indirect, req_addr, 16, false);
+ qvring_indirect_desc_add(dev, qts, indirect, req_addr + 16, 513, true);
+ free_head = qvirtqueue_add_indirect(qts, vq, indirect);
+ qvirtqueue_kick(qts, dev, vq, free_head);
+
+ qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL,
+ QVIRTIO_BLK_TIMEOUT_US);
+ status = readb(req_addr + 528);
+ g_assert_cmpint(status, ==, 0);
+
+ data = g_malloc0(512);
+ qtest_memread(qts, req_addr + 16, data, 512);
+ g_assert_cmpstr(data, ==, "TEST");
+ g_free(data);
+
+ g_free(indirect);
+ guest_free(t_alloc, req_addr);
+ qvirtqueue_cleanup(dev->bus, vq, t_alloc);
+}
+
+static void idx(void *obj, void *u_data, QGuestAllocator *t_alloc)
+{
+ QVirtQueue *vq;
+ QVhostUserBlkPCI *blk = obj;
+ QVirtioPCIDevice *pdev = &blk->pci_vdev;
+ QVirtioDevice *dev = &pdev->vdev;
+ QVirtioBlkReq req;
+ uint64_t req_addr;
+ uint64_t capacity;
+ uint64_t features;
+ uint32_t free_head;
+ uint32_t write_head;
+ uint32_t desc_idx;
+ uint8_t status;
+ char *data;
+ QOSGraphObject *blk_object = obj;
+ QPCIDevice *pci_dev = blk_object->get_driver(blk_object, "pci-device");
+ QTestState *qts = global_qtest;
+
+ if (qpci_check_buggy_msi(pci_dev)) {
+ return;
+ }
+
+ qpci_msix_enable(pdev->pdev);
+ qvirtio_pci_set_msix_configuration_vector(pdev, t_alloc, 0);
+
+ features = qvirtio_get_features(dev);
+ features = features & ~(QVIRTIO_F_BAD_FEATURE |
+ (1u << VIRTIO_RING_F_INDIRECT_DESC) |
+ (1u << VIRTIO_F_NOTIFY_ON_EMPTY) |
+ (1u << VIRTIO_BLK_F_SCSI));
+ qvirtio_set_features(dev, features);
+
+ capacity = qvirtio_config_readq(dev, 0);
+ g_assert_cmpint(capacity, ==, TEST_IMAGE_SIZE / 512);
+
+ vq = qvirtqueue_setup(dev, t_alloc, 0);
+ qvirtqueue_pci_msix_setup(pdev, (QVirtQueuePCI *)vq, t_alloc, 1);
+
+ qvirtio_set_driver_ok(dev);
+
+ /* Write request */
+ req.type = VIRTIO_BLK_T_OUT;
+ req.ioprio = 1;
+ req.sector = 0;
+ req.data = g_malloc0(512);
+ strcpy(req.data, "TEST");
+
+ req_addr = virtio_blk_request(t_alloc, dev, &req, 512);
+
+ g_free(req.data);
+
+ free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 16, 512, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false);
+ qvirtqueue_kick(qts, dev, vq, free_head);
+
+ qvirtio_wait_used_elem(qts, dev, vq, free_head, NULL,
+ QVIRTIO_BLK_TIMEOUT_US);
+
+ /* Write request */
+ req.type = VIRTIO_BLK_T_OUT;
+ req.ioprio = 1;
+ req.sector = 1;
+ req.data = g_malloc0(512);
+ strcpy(req.data, "TEST");
+
+ req_addr = virtio_blk_request(t_alloc, dev, &req, 512);
+
+ g_free(req.data);
+
+ /* Notify after processing the third request */
+ qvirtqueue_set_used_event(qts, vq, 2);
+ free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 16, 512, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false);
+ qvirtqueue_kick(qts, dev, vq, free_head);
+ write_head = free_head;
+
+ /* No notification expected */
+ status = qvirtio_wait_status_byte_no_isr(qts, dev,
+ vq, req_addr + 528,
+ QVIRTIO_BLK_TIMEOUT_US);
+ g_assert_cmpint(status, ==, 0);
+
+ guest_free(t_alloc, req_addr);
+
+ /* Read request */
+ req.type = VIRTIO_BLK_T_IN;
+ req.ioprio = 1;
+ req.sector = 1;
+ req.data = g_malloc0(512);
+
+ req_addr = virtio_blk_request(t_alloc, dev, &req, 512);
+
+ g_free(req.data);
+
+ free_head = qvirtqueue_add(qts, vq, req_addr, 16, false, true);
+ qvirtqueue_add(qts, vq, req_addr + 16, 512, true, true);
+ qvirtqueue_add(qts, vq, req_addr + 528, 1, true, false);
+
+ qvirtqueue_kick(qts, dev, vq, free_head);
+
+ /* We get just one notification for both requests */
+ qvirtio_wait_used_elem(qts, dev, vq, write_head, NULL,
+ QVIRTIO_BLK_TIMEOUT_US);
+ g_assert(qvirtqueue_get_buf(qts, vq, &desc_idx, NULL));
+ g_assert_cmpint(desc_idx, ==, free_head);
+
+ status = readb(req_addr + 528);
+ g_assert_cmpint(status, ==, 0);
+
+ data = g_malloc0(512);
+ qtest_memread(qts, req_addr + 16, data, 512);
+ g_assert_cmpstr(data, ==, "TEST");
+ g_free(data);
+
+ guest_free(t_alloc, req_addr);
+
+ /* End test */
+ qpci_msix_disable(pdev->pdev);
+
+ qvirtqueue_cleanup(dev->bus, vq, t_alloc);
+}
+
+static void pci_hotplug(void *obj, void *data, QGuestAllocator *t_alloc)
+{
+ QVirtioPCIDevice *dev1 = obj;
+ QVirtioPCIDevice *dev;
+ QTestState *qts = dev1->pdev->bus->qts;
+
+ /* plug secondary disk */
+ qtest_qmp_device_add(qts, "vhost-user-blk-pci", "drv1",
+ "{'addr': %s, 'chardev': 'char2'}",
+ stringify(PCI_SLOT_HP) ".0");
+
+ dev = virtio_pci_new(dev1->pdev->bus,
+ &(QPCIAddress) { .devfn = QPCI_DEVFN(PCI_SLOT_HP, 0)
+ });
+ g_assert_nonnull(dev);
+ g_assert_cmpint(dev->vdev.device_type, ==, VIRTIO_ID_BLOCK);
+ qvirtio_pci_device_disable(dev);
+ qos_object_destroy((QOSGraphObject *)dev);
+
+ /* unplug secondary disk */
+ qpci_unplug_acpi_device_test(qts, "drv1", PCI_SLOT_HP);
+}
+
+/*
+ * Check that setting the vring addr on a non-existent virtqueue does
+ * not crash.
+ */
+static void test_nonexistent_virtqueue(void *obj, void *data,
+ QGuestAllocator *t_alloc)
+{
+ QVhostUserBlkPCI *blk = obj;
+ QVirtioPCIDevice *pdev = &blk->pci_vdev;
+ QPCIBar bar0;
+ QPCIDevice *dev;
+
+ dev = qpci_device_find(pdev->pdev->bus, QPCI_DEVFN(4, 0));
+ g_assert(dev != NULL);
+ qpci_device_enable(dev);
+
+ bar0 = qpci_iomap(dev, 0, NULL);
+
+ qpci_io_writeb(dev, bar0, VIRTIO_PCI_QUEUE_SEL, 2);
+ qpci_io_writel(dev, bar0, VIRTIO_PCI_QUEUE_PFN, 1);
+
+ g_free(dev);
+}
+
+static const char *qtest_qemu_storage_daemon_binary(void)
+{
+ const char *qemu_storage_daemon_bin;
+
+ qemu_storage_daemon_bin = getenv("QTEST_QEMU_STORAGE_DAEMON_BINARY");
+ if (!qemu_storage_daemon_bin) {
+ fprintf(stderr, "Environment variable "
+ "QTEST_QEMU_STORAGE_DAEMON_BINARY required\n");
+ exit(0);
+ }
+
+ return qemu_storage_daemon_bin;
+}
+
+static void drive_destroy(void *path)
+{
+ unlink(path);
+ g_free(path);
+ qos_invalidate_command_line();
+}
+
+static char *drive_create(void)
+{
+ int fd, ret;
+ /** vhost-user-blk won't recognize drive located in /tmp */
+ char *t_path = g_strdup("qtest.XXXXXX");
+
+ /** Create a temporary raw image */
+ fd = mkstemp(t_path);
+ g_assert_cmpint(fd, >=, 0);
+ ret = ftruncate(fd, TEST_IMAGE_SIZE);
+ g_assert_cmpint(ret, ==, 0);
+ close(fd);
+
+ g_test_queue_destroy(drive_destroy, t_path);
+ return t_path;
+}
+
+static char sock_path_tempate[] = "/tmp/qtest.vhost_user_blk.XXXXXX";
+static char qmp_sock_path_tempate[] = "/tmp/qtest.vhost_user_blk.qmp.XXXXXX";
+
+static void quit_storage_daemon(void *qmp_test_state)
+{
+ const char quit_str[] = "{ 'execute': 'quit' }";
+
+ /* Before quiting storate-daemon, quit qemu to avoid dubious messages */
+ qobject_unref(qtest_qmp(global_qtest, quit_str));
+
+ /*
+ * Give storage-daemon enough time to wake up&terminate
+ * vu_client_trip coroutine so the Coroutine object could
+ * be cleaned up. Otherwise LeakSanitizer would complain
+ * about memory leaks.
+ */
+ g_usleep(1000);
+
+ qobject_unref(qtest_qmp((QTestState *)qmp_test_state, quit_str));
+ g_free(qmp_test_state);
+}
+
+static char *start_vhost_user_blk(GString *cmd_line, int vus_instances)
+{
+ const char *vhost_user_blk_bin = qtest_qemu_storage_daemon_binary();
+ int fd, qmp_fd, i;
+ QTestState *qmp_test_state;
+ gchar *img_path;
+ char *sock_path = NULL;
+ char *qmp_sock_path = g_strdup(qmp_sock_path_tempate);
+ GString *storage_daemon_command = g_string_new(NULL);
+
+ qmp_fd = mkstemp(qmp_sock_path);
+ g_assert_cmpint(qmp_fd, >=, 0);
+ g_test_queue_destroy(drive_destroy, qmp_sock_path);
+
+ g_string_append_printf(storage_daemon_command,
+ "exec %s "
+ "--chardev socket,id=qmp,path=%s,server,nowait --monitor chardev=qmp ",
+ vhost_user_blk_bin, qmp_sock_path);
+
+ g_string_append_printf(cmd_line,
+ " -object memory-backend-memfd,id=mem,size=128M,share=on -numa node,memdev=mem ");
+
+ for (i = 0; i < vus_instances; i++) {
+ sock_path = g_strdup(sock_path_tempate);
+ fd = mkstemp(sock_path);
+ g_assert_cmpint(fd, >=, 0);
+ g_test_queue_destroy(drive_destroy, sock_path);
+ /* create image file */
+ img_path = drive_create();
+ g_string_append_printf(storage_daemon_command,
+ "--blockdev driver=file,node-name=disk%d,filename=%s "
+ "--object vhost-user-blk-server,id=disk%d,unix-socket=%s,"
+ "node-name=disk%i,writable=on ",
+ i, img_path, i, sock_path, i);
+
+ g_string_append_printf(cmd_line, "-chardev socket,id=char%d,path=%s ",
+ i + 1, sock_path);
+ }
+
+ g_test_message("starting vhost-user backend: %s",
+ storage_daemon_command->str);
+ pid_t pid = fork();
+ if (pid == 0) {
+ execlp("/bin/sh", "sh", "-c", storage_daemon_command->str, NULL);
+ exit(1);
+ }
+ g_string_free(storage_daemon_command, true);
+
+ qmp_test_state = qtest_create_state_with_qmp_fd(
+ qtest_socket_client(qmp_sock_path));
+ /*
+ * Ask qemu-storage-daemon to quit so it
+ * will not block scripts/tap-driver.pl.
+ */
+ g_test_queue_destroy(quit_storage_daemon, qmp_test_state);
+
+ qobject_unref(qtest_qmp(qmp_test_state, "{'execute': 'qmp_capabilities'}"));
+ return sock_path;
+}
+
+static void *vhost_user_blk_test_setup(GString *cmd_line, void *arg)
+{
+ start_vhost_user_blk(cmd_line, 1);
+ return arg;
+}
+
+/*
+ * Setup for hotplug.
+ *
+ * Since vhost-user server only serves one vhost-user client one time,
+ * another exprot
+ *
+ */
+static void *vhost_user_blk_hotplug_test_setup(GString *cmd_line, void *arg)
+{
+ /* "-chardev socket,id=char2" is used for pci_hotplug*/
+ start_vhost_user_blk(cmd_line, 2);
+ return arg;
+}
+
+static void register_vhost_user_blk_test(void)
+{
+ QOSGraphTestOptions opts = {
+ .before = vhost_user_blk_test_setup,
+ };
+
+ /*
+ * tests for vhost-user-blk and vhost-user-blk-pci
+ * The tests are borrowed from tests/virtio-blk-test.c. But some tests
+ * regarding block_resize don't work for vhost-user-blk.
+ * vhost-user-blk device doesn't have -drive, so tests containing
+ * block_resize are also abandoned,
+ * - config
+ * - resize
+ */
+ qos_add_test("basic", "vhost-user-blk", basic, &opts);
+ qos_add_test("indirect", "vhost-user-blk", indirect, &opts);
+ qos_add_test("idx", "vhost-user-blk-pci", idx, &opts);
+ qos_add_test("nxvirtq", "vhost-user-blk-pci",
+ test_nonexistent_virtqueue, &opts);
+
+ opts.before = vhost_user_blk_hotplug_test_setup;
+ qos_add_test("hotplug", "vhost-user-blk-pci", pci_hotplug, &opts);
+}
+
+libqos_init(register_vhost_user_blk_test);
--
2.28.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* Re: [PATCH v10 6/7] test: new qTest case to test the vhost-user-blk-server
2020-09-18 8:09 ` [PATCH v10 6/7] test: new qTest case to test the vhost-user-blk-server Coiby Xu
@ 2020-09-23 12:36 ` Stefan Hajnoczi
2020-10-10 7:59 ` Coiby Xu
0 siblings, 1 reply; 20+ messages in thread
From: Stefan Hajnoczi @ 2020-09-23 12:36 UTC (permalink / raw)
To: Coiby Xu
Cc: kwolf, Laurent Vivier, Thomas Huth, qemu-devel, bharatlkmlkvm,
Paolo Bonzini
[-- Attachment #1: Type: text/plain, Size: 2064 bytes --]
On Fri, Sep 18, 2020 at 04:09:11PM +0800, Coiby Xu wrote:
> +int qtest_socket_client(char *server_socket_path)
> +{
> + struct sockaddr_un serv_addr;
> + int sock;
> + int ret;
> + int retries = 0;
> + sock = socket(PF_UNIX, SOCK_STREAM, 0);
> + g_assert_cmpint(sock, !=, -1);
> + serv_addr.sun_family = AF_UNIX;
> + snprintf(serv_addr.sun_path, sizeof(serv_addr.sun_path), "%s",
> + server_socket_path);
> +
> + for (retries = 0; retries < 3; retries++) {
> + ret = connect(sock, (struct sockaddr *)&serv_addr, sizeof(serv_addr));
> + if (ret == 0) {
> + break;
> + }
> + g_usleep(G_USEC_PER_SEC);
> + }
This is a race condition. On a heavily loaded machine the server might
not be available within 3 seconds and the test will fail randomly.
Solutions:
1. Wait output from the server indicating it is ready (e.g. 'Listening
on /path/to/foo.sock...') when spawning the server process.
2. Create the listen socket and pass the fd to the server process. This
way the socket already exists can the client will block in connect
until the server accepts the connection.
3. Create a socketpair. Pass one side to the server and use the other
side in the client.
However, I think this is okay for now. After my patch series that
converts the vhost-user-blk server to the new block exports API we can
consider how to pass file descriptors.
> +static void quit_storage_daemon(void *qmp_test_state)
> +{
> + const char quit_str[] = "{ 'execute': 'quit' }";
> +
> + /* Before quiting storate-daemon, quit qemu to avoid dubious messages */
> + qobject_unref(qtest_qmp(global_qtest, quit_str));
> +
> + /*
> + * Give storage-daemon enough time to wake up&terminate
> + * vu_client_trip coroutine so the Coroutine object could
> + * be cleaned up. Otherwise LeakSanitizer would complain
> + * about memory leaks.
> + */
> + g_usleep(1000);
Also a race that may cause random failures. This can be addressed after
the block exports API conversion.
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 20+ messages in thread* Re: [PATCH v10 6/7] test: new qTest case to test the vhost-user-blk-server
2020-09-23 12:36 ` Stefan Hajnoczi
@ 2020-10-10 7:59 ` Coiby Xu
0 siblings, 0 replies; 20+ messages in thread
From: Coiby Xu @ 2020-10-10 7:59 UTC (permalink / raw)
To: Stefan Hajnoczi
Cc: kwolf, Laurent Vivier, Thomas Huth, qemu-devel, bharatlkmlkvm,
Paolo Bonzini
On Wed, Sep 23, 2020 at 01:36:06PM +0100, Stefan Hajnoczi wrote:
>On Fri, Sep 18, 2020 at 04:09:11PM +0800, Coiby Xu wrote:
>> +int qtest_socket_client(char *server_socket_path)
>> +{
>> + struct sockaddr_un serv_addr;
>> + int sock;
>> + int ret;
>> + int retries = 0;
>> + sock = socket(PF_UNIX, SOCK_STREAM, 0);
>> + g_assert_cmpint(sock, !=, -1);
>> + serv_addr.sun_family = AF_UNIX;
>> + snprintf(serv_addr.sun_path, sizeof(serv_addr.sun_path), "%s",
>> + server_socket_path);
>> +
>> + for (retries = 0; retries < 3; retries++) {
>> + ret = connect(sock, (struct sockaddr *)&serv_addr, sizeof(serv_addr));
>> + if (ret == 0) {
>> + break;
>> + }
>> + g_usleep(G_USEC_PER_SEC);
>> + }
>
>This is a race condition. On a heavily loaded machine the server might
>not be available within 3 seconds and the test will fail randomly.
>
>Solutions:
>1. Wait output from the server indicating it is ready (e.g. 'Listening
> on /path/to/foo.sock...') when spawning the server process.
>2. Create the listen socket and pass the fd to the server process. This
> way the socket already exists can the client will block in connect
> until the server accepts the connection.
>3. Create a socketpair. Pass one side to the server and use the other
> side in the client.
>
>However, I think this is okay for now. After my patch series that
>converts the vhost-user-blk server to the new block exports API we can
>consider how to pass file descriptors.
>
>> +static void quit_storage_daemon(void *qmp_test_state)
>> +{
>> + const char quit_str[] = "{ 'execute': 'quit' }";
>> +
>> + /* Before quiting storate-daemon, quit qemu to avoid dubious messages */
>> + qobject_unref(qtest_qmp(global_qtest, quit_str));
>> +
>> + /*
>> + * Give storage-daemon enough time to wake up&terminate
>> + * vu_client_trip coroutine so the Coroutine object could
>> + * be cleaned up. Otherwise LeakSanitizer would complain
>> + * about memory leaks.
>> + */
>> + g_usleep(1000);
>
>Also a race that may cause random failures. This can be addressed after
>the block exports API conversion.
Thank you for spotting two race conditions!
--
Best regards,
Coiby
^ permalink raw reply [flat|nested] 20+ messages in thread
* [PATCH v10 7/7] MAINTAINERS: Add vhost-user block device backend server maintainer
2020-09-18 8:09 [PATCH v10 0/7] vhost-user block device backend implementation Coiby Xu
` (5 preceding siblings ...)
2020-09-18 8:09 ` [PATCH v10 6/7] test: new qTest case to test the vhost-user-blk-server Coiby Xu
@ 2020-09-18 8:09 ` Coiby Xu
2020-09-23 12:37 ` Stefan Hajnoczi
2020-09-21 15:20 ` [PATCH v10 0/7] vhost-user block device backend implementation Stefan Hajnoczi
` (3 subsequent siblings)
10 siblings, 1 reply; 20+ messages in thread
From: Coiby Xu @ 2020-09-18 8:09 UTC (permalink / raw)
To: qemu-devel; +Cc: kwolf, bharatlkmlkvm, stefanha, Stefano Garzarella
Suggested-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Coiby Xu <coiby.xu@gmail.com>
---
MAINTAINERS | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/MAINTAINERS b/MAINTAINERS
index 3d17cad19a..55ad6abe73 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3039,6 +3039,14 @@ L: qemu-block@nongnu.org
S: Supported
F: tests/image-fuzzer/
+Vhost-user block device backend server
+M: Coiby Xu <Coiby.Xu@gmail.com>
+S: Maintained
+F: block/export/vhost-user-blk-server.c
+F: util/vhost-user-server.c
+F: tests/qtest/vhost-user-blk-test.c
+F: tests/qtest/libqos/vhost-user-blk.c
+
Replication
M: Wen Congyang <wencongyang2@huawei.com>
M: Xie Changlong <xiechanglong.d@gmail.com>
--
2.28.0
^ permalink raw reply related [flat|nested] 20+ messages in thread* Re: [PATCH v10 7/7] MAINTAINERS: Add vhost-user block device backend server maintainer
2020-09-18 8:09 ` [PATCH v10 7/7] MAINTAINERS: Add vhost-user block device backend server maintainer Coiby Xu
@ 2020-09-23 12:37 ` Stefan Hajnoczi
0 siblings, 0 replies; 20+ messages in thread
From: Stefan Hajnoczi @ 2020-09-23 12:37 UTC (permalink / raw)
To: Coiby Xu; +Cc: kwolf, bharatlkmlkvm, qemu-devel, Stefano Garzarella
[-- Attachment #1: Type: text/plain, Size: 806 bytes --]
On Fri, Sep 18, 2020 at 04:09:12PM +0800, Coiby Xu wrote:
> Suggested-by: Stefano Garzarella <sgarzare@redhat.com>
> Signed-off-by: Coiby Xu <coiby.xu@gmail.com>
> ---
> MAINTAINERS | 8 ++++++++
> 1 file changed, 8 insertions(+)
>
> diff --git a/MAINTAINERS b/MAINTAINERS
> index 3d17cad19a..55ad6abe73 100644
> --- a/MAINTAINERS
> +++ b/MAINTAINERS
> @@ -3039,6 +3039,14 @@ L: qemu-block@nongnu.org
> S: Supported
> F: tests/image-fuzzer/
>
> +Vhost-user block device backend server
> +M: Coiby Xu <Coiby.Xu@gmail.com>
> +S: Maintained
> +F: block/export/vhost-user-blk-server.c
> +F: util/vhost-user-server.c
> +F: tests/qtest/vhost-user-blk-test.c
> +F: tests/qtest/libqos/vhost-user-blk.c
I will send a patch to also include the header files and move them to
include/.
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 20+ messages in thread
* Re: [PATCH v10 0/7] vhost-user block device backend implementation
2020-09-18 8:09 [PATCH v10 0/7] vhost-user block device backend implementation Coiby Xu
` (6 preceding siblings ...)
2020-09-18 8:09 ` [PATCH v10 7/7] MAINTAINERS: Add vhost-user block device backend server maintainer Coiby Xu
@ 2020-09-21 15:20 ` Stefan Hajnoczi
2020-09-22 16:06 ` Stefan Hajnoczi
` (2 subsequent siblings)
10 siblings, 0 replies; 20+ messages in thread
From: Stefan Hajnoczi @ 2020-09-21 15:20 UTC (permalink / raw)
To: Coiby Xu; +Cc: kwolf, bharatlkmlkvm, qemu-devel
[-- Attachment #1: Type: text/plain, Size: 888 bytes --]
On Fri, Sep 18, 2020 at 04:09:05PM +0800, Coiby Xu wrote:
> v10
> - Use a linked list of VuFdWatch objects to keep kick info [Stefan]
> - Merge improvements and fixes from Stefan
> - Rename libvhost-user's vu_message_read to vu_message_read_default [Kevin]
> - When shutting down the client, wait for the coroutine of processing
> vhost-user messages to be finished [Kevin]
> - Allocate struct req_data on the heap [Kevin]
> - Improve coding of qtest case [Thomas]
> - Fix several memory leaks detected by ASAN
Great, thank you for sending this. I spent Friday looking at the first
few patches and running qemu-storage-daemon with this.
I will post a follow-up series with cleanups and port it to the new QAPI
block exports API (NBD, FUSE, vhost-user-blk, etc).
Kevin is currently on vacation but will be back soon. If he has no
further comments we could merge this.
Stefan
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 20+ messages in thread* Re: [PATCH v10 0/7] vhost-user block device backend implementation
2020-09-18 8:09 [PATCH v10 0/7] vhost-user block device backend implementation Coiby Xu
` (7 preceding siblings ...)
2020-09-21 15:20 ` [PATCH v10 0/7] vhost-user block device backend implementation Stefan Hajnoczi
@ 2020-09-22 16:06 ` Stefan Hajnoczi
2020-09-23 12:39 ` Stefan Hajnoczi
2020-10-09 10:18 ` Stefan Hajnoczi
10 siblings, 0 replies; 20+ messages in thread
From: Stefan Hajnoczi @ 2020-09-22 16:06 UTC (permalink / raw)
To: Coiby Xu; +Cc: kwolf, bharatlkmlkvm, qemu-devel
[-- Attachment #1: Type: text/plain, Size: 749 bytes --]
On Fri, Sep 18, 2020 at 04:09:05PM +0800, Coiby Xu wrote:
> v10
> - Use a linked list of VuFdWatch objects to keep kick info [Stefan]
> - Merge improvements and fixes from Stefan
> - Rename libvhost-user's vu_message_read to vu_message_read_default [Kevin]
> - When shutting down the client, wait for the coroutine of processing
> vhost-user messages to be finished [Kevin]
> - Allocate struct req_data on the heap [Kevin]
> - Improve coding of qtest case [Thomas]
> - Fix several memory leaks detected by ASAN
Hi,
I have sent a patch series with cleanups and a conversion to the new
block exports API:
https://lists.gnu.org/archive/html/qemu-devel/2020-09/msg07946.html
I will do a final review of your series tomorrow. Thanks!
Stefan
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 20+ messages in thread* Re: [PATCH v10 0/7] vhost-user block device backend implementation
2020-09-18 8:09 [PATCH v10 0/7] vhost-user block device backend implementation Coiby Xu
` (8 preceding siblings ...)
2020-09-22 16:06 ` Stefan Hajnoczi
@ 2020-09-23 12:39 ` Stefan Hajnoczi
2020-10-09 10:18 ` Stefan Hajnoczi
10 siblings, 0 replies; 20+ messages in thread
From: Stefan Hajnoczi @ 2020-09-23 12:39 UTC (permalink / raw)
To: Coiby Xu; +Cc: kwolf, bharatlkmlkvm, qemu-devel
[-- Attachment #1: Type: text/plain, Size: 202 bytes --]
Thanks for contributing this feature! I have replied with comments about
additional steps I'm taking (fixes, cleanups, etc).
This series looks good:
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 20+ messages in thread* Re: [PATCH v10 0/7] vhost-user block device backend implementation
2020-09-18 8:09 [PATCH v10 0/7] vhost-user block device backend implementation Coiby Xu
` (9 preceding siblings ...)
2020-09-23 12:39 ` Stefan Hajnoczi
@ 2020-10-09 10:18 ` Stefan Hajnoczi
2020-10-10 8:45 ` Coiby Xu
10 siblings, 1 reply; 20+ messages in thread
From: Stefan Hajnoczi @ 2020-10-09 10:18 UTC (permalink / raw)
To: Coiby Xu; +Cc: kwolf, bharatlkmlkvm, qemu-devel
[-- Attachment #1: Type: text/plain, Size: 5571 bytes --]
On Fri, Sep 18, 2020 at 04:09:05PM +0800, Coiby Xu wrote:
> v10
> - Use a linked list of VuFdWatch objects to keep kick info [Stefan]
> - Merge improvements and fixes from Stefan
> - Rename libvhost-user's vu_message_read to vu_message_read_default [Kevin]
> - When shutting down the client, wait for the coroutine of processing
> vhost-user messages to be finished [Kevin]
> - Allocate struct req_data on the heap [Kevin]
> - Improve coding of qtest case [Thomas]
> - Fix several memory leaks detected by ASAN
>
> v9
> - move logical block size check function to a utility function
> - fix issues regarding license, coding style, memory deallocation, etc.
>
> v8
> - re-try connecting to socket server to fix asan error
> - fix license naming issue
>
> v7
> - fix docker-test-debug@fedora errors by freeing malloced memory
>
> v6
> - add missing license header and include guard
> - vhost-user server only serve one client one time
> - fix a bug in custom vu_message_read
> - using qemu-storage-daemon to start vhost-user-blk-server
> - a bug fix to pass docker-test-clang@ubuntu
>
> v5:
> * re-use vu_kick_cb in libvhost-user
> * keeping processing VhostUserMsg in the same coroutine until there is
> detachment/attachment of AIOContext
> * Spawn separate coroutine for each VuVirtqElement
> * Other changes including relocating vhost-user-blk-server.c, coding
> style etc.
>
> v4:
> * add object properties in class_init
> * relocate vhost-user-blk-test
> * other changes including using SocketAddress, coding style, etc.
>
> v3:
> * separate generic vhost-user-server code from vhost-user-blk-server
> code
> * re-write vu_message_read and kick hander function as coroutines to
> directly call blk_co_preadv, blk_co_pwritev, etc.
> * add aio_context notifier functions to support multi-threading model
> * other fixes regarding coding style, warning report, etc.
>
> v2:
> * Only enable this feature for Linux because eventfd is a Linux-specific
> feature
>
>
> This patch series is an implementation of vhost-user block device
> backend server, thanks to Stefan and Kevin's guidance.
>
> Vhost-user block device backend server is a UserCreatable object and can be
> started using object_add,
>
> (qemu) object_add vhost-user-blk-server,id=ID,unix-socket=/tmp/vhost-user-blk_vhost.socket,node-name=DRIVE_NAME,writable=off,logical-block-size=512
> (qemu) object_del ID
>
> or appending the "-object" option when starting QEMU,
>
> $ -object vhost-user-blk-server,id=disk,unix-socket=/tmp/vhost-user-blk_vhost.socket,node-name=DRIVE_NAME,writable=off,logical-block-size=512
>
> Then vhost-user client can connect to the server backend.
> For example, QEMU could act as a client,
>
> $ -m 256 -object memory-backend-memfd,id=mem,size=256M,share=on -numa node,memdev=mem -chardev socket,id=char1,path=/tmp/vhost-user-blk_vhost.socket -device vhost-user-blk-pci,id=blk0,chardev=char1
>
> And guest OS could access this vhost-user block device after mounting it.
>
> Coiby Xu (7):
> libvhost-user: Allow vu_message_read to be replaced
> libvhost-user: remove watch for kick_fd when de-initialize vu-dev
> util/vhost-user-server: generic vhost user server
> block: move logical block size check function to a common utility
> function
> block/export: vhost-user block device backend server
> test: new qTest case to test the vhost-user-blk-server
> MAINTAINERS: Add vhost-user block device backend server maintainer
>
> MAINTAINERS | 8 +
> block/export/vhost-user-blk-server.c | 661 ++++++++++++++++++
> block/export/vhost-user-blk-server.h | 36 +
> block/meson.build | 1 +
> contrib/libvhost-user/libvhost-user-glib.c | 2 +-
> contrib/libvhost-user/libvhost-user.c | 15 +-
> contrib/libvhost-user/libvhost-user.h | 21 +
> hw/core/qdev-properties.c | 31 +-
> softmmu/vl.c | 4 +
> tests/qtest/libqos/libqtest.h | 17 +
> tests/qtest/libqos/meson.build | 1 +
> tests/qtest/libqos/vhost-user-blk.c | 129 ++++
> tests/qtest/libqos/vhost-user-blk.h | 48 ++
> tests/qtest/libqtest.c | 36 +-
> tests/qtest/meson.build | 4 +-
> tests/qtest/vhost-user-blk-test.c | 751 +++++++++++++++++++++
> tests/vhost-user-bridge.c | 2 +
> tools/virtiofsd/fuse_virtio.c | 4 +-
> util/block-helpers.c | 46 ++
> util/block-helpers.h | 19 +
> util/meson.build | 2 +
> util/vhost-user-server.c | 428 ++++++++++++
> util/vhost-user-server.h | 65 ++
> 23 files changed, 2292 insertions(+), 39 deletions(-)
> create mode 100644 block/export/vhost-user-blk-server.c
> create mode 100644 block/export/vhost-user-blk-server.h
> create mode 100644 tests/qtest/libqos/vhost-user-blk.c
> create mode 100644 tests/qtest/libqos/vhost-user-blk.h
> create mode 100644 tests/qtest/vhost-user-blk-test.c
> create mode 100644 util/block-helpers.c
> create mode 100644 util/block-helpers.h
> create mode 100644 util/vhost-user-server.c
> create mode 100644 util/vhost-user-server.h
>
> --
> 2.28.0
>
Thanks, applied to my block tree:
https://github.com/stefanha/qemu/commits/block
Stefan
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 488 bytes --]
^ permalink raw reply [flat|nested] 20+ messages in thread* Re: [PATCH v10 0/7] vhost-user block device backend implementation
2020-10-09 10:18 ` Stefan Hajnoczi
@ 2020-10-10 8:45 ` Coiby Xu
0 siblings, 0 replies; 20+ messages in thread
From: Coiby Xu @ 2020-10-10 8:45 UTC (permalink / raw)
To: Stefan Hajnoczi; +Cc: kwolf, bharatlkmlkvm, qemu-devel
On Fri, Oct 09, 2020 at 11:18:43AM +0100, Stefan Hajnoczi wrote:
>On Fri, Sep 18, 2020 at 04:09:05PM +0800, Coiby Xu wrote:
>> v10
>> - Use a linked list of VuFdWatch objects to keep kick info [Stefan]
>> - Merge improvements and fixes from Stefan
>> - Rename libvhost-user's vu_message_read to vu_message_read_default [Kevin]
>> - When shutting down the client, wait for the coroutine of processing
>> vhost-user messages to be finished [Kevin]
>> - Allocate struct req_data on the heap [Kevin]
>> - Improve coding of qtest case [Thomas]
>> - Fix several memory leaks detected by ASAN
>>
>> v9
>> - move logical block size check function to a utility function
>> - fix issues regarding license, coding style, memory deallocation, etc.
>>
>> v8
>> - re-try connecting to socket server to fix asan error
>> - fix license naming issue
>>
>> v7
>> - fix docker-test-debug@fedora errors by freeing malloced memory
>>
>> v6
>> - add missing license header and include guard
>> - vhost-user server only serve one client one time
>> - fix a bug in custom vu_message_read
>> - using qemu-storage-daemon to start vhost-user-blk-server
>> - a bug fix to pass docker-test-clang@ubuntu
>>
>> v5:
>> * re-use vu_kick_cb in libvhost-user
>> * keeping processing VhostUserMsg in the same coroutine until there is
>> detachment/attachment of AIOContext
>> * Spawn separate coroutine for each VuVirtqElement
>> * Other changes including relocating vhost-user-blk-server.c, coding
>> style etc.
>>
>> v4:
>> * add object properties in class_init
>> * relocate vhost-user-blk-test
>> * other changes including using SocketAddress, coding style, etc.
>>
>> v3:
>> * separate generic vhost-user-server code from vhost-user-blk-server
>> code
>> * re-write vu_message_read and kick hander function as coroutines to
>> directly call blk_co_preadv, blk_co_pwritev, etc.
>> * add aio_context notifier functions to support multi-threading model
>> * other fixes regarding coding style, warning report, etc.
>>
>> v2:
>> * Only enable this feature for Linux because eventfd is a Linux-specific
>> feature
>>
>>
>> This patch series is an implementation of vhost-user block device
>> backend server, thanks to Stefan and Kevin's guidance.
>>
>> Vhost-user block device backend server is a UserCreatable object and can be
>> started using object_add,
>>
>> (qemu) object_add vhost-user-blk-server,id=ID,unix-socket=/tmp/vhost-user-blk_vhost.socket,node-name=DRIVE_NAME,writable=off,logical-block-size=512
>> (qemu) object_del ID
>>
>> or appending the "-object" option when starting QEMU,
>>
>> $ -object vhost-user-blk-server,id=disk,unix-socket=/tmp/vhost-user-blk_vhost.socket,node-name=DRIVE_NAME,writable=off,logical-block-size=512
>>
>> Then vhost-user client can connect to the server backend.
>> For example, QEMU could act as a client,
>>
>> $ -m 256 -object memory-backend-memfd,id=mem,size=256M,share=on -numa node,memdev=mem -chardev socket,id=char1,path=/tmp/vhost-user-blk_vhost.socket -device vhost-user-blk-pci,id=blk0,chardev=char1
>>
>> And guest OS could access this vhost-user block device after mounting it.
>>
>> Coiby Xu (7):
>> libvhost-user: Allow vu_message_read to be replaced
>> libvhost-user: remove watch for kick_fd when de-initialize vu-dev
>> util/vhost-user-server: generic vhost user server
>> block: move logical block size check function to a common utility
>> function
>> block/export: vhost-user block device backend server
>> test: new qTest case to test the vhost-user-blk-server
>> MAINTAINERS: Add vhost-user block device backend server maintainer
>>
>> MAINTAINERS | 8 +
>> block/export/vhost-user-blk-server.c | 661 ++++++++++++++++++
>> block/export/vhost-user-blk-server.h | 36 +
>> block/meson.build | 1 +
>> contrib/libvhost-user/libvhost-user-glib.c | 2 +-
>> contrib/libvhost-user/libvhost-user.c | 15 +-
>> contrib/libvhost-user/libvhost-user.h | 21 +
>> hw/core/qdev-properties.c | 31 +-
>> softmmu/vl.c | 4 +
>> tests/qtest/libqos/libqtest.h | 17 +
>> tests/qtest/libqos/meson.build | 1 +
>> tests/qtest/libqos/vhost-user-blk.c | 129 ++++
>> tests/qtest/libqos/vhost-user-blk.h | 48 ++
>> tests/qtest/libqtest.c | 36 +-
>> tests/qtest/meson.build | 4 +-
>> tests/qtest/vhost-user-blk-test.c | 751 +++++++++++++++++++++
>> tests/vhost-user-bridge.c | 2 +
>> tools/virtiofsd/fuse_virtio.c | 4 +-
>> util/block-helpers.c | 46 ++
>> util/block-helpers.h | 19 +
>> util/meson.build | 2 +
>> util/vhost-user-server.c | 428 ++++++++++++
>> util/vhost-user-server.h | 65 ++
>> 23 files changed, 2292 insertions(+), 39 deletions(-)
>> create mode 100644 block/export/vhost-user-blk-server.c
>> create mode 100644 block/export/vhost-user-blk-server.h
>> create mode 100644 tests/qtest/libqos/vhost-user-blk.c
>> create mode 100644 tests/qtest/libqos/vhost-user-blk.h
>> create mode 100644 tests/qtest/vhost-user-blk-test.c
>> create mode 100644 util/block-helpers.c
>> create mode 100644 util/block-helpers.h
>> create mode 100644 util/vhost-user-server.c
>> create mode 100644 util/vhost-user-server.h
>>
>> --
>> 2.28.0
>>
>
>Thanks, applied to my block tree:
>https://github.com/stefanha/qemu/commits/block
>
Thank you for improving the code! I'm going to study the changes to
understand how the improvements are made.
>Stefan
--
Best regards,
Coiby
^ permalink raw reply [flat|nested] 20+ messages in thread