From: Johannes Berg <johannes.b...@intel.com>
Add support for VHOST_USER_PROTOCOL_F_IN_BAND_NOTIFICATIONS, but
as it's not desired by default, don't enable it unless the device
implementation opts in by returning it from its protocol features
callback.
Note that I updated vu_set_vring_err_exec(), but didn't add any
sending of the VHOST_USER_SLAVE_VRING_ERR message as there's no
write to the err_fd today either.
Signed-off-by: Johannes Berg <johannes.b...@intel.com>
---
contrib/libvhost-user/libvhost-user.c | 94 ++++++++++++++++++++++++---
contrib/libvhost-user/libvhost-user.h | 4 ++
2 files changed, 89 insertions(+), 9 deletions(-)
diff --git a/contrib/libvhost-user/libvhost-user.c
b/contrib/libvhost-user/libvhost-user.c
index f1677da21201..6367ddeb17fb 100644
--- a/contrib/libvhost-user/libvhost-user.c
+++ b/contrib/libvhost-user/libvhost-user.c
@@ -136,6 +136,7 @@ vu_request_to_string(unsigned int req)
REQ(VHOST_USER_GET_INFLIGHT_FD),
REQ(VHOST_USER_SET_INFLIGHT_FD),
REQ(VHOST_USER_GPU_SET_SOCKET),
+ REQ(VHOST_USER_VRING_KICK),
REQ(VHOST_USER_MAX),
};
#undef REQ
@@ -163,7 +164,10 @@ vu_panic(VuDev *dev, const char *msg, ...)
dev->panic(dev, buf);
free(buf);
- /* FIXME: find a way to call virtio_error? */
+ /*
+ * FIXME:
+ * find a way to call virtio_error, or perhaps close the connection?
+ */
}
/* Translate guest physical address to our virtual address. */
@@ -920,6 +924,7 @@ static bool
vu_check_queue_msg_file(VuDev *dev, VhostUserMsg *vmsg)
{
int index = vmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
+ bool nofd = vmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK;
if (index >= dev->max_queues) {
vmsg_close_fds(vmsg);
@@ -927,8 +932,12 @@ vu_check_queue_msg_file(VuDev *dev, VhostUserMsg *vmsg)
return false;
}
- if (vmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK ||
- vmsg->fd_num != 1) {
+ if (nofd) {
+ vmsg_close_fds(vmsg);
+ return true;
+ }
+
+ if (vmsg->fd_num != 1) {
vmsg_close_fds(vmsg);
vu_panic(dev, "Invalid fds in request: %d", vmsg->request);
return false;
@@ -1025,6 +1034,7 @@ static bool
vu_set_vring_kick_exec(VuDev *dev, VhostUserMsg *vmsg)
{
int index = vmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
+ bool nofd = vmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK;
DPRINT("u64: 0x%016"PRIx64"\n", vmsg->payload.u64);
@@ -1038,8 +1048,8 @@ vu_set_vring_kick_exec(VuDev *dev, VhostUserMsg *vmsg)
dev->vq[index].kick_fd = -1;
}
- dev->vq[index].kick_fd = vmsg->fds[0];
- DPRINT("Got kick_fd: %d for vq: %d\n", vmsg->fds[0], index);
+ dev->vq[index].kick_fd = nofd ? -1 : vmsg->fds[0];
+ DPRINT("Got kick_fd: %d for vq: %d\n", dev->vq[index].kick_fd, index);
dev->vq[index].started = true;
if (dev->iface->queue_set_started) {
@@ -1116,6 +1126,7 @@ static bool
vu_set_vring_call_exec(VuDev *dev, VhostUserMsg *vmsg)
{
int index = vmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
+ bool nofd = vmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK;
DPRINT("u64: 0x%016"PRIx64"\n", vmsg->payload.u64);
@@ -1128,14 +1139,14 @@ vu_set_vring_call_exec(VuDev *dev, VhostUserMsg *vmsg)
dev->vq[index].call_fd = -1;
}
- dev->vq[index].call_fd = vmsg->fds[0];
+ dev->vq[index].call_fd = nofd ? -1 : vmsg->fds[0];
/* in case of I/O hang after reconnecting */
- if (eventfd_write(vmsg->fds[0], 1)) {
+ if (dev->vq[index].call_fd != -1 && eventfd_write(vmsg->fds[0], 1)) {
return -1;
}
- DPRINT("Got call_fd: %d for vq: %d\n", vmsg->fds[0], index);
+ DPRINT("Got call_fd: %d for vq: %d\n", dev->vq[index].call_fd, index);
return false;
}
@@ -1144,6 +1155,7 @@ static bool
vu_set_vring_err_exec(VuDev *dev, VhostUserMsg *vmsg)
{
int index = vmsg->payload.u64 & VHOST_USER_VRING_IDX_MASK;
+ bool nofd = vmsg->payload.u64 & VHOST_USER_VRING_NOFD_MASK;
DPRINT("u64: 0x%016"PRIx64"\n", vmsg->payload.u64);
@@ -1156,7 +1168,7 @@ vu_set_vring_err_exec(VuDev *dev, VhostUserMsg *vmsg)
dev->vq[index].err_fd = -1;
}
- dev->vq[index].err_fd = vmsg->fds[0];
+ dev->vq[index].err_fd = nofd ? -1 : vmsg->fds[0];
return false;
}
@@ -1164,6 +1176,14 @@ vu_set_vring_err_exec(VuDev *dev, VhostUserMsg *vmsg)
static bool
vu_get_protocol_features_exec(VuDev *dev, VhostUserMsg *vmsg)
{
+ /*
+ * Note that we support, but intentionally do not set,
+ * VHOST_USER_PROTOCOL_F_IN_BAND_NOTIFICATIONS. This means that
+ * a device implementation can return it in its callback
+ * (get_protocol_features) if it wants to use this for
+ * simulation, but it is otherwise not desirable (if even
+ * implemented by the master.)
+ */
uint64_t features = 1ULL << VHOST_USER_PROTOCOL_F_MQ |
1ULL << VHOST_USER_PROTOCOL_F_LOG_SHMFD |
1ULL << VHOST_USER_PROTOCOL_F_SLAVE_REQ |
@@ -1196,6 +1216,25 @@ vu_set_protocol_features_exec(VuDev *dev, VhostUserMsg
*vmsg)
dev->protocol_features = vmsg->payload.u64;
+ if (vu_has_protocol_feature(dev,
+ VHOST_USER_PROTOCOL_F_IN_BAND_NOTIFICATIONS) &&
+ (!vu_has_protocol_feature(dev, VHOST_USER_PROTOCOL_F_SLAVE_REQ) ||
+ !vu_has_protocol_feature(dev, VHOST_USER_PROTOCOL_F_REPLY_ACK))) {
+ /*
+ * The use case for using messages for kick/call is simulation, to make
+ * the kick and call synchronous. To actually get that behaviour, both
+ * of the other features are required.
+ * Theoretically, one could use only kick messages, or do them without
+ * having F_REPLY_ACK, but too many (possibly pending) messages on the
+ * socket will eventually cause the master to hang, to avoid this in
+ * scenarios where not desired enforce that the settings are in a way
+ * that actually enables the simulation case.
+ */
+ vu_panic(dev,
+ "F_IN_BAND_NOTIFICATIONS requires F_SLAVE_REQ &&
F_REPLY_ACK");
+ return false;
+ }
+
if (dev->iface->set_protocol_features) {
dev->iface->set_protocol_features(dev, features);
}
@@ -1456,6 +1495,25 @@ vu_set_inflight_fd(VuDev *dev, VhostUserMsg *vmsg)
return false;
}
+static bool
+vu_handle_vring_kick(VuDev *dev, VhostUserMsg *vmsg)
+{
+ unsigned int index = vmsg->payload.state.index;
+
+ if (index >= dev->max_queues) {
+ vu_panic(dev, "Invalid queue index: %u", index);
+ return false;
+ }
+
+ DPRINT("Got kick message: handler:%p idx:%d\n",
+ dev->vq[index].handler, index);
+ if (dev->vq[index].handler) {
+ dev->vq[index].handler(dev, index);
+ }
+
+ return false;
+}
+
static bool
vu_process_message(VuDev *dev, VhostUserMsg *vmsg)
{
@@ -1538,6 +1596,8 @@ vu_process_message(VuDev *dev, VhostUserMsg *vmsg)
return vu_get_inflight_fd(dev, vmsg);
case VHOST_USER_SET_INFLIGHT_FD:
return vu_set_inflight_fd(dev, vmsg);
+ case VHOST_USER_VRING_KICK:
+ return vu_handle_vring_kick(dev, vmsg);
default:
vmsg_close_fds(vmsg);
vu_panic(dev, "Unhandled request: %d", vmsg->request);
@@ -2010,6 +2070,22 @@ vu_queue_notify(VuDev *dev, VuVirtq *vq)
return;
}
+ if (vu_has_protocol_feature(dev,
+ VHOST_USER_PROTOCOL_F_IN_BAND_NOTIFICATIONS) &&
+ vu_has_protocol_feature(dev, VHOST_USER_PROTOCOL_F_SLAVE_REQ)) {
+ VhostUserMsg vmsg = {
+ .request = VHOST_USER_SLAVE_VRING_CALL,
+ .flags = VHOST_USER_VERSION,
+ .size = sizeof(vmsg.payload.state),
+ .payload.state = {
+ .index = vq - dev->vq,
+ },
+ };
+
+ vu_message_write(dev, dev->slave_fd, &vmsg);
+ return;
+ }
+
if (eventfd_write(vq->call_fd, 1) < 0) {
vu_panic(dev, "Error writing eventfd: %s", strerror(errno));
}
diff --git a/contrib/libvhost-user/libvhost-user.h
b/contrib/libvhost-user/libvhost-user.h
index 46b600799b2e..a22dc4733849 100644
--- a/contrib/libvhost-user/libvhost-user.h
+++ b/contrib/libvhost-user/libvhost-user.h
@@ -53,6 +53,7 @@ enum VhostUserProtocolFeature {
VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD = 10,
VHOST_USER_PROTOCOL_F_HOST_NOTIFIER = 11,
VHOST_USER_PROTOCOL_F_INFLIGHT_SHMFD = 12,
+ VHOST_USER_PROTOCOL_F_IN_BAND_NOTIFICATIONS = 13,
VHOST_USER_PROTOCOL_F_MAX
};
@@ -94,6 +95,7 @@ typedef enum VhostUserRequest {
VHOST_USER_GET_INFLIGHT_FD = 31,
VHOST_USER_SET_INFLIGHT_FD = 32,
VHOST_USER_GPU_SET_SOCKET = 33,
+ VHOST_USER_VRING_KICK = 34,
VHOST_USER_MAX
} VhostUserRequest;
@@ -102,6 +104,8 @@ typedef enum VhostUserSlaveRequest {
VHOST_USER_SLAVE_IOTLB_MSG = 1,
VHOST_USER_SLAVE_CONFIG_CHANGE_MSG = 2,
VHOST_USER_SLAVE_VRING_HOST_NOTIFIER_MSG = 3,
+ VHOST_USER_SLAVE_VRING_CALL = 4,
+ VHOST_USER_SLAVE_VRING_ERR = 5,
VHOST_USER_SLAVE_MAX
} VhostUserSlaveRequest;
--
2.20.1
