We used to use rte_vhost_driver_session_start() to trigger the vhost-user
session. It takes no argument, thus it's a global trigger. And it could
be problematic.
The issue is, currently, rte_vhost_driver_register(path, flags) actually
tries to put it into the session loop (by fdset_add). However, it needs
a set of APIs to set a vhost-user driver properly:
* rte_vhost_driver_register(path, flags);
* rte_vhost_driver_set_features(path, features);
* rte_vhost_driver_callback_register(path, vhost_device_ops);
If a new vhost-user driver is registered after the trigger (think OVS-DPDK
that could add a port dynamically from cmdline), the current code will
effectively starts the session for the new driver just after the first
API rte_vhost_driver_register() is invoked, leaving later calls taking
no effect at all.
To handle the case properly, this patch introduce a new API,
rte_vhost_driver_start(path), to trigger a specific vhost-user driver.
To do that, the rte_vhost_driver_register(path, flags) is simplified
to create the socket only and let rte_vhost_driver_start(path) to
actually put it into the session loop.
Meanwhile, the rte_vhost_driver_session_start is removed: we could hide
the session thread internally (create the thread if it has not been
created). This would also simplify the application.
NOTE: the API order in prog guide is slightly adjusted for showing the
correct invoke order.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Export few APIs for the vhost-user driver to log the guest memory writes,
which is a must for live migration support.
This patch basically moves vhost_log_write() and vhost_log_used_vring()
into vhost.h and then add an wrapper (the public API) to them.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Features could be changed after the feature negotiation. For example,
VHOST_F_LOG_ALL will be set/cleared at the start/end of live migration,
respecitively. Thus, we need a new callback to inform the application
on such change.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Rename "virtio-net" to "vhost" in the API comments and vhost prog guide.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
rename "virtio_net_device_ops" to "vhost_device_ops", to not let it
be virtio-net specific.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
They are virtio-net specific and should be defined inside the virtio-net
driver.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Currently, we check vq->desc, vq->kickfd and vq->callfd to know whether
a virtio device is ready or not. However, we only do it when handling
SET_VRING_KICK message, which could be wrong if a vhost-user frontend
send SET_VRING_KICK first and SET_VRING_CALL later.
To work for all possible vhost-user frontend implementations, we could
move the ready check at the end of vhost-user message handler.
Meanwhile, since we do the check more often than before, the "virtio
not ready" message is dropped, to not flood the screen.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
We used to use rte_vhost_get_queue_num() for telling how many vrings.
However, the return value is the number of "queue pairs", which is
very virtio-net specific. To make it generic, we should return the
number of vrings instead, and let the driver do the proper translation.
Say, virtio-net driver could turn it to the number of queue pairs by
dividing 2.
Meanwhile, mark rte_vhost_get_queue_num as deprecated.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
The queue pair is very virtio-net specific, other devices don't have
such concept. To make it generic, we should log the number of vrings
instead of the number of queue pairs.
This patch just does a simple convert, a later patch would export the
number of vrings to applications.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Some vhost-user driver may need this info to setup its own page tables
for GPA (guest physical addr) to HPA (host physical addr) translation.
SPDK (Storage Performance Development Kit) is one example.
Besides, by exporting this memory info, we could also export the
gpa_to_vva() as an inline function, which helps for performance.
Otherwise, it has to be referenced indirectly by a "vid".
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Assume there is an application both support vhost-user net and
vhost-user scsi, the callback should be different. Making notify
ops per vhost driver allow application define different set of
callbacks for different driver.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
The rte_eth_vhost_feature_disable/enable/get APIs are just a wrapper of
rte_vhost_feature_disable/enable/get. However, the later are going to
be refactored; it's going to take an extra parameter (socket_file path),
to let it be per-device.
Instead of changing those vhost-pmd APIs to adapt to the new vhost APIs,
we could simply remove them, and let vdev to serve this purpose. After
all, vdev options is better for disabling/enabling some features.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Acked-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Introduce few APIs to set/get/enable/disable driver features.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
A vhost-user server socket could have many connections, thus many connfd.
However, we currently just use one single int var to store it. Meaning,
it will get overwritten every time a new connection is created.
While this will not create fatal issue as it sounds (since the correct
connfd is closured to the event loop thread by fdset_add), it may cause
fd leaks if a user invokes rte_vhost_driver_unregister before shutting
down all connections: it just closes the recent connfd.
A simple example that should be able to reproduce this leaks issues is,
del the ovs vhost-user port while the connected VMs are still alive. (Note
that it's suggested to use one socket for one VM, which makes the issue
not that fatal as it sounds again).
Since we already use a struct "vhost_user_connection" to track all info
about one connection, it's obvious that we should put the connfd there.
Then we could build a connection list inside the vhost_user_socket struct,
to represent all connections belong that socket file.
Fixes: 164fd39678 ("vhost: fix unregistering in client mode")
Cc: stable@dpdk.org
Cc: Ilya Maximets <i.maximets@samsung.com>
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
So far, virtio-user with vhost-user as the backend can only support
client mode. So when vhost user backend is down, i.e., unix socket
connection is broken, the connection cannot be re-connected. We will
forcely set the link state to be down.
Note: virtio-user with vhost-kernel as the backend still cannot
support lsc now as we fail to find a way to monitor the backend, tap
device, up/down events.
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Originally, we did not report support of VIRTIO_NET_F_STATUS.
This feature is not reported by vhost backend, instead, it
is added/removed by QEMU in virtio PCI case.
We report the support of this feature so that following patch
will depend on this feature to enable LSC interrupt.
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
For rxq interrupt, the device (backend driver) will notify driver
through callfd. Each virtqueue has a callfd. To keep compatible
with the existing framework, we will give these callfds to
interrupt thread for listening for interrupts.
Before that, we need to allocate intr_handle, and fill callfds
into it so that driver can use it to set up rxq interrupt mode.
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Originally, eventfd is opened when initializing each vq; and gets closded
in virtio_user_stop_device().
To make it possible to initialize intr_handle struct in init() in following
patch, we put the open() of all eventfds into init(); and put the close()
into uninit().
Suggested-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
A new interrupt type, RTE_INTR_HANDLE_VDEV, is added to support lsc and rxq
interrupt for vdev.
For lsc interrupt, except from original EPOLLIN events, we also listen for
socket peer closed connection event (EPOLLRDHUP and EPOLLHUP).
For rxq interrupt, add a precondition to avoid invoking any vfio and uio
code.
For intr_handle initialization, let each vdev driver to do that.
Signed-off-by: Jianfeng Tan <jianfeng.tan@intel.com>
This patch adds a new option 'iface' to change the interface name of
tap device with vhost-kernel as backend.
Signed-off-by: Wenfeng Liu <liuwf@arraynetworks.com.cn>
Reviewed-by: Jianfeng Tan <jianfeng.tan@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
The broadcast_rarp field in the virtio_net struct is checked in the
dequeue datapath regardless of whether descriptors are available or not.
As it is checked with cmpset leading to a write, false sharing on the
virtio_net struct can happen between enqueue and dequeue datapaths
regardless of whether a RARP is requested. In OVS, the issue can cause
a uni-directional performance drop of up to 15%.
Fix that by only performing the cmpset if a read of broadcast_rarp
indicates that the cmpset is likely to succeed.
Fixes: a66bcad322 ("vhost: arrange struct fields for better cache sharing")
Cc: stable@dpdk.org
Signed-off-by: Kevin Traynor <ktraynor@redhat.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Update the "Virtio_user for Container Networking" doc, add the
"--file-prefix" option to testpmd in host and container to avoid
hugepage config file conflict.
Fixes: 50665deebd ("doc: add guide to use virtio-user for container networking")
Cc: stable@dpdk.org
Signed-off-by: Yong Wang <wang.yong19@zte.com.cn>
Acked-by: John McNamara <john.mcnamara@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
This patch adds MTU display to "show port info" command.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
This patch implements support for the Virtio MTU feature.
When negotiated, the host shares its maximum supported MTU,
which is used as initial MTU and as maximum MTU the application
can set.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
This patch adds a call to rte_vhost_mtu_get() at device creation
time to fill device's MTU property when available.
This makes the MTU value defined in QEMU cmdline accessible to the
application by calling rte_eth_dev_get_mtu().
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
This patch implements the function for the application to
get the MTU value.
rte_vhost_get_mtu() fills the mtu parameter with the MTU value
set in QEMU if VIRTIO_NET_F_MTU has been negotiated and returns 0,
-ENOTSUP otherwise.
The function returns -EAGAIN if Virtio feature negotiation
didn't happened yet.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
This patch adds a new status flag indicating the Virtio device
is ready to operate.
This is required to be able to call rte_vhost_mtu_get() in the
.new_device() callback, as rte_vhost_mtu_get needs that the
negotiation is done, but it is too early to rely on running status
flag, which is set just after .new_device() returns.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
This patch implements the vhost-user MTU protocol feature support.
When VIRTIO_NET_F_MTU is negotiated, QEMU notifies the vhost-user
backend with the configured MTU if dedicated protocol feature is
supported.
The value can be used by the application to ensure consistency with
value set by the user.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
This patch enables the new VIRTIO_NET_F_MTU feature,
which makes possible for the host to advise the guest
with its maximum supported MTU.
MTU value is set via QEMU parameters, either via Libvirt XML, or
directly in virtio-net device command line arguments.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
We used to allocate queues based on the index from SET_VRING_CALL
request: if corresponding queue hasn't been allocated, allocate it.
Though it's pratically right (it's the first per-vring request we
will get from QEMU for vhost-user negotiation), but it's not technically
right: it's not documented in the vhost-user spec that it will always
be the first per-vring request. For example, SET_VRING_ADDR could also
be the first per-vring request.
Thus, we should not depend the SET_VRING_CALL on queue allocation.
Instead, we could catch all the per-vring messages at the entrance of
request handler, and allocate one if it hasn't been allocated before.
By that, we could remove a hack.
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
0x8000 is the max virito-net queue pairs the virtio 1.0 spec claims to
support. While for vhost-user, it's a different story: the max vring
index could be passed by the vhost-user spec is 0xff, masked by the
VHOST_USER_VRING_IDX_MASK.
That said, the max queue pairs could vhost-user could supported is 0x80.
If user are asking more, I think the vhost-user need be extended.
Fixes: b09b198bfb ("vhost-user: announce queue number in message")
Cc: stable@dpdk.org
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Some macros (say VIRTIO_NET_F_MQ) are needed for enabling multiple queue,
however they are introduced since kernel v3.8, meaning build error happens
if we build DPDK vhost on those platforms.
71dfdbe66a ("vhost: fix build with kernel < 3.8") meant to fix it, but
in a wrong way: it completely disables the MQ features for those kernels.
However, the MQ feature doesn't depend on the kernel at all (except the
macros dependency stated above), that we could still enable the MQ feature
even the host kernel has no such support.
The right fix is to define the macro if it's not defined.
Fixes: 71dfdbe66a ("vhost: fix build with kernel < 3.8")
Cc: stable@dpdk.org
Signed-off-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
The link state change interrupt can only be configured if the virtio device
supports MSIX. Prior to this change the writing of the vector to the PCI
config space was causing it to overwrite the initial part of the MAC
address since the MSIX vector is not in the config space and is occupied by
the MAC address.
This has been reproduced in Virtual Box (v5.0.30.r112061) in Windows 7.
Fixes: 954ea11540 ("virtio: do not report link state feature unless available")
Cc: stable@dpdk.org
Signed-off-by: Matt Peters <matt.peters@windriver.com>
Signed-off-by: Allain Legacy <allain.legacy@windriver.com>
virtio-user limits the qeueue number to 8 but provides no limit
check against the queue number input from user. If a bigger queue
number (> 8) is given, there is an overflow issue. Doing a sanity
check could avoid it.
Fixes: 37a7eb2ae8 ("net/virtio-user: add device emulation layer")
Cc: stable@dpdk.org
Signed-off-by: Wenfeng Liu <liuwf@arraynetworks.com.cn>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
The valid tap file descriptor range should be equal or greater
than zero instead of non-zero
Fixes: e3b434818b ("net/virtio-user: support kernel vhost")
Cc: stable@dpdk.org
Signed-off-by: Wenfeng Liu <liuwf@arraynetworks.com.cn>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Inability to connect to socket is a normal situation
in client mode because, in common case, server isn't
started yet. RTE_LOG_WARNING should be suitable for
the case of some unusual errors.
Message about reconnection is not an error at all.
Fixes: e623e0c6d8 ("vhost: add reconnect ability")
Cc: stable@dpdk.org
Signed-off-by: Ilya Maximets <i.maximets@samsung.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
This patch revmoves include of the numaif.h header from rte_eth_vhost.c.
Commit 586e390013 ("vhost: export numa node") moved the invocation of
get_mempolicy() from rte_eth_vhost.c to librte_vhost. So there is no need
to include the numaif.h header anymore in rte_eth_vhost.c.
Signed-off-by: Rami Rosen <rami.rosen@intel.com>
Acked-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
The minor change aims to remove the redundant computing and make
it easier to understand the code.
Signed-off-by: Zhiyong Yang <zhiyong.yang@intel.com>
fdset_add increments pfdset->num, but fdset_del doesn't decrement
pfdset->num, so if we call fdset_add then fdset_del in a loop without
calling fdset_shrink, we can easily exceed MAX_FDS with only a few
number of fds used.
So my solution is simply to call fdset_shrink in fdset_add when it
exceeds MAX_FDS.
Because fdset_shrink and fdset_add locks pfdset->fd_mutex we can't
call fdset_shrink inside fdset_add because that would cause a dead
lock, so this patch split fdset_shrink in two, fdset_shrink and
fdset_shrink_nolock.
Fixes: 59317cef24 ("vhost: allow many vhost-user ports")
Cc: stable@dpdk.org
Signed-off-by: Matthias Gatto <matthias.gatto@outscale.com>
Improve error checking to avoid a caller overflowing the MCDI
request buffer if the requested TXQ size was excessively large.
Coverity issue: 1305527
Fixes: e7cd430c86 ("net/sfc/base: import SFN7xxx family support")
CC: stable@dpdk.org
Signed-off-by: Andy Moreton <amoreton@solarflare.com>
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Add a CLI in testpmd to test the TC min bandwidth
setting.
Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Ixgbe supports to set the relative bandwidth for the TCs.
It's a global setting for the PF and all the VFs of a
physical port.
This feature provide the API to set the bandwidth.
Signed-off-by: Bernard Iremonger <bernard.iremonger@intel.com>
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Some DPDK applications/examples check link status on their
start. NICVF does not wait for the link, so those apps fail.
Wait up to 9 seconds for the link as other PMDs do in order
to fix those apps/examples.
Signed-off-by: Andriy Berestovskyy <andriy.berestovskyy@caviumnetworks.com>
Acked-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
