Secondary process doesn't properly attach to the rte_eth_device
initialized by the primary process.
Accessing device from secondary process (e.g. via rte_eth_rx_burst),
causes process to crash. because rte_eth_dev_data is not properly set.
The issue was flood by
'commit 7f95f78a8aea ("ethdev: clear data when allocating device")'
which now clears rte_eth_dev_data entry.
For pci devices the struct is initialized by rte_eth_dev_pci_probe
->eth_dev_attach_secondary().
However, for virtio-user virtio_user_pmd_probe() is called instead of
rte_eth_dev_pci_probe().
The fix is to call rte_eth_dev_attach_secondary(), for secondary
process, from virtio_user_pmd_probe.
Fixes: 7f95f78a8aea ("ethdev: clear data when allocating device")
Cc: stable@dpdk.org
Signed-off-by: Ami Sabo <amis@radware.com>
The patch change the prototype of callback function
(rte_intr_callback_fn) by removing the unnecessary parameter.
Signed-off-by: Qi Zhang <qi.z.zhang@intel.com>
Failed to destroy tunnel filter rule if the action of
the tunnel filter is VF, root cause is the wrong vsi
used.
Fixes: c50474f31efe ("net/i40e: support tunnel filter to VF")
Signed-off-by: Beilei Xing <beilei.xing@intel.com>
Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Disable for gcc < 4.7 and icc <= 14.0
PMD uses some compiler builtins and new compiler options. Tested with
gcc 4.5.1 and following were not supported:
option:
-Ofast
macros:
_Static_assert
__ORDER_LITTLE_ENDIAN__
__ORDER_BIG_ENDIAN__
__BYTE_ORDER__
__atomic_fetch_add
__ATOMIC_ACQUIRE
__atomic_load_n
__ATOMIC_RELAXED
__atomic_store_n
__ATOMIC_RELEASE
It is not easy to fix all in PMD, disabling PMD for older compilers.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
The macro RTE_PMD_TAP_MAX_QUEUES was defined twice.
On machines with kernel < 3.8, IFF_MULTI_QUEUE didn't exist, and thus
both definitions used different values.
Fixes: cf5643661161 ("net/tap: move private elements to external header")
Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Since patch "mbuf: structure reorganization" the compiler complains
sometimes (in some conditions):
.../drivers/net/mlx5/mlx5_rxtx.c: In function ‘mlx5_rx_burst’:
.../drivers/net/mlx5/mlx5_rxtx.c:2082:17: error: ‘len’ may be used
uninitialized in this function [-Werror=maybe-uninitialized]
len is not initialised as it will be at the first segment of a received
packet, but it remains hard for the compiler to determine it.
Fixes: 9964b965ad69 ("net/mlx5: re-add Rx scatter support")
Cc: stable@dpdk.org
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Acked-by: Olivier Matz <olivier.matz@6wind.com>
To avoid multiple stores on fast path, Ethernet drivers
aggregate the writes to data_off, refcnt, nb_segs and port
to an uint64_t data and write the data in one shot
with uint64_t* at &mbuf->rearm_data address.
Some of the non-IA platforms have store operation overhead
if the store address is not naturally aligned.This patch
fixes the performance issue on those targets.
Signed-off-by: Jerin Jacob <jerin.jacob@caviumnetworks.com>
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Now that the m->next pointer and m->nb_segs is expected to be set (to
NULL and 1 respectively) after a mempool_get(), we can avoid to write them
in the Rx functions of drivers.
Only some drivers are patched, it's not an exhaustive patch. It gives
the idea to do the same in other drivers.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Set the value of m->refcnt to 1, m->nb_segs to 1 and m->next
to NULL when the mbuf is stored inside the mempool (unused).
This is done in rte_pktmbuf_prefree_seg(), before freeing or
recycling a mbuf.
Before this patch, the value of m->refcnt was expected to be 0
while in pool.
The objectives are:
- to avoid drivers to set m->next to NULL in the early Rx path, since
this field is in the second 64B of the mbuf and its access could
trigger a cache miss
- rationalize the behavior of raw_alloc/raw_free: one is now the
symmetric of the other, and refcnt is never changed in these functions.
To optimize the freeing of the segments, we try try to only update
m->refcnt, m->next, and m->nb_segs when it's required (idea from
Konstantin Ananyev <konstantin.ananyev@intel.com>).
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Rename __rte_mbuf_raw_free() as rte_mbuf_raw_free() and make
it public. The old function is kept for compat but is marked as
deprecated.
The next commit changes the behavior of rte_mbuf_raw_free() to
make it more consistent with rte_mbuf_raw_alloc().
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Document the function and make it public, since it is used at several
places in the drivers. The old one is marked as deprecated.
Signed-off-by: Olivier Matz <olivier.matz@6wind.com>
Rename "rte_virtio_net.h" to "rte_vhost.h", 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>
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>
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>
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>
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>
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>
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>
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>
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: 954ea11540b6 ("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: 37a7eb2ae816 ("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: e3b434818bbb ("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>
This patch revmoves include of the numaif.h header from rte_eth_vhost.c.
Commit 586e39001317 ("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>
Improve error checking to avoid a caller overflowing the MCDI
request buffer if the requested TXQ size was excessively large.
Coverity issue: 1305527
Fixes: e7cd430c864f ("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>
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>
After adding VLAN filter, the VLAN promiscuous mode is
disabled. But there's no chance to enable it.
So add the check after deleting VLAN filter. If there's
no VLAN filter left, enable the VLAN promiscuous mode.
Fixes: 9f0645cd147c ("net/i40e: fix VLAN filter")
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
This is necessary to ensure packets with the new MAC address as
destination get redirected to the tap device.
Also change the MAC address only if the current one is different from
the requested one.
Fixes: 2bc06869cd94 ("net/tap: add remote netdevice traffic capture")
Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Immediately after init (probing), the device MAC address is all zeroes.
It should be possible to get a correct MAC address as soon as that,
without need for a dev_configure().
With this patch, a MAC address is set in eth_dev_tap_create()
explicitly. It either comes from the remote if any was configured, or is
randomly generated. In any case, the device MAC address is guaranteed to
be the correct one when the tap netdevice actually gets created in
tun_alloc().
Fixes: f76d46b4ff08 ("net/tap: add MAC address management")
Fixes: 2bc06869cd94 ("net/tap: add remote netdevice traffic capture")
Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Some errors received from the kernel are acceptable, such as a -ENOENT
for a rule deletion (the rule was already no longer existing in the
kernel). Make sure we consider return codes properly. For that,
nl_recv() has been simplified.
qdisc_exists() function is no longer needed as we can check whether the
kernel returned -EEXIST when requiring the qdisc creation. It's simpler
and faster.
Add a few messages for clarity when a netlink error occurs.
Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Flow validation already processes the final actions to verify if a rule can
be applied or not and the same is done during creation. As the creation
function relies on validation to generate and apply a rule, this job can be
fully handled by the validation function.
Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
With support for segmented packets, it is now possible to easily receive
packets of many sizes, given an adequate number of descriptors.
Remove limitation on the minimum size of mbuf: on reception, if a packet
won't fit in the queue's mbufs, it will be detected in the packet info
and the packet will be discarded.
Fixes: 0781f5762cfe ("net/tap: support segmented mbufs")
Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
Only full mask (0xffff) is accepted, there is no way to specify a mask
for layer 4 ports to the kernel using TC rules.
Fixes: de96fe68ae95 ("net/tap: add basic flow API patterns and actions")
Signed-off-by: Pascal Mazon <pascal.mazon@6wind.com>
Acked-by: Keith Wiles <keith.wiles@intel.com>
Remove unnecessary interface queries and the Resource Domain when
creating the Queue Pair. Since mlx5 PMD data path is on top of native
APIs, such Verbs library calls are no longer needed.
Signed-off-by: Shahaf Shuler <shahafs@mellanox.com>
Acked-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com>
Acked-by: Yongseok Koh <yskoh@mellanox.com>
Currently mlx5_dev_rss_reta_update() just updates tables in the host,
therefore it isn't immediately effective until restarting the device by
calling mlx5_dev_stop()/mlx5_dev_start() to update the changes in the
device side. This patch adds rebuilding the device-specific data
structure and applying it to the device right away.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
When querying and updating RSS RETA table, it always uses the max size of
the device instead of configured value. This patch fixes it and removed the
related comments in the code.
Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
