Add support to select RSS hash based on innermost or outermost
headers. If an application is started without any specific settings
the default mode configured by FW or HW shall be used.
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Add fill operation enqueue support for IOAT and IDXD. The fill enqueue is
similar to the copy enqueue, but takes a 'pattern' rather than a source
address to transfer to the destination address. This patch also includes an
additional test case for the new operation type.
Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Radu Nicolau <radu.nicolau@intel.com>
Intel Data Streaming Accelerator (Intel DSA) is a high-performance data
copy and transformation accelerator which will be integrated in future
Intel processors [1].
Add DSA device support to dpdk-devbind.py script.
[1] https://01.org/blogs/2019/introducing-intel-data-streaming-accelerator
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
Acked-by: Radu Nicolau <radu.nicolau@intel.com>
Rather than having the fence signalled via a flag on a descriptor - which
requires reading the docs to find out whether the flag needs to go on the
last descriptor before, or the first descriptor after the fence - we can
instead add a separate fence API call. This becomes unambiguous to use,
since the fence call explicitly comes between two other enqueue calls. It
also allows more freedom of implementation in the driver code.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Kevin Laatz <kevin.laatz@intel.com>
Acked-by: Radu Nicolau <radu.nicolau@intel.com>
Since the hardware supported by the ioat driver is capable of operations
other than just copies, we can rename the doorbell and completion-return
functions to not have "copies" in their names. These functions are not
copy-specific, and so would apply for other operations which may be added
later to the driver.
Also add a suitable warning using deprecation attribute for any code using
the old functions names.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Kevin Laatz <kevin.laatz@intel.com>
Acked-by: Radu Nicolau <radu.nicolau@intel.com>
Add a flag which controls whether rte_ioat_enqueue_copy and
rte_ioat_completed_copies function should process handle parameters. Not
doing so can improve the performance when handle parameters are not
necessary.
Signed-off-by: Cheng Jiang <cheng1.jiang@intel.com>
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Kevin Laatz <kevin.laatz@intel.com>
Acked-by: Radu Nicolau <radu.nicolau@intel.com>
VXLAN UDP/IPv4 GRO can help improve VM-to-VM UDP
performance when UFO or GSO is enabled in VM, GRO
must be supported if UFO or GSO is enabled,
otherwise, performance can't get big improvement
if only GSO is there.
With this enabled in DPDK, OVS DPDK can leverage it
to improve VM-to-VM UDP performance, it will reassemble
VXLAN UDP/IPv4 fragments immediate after they are
received from a physical NIC. It is very helpful in
OVS DPDK VXLAN use case.
Signed-off-by: Yi Yang <yangyi01@inspur.com>
Acked-by: Jiayu Hu <jiayu.hu@intel.com>
UDP/IPv4 GRO can help improve VM-to-VM UDP performance
when UFO or GSO is enabled in VM, GRO must be supported
if UFO or GSO is enabled, otherwise, performance can't
get big improvement if only GSO is there.
With this enabled in DPDK, OVS DPDK can leverage it
to improve VM-to-VM UDP performance, it will reassemble
UDP fragments immediate after they are received from
a physical NIC. It is very helpful in OVS DPDK VLAN use
case.
Signed-off-by: Yi Yang <yangyi01@inspur.com>
Acked-by: Jiayu Hu <jiayu.hu@intel.com>
As decided in the Technical Board in November 2019,
the kernel module igb_uio is moved to the dpdk-kmods repository
in the /linux/igb_uio/ directory.
Minutes of Technical Board meeting:
https://mails.dpdk.org/archives/dev/2019-November/151763.html
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Since the rawdev autotest can now be used to test all rawdevs on the
system, there is no need for a dedicated ioat autotest command.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Kevin Laatz <kevin.laatz@intel.com>
Rather than having each rawdev provide its own autotest command, we can
instead just use the generic rawdev_autotest to test any and all available
rawdevs.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com>
Reviewed-by: Kevin Laatz <kevin.laatz@intel.com>
Add NTB device support (4th generation) for Intel Ice Lake platform.
Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
Acked-by: Jingjing Wu <jingjing.wu@intel.com>
The stack library was first released in 19.05, and its interfaces have been
stable since their initial introduction. This commit promotes the full
interface to stable, starting with the 20.11 major version.
Signed-off-by: Gage Eads <gage.eads@intel.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Python 2 support has now been dropped. Remove references to it in the
documentation.
Since all python scripts now have a proper shebang that calls python3,
execute the scripts directly without specifying the interpreter.
Sphinx version from most Linux distros is OK in 2020, do not encourage
people to break their system by installing with pip. Use the distros
official packages.
Signed-off-by: Robin Jarry <robin.jarry@6wind.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Kevin Laatz <kevin.laatz@intel.com>
Changed scripts to explicitly use Python 3 only, to avoid
maintaining Python 2.
Removed deprecation notices.
Signed-off-by: Louise Kilheeney <louise.kilheeney@intel.com>
Signed-off-by: Kevin Laatz <kevin.laatz@intel.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Acked-by: Robin Jarry <robin.jarry@6wind.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
vhost-vDPA is a new virtio backend type introduced by vDPA kernel
framework, which provides abstraction to the vDPA devices and
exposes an unified control interface through a char dev.
This patch adds support to the vhost-vDPA backend. As similar to
the existing vhost kernel backend, a set of virtio_user ops were
introduced for vhost-vDPA backend to handle device specific operations
such as:
- device setup
- ioctl message handling
- queue pair enabling
- dma map/unmap
vDPA relevant ioctl codes and data structures are also defined in
this patch.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
Dequeue zero-copy removal was announced in DPDK v20.08.
This feature brings constraints which makes the maintenance
of the Vhost library difficult. Its limitations makes it also
difficult to use by the applications (Tx vring starvation).
Removing it makes it easier to add new features, and also remove
some code in the hot path, which should bring a performance
improvement for the standard path.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
ethdev library was updated with new speed 200G
Add 200G speed capa to virtio device
Signed-off-by: Ivan Dyukov <i.dyukov@samsung.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
rte_ethdev states new rule for NICs: they should return UNKNOWN
speed if speed is unknown and interface is up, in case of down
interface, NONE speed should be returned.
Signed-off-by: Ivan Dyukov <i.dyukov@samsung.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
As announced in v20.08, this patch makes the vDPA
and related Vhost API stable.
Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Chenbo Xia <chenbo.xia@intel.com>
PF driver is responsible for vSwitch creation and vPorts allocation
for VFs.
Signed-off-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Andy Moreton <amoreton@xilinx.com>
The temporary flag RTE_ETH_DEV_CLOSE_REMOVE is removed.
It was introduced in DPDK 18.11 in order to give time for PMDs to migrate.
The old behaviour was to free only queues when closing a port.
The new behaviour is calling rte_eth_dev_release_port() which does
three more tasks:
- trigger event callback
- reset state and few pointers
- free all generic port resources
The private port resources must be released in the .dev_close callback.
The .remove callback should:
- call .dev_close callback
- call rte_eth_dev_release_port()
- free multi-port device shared resources
Despite waiting two years, some drivers have not migrated,
so they may hit issues with the incompatible new behaviour.
After sending emails, adding logs, and announcing the deprecation,
the only last solution is to declare these drivers as unmaintained:
ionic, liquidio, nfp
Below is a summary of what to implement in those drivers.
* The freeing of private port resources must be moved
from the ".remove(device)" function to the ".dev_close(port)" function.
* If a generic resource (.mac_addrs or .hash_mac_addrs) cannot be freed,
it must be set to NULL in ".dev_close" function to protect from
subsequent rte_eth_dev_release_port() freeing.
* Note 1:
The generic resources are freed in rte_eth_dev_release_port(),
after ".dev_close" is called in rte_eth_dev_close(), but not when
calling ".dev_close" directly from the ".remove" PMD function.
That's why rte_eth_dev_release_port() must still be called explicitly
from ".remove(device)" after calling the ".dev_close" PMD function.
* Note 2:
If a device can have multiple ports, the common resources must be freed
only in the ".remove(device)" function.
* Note 3:
The port is supposed to be in a stopped state when it is closed.
If it is not the case, it is free to the PMD implementation
how to react when trying to close a non-stopped port:
either try to stop it automatically or just return an error.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Reviewed-by: Liron Himi <lironh@marvell.com>
Reviewed-by: Haiyue Wang <haiyue.wang@intel.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Thor based NICs can support PAM4 as wells as NRZ link negotiation.
With this patch we are adding support for 200G link speeds based on
PAM4 signaling. While PAM4 can negotiate speeds for 50G and 100G as
well, the PMD will use NRZ signalling for these speeds.
Signed-off-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Replace use of RTE_MACHINE_CPUFLAG macros with regular compiler
macros, which are more complete than those provided by DPDK, and as such
it allows new instruction sets to be leveraged without having to do
extra work to set them up in DPDK.
Signed-off-by: Sean Morrissey <sean.morrissey@intel.com>
Signed-off-by: Radu Nicolau <radu.nicolau@intel.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Since the 20.08 release deprecated rte_cio_*mb APIs because these APIs
provide the same functionality as rte_io_*mb APIs on all platforms, so
remove them and use rte_io_*mb instead.
Signed-off-by: Phil Yang <phil.yang@arm.com>
Signed-off-by: Joyce Kong <joyce.kong@arm.com>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Reviewed-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Flow Manager (flowman) provides DECAP_STRIP operation which
decapsulates VXLAN header and then removes VLAN header from the inner
packet. Use this operation to support vxlan_decap followed by
of_pop_vlan.
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
Group 0 corresponds to TCAM which supports priorities. Accept non-zero
priorities for group 0 flows.
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
Use Flow Manager (flowman) to support egress PORT_ID action. It can
steer egress packets from PFs and VFs to any uplink port as long as
they are all on the same VIC adapter. It can also steer packets
between ports on the same VIC adapter (i.e. loopback).
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
Use Flow Manager (flowman) to support flow API for
representors. Representor's flow handlers simply invoke PF handlers
and pass the representor's flowman structure. The PF flowman handlers
are aware of representors and perform appropriate devcmds to create
flows on the NIC.
Also use flowman to create internal flows for implicit VF-representor
path. With that, representor Tx/Rx is now functional.
Signed-off-by: Hyong Youb Kim <hyonkim@cisco.com>
Reviewed-by: John Daley <johndale@cisco.com>
Add a field named rx_buf_size in rte_eth_rxq_info to indicate the buffer
size used in receiving packets for HW.
In this way, upper-layer users can get this information by calling
rte_eth_rx_queue_info_get.
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
Reviewed-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
Start support matching on icmpv4 and icmpv6.
Usage:
--icmpv4: add icmp item to match on.
--icmpv6: add icmpv6 item to match on.
Signed-off-by: Wisam Jaddo <wisamm@mellanox.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
Sometimes you need to check flow performance for
certain port and not all ports. Thus a portmask
option is needed.
Usage:
--portmask=N
Where N represent the hexadecimal bitmask of ports
used.
Signed-off-by: Wisam Jaddo <wisamm@mellanox.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
Introduce raw-encap and raw-decap actions.
The two actions are added in command line
options, and for the data to encap or decap
the user need to parse it within the command
line.
All values of raw-encap data is set to be fixed
values.
Usage example:
--raw-encap=ether,ipv4,udp,vxlan
Signed-off-by: Wisam Jaddo <wisamm@mellanox.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
Introduce flag action support to flow perf
application.
Signed-off-by: Wisam Jaddo <wisamm@mellanox.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
Introduce headers modify actions in the app.
All header modify actions will add different value
for each flow, to make sure each flow will create
and use it's own actions.
Signed-off-by: Wisam Jaddo <wisamm@mellanox.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
The old design was using the bit mask to identify
items, action and attributes.
So it was all based on the order of the code itself,
to place the order of the actions, items & attributes
inside the flows. Such design will lead into many failures
when some PMD support order different than other PMD,
in the end the rules will fail to create. Also sometimes
the user needs to have one action before other actions
and vice versa, so using new design of arrays that
take user order into consideration make more sense.
After this patch, we start supporting inner items
and more than one instance of same action.
Signed-off-by: Wisam Jaddo <wisamm@mellanox.com>
Acked-by: Alexander Kozyrev <akozyrev@nvidia.com>
Updating the type for 'port' variable from 'uint8_t' to 'uint16_t'.
Fixes: 8c3495f5d2dd ("net/dpaa: support loopback API")
Cc: stable@dpdk.org
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
'_rte_eth_dev_callback_process()' & '_rte_eth_dev_reset()' internal APIs
has unconventional underscore ('_') prefix.
Although this is not documented most probably this is to mark them as
internal. Since we have '__rte_internal' flag to mark this, removing '_'
from API names.
For '_rte_eth_dev_reset()', there is already a public API named
'rte_eth_dev_reset()', so renaming '_rte_eth_dev_reset()' to
'rte_eth_dev_internal_reset'.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Acked-by: Sachin Saxena <sachin.saxena@nxp.com>
Some ethdev functions are for drivers only, not for applications.
Since we have '__rte_internal' tag available now, marking internal
functions with it and moving functions to INTERNAL section in linker
script.
This is also good for documenting the internal functions.
Some internal APIs seems marked as experimental, but it doesn't make
sense to have internals APIs as experimental, updating their tag and
doxygen comments.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: David Marchand <david.marchand@redhat.com>
This patch is a preparation to hide the 'struct eth_dev_ops' from
applications by moving some device operations from 'struct eth_dev_ops'
to 'struct rte_eth_dev'.
Mentioned ethdev APIs are in the data path and implemented as inline
because of performance reasons.
Exposing 'struct eth_dev_ops' to applications is bad because it is a
contract between ethdev and PMDs, not really needs to be known by
applications, also changes in the struct causing ABI breakages which
shouldn't.
To be able to both keep APIs inline and hide the 'struct eth_dev_ops',
moving device operations used in ethdev inline APIs to 'struct
rte_eth_dev' to the same level with Rx/Tx burst functions.
The list of dev_ops moved:
eth_rx_queue_count_t rx_queue_count;
eth_rx_descriptor_done_t rx_descriptor_done;
eth_rx_descriptor_status_t rx_descriptor_status;
eth_tx_descriptor_status_t tx_descriptor_status;
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Reviewed-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Acked-by: Sachin Saxena <sachin.saxena@nxp.com>
Marking 'rte_eth_rx_descriptor_done()' API as deprecated.
``rte_eth_rx_descriptor_status`` and ``rte_eth_tx_descriptor_status``
APIs can be used as replacement.
Plan is to remove the API on 21.11 release.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
Acked-by: David Marchand <david.marchand@redhat.com>
This structure is not used in the public API.
Fixes: a753e53d517b ("eal: add device event monitor framework")
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Jeff Guo <jia.guo@intel.com>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
As reported during 20.08 work for Windows, the pci_map_resource API was
built with the assumption that its flags would be passed to mmap().
This introduced a regression when adding the rte_mem_map API as reported
in the workaround commit 9d2b24593724 ("pci: keep API compatibility with
mmap values").
This API was only used in the PCI bus code, so move it there.
There is no code change happening during the move.
The only change is in the pci_map_resource description where the
additional flags are now documented as rte_mem_map API flags:
- * The additional flags for the mapping range.
+ * The additional rte_mem_map() flags for the mapping range.
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
The rte_kernel_driver enum actually only pointed at PCI drivers and is
only used in the PCI subsystem.
Remove it from the generic device API and use a private enum in the PCI
code.
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
This field was not generic as it was filled with PCI kernel drivers only.
It has no known in-tree user (and I could not find opensource projects
using it).
Signed-off-by: David Marchand <david.marchand@redhat.com>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Remove the deprecated buf_physaddr union field from rte_mbuf.
It is replaced with buf_iova which is at the same offset.
The single field buf_physaddr in rte_kni_mbuf is also renamed.
This concludes a 3-year process of semantic change.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Acked-by: Andrew Rybchenko <arybchenko@solarflare.com>
Acked-by: Ray Kinsella <mdr@ashroe.eu>
