Add support for queue operations:
- rx_queue_release
- tx_queue_release
Previous gve_tx_queue_release and gve_rx_queue_release functions are
only used internally to release Rx/Tx queue related resources.
But when the queues or ports are required to re-config, both of the dev
ops tx_queue_release and ops rx_queue_release will be checked and then
called.
Without these two dev ops, the Rx/Tx queue struct will be set as NULL
directly.
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@amd.com>
Some of the HW has support for choosing memory pools based on
the packet's size. The pool sort capability allows PMD/NIC to
choose a memory pool based on the packet's length.
On multiple mempool support enabled, populate mempool array
accordingly. Also, print pool name on which packet is received.
Signed-off-by: Hanumanth Pothula <hpothula@marvell.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
The "show config rxhdrs" cmd displays the configured protocol headers
that are used for protocol-based buffer split.
However, it shows inner-ipv6 as inner-ipv4.
This patch fixes that by redefining rx_pkt_hdr_protos to hold
the full ptypes, and the show and set commands therefore
remain symmetrical.
Fixes: 52e2e7edcf ("app/testpmd: add protocol-based buffer split")
Signed-off-by: Yuan Wang <yuanx.wang@intel.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Flows created with the new asynchronous flow API lack attributes
(direction, priority, group number). These attributes are part of
a template table for flows created via rte_flow_async_create().
When testpmd tries to list all the flows it accesses flow
attributes via pointer and crashes. Save flow attributes during
the template table creation and use them in the "flow list" output.
Fixes: ecdc927b99 ("app/testpmd: add async flow create/destroy operations")
Cc: stable@dpdk.org
Signed-off-by: Alexander Kozyrev <akozyrev@nvidia.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
The RTE_ETH_TX_OFFLOAD_MBUF_FAST_FREE offload can't be used in bonding
mode Broadcast and mode 8023AD. Currently, bonding driver forcibly removes
from the dev->data->dev_conf.txmode.offloads and processes as success in
bond_ethdev_configure(). But this still cause that rte_eth_dev_configure()
fails to execute because of the failure of validating Tx offload in the
eth_dev_validate_offloads(). So this patch moves the modification of txmode
offlaods to the stage of adding slave device to report the correct txmode
offloads.
Fixes: 18c41457cb ("net/bonding: fix mbuf fast free usage")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Since f_quit is set in a signal handler it needs to be marked
volatile. Otherwise, compiler is allowed to optimize the loop because
it can assume the value never changes. The flag can also be made local
to the file it is used in.
Fixes: d9a191a00e ("app/testpmd: fix quitting in container")
Cc: stable@dpdk.org
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com>
Some capabilities (like, rx_offload_capa and tx_offload_capa) of bonding
device in dev_info is zero when no slave is added. And its capability will
be updated when add a new slave device.
The capability to update dynamically may introduce some problems if not
handled properly. For example, the reconfig() is called to initialize
bonding port configurations when create a bonding device. The global
tx_mode is assigned to dev_conf.txmode. The DEV_TX_OFFLOAD_MBUF_FAST_FREE
which is the default value of global tx_mode.offloads in testpmd is removed
from bonding device configuration because of zero rx_offload_capa.
As a result, this offload isn't set to bonding device.
Generally, port configurations of bonding device must be within the
intersection of the capability of all slave devices. If use original port
configurations, the removed capabilities because of adding a new slave may
cause failure when re-initialize bonding device.
So port configurations of bonding device need to be updated because of the
added and removed capabilities. In addition, this also helps to ensure
consistency between testpmd and bonding device.
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Reviewed-by: Min Hu (Connor) <humin29@huawei.com>
Currently, by default, bond4 will first try to enable allmulti and
then enable promiscuous if fail to enable allmulti. On reception,
whether unicast and multicast packets should be dropped depends on
which mode has been enabled on the bonding interface.
In fact, if MAC address of packets in mac_addrs array of bonding
interface, these packets should not be dropped. However, now only
check the default MAC address, which will cause the packets with
MAC added by the '.mac_addr_add' are dropped.
Fixes: 68218b87c1 ("net/bonding: prefer allmulti to promiscuous for LACP")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Change the advertised link speed from 10G to 100G as the memory
interfaces can reach higher throughput than 10G with large packets.
Signed-off-by: Nathan Skrzypczak <nathan.skrzypczak@gmail.com>
Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
MLX5 SR-IOV Tx engine will not transmit Ethernet frame
if destination MAC address matched local port address. The frame ether
looped-back to Rx or dropped, depending on the port configuration.
Application running over MLX5 SR-IOV port cannot transmit packet
polled from Rx queue as is. The packet Ethernet destination address
must be changed.
Add new run-time configuration parameter to the `csum` forwarding
engine to control MAC addresses configuration:
testpmd> csum mac-swap on|off <port_id>
`mac-swap on` replace MAC addresses.
`mac-swap off` keep Ethernet header unchanged.
Fixes: 9b4ea7ae77 ("app/testpmd: revert MAC update in checksum forwarding")
Cc: stable@dpdk.org
Signed-off-by: Gregory Etelson <getelson@nvidia.com>
Acked-by: Huisong Li <lihuisong@huawei.com>
Normally, the Rx/Tx offload capability of bonding interface is
the intersection of the capability of all slave devices. And
Rx/Tx offloads configuration of slave device comes from bonding
interface. But now there is a risk that slave device retains its
previous offload configurations which is not within the offload
configurations of bond interface.
Fixes: 57b156540f ("net/bonding: fix offloading configuration")
Cc: stable@dpdk.org
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Acked-by: Min Hu (Connor) <humin29@huawei.com>
The driver had once been broken by patch [1] looking to have
a non-zero "nb_max" value in a use case not involving adding
any back-end ports. That was addressed afterwards ([2]). But,
as per report [3], similar test cases exist which attempt to
setup Rx queues on a void bond before attaching any back-end
ports. Rx queue setup, in turn, involves device info get API
invocation, and one of the checks on received data causes an
exception (division by zero). The "nb_align" value is indeed
zero at that time, but, as explained in [2], such test cases
are totally incorrect since a bond device must have at least
one back-end port plugged before any ethdev APIs can be used.
Once again, to avoid any problems with fixing the test cases,
this patch adjusts the bond PMD itself to workaround the bug.
[1] commit 5be3b40fea ("net/bonding: fix values of descriptor limits")
[2] commit d03c0e83cc ("net/bonding: fix descriptor limit reporting")
[3] https://bugs.dpdk.org/show_bug.cgi?id=1118
Bugzilla ID: 1118
Fixes: d03c0e83cc ("net/bonding: fix descriptor limit reporting")
Cc: stable@dpdk.org
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Acked-by: Min Hu (Connor) <humin29@huawei.com>
Tested-by: Weiyuan Li <weiyuanx.li@intel.com>
As per report [1], the previous patch for device
configure code apparently overlooks the corner
case of manually adding back-end devices to
the bond using testpmd CLI. The problem is
in removing back-end ports on re-configure
instead of just stopping them. Fix that.
[1] https://bugs.dpdk.org/show_bug.cgi?id=1119
Bugzilla ID: 1119
Fixes: 339f1ba513 ("net/bonding: make configure method re-entrant")
Cc: stable@dpdk.org
Signed-off-by: Ivan Malov <ivan.malov@oktetlabs.ru>
Tested-by: Dukai Yuan <dukaix.yuan@intel.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Fix the check logic of the index of the array, which
caused the out of bounds write problem.
Coverity issue: 381616
Fixes: c55abf6141 ("net/nfp: support RSS on VXLAN inner layer")
Signed-off-by: Chaoyong He <chaoyong.he@corigine.com>
Reviewed-by: Niklas Söderlund <niklas.soderlund@corigine.com>
If tx_pkts is NULL, nb_pkts must be 0. Coverity doesn't know
this so it thinks this is a forward-NULL violation.
Make things more clear by checking for nb_pkts instead.
Coverity issue: 381614
Coverity issue: 381619
Fixes: e86a6fcc7c ("net/ionic: add optimized non-scattered Rx/Tx")
Signed-off-by: Andrew Boyer <andrew.boyer@amd.com>
(uint16_t * uint16_t) promoted to uint64_t has a sign extension
problem reported by Coverity. Cast one arg to uint64_t first
to eliminate the sign extension.
Coverity issue: 381617
Coverity issue: 381618
Fixes: 7b20fc2f3c ("net/ionic: overhaul Rx for performance")
Signed-off-by: Andrew Boyer <andrew.boyer@amd.com>
The pointers 'rxq' and 'txq' are dereferenced before the null check.
Fixed the logic in this patch.
Fixes: 4bec2d0b55 ("net/gve: support queue operations")
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Reviewed-by: Ferruh Yigit <ferruh.yigit@amd.com>
When built with stats enabled (RTE_LIBRTE_MEMPOOL_STATS defined),
the performance of mempools with caches is improved as follows.
When accessing objects in the mempool, either the put_bulk and put_objs or
the get_success_bulk and get_success_objs statistics counters are likely
to be incremented.
By adding an alternative set of these counters to the mempool cache
structure, accessing the dedicated statistics structure is avoided
in the likely cases where these counters are incremented.
The trick here is that the cache line holding the mempool cache structure
is accessed anyway, in order to access the 'len' or 'flushthresh' fields.
Updating some statistics counters in the same cache line has lower
performance cost than accessing the statistics counters in the dedicated
statistics structure, which resides in another cache line.
mempool_perf_autotest with this patch shows the following improvements in
rate_persec.
The cost of enabling mempool stats (without debug) after this patch:
-6.8 % and -6.7 %, respectively without and with cache.
Signed-off-by: Morten Brørup <mb@smartsharesystems.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Mattias Rönnblom <mattias.ronnblom@ericsson.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
This patch adds statistics for unregistered non-EAL threads,
which was previously not included in the statistics.
Add one more entry to the stats array,
and use the last index for unregistered non-EAL threads.
The unregistered non-EAL thread statistics are incremented atomically.
In theory, the EAL thread counters should also be accessed atomically to
avoid tearing on 32 bit architectures. However, it was decided to avoid
the performance cost of using atomic operations, because:
1. these are debug counters, and
2. statistics counters in DPDK are usually incremented non-atomically.
Suggested-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Morten Brørup <mb@smartsharesystems.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Mattias Rönnblom <mattias.ronnblom@ericsson.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
Split stats from debug, to make mempool statistics available without the
performance cost of continuously validating the debug cookies in the
mempool elements.
mempool_perf_autotest shows the following improvements in rate_persec.
The cost of enabling mempool debug without this patch:
-28.1 % and -74.0 %, respectively without and with cache.
The cost of enabling mempool stats (without debug) after this patch:
-5.8 % and -21.2 %, respectively without and with cache.
Signed-off-by: Morten Brørup <mb@smartsharesystems.com>
Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Reviewed-by: Mattias Rönnblom <mattias.ronnblom@ericsson.com>
Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>
The module implements methods needed to run DTS. It handles the creation
of objects and eventually the whole DTS workflow, such as running node
setups, test gathering, setup and execution and various cleanups.
Signed-off-by: Owen Hilyard <ohilyard@iol.unh.edu>
Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech>
The base class implements basic node management methods - connect and
execute commands.
Signed-off-by: Owen Hilyard <ohilyard@iol.unh.edu>
Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech>
The module uses the pexpect python library and implements connection to
a node and two ways to interact with the node:
1. Send a string with specified prompt which will be matched after
the string has been sent to the node.
2. Send a command to be executed. No prompt is specified here.
Signed-off-by: Owen Hilyard <ohilyard@iol.unh.edu>
Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech>
The abstraction allows for easy switching of implementations of remote
connections (ssh, telnet, etc.). It implements some common features,
such as logging of commands and their outputs and history bookkeeping
and defines methods that must be implemented by derived classes.
Signed-off-by: Owen Hilyard <ohilyard@iol.unh.edu>
Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech>
The logging module provides loggers distinguished by two attributes,
a custom format and a verbosity switch. The loggers log to both console
and more verbosely to files.
Signed-off-by: Owen Hilyard <ohilyard@iol.unh.edu>
Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech>
The configuration is split into two parts, one defining the parameters
of the test run and the other defining the topology to be used.
The format of the configuration is YAML. It is validated according to a
json schema which also server as detailed documentation of the various
configuration fields. This means that the complete set of allowed values
are tied to the schema as a source of truth. This enables making changes
to parts of DTS that interface with config files without a high risk of
breaking someone's configuration.
This configuration system uses immutable objects to represent the
configuration, making IDE/LSP autocomplete work properly.
There are two ways to specify the configuration file path, an
environment variable or a command line argument, applied in that order.
Signed-off-by: Owen Hilyard <ohilyard@iol.unh.edu>
Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech>
The devtools that check Python code are Black and Isort to format the
code and Pylama to do static analysis.
Signed-off-by: Owen Hilyard <ohilyard@iol.unh.edu>
Signed-off-by: Juraj Linkeš <juraj.linkes@pantheon.tech>
An additional check is added to avoid extra processing if
receive packets are 0.
Performance impact: with Marvell OCTEON TX2 platform, observed an
improvement by ~14%.
Signed-off-by: Rahul Bhansali <rbhansali@marvell.com>
Acked-by: Jerin Jacob <jerinj@marvell.com>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com>
With some higher GCC/CLANG version, it is not recommended to use a
structure with a tailing flexible array inside another structure.
Accessing this array may be considered as a risk to corrupt the
following field even if it is by intention.
The error below was observed:
drivers/net/mlx5/linux/mlx5_ethdev_os.c: In function 'mlx5_get_flag_dropless_rq':
drivers/net/mlx5/linux/mlx5_ethdev_os.c:1679:42: error:
invalid use of structure with flexible array member [-Werror=pedantic]
1679 | struct ethtool_sset_info hdr;
| ^~~
Changing it to memory dynamic allocation method will help to get
rid of this complain.
Fixes: e848218741 ("net/mlx5: check delay drop settings in kernel driver")
Cc: stable@dpdk.org
Signed-off-by: Bing Zhao <bingz@nvidia.com>
Acked-by: Thomas Monjalon <thomas@monjalon.net>
Harish is the new maintainer of Rx/Tx adapters due to role change of Jay.
Signed-off-by: Jay Jayatheerthan <jay.jayatheerthan@intel.com>
Acked-by: Naga Harish K S V <s.v.naga.harish.k@intel.com>
The script devtools/parse-flow-support.sh uses the git-grep
option (-o, --only-matching), which is only supported from
git version 2.19 and onwards.[1]
The script now exits early providing a clear message to the user
about the required git version instead of showing the following
error messages multiple times:
error: unknown switch `o'
usage: git grep [<options>] [-e] <pattern> [<rev>...] [[--] <path>...]
[..]
[1] https://github.com/git/git/blob/v2.19.0/Documentation/RelNotes/2.19.0.txt
Signed-off-by: Ali Alnubani <alialnu@nvidia.com>
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Tested-by: Chaoyong He <chaoyong.he@corigine.com>
The 4.4 kernel was end of life in February 2022,
and the next LTS is 4.9 and it is reaching EOL in January 2023.
The main distro using 4.9 is Debian Stretch and it is no longer
supported. When DPDK 22.11 is released, the 4.9 kernel would
only be receiving fixes for three months; therefore
lets make the official version 4.14.
As always, current major enterprise Linux releases will continue
to be supported, but those releases don't track regular kernel
version numbering.
For full details on kernel support see:
https://www.kernel.org/category/releases.htmlhttps://en.wikipedia.org/wiki/Linux_kernel_version_history
Debian Stretch:
https://www.debian.org/releases/stretch/
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Currently, the dpdk-telemetry.py show JSON in raw format under
interactive mode, which is not good for human reading.
E.g. The command '/ethdev/xstats,0' will output:
{"/ethdev/xstats": {"rx_good_packets": 0, "tx_good_packets": 0,
"rx_good_bytes": 0, "tx_good_bytes": 0, "rx_missed_errors": 0,
"rx_errors": 0, "tx_errors": 0, "rx_mbuf_allocation_errors": 0,
"rx_q0_packets": 0,...}}
This patch supports JSON pretty print by adding extra indent=2
parameter under interactive mode, so the same command will output:
{
"/ethdev/xstats": {
"rx_good_packets": 0,
"tx_good_packets": 0,
"rx_good_bytes": 0,
"tx_good_bytes": 0,
"rx_missed_errors": 0,
"rx_errors": 0,
"rx_mbuf_allocation_errors": 0,
"rx_q0_packets": 0,
...
}
}
Note: the non-interactive mode is made machine-readable and remains the
original way (it means don't use indent to pretty print).
Signed-off-by: Chengwen Feng <fengchengwen@huawei.com>
Acked-by: David Marchand <david.marchand@redhat.com>
Acked-by: Ciara Power <ciara.power@intel.com>
Tested-by: Bruce Richardson <bruce.richardson@intel.com>
In this patch,
* It is possible to switch the running mode of the distributor
using the command line argument.
* With "-c" parameter, you can run RX and Distributor
on the same core.
* Without "-c" parameter, you can run RX and Distributor
on the different core.
* Consecutive termination of the lcores fixed.
The termination order was wrong, and you couldn't terminate the
application while traffic was capturing. The current order is
RX -> Distributor -> TX -> Workers
* When "-c" parameter is active, the wasted distributor core is
also deactivated in the main function.
Signed-off-by: Abdullah Ömer Yamaç <omer.yamac@ceng.metu.edu.tr>
Split packet processing from packet send stage, as send stage
is not common for poll and event mode.
Signed-off-by: Pavan Nikhilesh <pbhagavatula@marvell.com>
Acked-by: Shijith Thotton <sthotton@marvell.com>
Add support of AVX512 vector data path for single queue model.
Signed-off-by: Wenjun Wu <wenjun1.wu@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Add Tx offloading support:
- support TSO for single queue model and split queue model.
Signed-off-by: Beilei Xing <beilei.xing@intel.com>
Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Add Rx offloading support:
- support CHKSUM and RSS offload for split queue model
- support CHKSUM offload for single queue model
Signed-off-by: Beilei Xing <beilei.xing@intel.com>
Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
Enable write back on ITR expire, then packets can be received one by
one.
Signed-off-by: Beilei Xing <beilei.xing@intel.com>
Signed-off-by: Junfeng Guo <junfeng.guo@intel.com>
