Ivan Ilchenko [Tue, 28 Sep 2021 11:29:02 +0000 (14:29 +0300)]
net/sfc: rename array of SW stats descriptions
Rename global array of SW stats descriptions declared as
'struct sfc_sw_xstat_descr sfc_sw_xstats[]' to
'sfc_sw_stats_descr[]' to avoid ambiguity since there is
structure declared as 'struct sfc_sw_xstats'.
Signed-off-by: Ivan Ilchenko <ivan.ilchenko@oktetlabs.ru> Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Ferruh Yigit [Mon, 4 Oct 2021 17:27:02 +0000 (18:27 +0100)]
net/ena: remove useless address check
Reported by "gcc (GCC) 12.0.0 20211003 (experimental)":
./drivers/net/ena/ena_rss.c: In function ‘ena_rss_reta_query’:
./drivers/net/ena/ena_rss.c:140:66:
error: the comparison will always evaluate as ‘false’ for the
pointer operand in ‘reta_conf + 136’ must not be NULL
[-Werror=address]
140 | (reta_size > RTE_RETA_GROUP_SIZE && ((reta_conf + 1) == NULL)))
| ^~
Fixing it by removing useless check.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Michal Krawczyk <mk@semihalf.com>
Huisong Li [Mon, 11 Oct 2021 09:12:46 +0000 (17:12 +0800)]
app/testpmd: retain all original dev conf when config DCB
When configuring DCB, testpmd retains the rx_mode/tx_mode configuration in
rte_port->dev_conf. But some configurations, such as the link_speed, were
not saved if they were set before configuring DCB.
Fixes: 1a572499beb6 ("app/testpmd: setup DCB forwarding based on traffic class") Cc: stable@dpdk.org Signed-off-by: Huisong Li <lihuisong@huawei.com> Signed-off-by: Min Hu (Connor) <humin29@huawei.com> Acked-by: Xiaoyun Li <xiaoyun.li@intel.com>
app/testpmd: add command to show LACP bonding info
Add a new cmdline to help diagnostic the bonding mode 4 in testpmd.
Show the lacp information about the bonded device and its slaves:
show bonding lacp info <bonded device port_id>
Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Min Hu (Connor) <humin29@huawei.com> Acked-by: Xiaoyun Li <xiaoyun.li@intel.com>
Currently the hash_key_size information has not been set. So, apps can
not get the key size from dev_info(), this make some problem.
e.g, in testpmd, the hash_key_size will be checked before configure
or get the hash key:
testpmd> show port 4 rss-hash
dev_info did not provide a valid hash key size
testpmd> show port 4 rss-hash key
dev_info did not provide a valid hash key size
testpmd> port config 4 rss-hash-key ipv4 (hash key)
dev_info did not provide a valid hash key size
In this patch, the meaning of rss_key_len has been modified. It only
indicated the length of the configured hash key before. Therefore,
its value depends on the user's configuration. This seems unreasonable.
And now, it indicates the minimum hash key length required by the
bonded device. Its value will be the shortest hash key among all slave
drivers.
Fixes: 734ce47f71e0 ("bonding: support RSS dynamic configuration") Cc: stable@dpdk.org Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
net/bonding: fix dedicated queue mode in vector burst
If the vector burst mode is selected, the dedicated queue mode will not
take effect on some PMDs because these PMDs may have some limitations
in vector burst mode. For example, the limit on burst size. Currently,
both hns3 and intel I40E require four alignments when receiving packets
in vector mode. As a result, they can't accept packets if burst size
below four. However, in dedicated queue mode, the burst size of periodic
packets processing is one.
This patch fixes the above problem by modifying the burst size to 32.
This approach also makes the packet processing of the dedicated queue
mode more reasonable. Currently, if multiple LACP protocol packets are
received in the hardware queue in a cycle, only one LACP packet will be
processed in this cycle, and the left packets will be processed in the
following cycle. After the modification, all the LACP packets will be
processed at one time, which seems more reasonable and closer to the
behavior of the bonding driver when the dedicated queue is not turned on.
Fixes: 112891cd27e5 ("net/bonding: add dedicated HW queues for LACP control") Cc: stable@dpdk.org Signed-off-by: Chengchang Tang <tangchengchang@huawei.com> Signed-off-by: Min Hu (Connor) <humin29@huawei.com>
When random number of Tx segments is enabled, because the actual
number of segments may be only one, the first segment of the Tx
packets must accommodate a complete being sending Eth/IP/UDP packet.
Besides, if multiple flow is enabled, the forwarding will update
the IP and UDP header, these headers shouldn't cross segments.
This also requires the first Tx segment can accommodate a complete
Eth/IP/UDP packet.
In addition, if time stamp is enabled, the forwarding needs more
Tx segment space for time stamp information.
This patch adds checks in beginning of forward engine to make sure
all above conditions are met.
For each forward engine, there may be some special conditions
must be met before the forwarding runs.
Adding checks for these conditions in configuring is not suitable,
because one condition may rely on multiple configurations, and the
conditions required by each forward engine is not general.
The best solution is each forward engine has a callback to check
whether these conditions are met, and then testpmd can call the
callback to determine whether the forwarding can be started.
There was a void callback 'port_fwd_begin' in forward engine,
it did some initialization for forwarding, this patch updates its
return value then we can add some checks in it to confirm whether
the forwarding can be started. In addition, this patch calls the
callback before the forwarding stats is reset and then launches the
forwarding engine.
Ciara Loftus [Fri, 8 Oct 2021 07:50:20 +0000 (07:50 +0000)]
net/af_xdp: disable secondary process support
Since the AF_XDP PMD does not work for secondary processes as reported
in Bugzilla 805, check for the process type at the beginning of probe
and return ENOTSUP if the process type is secondary.
It is planned that secondary processes will be supported by the PMD in
full in a future release by using rte_mp_msg to pass the state to the
secondary process that it requires in order to work.
test_shift1_check() function fails with clang build.
The reason for that is that clang uses 64-bit shift instruction for
what expected to be 32-bit operation.
To be more specific, this C code:
r2 = (uint32_t)r2 >> r4;
With clang produces:
41a4eb: 48 d3 ef shr %cl,%rdi
In that particular case it is an allowed choice, as from one side
left-operand value is known to fit into 32 bits, from other side
according to 'C' standard:
"...if the value of the right operand is negative or is greater than
or equal to the width of the promoted left operand, the behavior is
undefined."
The problem is that on x86 behavior for 64-bit and 32-bit shift
operation might differ.
The fix avoids undefined behavior by making sure
that right operand will not exceed width of the promoted left operand.
Bugzilla ID: 811 Fixes: 9f8f9d91a701 ("test/bpf: introduce functional test") Cc: stable@dpdk.org Reported-by: Stephen Hemminger <stephen@networkplumber.org> Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Akhil Goyal [Mon, 18 Oct 2021 05:22:47 +0000 (10:52 +0530)]
security: add reserved bit fields
In struct rte_security_ipsec_sa_options, for every new option
added, there is an ABI breakage, to avoid, a reserved_opts
bitfield is added to for the remaining bits available in the
structure.
Now for every new sa option, these reserved_opts can be reduced
and new option can be added.
Signed-off-by: Akhil Goyal <gakhil@marvell.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Ray Kinsella <mdr@ashroe.eu>
Nipun Gupta [Sun, 17 Oct 2021 06:53:31 +0000 (12:23 +0530)]
app/bbdev: handle endianness of test data
With data input, output and harq also supported in big
endian format, this patch updates the testbbdev application
to handle the endianness conversion as directed by the
the driver being used.
The test vectors assumes the data in the little endian order, and
thus if the driver supports big endian data processing, conversion
from little endian to big is handled by the testbbdev application.
Gagandeep Singh [Wed, 13 Oct 2021 19:00:19 +0000 (00:30 +0530)]
cryptodev: add total raw buffer length
The current crypto raw data vectors is extended to support
rte_security usecases, where we need total data length to know
how much additional memory space is available in buffer other
than data length so that driver/HW can write expanded size
data after encryption.
Radu Nicolau [Thu, 14 Oct 2021 16:03:23 +0000 (17:03 +0100)]
security: add UDP parameters for IPsec NAT-T
Add support for specifying UDP port params for UDP encapsulation option.
RFC3948 section-2.1 does not enforce using specific the UDP ports for
UDP-Encapsulated ESP Header
Signed-off-by: Declan Doherty <declan.doherty@intel.com> Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Signed-off-by: Abhijit Sinha <abhijit.sinha@intel.com> Signed-off-by: Daniel Martin Buckley <daniel.m.buckley@intel.com> Acked-by: Fan Zhang <roy.fan.zhang@intel.com> Acked-by: Anoob Joseph <anoobj@marvell.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Akhil Goyal <gakhil@marvell.com>
Matan Azrad [Mon, 4 Oct 2021 06:36:38 +0000 (09:36 +0300)]
cryptodev: extend data-unit length field
As described in [1] and as announced in [2], The field ``dataunit_len``
of the ``struct rte_crypto_cipher_xform`` moved to the end of the
structure and extended to ``uint32_t``.
In this way, sizes bigger than 64K bytes can be supported for data-unit
lengths.
[1] commit d014dddb2d69 ("cryptodev: support multiple cipher
data-units")
[2] commit 9a5c09211b3a ("doc: announce extension of crypto data-unit
length")
Przemyslaw Zegan [Tue, 12 Oct 2021 12:56:11 +0000 (12:56 +0000)]
app/crypto-perf: fix AAD template copy overrun
This patch fixes a possible buffer overrun problem in crypto perf test.
Previously when user configured AAD size is over 12 bytes the copy
of template AAD will cause a buffer overrun.
The problem is fixed by only copy up to 12 bytes of AAD template.
examples/ipsec-secgw: accept inline packet in single SA
In inline protocol inbound SA's, plain IPv4 and IPv6 packets are
delivered to application unlike inline crypto or lookaside.
Hence fix the application to not drop them when working in
single SA mode.
Adds max queue pairs limit devargs for crypto cnxk driver. This
can be used to set a limit on the number of maximum queue pairs
supported by the device. The default value is 63.
Signed-off-by: Ankur Dwivedi <adwivedi@marvell.com> Reviewed-by: Anoob Joseph <anoobj@marvell.com> Reviewed-by: Jerin Jacob <jerinj@marvell.com>
David Marchand [Mon, 18 Oct 2021 08:26:35 +0000 (10:26 +0200)]
mempool: accept user flags only
As reported by Dmitry, RTE_MEMPOOL_F_POOL_CREATED is a flag only
manipulated internally.
This flag is not supposed to be requested from an application and would
probably result in an incorrect behavior if an application did pass it.
At least one other internal flag has been added recently and more may be
introduced later.
Rework the check and export a mask of valid user flags for use in the
unit test.
Fixes: b240af8b10f9 ("mempool: enforce valid flags at creation") Reported-by: Dmitry Kozlyuk <dkozlyuk@nvidia.com> Signed-off-by: David Marchand <david.marchand@redhat.com> Acked-by: Olivier Matz <olivier.matz@6wind.com> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
Andrew Rybchenko [Tue, 19 Oct 2021 17:40:19 +0000 (20:40 +0300)]
mempool: add namespace to internal helpers
Add RTE_ prefix to internal API defined in public header.
Use the prefix instead of double underscore.
Use uppercase for macros in the case of name conflict.
Signed-off-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Olivier Matz <olivier.matz@6wind.com>
Convert rte_atomic usages to compiler atomic built-ins
for stats sync.
Signed-off-by: Dharmik Thakkar <dharmik.thakkar@arm.com> Reviewed-by: Joyce Kong <joyce.kong@arm.com> Reviewed-by: Ruifeng Wang <ruifeng.wang@arm.com> Acked-by: Yipeng Wang <yipeng1.wang@intel.com> Tested-by: David Christensen <drc@linux.vnet.ibm.com>
Conor Walsh [Mon, 18 Oct 2021 10:09:52 +0000 (10:09 +0000)]
usertools/telemetry: list file-prefixes
This patch adds the option --list (-l) to dpdk-telemetry.py which will
print all of the available file-prefixes for DPDK processes that have
telemetry enabled.
The prefixes will also be printed if the user passes an incorrect prefix
in the --file-prefix (-f) option.
Signed-off-by: Conor Walsh <conor.walsh@intel.com> Acked-by: Ciara Power <ciara.power@intel.com>
Conor Walsh [Mon, 18 Oct 2021 10:39:29 +0000 (10:39 +0000)]
usertools/telemetry: fix instance option help
The instance option help text was incorrect, this patch corrects it.
Fixes: 11435aae2089 ("usertools/telemetry: connect to separate instances") Signed-off-by: Conor Walsh <conor.walsh@intel.com> Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Dmitry Kozlyuk [Mon, 18 Oct 2021 22:43:53 +0000 (01:43 +0300)]
net/mlx5: support mempool registration
When the first port in a given protection domain (PD) starts,
install a mempool event callback for this PD and register all existing
memory regions (MR) for it. When the last port in a PD closes,
remove the callback and unregister all mempools for this PD.
This behavior can be switched off with a new devarg: mr_mempool_reg_en.
On TX slow path, i.e. when an MR key for the address of the buffer
to send is not in the local cache, first try to retrieve it from
the database of registered mempools. Supported are direct and indirect
mbufs, as well as externally-attached ones from MLX5 MPRQ feature.
Lookup in the database of non-mempool memory is used as the last resort.
RX mempools are registered regardless of the devarg value.
On RX data path only the local cache and the mempool database is used.
If implicit mempool registration is disabled, these mempools
are unregistered at port stop, releasing the MRs.
Dmitry Kozlyuk [Mon, 18 Oct 2021 22:43:52 +0000 (01:43 +0300)]
common/mlx5: add mempool registration facilities
Add internal API to register mempools, that is, to create memory
regions (MR) for their memory and store them in a separate database.
Implementation deals with multi-process, so that class drivers don't
need to. Each protection domain has its own database. Memory regions
can be shared within a database if they represent a single hugepage
covering one or more mempools entirely.
Add internal API to lookup an MR key for an address that belongs
to a known mempool. It is a responsibility of a class driver
to extract the mempool from an mbuf.
Dmitry Kozlyuk [Mon, 18 Oct 2021 22:43:51 +0000 (01:43 +0300)]
mempool: add non-IO flag
Mempool is a generic allocator that is not necessarily used
for device IO operations and its memory for DMA.
Add MEMPOOL_F_NON_IO flag to mark such mempools automatically
a) if their objects are not contiguous;
b) if IOVA is not available for any object.
Other components can inspect this flag
in order to optimize their memory management.
Dmitry Kozlyuk [Mon, 18 Oct 2021 22:43:50 +0000 (01:43 +0300)]
mempool: add event callbacks
Data path performance can benefit if the PMD knows which memory it will
need to handle in advance, before the first mbuf is sent to the PMD.
It is impractical, however, to consider all allocated memory for this
purpose. Most often mbuf memory comes from mempools that can come and
go. PMD can enumerate existing mempools on device start, but it also
needs to track creation and destruction of mempools after the forwarding
starts but before an mbuf from the new mempool is sent to the device.
Add an API to register callback for mempool life cycle events:
* rte_mempool_event_callback_register()
* rte_mempool_event_callback_unregister()
Currently tracked events are:
* RTE_MEMPOOL_EVENT_READY (after populating a mempool)
* RTE_MEMPOOL_EVENT_DESTROY (before freeing a mempool)
Provide a unit test for the new API.
The new API is internal, because it is primarily demanded by PMDs that
may need to deal with any mempools and do not control their creation,
while an application, on the other hand, knows which mempools it creates
and doesn't care about internal mempools PMDs might create.
Removing the rawdev based octeontx2-ep driver as the dependent
common/octeontx2 will soon be going away. Moreover this driver is no
longer required as the net/octeontx_ep driver is sufficient.
Removing the rawdev based octeontx2-dma driver as the dependent
common/octeontx2 will be soon be going away. Also a new DMA driver will
be coming in this place once the rte_dmadev library is in.
Bruce Richardson [Wed, 13 Oct 2021 15:17:34 +0000 (16:17 +0100)]
test/dma: add failure handling tests
Add a series of tests to inject bad copy operations into a dmadev to
test the error handling and reporting capabilities. Various combinations
of errors in various positions in a burst are tested, as are errors in
bursts with fence flag set, and multiple errors in a single burst.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Reviewed-by: Kevin Laatz <kevin.laatz@intel.com> Reviewed-by: Conor Walsh <conor.walsh@intel.com>
Bruce Richardson [Wed, 13 Oct 2021 15:17:33 +0000 (16:17 +0100)]
dmadev: add flag for error handling support
Due to HW or driver limitations, not all dmadevs may support full error
handling e.g. safely managing and reporting an invalid address to a copy
operation. The skeleton dmadev, for example, being pure software will
always seg-fault if passed an invalid address. To indicate the
availability of safe error handling by a device, we add a capability
flag for it.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Reviewed-by: Conor Walsh <conor.walsh@intel.com> Reviewed-by: Kevin Laatz <kevin.laatz@intel.com>
Bruce Richardson [Wed, 13 Oct 2021 15:17:32 +0000 (16:17 +0100)]
test/dma: add more comprehensive copy tests
Add unit tests for various combinations of use for dmadev, copying
bursts of packets in various formats, e.g.
1. enqueuing two smaller bursts and completing them as one burst
2. enqueuing one burst and gathering completions in smaller bursts
3. using completed_status() function to gather completions rather than
just completed()
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Reviewed-by: Kevin Laatz <kevin.laatz@intel.com> Reviewed-by: Conor Walsh <conor.walsh@intel.com>
Bruce Richardson [Wed, 13 Oct 2021 15:17:31 +0000 (16:17 +0100)]
test/dma: run test suite on skeleton driver
When running the dmadev_autotest, run the suite of copy tests on the
skeleton driver created for API testing too, rather than just destroying
the driver instances once the API tests are complete. This helps to
sanity check the tests themselves are reasonable.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Reviewed-by: Kevin Laatz <kevin.laatz@intel.com>
Bruce Richardson [Wed, 13 Oct 2021 15:17:29 +0000 (16:17 +0100)]
test/dma: add basic dmadev instance tests
Run basic sanity tests for configuring, starting and stopping a dmadev
instance to help validate drivers. This also provides the framework for
future tests for data-path operation.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Reviewed-by: Conor Walsh <conor.walsh@intel.com> Reviewed-by: Kevin Laatz <kevin.laatz@intel.com>
Kevin Laatz [Wed, 13 Oct 2021 15:17:26 +0000 (16:17 +0100)]
dmadev: add burst capacity API
Add a burst capacity check API to the dmadev library. This API is useful to
applications which need to how many descriptors can be enqueued in the
current batch. For example, it could be used to determine whether all
segments of a multi-segment packet can be enqueued in the same batch or not
(to avoid half-offload of the packet).
Signed-off-by: Kevin Laatz <kevin.laatz@intel.com> Reviewed-by: Conor Walsh <conor.walsh@intel.com>
Bruce Richardson [Wed, 13 Oct 2021 15:17:24 +0000 (16:17 +0100)]
dmadev: add channel status check for testing use
Add in a function to check if a device or vchan has completed all jobs
assigned to it, without gathering in the results. This is primarily for
use in testing, to allow the hardware to be in a known-state prior to
gathering completions.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Reviewed-by: Conor Walsh <conor.walsh@intel.com> Reviewed-by: Kevin Laatz <kevin.laatz@intel.com>
David Marchand [Tue, 12 Oct 2021 19:39:57 +0000 (21:39 +0200)]
mbuf: enforce no option for dynamic fields and flags
As stated in the API, dynamic field and flags should be created with no
additional flag (simply in the API for future changes).
Fix the dynamic flag register helper which was not enforcing it and add
unit tests.
Fixes: 4958ca3a443a ("mbuf: support dynamic fields and flags") Signed-off-by: David Marchand <david.marchand@redhat.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ray Kinsella <mdr@ashroe.eu>
David Marchand [Tue, 12 Oct 2021 19:39:26 +0000 (21:39 +0200)]
memzone: enforce valid flags when reserving
If we do not enforce valid flags are passed by an application, this
application might face issues in the future when we add more flags.
Signed-off-by: David Marchand <david.marchand@redhat.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ray Kinsella <mdr@ashroe.eu>
David Marchand [Thu, 14 Oct 2021 19:29:16 +0000 (21:29 +0200)]
mempool: enforce valid flags at creation
If we do not enforce valid flags are passed by an application, this
application might face issues in the future when we add more flags.
Signed-off-by: David Marchand <david.marchand@redhat.com> Reviewed-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru> Acked-by: Ray Kinsella <mdr@ashroe.eu> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Andrew Rybchenko <andrew.rybchenko@oktetlabs.ru>
git.droids-corp.org / dpdk.git / log