If libbsd is enabled in DPDK, the strlcpy and strlcat functions in
rte_string_fns.h redirect to the varients in libbsd, only using the
fallbacks if it is not enabled. Therefore, if libbsd is enabled, it needs
to be called out as a DPDK dependency in the pkgconfig file.
To ensure that we don't have undefined variables on non-Linux platforms, we
can remove the linux condition around the libbsd check - no harm comes in
looking for it on other OS, since it's an optional dependency.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
The post-install script to symlink the PMDs from their own PMD directory to
the regular lib directory (so they would be found by ld at runtime) was
using the "-r" flag to ln to create relative symlinks. This flag is
unsupported by ln on FreeBSD causing the ninja install step to fail.
Reworking the script to take the relative driver path as parameter removes
the need for ln to calculate the relative path ensuring compatibility with
FreeBSD.
As part of the fix, we move the registration of the install script to the
config/meson.build file, from the top level one. This improves readability
as the script takes as parameters the variables set in that file.
Fixes: ed4d43d73e2b ("build: symlink drivers to library directory") Cc: stable@dpdk.org Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
On freebsd we need to include sys/socket.h to get the definition of
AF_INET in order to compile.
Fixes: d5ceea4ab160 ("examples/l3fwd: format IP addresses for printing") Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
Reshma Pattan [Thu, 2 May 2019 09:33:34 +0000 (10:33 +0100)]
mk: disable warning for packed member pointer
gcc 9 on Fedora 30 gives an error
"taking address of packed member may result in an
unaligned pointer value" warnings.
For clang builds this warning is already disabled,
so disable "-Waddress-of-packed-member" for gcc builds
also.
Snippet of build error:
lib/librte_eal/linux/eal/eal_memalloc.c: In function ‘alloc_seg_walk’:
lib/librte_eal/linux/eal/eal_memalloc.c:768:12: error:
taking address of packed member of ‘struct rte_mem_config’ may result
in an unaligned pointer value [-Werror=address-of-packed-member]
768 | cur_msl = &mcfg->memsegs[msl_idx];
| ^~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: Reshma Pattan <reshma.pattan@intel.com> Tested-by: David Marchand <david.marchand@redhat.com>
Thomas Monjalon [Thu, 2 May 2019 14:53:45 +0000 (16:53 +0200)]
maintainers: fix added or removed files
Reference to test/Makefile was forgotten when removing this file.
Reference to app/test/test_rcu* was forgotten when adding the files.
Fixes: a9de470cc7c0 ("test: move to app directory") Fixes: b87089b0bb19 ("test/rcu: add API and functional tests") Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Ferruh Yigit [Thu, 2 May 2019 13:35:26 +0000 (14:35 +0100)]
build: fix crash by disabling AVX512 with binutils 2.31
On Skylake platform, with native build, KNI kernel module crashes
because of the corrupted values passed to kernel module.
The corruption occurs because the userspace kni library works
unexpectedly. Compiler [1] is using AVX512 instructions and generated
binary is wrong [2].
It turned around gcc does its job correct, but gas is generating binary
wrong. And expected binutils 2.30, 2.31 & 2.31.1 are affected. Issue has
been fixed in binutils 2.32 with:
Commit x86: don't mistakenly scale non-8-bit displacements
AVX512 was already disabled with bintuils 2.30 [3], extending it to
2.31 & 2.31.1 too.
Ferruh Yigit [Thu, 2 May 2019 13:35:25 +0000 (14:35 +0100)]
build: fix meson binutils workaround
The '-mno-avx512f' compiler flag is not passed to the compiler,
detection of the binutils and setting flags works fine, but the flag
itself not used by compiler.
Removing the interim 'march_opt' variable and using directly
'machine_args' and setting '-mno-avx512f' to 'machine_args'
Fixes: 566b4d7a968f ("build: fix meson check for binutils 2.30") Cc: stable@dpdk.org Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com> Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Compiling on Fedora 30, we get the following warning, causing build failure
when Werror flag is set:
../drivers/net/ixgbe/ixgbe_rxtx.c:2141:14: warning:
‘nmb’ may be used uninitialized in this function [-Wmaybe-uninitialized]
2141 | rxe->mbuf = nmb;
| ~~~~~~~~~~^~~~~
The check for the zuc library dependency did not check for the include
file needed for compilation. It's also recommended when looking for a
library to use the name without the lib prefix.
The check for the kasumi library dependency did not check for the include
file needed for compilation. It's also recommended when looking for a
library to use the name without the lib prefix.
The new default-taget "linux" is introduced in v19.05-rc1
but not exist in before release such as v19.02 which have
default-target "linuxapp", there is no compatibility report
when run validate-abi.sh to check ABI compatibility between
v19.05-rc1 and v19.02, changed default-target from "linux"
to "linuxapp" in validate-abi.sh
Fixes: 218c4e68c1d9 ("mk: use linux and freebsd in config names") Cc: stable@dpdk.org Signed-off-by: Peng Huang <peng.huang@intel.com> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: Bruce Richardson <bruce.richardson@intel.com>
Add RCU library supporting quiescent state based memory reclamation method.
This library helps identify the quiescent state of the reader threads so
that the writers can free the memory associated with the lock less data
structures.
Signed-off-by: Honnappa Nagarahalli <honnappa.nagarahalli@arm.com> Reviewed-by: Steve Capper <steve.capper@arm.com> Reviewed-by: Gavin Hu <gavin.hu@arm.com> Reviewed-by: Ola Liljedahl <ola.liljedahl@arm.com> Acked-by: Paul E. McKenney <paulmck@linux.ibm.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Tested-by: Jerin Jacob <jerinj@marvell.com> Tested-by: Ruifeng Wang <ruifeng.wang@arm.com> Tested-by: Hemant Agrawal <hemant.agrawal@nxp.com>
eventdev: add experimental tag back for Rx adapter
Add the experimental tag back to the Rx event adapter callback,
the Rx event callback register and the Rx event adapter statistics
retrieval functions due to an API change to be proposed in a
future patch.
This patch also adds the experimental tag to these
function definitions and adds the functions to the EXPERIMENTAL
section of the map file, these were missing previously.
Fixes: 80bdf91dc8ee ("eventdev: promote adapter functions as stable") Signed-off-by: Nikhil Rao <nikhil.rao@intel.com> Acked-by: Kevin Traynor <ktraynor@redhat.com> Acked-by: Jerin Jacob <jerinj@marvell.com>
doc: update guide and release notes for QAT crypto
This patch adds release notes to 19.05 release document, and more
detailed description to Intel QuickAssist Technology driver
documentation files for asymmmetric crypto PMD.
Anoob Joseph [Thu, 18 Apr 2019 05:20:29 +0000 (10:50 +0530)]
crypto/octeontx: use distinct metabuf pool for each queue
The metabuf pool is shared across all queue pairs belonging to the
PMD. In order to prevent one queue pair from starving another,
use a distinct mempool for each queue pair.
Fixes: 273487f7b381 ("crypto/octeontx: add global resource init") Cc: stable@dpdk.org Signed-off-by: Anoob Joseph <anoobj@marvell.com> Acked-by: Shally Verma <shallyv@marvell.com>
Bruce Richardson [Tue, 23 Apr 2019 15:43:57 +0000 (16:43 +0100)]
crypto/aesni_gcm: check dependency version with make
The aesni_mb driver has a check in its Makefile for the correct version of
the IPsec_MB library, but this check was missed for the aesni_gcm driver.
Add this check to the makefile, removing an unnecessary assignment in the
process.
Suggested-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
Bruce Richardson [Tue, 23 Apr 2019 15:43:56 +0000 (16:43 +0100)]
crypto/aesni_mb: cleanup version check
The version check for the IPSec_MB library present in the aesni_gcm
library's meson.build file is a little cleaner than that given here,
so update this one so that both work identically.
While one could use the checks done in the other right now, potentially in
future they may have different version dependencies, or may be compiled in
different orders, so keep the code duplicated for safety, since it's only a
few lines.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
Bruce Richardson [Tue, 23 Apr 2019 15:43:55 +0000 (16:43 +0100)]
crypto/aesni_gcm: check dependency version with meson
The aesni_mb driver and the aesni_gcm driver both require the same version
of the IPSec_MB library, but only the former has a check of the library
found by meson to see if it's the correct version. Add a similar check to
the aesni_gcm library's meson.build file, so that the auto-detection of
dependencies works correctly.
Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Pablo de Lara <pablo.de.lara.guarch@intel.com> Acked-by: Luca Boccassi <bluca@debian.org>
examples/ipsec-secgw: fix pool usage for security session
Currently, two separate mempools are being used for creating crypto
sessions and its private data.
crypto sessions are created and initialized separately, so a separate
mempool is passed to each API, but in case of security sessions, where
only one API create and initialize the private data as well.
So if session mempool is passed to create a security session, the
mempool element size is not sufficient enough to hold the private
data as well.
As a perfect solution, the security session create API should take 2
mempools for header and private data and initiatlize accordingly,
but that would mean an API breakage, which will be done in the next
release cycle. So introducing this patch as a workaround to resolve this
issue.
Fixes: 261bbff75e34 ("examples: use separate crypto session mempools") Cc: stable@dpdk.org Signed-off-by: Akhil Goyal <akhil.goyal@nxp.com> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
acl_classify() returns zero value when no matching rule was found.
Currently ipsec-secgw treats it as a valid SPI value, though it has
to discard such packets.
Error could be easily observed by sending outbound unmatched packets,
user will see something like that in the log:
IPSEC: No cryptodev: core 7, cipher_algo 0, auth_algo 0, aead_algo 0
To fix it we need to treat packets with zero result from acl_classify()
as invalid ones. Also we can change DISCARD and BYPASS values to
simplify checks and save some extra space for valid SPI values.
To summarize the approach:
1. have special SPI values for DISCARD and BYPASS.
2. store in SPD full SPI value.
3. after acl_classify(), first check SPI value for DISCARD and BYPASS,
then convert it in SA index.
4. add check at initilisation time that for each SPD rule there is a
corresponding SA entry (with the same SPI).
Also marked few global variables as *static*.
Fixes: 906257e965b7 ("examples/ipsec-secgw: support IPv6") Fixes: 2a5106af132b ("examples/ipsec-secgw: fix corner case for SPI value") Cc: stable@dpdk.org Signed-off-by: Konstantin Ananyev <konstantin.ananyev@intel.com> Acked-by: Fan Zhang <roy.fan.zhang@intel.com> Acked-by: Akhil Goyal <akhil.goyal@nxp.com>
Thomas Monjalon [Mon, 15 Apr 2019 11:58:38 +0000 (13:58 +0200)]
doc: fix heading levels in bbdev test guide
The section "Test Vector files" should not be at the same level as
the main title "dpdk-test-bbdev Application".
Fixes: f714a18885a6 ("app/testbbdev: add test application for bbdev") Cc: stable@dpdk.org Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: John McNamara <john.mcnamara@intel.com>
Andrius Sirvys [Thu, 18 Apr 2019 08:52:06 +0000 (09:52 +0100)]
bitrate: fix unchecked return value
Checking the return value of rte_metrics_update_values, if failed
returning that value.
Coverity had picked up that that the return value wasn't being checked.
The value returned from rte_eth_dev_tx_offload_name() function is used
for string comparison before being checked for NULL. Move the NULL check
up to be done first.
Coverity issue: 279438 Fixes: c73a9071877a ("app/testpmd: add commands to test new offload API") Cc: stable@dpdk.org Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Rami Rosen <ramirose@gmail.com>
Coverity points out that there is a check in the main thread loop for the
ctrlr->bdev being NULL, but by that stage the pointer has already been
dereferenced. Therefore, for safety, before we enter the loop do an
initial check on the parameter structure.
Coverity issue: 158657 Fixes: db75c7af19bb ("examples/vhost_scsi: introduce a new sample app") Cc: stable@dpdk.org Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
examples/vhost_scsi: fix header check for meson build
The header check for the example app was looking for virtio_scsi.h without
the "linux/" prefix, which meant it was never getting found when it should
have been.
Fixes: 8d47a753b7cb ("examples/vhost_scsi: disable build if missing dependency") Cc: stable@dpdk.org Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Reviewed-by: Tiwei Bie <tiwei.bie@intel.com>
Running the devtools/test-build.sh script on IBM Power systems fails
because the IXGBE_PMD is explicity disabled for Power as an untested
driver, but the examples/vm_power_manager application has a hard
dependency on a function call in the IXGBE_PMD.
Modify the example application so that all dependencies on PMD code
are conditionally compiled.
Bugzilla ID: 237 Fixes: c9a4779135c9 ("examples/vm_power_mgr: set MAC address of VF") Signed-off-by: David Christensen <drc@linux.vnet.ibm.com> Acked-by: David Hunt <david.hunt@intel.com>
Fix the data type of last_branches, last_branch_misses
from uint32_t to uint64_t, and for hits_diff, miss_diff
from int to int64_t respectively to fix possible
overflow or truncation.
After the read() the jason_data null termination is missing
for the case "indent < 0", for "indent > 0" and "indent == 0"
cases null termination is already handled.
So add the missing case "indent < 0" to the existing "indent == 0"
case to fix null termination.
David Hunt [Wed, 10 Apr 2019 13:13:48 +0000 (14:13 +0100)]
examples/power: fix unreachable VF MAC init
A for loop to MAX_VFS had a break as the last line, so the w++
would never get called, breaking out of the loop after the
first iteration. Remove the break so that the loop can execute
properly.
Coverity issue: 337682 Fixes: ace158c4a821 ("examples/vm_power: add check for port count") Cc: stable@dpdk.org Signed-off-by: David Hunt <david.hunt@intel.com> Acked-by: Rami Rosen <ramirose@gmail.com>
David Hunt [Tue, 9 Apr 2019 09:22:01 +0000 (10:22 +0100)]
power: fix buffer overruns
A previous change removed the limit of 64 cores by
moving away from 64-bit masks to char arrays. However
this left a buffer overrun issue, where the max channels
was defined as 64, and max cores was defined as 256. These
should all be consistently set to RTE_MAX_LCORE.
The #defines being removed are CHANNEL_CMDS_MAX_CPUS,
CHANNEL_CMDS_MAX_CHANNELS, POWER_MGR_MAX_CPUS, and
CHANNEL_CMDS_MAX_VM_CHANNELS, and are being replaced
with RTE_MAX_LCORE for consistency and simplicity.
Lee Daly [Fri, 12 Apr 2019 15:57:27 +0000 (16:57 +0100)]
power: fix max frequency after turbo disabling
This patch will ensure the correct max frequency of a core is set in
the lcore_power_info struct when disabling turbo, while using the
intel pstate driver.
Fixes: e6c6dc0f96c8 ("power: add p-state driver compatibility") Cc: stable@dpdk.org Signed-off-by: Lee Daly <lee.daly@intel.com> Acked-by: David Hunt <david.hunt@intel.com> Acked-by: Liang Ma <liang.j.ma@intel.com>
Due to lack of thread safety in exisiting solution
use spinlock mechanism for atomic
modification of power environment related data.
Fixes: 445c6528b5 ("power: common interface for guest and host") Cc: stable@dpdk.org Signed-off-by: Marcin Hajkowski <marcinx.hajkowski@intel.com> Acked-by: Anatoly Burakov <anatoly.burakov@intel.com>
Add option --multi, to enhance pdump application to allow capture
on unique cores for each --pdump option. If option --multi is ignored
the default capture occurs on single core for all --pdump options.
PDUMP application is being limited to run on default first core.
The patch removes the restriction, allowing user to run on any of
selected cores in EAL args. If no args are passed, logic runs on
default master core.
test/timer: exercise new APIs in secondary process
This commit adds an autotest which exercises new timer reset/stop APIs
in a secondary process. Timers are created, and sometimes stopped, in
the secondary process, and their expiration is checked for and handled
in the primary process.
Signed-off-by: Erik Gabriel Carrillo <erik.g.carrillo@intel.com>
Bruce Richardson [Wed, 10 Apr 2019 11:24:47 +0000 (12:24 +0100)]
reorder: add checks for invalid function inputs
For APIs which can return an error value, do sanity checking of the input
parameters for NULL and return a suitable error value for those cases.
NOTE: The drain function is currently omitting NULL checks too, but this
function has no way to flag an error value, so checking in that case would
simply mask problems.
Reported-by: Bernard Iremonger <bernard.iremonger@intel.com> Signed-off-by: Bruce Richardson <bruce.richardson@intel.com> Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Thomas Monjalon [Tue, 9 Apr 2019 20:06:35 +0000 (22:06 +0200)]
mbuf: fix big endian build
Compilation was failing when using a big endian toolchain:
rte_mbuf.h:504:2: error: expected ',' or '}' before 'RTE_MBUF_L3_LEN_OFS'
Fixes: 8d9c2c3a1f01 ("mbuf: add function to generate raw Tx offload value") Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>
The l3fwd example should use the IPv4 addresses defined in RFC5735 and
the IPv6 addresses defined in RFC5180 for the L3 forwarding example
Longest Prefix Match table.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
app/testpmd: add ability to set Tx IP and UDP parameters
This patch changes what testpmd uses as IP addresses when
run in transmit only mode. The old code was using
192.168.0.1 -> 192.168.0.2
but these addresses are reserved for private Internet by RFC 1918.
The new code uses 192.18.0.1 and 192.18.0.2 which are on the
subnet reserved for performance testing by RFC 2544.
New command line option allows the user to pick any other src/dst
address desired.
Notice: this changes the default IP address for transmit only.
It may cause some user who has hardcoded network addresses to report
a regression.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Bernard Iremonger <bernard.iremonger@intel.com>
Jerin Jacob [Fri, 19 Apr 2019 12:10:40 +0000 (17:40 +0530)]
eventdev: promote adapter functions as stable
Promote the adapter functions and rte_event_port_unlinks_in_progress()
as stable as it's been added for a while now and multiple drivers and
test application like test-eventdev has been tested using the adapter APIs.
Thomas Monjalon [Thu, 18 Apr 2019 00:30:58 +0000 (02:30 +0200)]
eal: promote some experimental functions as stable
The function rte_eal_cleanup() was introduced more than one year ago,
in DPDK 18.02. It is no longer experimental, allowing
pdump, proc-info and hotplug_mp apps to not need any experimental API.
The function rte_ctrl_thread_create() was introduced one year ago
in DPDK 18.05. It is no longer experimental, allowing
KNI PMD and TEP example to not need any experimental API.
The functions rte_socket_count() and rte_socket_id_by_idx() were
introduced one year ago in DPDK 18.05. They are no longer experimental.
The function rte_dev_is_probed() was introduced half a year ago
in DPDK 18.11. It is no longer experimental.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Kevin Traynor <ktraynor@redhat.com>
A successful call to rte_mp_request_sync does not guarantee that there
are any messages in the buffer, and this should be checked for before
accessing data in the message. Buffer can be empty if IPC is disabled or
if we decide to ignore replies.
Fixes: c9aa56edec8e ("net/tap: access primary process queues from secondary") Cc: stable@dpdk.org Signed-off-by: Herakliusz Lipiec <herakliusz.lipiec@intel.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
This driver defines lots of functions (like init_rss) which are intended
to only be used in this device. But when doing static linking these
global functions cause link failures when similar function name is
used in application.
This patch prefixes all functions defined in cxgbe.h with cxgbe_
to avoid these kind of conflicts.
VMxnet3 v3 already has UDP RSS support, however it
depends on hypervisor provisioning on the VM through
ESX specific flags, which are not transparent or known
to the guest later on.
Vmxnet3 v4 introduces a new API transaction which allows
configuring RSS entirely from the guest. This API must be
invoked after device shared mem region is initialized.
IPv4 ESP RSS (SPI based) is also available, but currently
there are no ESP RSS definitions on rte_eth layer to
handle that.
Signed-off-by: Eduard Serra <eserra@vmware.com> Acked-by: Yong Wang <yongwang@vmware.com>
Radu Nicolau [Wed, 17 Apr 2019 14:36:47 +0000 (15:36 +0100)]
net/bonding: fix potential out of bounds read
Add validation to pointer constructed from the IPv4 header length
in order to prevent malformed packets from generating a potential
out of bounds memory read.
Fixes: 09150784a776 ("net/bonding: burst mode hash calculation") Cc: stable@dpdk.org Signed-off-by: Radu Nicolau <radu.nicolau@intel.com> Acked-by: Chas Williams <chas3@att.com>
Ori Kam [Thu, 18 Apr 2019 13:16:06 +0000 (13:16 +0000)]
net/mlx5: add Forward Database table type
Actions like encap/decap, modify header require setting the flow table
type. Until now we supported only Nic RX and Nic TX, this commits adds
the support for FDB table type for those actions.
Signed-off-by: Ori Kam <orika@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
Ori Kam [Thu, 18 Apr 2019 13:16:04 +0000 (13:16 +0000)]
net/mlx5: add transfer attribute to matcher
In current implementation the DV steering supported only NIC steering.
This commit adds the transfer attribute in order to create a matcher
on the FDB tables.
Signed-off-by: Ori Kam <orika@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
Ori Kam [Thu, 18 Apr 2019 13:16:01 +0000 (13:16 +0000)]
net/mlx5: support Direct Rules E-Switch
This commit checks the for DR E-Switch support.
The support is based on both Device and Kernel.
This commit also enables the user to manually disable this this feature.
Signed-off-by: Ori Kam <orika@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
Ori Kam [Thu, 18 Apr 2019 13:15:59 +0000 (13:15 +0000)]
net/mlx5: fix translate vport function name
Modify the translate vport function to match other translate items
naming conventions.
Fixes: 0fe3f18f78d8 ("net/mlx5: add source vport match to the ingress rules") Signed-off-by: Ori Kam <orika@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
Ori Kam [Wed, 17 Apr 2019 20:01:45 +0000 (20:01 +0000)]
net/mlx5: fix modify header action position
According to RTE flow the action order should be the order that the
actions were given.
In the case of modify actions the position of the action was always
last.
This commit solves this issue by saving the position of the first modify
action, and then adds to this position the pointer to the modify action.
Fixes: 4bb14c83df95 ("net/mlx5: support modify header using Direct Verbs") Cc: stable@dpdk.org Signed-off-by: Ori Kam <orika@mellanox.com> Acked-by: Shahaf Shuler <shahafs@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
Ori Kam [Sun, 14 Apr 2019 20:17:11 +0000 (20:17 +0000)]
net/mlx5: fix release of jump to queue action
Currently the allocation of the jump to QP is done in flow apply,
this results in memory leak.
This patch fixes this issue by moving the allocation and release of the
jump to QP action to the responsibility of the hrxq.
Fixes: cbb66daa3c85 ("net/mlx5: prepare Direct Verbs for Direct Rule") Cc: stable@dpdk.org Signed-off-by: Ori Kam <orika@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
On BlueField platform we have the new entity - PF representor.
This one represents the PCI PF attached to external host on the
side of ARM. The traffic sent by the external host to the NIC
via PF will be seem by ARM on this PF representor.
This patch refactors port recognizing capability on the base of
physical port name. We have two groups of name formats. Legacy
name formats are supported by kernels before ver 5.0 (being
more precise - before the patch [1]) or before Mellanox OFED 4.6,
and new naming formats added by the patch [1].
Legacy naming formats are supported:
- missing physical port name (no sysfs/netlink key) at all,
master is assumed
- decimal digits (for example "12"), representor is assumed,
the value is the index of attached VF
New naming formats are supported:
- "p" followed by decimal digits, for example "p2", master
is assumed
- "pf" followed by PF index concatenated with "vf" followed by
VF index, for example "pf0vf1", representor is assumed.
If index of VF is "-1" it is a special case of host PF
representor, this representor must be indexed in devargs
as 65535, for example representor=[0-3,65535] will
allow representors for VF0, VF1, VF2, VF3 and for host PF.
Note: do not specify representor=[0-65535], it causes devargs
processing error, because number of ports (rte_eth_dev) is
limited.
Applications should distinguish representors and master devices
exclusively by device flag RTE_ETH_DEV_REPRESENTOR and do not
rely on switch port_id (mlx5 PMD deduces ones from representor_id)
values returned by dev_infos_get() API.
[1] https://www.spinics.net/lists/netdev/msg547007.html
Linux-tree: c12ecc23 (Or Gerlitz 2018-04-25 17:32 +0300)
"net/mlx5e: Move to use common phys port names for vport representors"
mlx4 driver has a global list of Memory Regions created by
device, and there is a ml4_mr_release() routine which makes
a memory cleanup at device closing. The head of device MR list
was fetched outside the rwlock protected section. Also some
noticed typos are fixed.
Fixes: 9797bfcce1c9 ("net/mlx4: add new memory region support") Cc: stable@dpdk.org Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
mlx5 driver has a global list of Memory Regions created by
device, and there is a ml5_mr_release() routine which makes
a memory cleanup at device closing. The head of device MR list
was fetched outside the rwlock protected section. Also some
noticed typos are fixed.
Fixes: 974f1e7ef146 ("net/mlx5: add new memory region support") Cc: stable@dpdk.org Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
When passed to the application, Rx packets retain the port ID value
originally set by slave devices. Unfortunately these IDs have no
meaning to applications, which are typically unaware of their existence.
This confuses those caring about the source port field in mbufs
(m->port) which experience issues ranging from traffic drop to crashes.
Thomas Monjalon [Wed, 17 Apr 2019 22:59:27 +0000 (00:59 +0200)]
ethdev: avoid explicit check of valid port state
Some port iterations are manually checking against RTE_ETH_DEV_UNUSED
instead of using the iterators based on rte_eth_find_next().
A new macro RTE_ETH_FOREACH_VALID_DEV() is introduced, but kept private
because there should be no need of iterating over all devices in the
API. The public iterators have additional filters for ownership, parent
device or sibling ports.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net>
Thomas Monjalon [Wed, 17 Apr 2019 00:36:27 +0000 (02:36 +0200)]
ethdev: deprecate legacy filter API
As stated in the deprecation notice from December 2016,
"the legacy filter API, including rte_eth_dev_filter_supported(),
rte_eth_dev_filter_ctrl() as well as filter types MACVLAN, ETHERTYPE,
FLEXIBLE, SYN, NTUPLE, TUNNEL, FDIR, HASH and L2_TUNNEL, is superseded
by the generic flow API (rte_flow)".
After a long wait of more than two years, the legacy filter API
is marked as deprecated, while still tested with testpmd and
the tep_termination example.
The next step will be to announce a deadline for complete removal.
As preparation of the removal of rte_eth_ctrl.h,
RTE_ETH_FLOW_*, RTE_TUNNEL_TYPE_* and RTE_ETH_HASH_FUNCTION_* definitions
are moved to rte_ethdev.h and rte_flow.h.
Signed-off-by: Thomas Monjalon <thomas@monjalon.net> Acked-by: Shahaf Shuler <shahafs@mellanox.com> Acked-by: Andrew Rybchenko <arybchenko@solarflare.com> Acked-by: Jerin Jacob <jerinj@marvell.com> Acked-by: Stephen Hemminger <stephen@networkplumber.org> Acked-by: Hemant Agrawal <hemant.agrawal@nxp.com> Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com> Acked-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Pavel Belous [Thu, 18 Apr 2019 11:39:57 +0000 (11:39 +0000)]
net/atlantic: configure MACsec from interrupt handler
MACSEC should be configured only after link up event, thus we use
link interrupt to file an alarm for configuration.
FW also uses link interrupt line to indicate incoming events from
MACSEC. These may include key expiration, packet counter wrap, etc.
We pass these events to the upper layers.
Signed-off-by: Pavel Belous <pavel.belous@aquantia.com> Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Pavel Belous [Thu, 18 Apr 2019 11:39:55 +0000 (11:39 +0000)]
net/atlantic: implement MACsec firmware interface
Implementation of firmware interface for MACsec configuration.
Structure with config data is written into FW memory, then we trigger
FW to execute the request and wait for result.
Signed-off-by: Pavel Belous <pavel.belous@aquantia.com> Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Pavel Belous [Thu, 18 Apr 2019 11:39:51 +0000 (11:39 +0000)]
net/atlantic: enable MACsec configuration
These are driver MACsec configuration routines.
They fill in config structures and prepare these
to be send to FW. Actual configuration will happen in
link interrupt handler.
We declare MACsec offload bits in DPDK offload capabilities
and provide external experimental MACsec API wrappers.
Also update documentation with feature matrix for the
enabled feature.
Signed-off-by: Pavel Belous <pavel.belous@aquantia.com> Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Pavel Belous [Thu, 18 Apr 2019 11:39:48 +0000 (11:39 +0000)]
net/atlantic: declare MACsec hardware structures
Here we define hardware and software configuration structures
for MACsec interface. MACSEC itself is implemented in Phy module,
but its configuration is done via firmware interface
Signed-off-by: Pavel Belous <pavel.belous@aquantia.com> Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
When launch testpmd with VF and quit testpmd, there'll
be lots of messages "i40evf_handle_aq_msg(): Request 0
is not supported yet", which are triggered during VF
reset and VF needn't do anything. So cancel alarm handler
before VF reset to ignore the admin queue messages.
Fixes: e0e6a7f2154e ("net/i40e: cancel alarm handler at the end of closure") Cc: stable@dpdk.org Signed-off-by: Beilei Xing <beilei.xing@intel.com> Acked-by: Qi Zhang <qi.z.zhang@intel.com>
Enable CLEARPBA bit is required by ice NIC of A0/A1 version to
enable Tx and Rx queue interrupt.
Also enable CLEARPBA bit does no impact on IAVF behaviour when be
hosted by other devices, so we can make it as default.
git.droids-corp.org / dpdk.git / log