This PMD is availabe for BlueField2 DPU.
It requires libmlx5, so configure file is
updated to check if this library exists
Change-Id: Ic0cfbfdf24af393381667435009fb6afc49d9181
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8780
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
In latest 13.0 release of freebsd sed is not accepting \s anymore,
hence it needs to be replaced. Note that only parts of the repo
which are touched by freebsd during the tests are updated.
Details https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=253893
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: I217208511af8f98e7033f8f24a343b5ca9c48825
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7986
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Default to the more common Linux/GNU 'sed' edit in-place argument,
unless the platform is FreeBSD.
Tested by visually checking rte_build_config.h to confirm that the sed
in-place worked correctly.
Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
Change-Id: I68be69658930fb20318ac3aa2413bbf4a358e9bc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6531
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
When ./configure --enable-debug is specified, meson is invoked using
the default 'release' buildtype and '-O0 -g' is added to DPDK_CFLAGS.
Instead, specify --buildtype=debug so that meson knows it is a debug
build, will return the correct value from get_option('buildtype') and
can choose the appropriate toolset options to enable symbolic debugging.
Using --buildtype=debug generates unoptimised code which matches
the current intent.
Tested by building with and without --enable-debug and verifying that
meson reports 'debug' for the debug build.
Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
Change-Id: Iabb79cd2051145e03fea8fd749cfb18b78e625a0
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6497
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
If CONFIG_CROSS_PREFIX includes 'mingw', then specify --cross-file
'config/x86/cross-mingw' which is used as part of regular DPDK
testing, so is being maintained. For any other non-null prefix, default
to the current error message that automatic cross builds are not
supported.
Tested by running ./configure --cross-prefix=x86_64-w64-mingw32
and verified that 'make' in dpdkbuild used the cross tools.
Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
Change-Id: I75c401dfe8422f6c5f1bbe631695e7ae6118f723
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6530
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
DPDK 20.11 moved the kernel modules to separate
dpdk-kmod repository. It has to be built separate
from DPDK.
If needed for testing vm_setup.sh script now contains option
to build this driver.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I98a5eb956eb0cc60ec402d88fcdbd66d4854f19a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6033
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Michal Berger <michalx.berger@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Intel Control-flow Enforcement Technology (CET) is a
processor feature that blocks return/jump-oriented
programming (ROP) attacks.
It is currently only supported on Tiger Lake client
processors, but will be available on other processors
in the future.
CET requires toolchain support. gcc8 does support it.
For now, this will opt-in only at least until the
technology is available on server processors.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8c7f882eeeaed26484c31dc0d67d5cc42baeaa2d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5921
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
When configuring with --with-shared, you would see all
applications getting relinked, even if nothing has
changed. This was root caused to DPDK re-installing
shared libraries that hadn't been rebuilt.
Switching from 'ninja install' to 'meson install --only-changed'
fixes this behavior. Note that meson install doesn't
support -j, but at this point we are only installing
files, not building them - and now we won't even be
installing the files again if they haven't changed.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: If0491b2ad6e8564ad0fd8dee39a2e357e1329ea9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4465
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
DPDK compilation fails when we configure SPDK using --with-reduce:
../drivers/common/qat/qat_qp.c:18:10: fatal error: qat_sym.h: No such file or directory
#include "qat_sym.h"
^~~~~~~~~~~
But when SPDK is also configured using --with-crypto, DPDK is built successfully
--with-crypto enables build of crypto/qat driver and meson config for
this driver adds dpdk/driver/crypto/qat directory to QAT includes. This
directory contains the missing qat_sym.h and qat_sym_pmd.h files.
Group common drivers required by crypto/reduce
Fixes issue #1529
Change-Id: I7a53411798091e9a3c16442f3951ff73138d7337
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4179
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Makefile support in DPDK was deprecated and will be removed soon,
so switch to the officially supported way of building DPDK -
with meson and ninja. Two new tools. Basically, our Makefiles
will invoke meson+ninja for DPDK, no other SPDK components are
affected.
Apparently DPDK wanted to move away from an octopus-like config
system and the ideology behind meson configuration is simple now:
build everything by default. Some PMDs can be explicitly disabled
with meson command line, but all libraries (both static and shared
versions) and test apps are built unconditionally.
How long does it take to build minimal DPDK with meson? Too much.
On my machine half of the total build time is spent on libraries
we don't need at all. (I have some hacks up my sleeve to disable
building those libraries - see the subsequent patch.) As for the
official way of building a minimal DPDK, there was a patch [1]
on dpdk mailing list to introduce more specific configuration,
but it was rejected:
> We talked about this a few times in the past, and it was actually one
> of the design goals to _avoid_ replicating the octopus-like config
> system of the makefiles. That's because it makes the test matrix
> insanely complicated, not to mention the harm to user friendliness,
> among other things.
>
> If someone doesn't want to use a PMD, they can just avoid installing it
> - it's simple enough.
>
> Sorry, but from me it's a very strong NACK.
Let's not follow that direction, hack the DPDK build system instead.
As for advantages of meson+ninja over Makefiles? I can't find any.
It's another build system that does a lot for you with some functions,
magic options, and a built-in dependency system. It seems nice if you know
the syntax, but it's another component that you need to learn, debug,
and possibly find bugs in (there's a lot of github issues open for meson).
I would compare it to CMake.
As for changes in this patch: rather that explicitly disabling
PMDs we don't need, specify a list of PMDs we do need and disable
everything else found in ./dpdk/drivers/*. This way we won't have
to disable the new PMDs as they're added to DPDK.
Meson configuration also sets RTE_EAL_PMD_PATH #define to a valid directory
with built PMD shared libs. When it's set, DPDK dynamically loads all shared
libraries inside. The drivers there depend on DPDK shared libs and fail to
load in static SPDK builds, so we disable them altogether by unsetting
RTE_EAL_PMD_PATH in the meson-generated config file - just like
DPDK Makefiles did. EAL checks for RTE_EAL_PMD_PATH being empty and skips
loading any external PMDs then. We do it for both static and shared libs.
We specify all PMDs at build time for now, so there's just no need to load
them dynamically.
We have three more hacks in our submodule:
* disable building dpdk apps by commenting-out a line in dpdk/meson.build
* disable building unnecessary libs (build everything that spdk *may*
need)
* build isa-l compress pmd with `-L[...] -lisal`. DPDK expects to find
libisal with pkg-config. We don't want to prepare a pkg-config file,
so comment-out a failing check in another meson.build file and provide
isa-l through CFLAGS and LDFLAGS.
We also need to make some changes to our test/external_code. First of
all, -ldpdk is no more. Meson build generates a pkg-config file with all
libs, but we'll switch to it in a separate patch - for now just specify
all -lrte_ libs one by one. -Wl,--no-as-needed has to be added to some
test cases, otherwise rte_mempool_ring isn't loaded. We don't use any
APIs from this library, it only has a static constructor that provides
a few callbacks used by rte_mempool_create(). Also, since DPDK now builds
both static and shared libraries, we need to add -Wl,-Bstatic to force
using static libswhere required. It's only needed for DPDK libs, but we
use it for SPDK libs as well since there's no harm.
As for performance:
$ ./configure --enable-debug --with-crypto --with-reduce
$ time make -j40 -C dpdkbuild all
with meson:
real 0m8.287s
user 1m7.983s
sys 0m10.548s
before, with the old DPDK makefiles:
real 0m20.232s
user 0m55.921s
sys 0m16.491s
The subsequent builds are much faster too:
$ time make -j40 -C dpdkbuild all
meson:
real 0m0.876s
user 0m0.663s
sys 0m0.217s
makefiles:
real 0m10.150s
user 0m11.740s
sys 0m6.772s
[1] http://inbox.dpdk.org/dev/1a07d1cd59d84dce84e56c10fdabf5e5504560a6.camel@debian.org/
Change-Id: Ic65db563014100bafb12e61ee0530cc2ae64401d
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1440
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Suppres the following warnings which causes compilation errors:
1. gcc 10 complains on operations with zero size arrays in rte_cryptodev.c
Suppress this warning by adding -Wno-stringop-overflow compilation flag
2. gcc 10 disables fcommon by default and complains on multiple definition of
aesni_mb_logtype_driver symbol which is defined in header file and presented in sevral
translation units. Add -fcommon compilation flag.
Fixes issue #1493
Change-Id: I9241bf1fd78e86df6a6eb46b4ff787b2f7027b7d
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3373
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Compiling raid5 has a direct dependency on rte_hash,
which was only built if vhost was built.
The following didn't work:
./configure --with-raid5 --without-vhost
Change-Id: Id36a7d4a21c2e0db00b0641581542e244c4cbbb4
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1013
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This serves as cleanup. Dont build anything by default,
enable stuff if needed. Enabling a library twice doesn't
cause any issues, so drop the piece of logic preventing that.
Change-Id: Ia1877635b100f73b27d9c63ed8baed8184729f1c
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1012
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Apparently make doesn't like it:
make[2]: warning: -jN forced in submake: disabling jobserver mode.
We only did it because of scan-build - it detects a ton
of issues (or false positives) in our dependencies. To
disable it, we don't have to override MAKEFLAGS, but
just CC - that's what we'll do now.
Fixes#896
Change-Id: I5eea984d6bbfbf4caabdd704850fac840fed3524
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/927
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
It turns out that this driver is generally useful, not just within
the context of compress/crypto.
fixes GitHub issue #1189
Change-Id: Ieea8037a240f0302e45ce865632be29821f82a7e
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/792
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
When building SPDK with shared objects, we should also build the DPDK
submodule shared libraries. This will make it much easier for peole to
link their applications against a dpdk shared library if the DPDK shared
libraries installed on their system don't have all the symbols that SPDK
needs.
Also, add a linker argument to DPDK to specify that it should look in
the dpdk subdirectory when linking libraries.
Note: this change will not work until the default config options in the
DPDK submodule are updated.
Change-Id: I9546df7b84952eb20fe1ac98e3b3bbd0fcbda3a7
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463028
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jan Kryl <jan.kryl@mayadata.io>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
We commented out this build option in our DPDK fork,
but DPDK makefiles check its value specifically against
'n' to set linking flags properly. It's currently unset,
so it fails both == 'n' and == 'y' checks, which fails
the build. Shared lib build has some issues on FreeBSD
right now, so to fix the immediate problem, just define
the shared lib option to 'n' for now.
This matches the original behavior. We've always built
DPDK as a static library.
Change-Id: I5a880b777153cc169c3a135d412aa2014f4de8e0
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463290
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
There might be a need for user to cross-compile SPDK for other platforms
than native. Since DPDK supports cross-compilation already, only enablement of
cross-compilation for SPDK is missing. This patch aims to provide the user
with additional option to configure script that works similar to what DPDK already provides.
To enable cross-compilation run ./configure.sh with additional --cross-prefix parameter.
The parameter should work in similar manner to DPDK CROSS parameter
and specifies prefix of cross-compiler defined in PATH variable.
Note: To cross-compile, toolchain must have SPDK dependencies such as e.g. Libaio.
Signed-off-by: Amelia Blachuciak <amelia.blachuciak@intel.com>
Change-Id: Ia7cb879d39d624552cad1af98a563070ea7676b2
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460977
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Configuring SPDK with different options might result
in enabling different CONFIG_RTE_LIB* options, but since
it does not modify any DPDK config files, DPDK doesn't
get rebuilt and keeps using older, potentially outdated
build options.
We'll now clear dpdk/build whenever SPDK config is modified,
which will result in automatically re-configuring DPDK.
Change-Id: I9c7c3434dc317e4f47767d7b3df3df48db2b0d5b
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460563
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
DPDK rte_vhost has some nasty dependencies which
we don't necessarily want to resolve if we don't
want to use vhost at all. We'll now build rte_vhost
only if SPDK vhost is built.
Change-Id: Icb830b11cc128eb8ee357dad94dfe62ac0cf2cce
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460529
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
In prep for full QAT compression support later in this patch
series. dpdkbuild/Makefile slightly refactored for readability,
x86 crypto check removed as it pre-dated checks we now have in
configure.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Iaaaf51b9eb5e18840f47d2d4f431c5a6e8c420ee
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/456408
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
In DPDK 19.05 there's a new test app which we obviously
don't need to build, but we have no way not to, as it's
built together with a library that we do need.
That app may try to link with crypto and compress PMDs,
which require IPSec and ISA-L respectively. If those were
not installed on the system, the linking would fail. We
fix it by providing DPDK with extra -L/path/to/[...]
Change-Id: I652efb669d10d2d03d0f643ce539404c1f0e38c4
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/455825
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Add uninstall target to makefiles to be able to perform
reverse of install target.
Fixes#464
This patch adds 'uninstall' target to makefile.
'make uninstall' will remove spdk_tgt app, headers, libraries
and shared libraries from system directories defined by $DESTDIR.
Additionaly, if there will be any empty directories left after
this operation, they will be removed as well.
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I7b07fb4b81081d3914ff09165991fbe3a26b9067
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/431471
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Currently we only include the dir just above ISA-L which allows
the isal.h file includes to be found however DPDK can't find
isa-l.h at that location because its one level deeper.
By adding a symlink in the isa-l subdir we can redirect DPDK to
find the isa-l header files.
Change-Id: Ieeabd4273bade0241db5581764b2169103f9770f
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/445767
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This driver has more generic use cases than just for the crypto driver.
See github issues 594 and 210.
Change-Id: I7adcb058418a9b56ffa150366584b22b38eb8398
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/444123
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Includes the required DPDK dependencies for SPDK block Reduce aka
Compression.
Change-Id: Ic1ea3cbeb9373a7700f6f0c2a3194d65d6a34a41
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/429523
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This allows us to remove the requirement to install intel-ipsec-mb to
system directories.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I579655a98b515cf148b7cd17823a9bb541ea6ad7
Reviewed-on: https://review.gerrithub.io/c/440785
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Addresses issues with building both compressDev and cryptoDev at the
same time that we will run into shortly. We now build both API all
the time but those things that have ext deps are still built only
when their respective configure options are set.
Change-Id: Ia4b1d4f18826a8d78c2f09881fb268a8aff61f56
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/437989
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
In early development of crypto we built the lirbary using
dpdkbuild/Makefile but later due to a DPDK change we needed
to move to a newer version of the ipsec library that is now
built and installed in pkgdep.sh btu we never removed it
from the makefile.
This patch removes the extra building of the ipsec module.
Change-Id: I367618440074d952ff13c6e2098fc3a572cc785e
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/429519
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Also use the DPDK's default T=x86_64-native-* configuration
target instead of T=spdk-*, as the T=spdk-* is no longer
available in spdk-18.08 branch of our DPDK fork.
Change-Id: If12e7ae1acabece129b63ba2f1bec6b0b65678ca
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/423053
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This must have been overlooked in the original patch
as we do depend on the symmetric crypto operations.
DPDK 18.08 starts to require this flag for building
crypto libs that we want to use - they are no longer
built unconditionally.
Change-Id: I356afcc4333820bf1503f7a3b0a44bd2edcf3449
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/429988
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Also, update the qat_setup script to point to this module.
Dependent upon:https://review.gerrithub.io/c/spdk/dpdk/+/428718
Change-Id: Ie8694a1996621165f52a513d9b19c7232aaed9ce
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/428719
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Users can specify this flag on the make command line to
pass extra CFLAGS to the DPDK submodule build. This can
be used with older compilers that are not supported by
DPDK, and require -fno-strict-aliasing to compile.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ib99e64297402c07395c009987ccffe29099dffab
Reviewed-on: https://review.gerrithub.io/429489
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <shahar.salzman@kaminario.com>
Didn't enable this in initial patch, probably could have, but we
need it for performance testing now and will need it to start getting
the hardware into CI.
Change-Id: I688cc94713146380933e5cddd7ed5b2d168c1fb2
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/427274
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Initial support for softare AESNI_MB DPDK driver only.
Have tested (both aesni and QAT seprately and concurrrently) on underlying NVMe devices
with bdevio and a bdevperf script that runs IOs from 512B to 128K each with Q depths from
1 to 512 in powers of 2 for 30 seconds each run.
QAT can be included in the code (but not makefile) and marked as experimental
until we are ready to test in CI. It works well on 2 systems but is a big PITA to get
the hardware setup and configured for use with DPDK (IMHO).
Change-Id: If518c3df8e74e00efa18afdf194824c5e69778fc
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/403107
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
We need it to compile our internal rte_vhost, and
starting with DPDK 18.08 it's an EAL dependency.
Even though CONFIG_RTE_LIBRTE_KVARGS got commented out in
common_base, it's still hardcoded to =y in common_spdk
and that's why our autotest works.
Trying to build a DPDK target that doesn't use common_spdk
fails terribly right now, because other PMDs and libraries
that are built by default (defined in common_base) actually
depend on kvargs.
Change-Id: I171e768a75c6a460fc090ae3c9c65807eaec5945
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/422237
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This is a dependency of the DPDK crypto framework.
The submodule is currently set to our SPDK fork of the ipsec library
which is based off of the library v0.48 tag, as required by DPDK plus
one minor Makefile change on the 'spdk' branch of the fork.
Also added is a configure option '--with-crypto' and the associated
conditionals for building DPDK with or without the library dependency.
The crypto vbdev patch will use this same configure option to determine
DPDK opts as well as whether the crypto vbdev should be built or not.
Change-Id: Ib1cfd15b63b29acf3c2f7345d0d7edfd94716620
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/404983
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
For now, this only installs libraries and headers; we will need to
consider which binaries should be installed and what they should be
named before we add them to the install rule.
Change-Id: I78dc8631f793d0df88cd884b0ac66406df9e4427
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/387637
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This patch arranges to have dpdk built with the
T=arm64-armv8a-linuxapp-gcc make option when building on
an ARM 64 platform.
Change-Id: I46d266af9171f02e78ed51cec8052c4f91304092
Signed-off-by: Barry Spinney <spinney@mellanox.com>
Reviewed-on: https://review.gerrithub.io/386708
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Change-Id: I0cbf2aa53dcdb82cc8bbdf3b47b5ae301a1191ec
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/363489
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I97ded298a6008fe73738e52c020b4a4d2d160256
Reviewed-on: https://review.gerrithub.io/363137
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Fix NPROC assignment to work for FreeBSD as well. Tested
with FreeBSD Release 10.3.0
Change-Id: I7ad6a6f7479a0fbf3261f44d9cd07248ce584df9
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/362963
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This will allow a git clone to default to an SPDK-specific
version of the DPDK repository. Users can still override
to use a separate DPDK repository/installation with the
--with-dpdk configure script options.
While here, remove gzip option for the git-archive operations
in autopackage.sh. We need to add a git-archive for the DPDK
submodule if we are using it, and compressing at -9 adds a lot
of unnecessary time. Since we are not archiving these packages,
there is no need to compress them. Also explicitly disable
coverage and ubsan for the autopackage build, since this build
is only to test compilation and is not actually used for any
test execution.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3cf8a2ed984003a175cdece6542636ede8cb2479
