diff --git a/.ci/linux-build.sh b/.ci/linux-build.sh
new file mode 100755
index 0000000000..61b73744d5
--- /dev/null
+++ b/.ci/linux-build.sh
@@ -0,0 +1,131 @@
+#!/bin/bash
+
+set -o errexit
+
+KERNELSRC=""
+CFLAGS="-Werror"
+SPARSE_FLAGS=""
+EXTRA_OPTS=""
+TARGET="x86_64-native-linuxapp-gcc"
+
+function install_kernel()
+{
+ if [[ "$1" =~ ^4.* ]]; then
+ PREFIX="v4.x"
+ elif [[ "$1" =~ ^3.* ]]; then
+ PREFIX="v3.x"
+ else
+ PREFIX="v2.6/longterm/v2.6.32"
+ fi
+
+ wget https://www.kernel.org/pub/linux/kernel/${PREFIX}/linux-${1}.tar.gz
+ tar xzvf linux-${1}.tar.gz > /dev/null
+ cd linux-${1}
+ make allmodconfig
+
+ # Cannot use CONFIG_KCOV: -fsanitize-coverage=trace-pc is not supported by compiler
+ sed -i 's/CONFIG_KCOV=y/CONFIG_KCOV=n/' .config
+
+ # stack validation depends on tools/objtool, but objtool does not compile on travis.
+ # It is giving following error.
+ # >>> GEN arch/x86/insn/inat-tables.c
+ # >>> Semantic error at 40: Unknown imm opnd: AL
+ # So for now disable stack-validation for the build.
+
+ sed -i 's/CONFIG_STACK_VALIDATION=y/CONFIG_STACK_VALIDATION=n/' .config
+ make oldconfig
+
+ # Older kernels do not include openvswitch
+ if [ -d "net/openvswitch" ]; then
+ make net/openvswitch/
+ else
+ make net/bridge/
+ fi
+
+ KERNELSRC=$(pwd)
+ if [ ! "$DPDK" ] && [ ! "$DPDK_SHARED" ]; then
+ EXTRA_OPTS="--with-linux=$(pwd)"
+ fi
+ echo "Installed kernel source in $(pwd)"
+ cd ..
+}
+
+function install_dpdk()
+{
+ if [ -n "$DPDK_GIT" ]; then
+ git clone $DPDK_GIT dpdk-$1
+ cd dpdk-$1
+ git checkout tags/v$1
+ else
+ wget https://fast.dpdk.org/rel/dpdk-$1.tar.xz
+ tar xvf dpdk-$1.tar.xz > /dev/null
+ DIR_NAME=$(tar -tf dpdk-$1.tar.xz | head -1 | cut -f1 -d"/")
+ if [ $DIR_NAME != "dpdk-$1" ]; then mv $DIR_NAME dpdk-$1; fi
+ cd dpdk-$1
+ fi
+ find ./ -type f | xargs sed -i 's/max-inline-insns-single=100/max-inline-insns-single=400/'
+ find ./ -type f | xargs sed -i 's/-Werror/-Werror -Wno-error=inline/'
+ echo 'CONFIG_RTE_BUILD_FPIC=y' >>config/common_linuxapp
+ sed -ri '/EXECENV_CFLAGS = -pthread -fPIC/{s/$/\nelse ifeq ($(CONFIG_RTE_BUILD_FPIC),y)/;s/$/\nEXECENV_CFLAGS = -pthread -fPIC/}' mk/exec-env/linuxapp/rte.vars.mk
+ if [ "$DPDK_SHARED" ]; then
+ sed -i '/CONFIG_RTE_BUILD_SHARED_LIB=n/s/=n/=y/' config/common_base
+ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$(pwd)/$TARGET/lib
+ fi
+ make config CC=gcc T=$TARGET
+ make CC=gcc RTE_KERNELDIR=$KERNELSRC
+ echo "Installed DPDK source in $(pwd)"
+ cd ..
+}
+
+function configure_ovs()
+{
+ ./boot.sh && ./configure $*
+}
+
+if [ "$KERNEL" ] || [ "$DPDK" ] || [ "$DPDK_SHARED" ]; then
+ install_kernel $KERNEL
+fi
+
+if [ "$DPDK" ] || [ "$DPDK_SHARED" ]; then
+ if [ -z "$DPDK_VER" ]; then
+ DPDK_VER="18.11.11"
+ fi
+ install_dpdk $DPDK_VER
+ if [ "$CC" = "clang" ]; then
+ # Disregard cast alignment errors until DPDK is fixed
+ CFLAGS="$CFLAGS -Wno-cast-align"
+ fi
+ EXTRA_OPTS="$EXTRA_OPTS --with-dpdk=./dpdk-$DPDK_VER/build"
+elif [ "$CC" != "clang" ]; then
+ # DPDK headers currently trigger sparse errors
+ SPARSE_FLAGS="$SPARSE_FLAGS -Wsparse-error"
+fi
+
+configure_ovs $EXTRA_OPTS $*
+
+make selinux-policy
+
+# Only build datapath if we are testing kernel w/o running testsuite
+if [ "$KERNEL" ] && [ ! "$TESTSUITE" ] && \
+ [ ! "$DPDK" ] && [ ! "$DPDK_SHARED" ]; then
+ cd datapath
+fi
+
+if [ "$CC" = "clang" ]; then
+ make -j2 CFLAGS="$CFLAGS -Wno-error=unused-command-line-argument"
+elif [[ $BUILD_ENV =~ "-m32" ]]; then
+ # Disable sparse for 32bit builds on 64bit machine
+ make -j2 CFLAGS="$CFLAGS $BUILD_ENV"
+else
+ make -j2 CFLAGS="$CFLAGS $BUILD_ENV $SPARSE_FLAGS" C=1
+fi
+
+if [ "$TESTSUITE" ] && [ "$CC" != "clang" ]; then
+ if ! make distcheck TESTSUITEFLAGS=-j4 RECHECK=yes; then
+ # testsuite.log is necessary for debugging.
+ cat */_build/tests/testsuite.log
+ exit 1
+ fi
+fi
+
+exit 0
diff --git a/.ci/linux-prepare.sh b/.ci/linux-prepare.sh
new file mode 100755
index 0000000000..89770c28d9
--- /dev/null
+++ b/.ci/linux-prepare.sh
@@ -0,0 +1,14 @@
+#!/bin/bash
+
+set -ev
+
+# Build and install sparse.
+#
+# Explicitly disable sparse support for llvm because some travis
+# environments claim to have LLVM (llvm-config exists and works) but
+# linking against it fails.
+git clone git://git.kernel.org/pub/scm/devel/sparse/chrisl/sparse.git
+cd sparse && make HAVE_LLVM= install && cd ..
+
+pip install --disable-pip-version-check --user six flake8 hacking
+pip install --user --upgrade docutils
diff --git a/.ci/osx-build.sh b/.ci/osx-build.sh
new file mode 100755
index 0000000000..f11d7b9af5
--- /dev/null
+++ b/.ci/osx-build.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+
+set -o errexit
+
+CFLAGS="-Werror $CFLAGS"
+EXTRA_OPTS=""
+
+function configure_ovs()
+{
+ ./boot.sh && ./configure $*
+}
+
+configure_ovs $EXTRA_OPTS $*
+
+if [ "$CC" = "clang" ]; then
+ make CFLAGS="$CFLAGS -Wno-error=unused-command-line-argument"
+else
+ make CFLAGS="$CFLAGS $BUILD_ENV"
+fi
+if [ "$TESTSUITE" ] && [ "$CC" != "clang" ]; then
+ if ! make distcheck RECHECK=yes; then
+ # testsuite.log is necessary for debugging.
+ cat */_build/tests/testsuite.log
+ exit 1
+ fi
+fi
+
+exit 0
diff --git a/.ci/osx-prepare.sh b/.ci/osx-prepare.sh
new file mode 100755
index 0000000000..4725fd829d
--- /dev/null
+++ b/.ci/osx-prepare.sh
@@ -0,0 +1,7 @@
+#!/bin/bash
+set -ev
+pip2 install --user six
+pip2 install --user --upgrade docutils
+
+brew update || true
+brew uninstall libtool && brew install libtool || true
diff --git a/.cirrus.yml b/.cirrus.yml
index eb6af0a719..1bf81a983a 100644
--- a/.cirrus.yml
+++ b/.cirrus.yml
@@ -2,21 +2,21 @@ freebsd_build_task:
freebsd_instance:
matrix:
- image: freebsd-12-0-release-amd64
- image: freebsd-11-2-release-amd64
+ image_family: freebsd-12-2-snap
+ image_family: freebsd-11-4-snap
cpu: 4
memory: 8G
env:
DEPENDENCIES: automake libtool gmake gcc wget openssl
- python py27-six py27-sphinx py27-openssl
- python3 py36-six py36-openssl
+ python3 py37-six py37-sphinx py37-openssl
matrix:
COMPILER: gcc
COMPILER: clang
prepare_script:
- sysctl -w kern.coredump=0
+ - pkg update -f
- pkg install -y ${DEPENDENCIES}
configure_script:
diff --git a/.github/workflows/build-and-test.yml b/.github/workflows/build-and-test.yml
new file mode 100644
index 0000000000..f7a4ef2b9f
--- /dev/null
+++ b/.github/workflows/build-and-test.yml
@@ -0,0 +1,162 @@
+name: Build and Test
+
+on: [push, pull_request]
+
+jobs:
+ build-linux:
+ env:
+ dependencies: |
+ automake libtool gcc bc libjemalloc1 libjemalloc-dev \
+ libssl-dev llvm-dev libelf-dev libnuma-dev \
+ python-sphinx selinux-policy-dev gcc-multilib
+ CC: ${{ matrix.compiler }}
+ DPDK: ${{ matrix.dpdk }}
+ DPDK_SHARED: ${{ matrix.dpdk_shared }}
+ KERNEL: ${{ matrix.kernel }}
+ LIBS: ${{ matrix.libs }}
+ BUILD_ENV: ${{ matrix.build_env }}
+ OPTS: ${{ matrix.opts }}
+ TESTSUITE: ${{ matrix.testsuite }}
+
+ name: linux ${{ join(matrix.*, ' ') }}
+ runs-on: ubuntu-16.04
+ timeout-minutes: 30
+
+ strategy:
+ fail-fast: false
+ matrix:
+ compiler: [gcc, clang]
+ kernel: ['4.18.20', '4.17.19', '4.16.18', '4.15.18', '4.14.111',
+ '4.9.149', '4.4.148', '3.16.57']
+ opts: ['']
+ testsuite: ['']
+ dpdk: ['']
+ dpdk_shared: ['']
+ build_env: ['']
+ include:
+ - compiler: gcc
+ opts: --disable-ssl
+ - compiler: clang
+ opts: --disable-ssl
+
+ - compiler: gcc
+ testsuite: test
+ kernel: 3.16.54
+ - compiler: clang
+ testsuite: test
+ kernel: 3.16.54
+
+ - compiler: gcc
+ testsuite: test
+ opts: --enable-shared
+ - compiler: clang
+ testsuite: test
+ opts: --enable-shared
+
+ - compiler: gcc
+ testsuite: test
+ libs: -ljemalloc
+ - compiler: clang
+ testsuite: test
+ libs: -ljemalloc
+
+ - compiler: gcc
+ dpdk: dpdk
+ kernel: 3.16.54
+ - compiler: clang
+ dpdk: dpdk
+ kernel: 3.16.54
+
+ - compiler: gcc
+ dpdk: dpdk
+ kernel: 3.16.54
+ opts: --enable-shared
+ - compiler: clang
+ dpdk: dpdk
+ kernel: 3.16.54
+ opts: --enable-shared
+
+ - compiler: gcc
+ dpdk_shared: dpdk-shared
+ kernel: 3.16.54
+ - compiler: clang
+ dpdk_shared: dpdk-shared
+ kernel: 3.16.54
+
+ - compiler: gcc
+ dpdk_shared: dpdk-shared
+ opts: --enable-shared
+ kernel: 3.16.54
+ - compiler: clang
+ dpdk_shared: dpdk-shared
+ kernel: 3.16.54
+ opts: --enable-shared
+
+ - compiler: gcc
+ build_env: -m32
+ opts: --disable-ssl
+
+ steps:
+ - name: checkout
+ uses: actions/checkout@v2
+
+ - name: update APT cache
+ run: sudo apt update || true
+ - name: install common dependencies
+ run: sudo apt install -y ${{ env.dependencies }}
+ - name: install libunbound
+ if: matrix.build_env == ''
+ run: sudo apt install -y libunbound-dev
+
+ - name: prepare
+ run: ./.ci/linux-prepare.sh
+
+ - name: build
+ run: PATH="$PATH:$HOME/bin" ./.ci/linux-build.sh ${{ env.OPTS }}
+
+ - name: copy logs on failure
+ if: failure() || cancelled()
+ run: |
+ # upload-artifact@v2 throws exceptions if it tries to upload socket
+ # files and we could have some socket files in testsuite.dir.
+ # Also, upload-artifact@v2 doesn't work well enough with wildcards.
+ # So, we're just archiving everything here to avoid any issues.
+ mkdir logs
+ cp config.log ./logs/
+ cp -r ./*/_build/sub/tests/testsuite.* ./logs/ || true
+ tar -czvf logs.tgz logs/
+
+ - name: upload logs on failure
+ if: failure() || cancelled()
+ uses: actions/upload-artifact@v2
+ with:
+ name: logs-linux-${{ join(matrix.*, '-') }}
+ path: logs.tgz
+
+ build-osx:
+ env:
+ CC: clang
+ OPTS: --disable-ssl
+
+ name: osx clang --disable-ssl
+ runs-on: macos-latest
+ timeout-minutes: 30
+
+ strategy:
+ fail-fast: false
+
+ steps:
+ - name: checkout
+ uses: actions/checkout@v2
+ - name: install dependencies
+ run: brew install automake libtool
+ - name: prepare
+ run: ./.ci/osx-prepare.sh
+ - name: build
+ run: PATH="$PATH:$HOME/bin" ./.ci/osx-build.sh
+ - name: upload logs on failure
+ if: failure()
+ uses: actions/upload-artifact@v2
+ with:
+ name: logs-osx-clang---disable-ssl
+ path: config.log
diff --git a/AUTHORS.rst b/AUTHORS.rst
index f3237e1828..e1e1e5fa36 100644
--- a/AUTHORS.rst
+++ b/AUTHORS.rst
@@ -523,6 +523,7 @@ Krishna Miriyala miriyalak@vmware.com
Krishna Mohan Elluru elluru.kri.mohan@hpe.com
László Sürü laszlo.suru@ericsson.com
Len Gao leng@vmware.com
+Linhaifeng haifeng.lin@huawei.com
Logan Rosen logatronico@gmail.com
Luca Falavigna dktrkranz@debian.org
Luiz Henrique Ozaki luiz.ozaki@gmail.com
@@ -619,6 +620,7 @@ Ying Chen yingchen@vmware.com
Yongqiang Liu liuyq7809@gmail.com
ZHANG Zhiming zhangzhiming@yunshan.net.cn
Zhangguanghui zhang.guanghui@h3c.com
+Zheng Jingzhou glovejmm@163.com
Ziyou Wang ziyouw@vmware.com
ankur dwivedi ankurengg2003@gmail.com
chen zhang 3zhangchen9211@gmail.com
diff --git a/Documentation/faq/configuration.rst b/Documentation/faq/configuration.rst
index cb2c6b4eca..ff3b71a5d4 100644
--- a/Documentation/faq/configuration.rst
+++ b/Documentation/faq/configuration.rst
@@ -212,6 +212,19 @@ Q: Does Open vSwitch support ERSPAN?
options:erspan_ver=2 options:erspan_dir=1 \
options:erspan_hwid=4
+Q: Does Open vSwitch support IPv6 GRE?
+
+ A: Yes. L2 tunnel interface GRE over IPv6 is supported.
+ L3 GRE tunnel over IPv6 is not supported.
+
+ ::
+
+ $ ovs-vsctl add-br br0
+ $ ovs-vsctl add-port br0 at_gre0 -- \
+ set int at_gre0 type=ip6gre \
+ options:remote_ip=fc00:100::1 \
+ options:packet_type=legacy_l2
+
Q: How do I connect two bridges?
A: First, why do you want to do this? Two connected bridges are not much
diff --git a/Documentation/faq/releases.rst b/Documentation/faq/releases.rst
index eeb949d4a6..d6a93b943b 100644
--- a/Documentation/faq/releases.rst
+++ b/Documentation/faq/releases.rst
@@ -164,9 +164,9 @@ Q: What DPDK version does each Open vSwitch release work with?
A: The following table lists the DPDK version against which the given
versions of Open vSwitch will successfully build.
- ============ =======
+ ============ ========
Open vSwitch DPDK
- ============ =======
+ ============ ========
2.2.x 1.6
2.3.x 1.6
2.4.x 2.0
@@ -174,10 +174,10 @@ Q: What DPDK version does each Open vSwitch release work with?
2.6.x 16.07.2
2.7.x 16.11.9
2.8.x 17.05.2
- 2.9.x 17.11.4
- 2.10.x 17.11.4
- 2.11.x 18.11.2
- ============ =======
+ 2.9.x 17.11.10
+ 2.10.x 17.11.10
+ 2.11.x 18.11.11
+ ============ ========
Q: Are all the DPDK releases that OVS versions work with maintained?
diff --git a/Documentation/internals/contributing/submitting-patches.rst b/Documentation/internals/contributing/submitting-patches.rst
index 5a314cc60a..f2039595e7 100644
--- a/Documentation/internals/contributing/submitting-patches.rst
+++ b/Documentation/internals/contributing/submitting-patches.rst
@@ -68,11 +68,9 @@ Testing is also important:
feature. A bug fix patch should preferably add a test that would
fail if the bug recurs.
-If you are using GitHub, then you may utilize the travis-ci.org CI build system
-by linking your GitHub repository to it. This will run some of the above tests
-automatically when you push changes to your repository. See the "Continuous
-Integration with Travis-CI" in :doc:`/topics/testing` for details on how to set
-it up.
+If you are using GitHub, then you may utilize the GitHub Actions CI build
+system. It will run some of the above tests automatically when you push
+changes to your repository.
Email Subject
-------------
diff --git a/Documentation/internals/mailing-lists.rst b/Documentation/internals/mailing-lists.rst
index 33f20277be..e8b3440943 100644
--- a/Documentation/internals/mailing-lists.rst
+++ b/Documentation/internals/mailing-lists.rst
@@ -93,4 +93,4 @@ security
The `security`__ mailing list is for submitting security vulnerabilities to the
security team.
-__ security@ovs.org
+__ security@openvswitch.org
diff --git a/Documentation/intro/install/dpdk.rst b/Documentation/intro/install/dpdk.rst
index 6e5f1ea60a..a441715fd4 100644
--- a/Documentation/intro/install/dpdk.rst
+++ b/Documentation/intro/install/dpdk.rst
@@ -42,7 +42,7 @@ Build requirements
In addition to the requirements described in :doc:`general`, building Open
vSwitch with DPDK will require the following:
-- DPDK 18.11.2
+- DPDK 18.11.11
- A `DPDK supported NIC`_
@@ -71,9 +71,9 @@ Install DPDK
#. Download the `DPDK sources`_, extract the file and set ``DPDK_DIR``::
$ cd /usr/src/
- $ wget http://fast.dpdk.org/rel/dpdk-18.11.2.tar.xz
- $ tar xf dpdk-18.11.2.tar.xz
- $ export DPDK_DIR=/usr/src/dpdk-stable-18.11.2
+ $ wget http://fast.dpdk.org/rel/dpdk-18.11.11.tar.xz
+ $ tar xf dpdk-18.11.11.tar.xz
+ $ export DPDK_DIR=/usr/src/dpdk-stable-18.11.11
$ cd $DPDK_DIR
#. (Optional) Configure DPDK as a shared library
@@ -687,6 +687,15 @@ Limitations
around is temporary and is expected to be removed once a method is provided
by DPDK to query the upper bound MTU value for a given device.
+- Flow Control: When using i40e devices (Intel(R) 700 Series) it is recommended
+ to set Link State Change detection to interrupt mode. Otherwise it has been
+ observed that using the default polling mode, flow control changes may not be
+ applied, and flow control states will not be reflected correctly.
+ The issue is under investigation, this is a temporary work around.
+
+ For information about setting Link State Change detection, refer to
+ :ref:`lsc-detection`.
+
Reporting Bugs
--------------
diff --git a/Documentation/topics/dpdk/bridge.rst b/Documentation/topics/dpdk/bridge.rst
index a3ed926ca9..2fae9188a4 100644
--- a/Documentation/topics/dpdk/bridge.rst
+++ b/Documentation/topics/dpdk/bridge.rst
@@ -74,6 +74,12 @@ OpenFlow14`` option::
$ ovs-ofctl -O OpenFlow14 dump-ports br0
+There are custom statistics that OVS accumulates itself and these stats has
+``ovs_`` as prefix. These custom stats are shown along with other stats
+using the following command::
+
+ $ ovs-vsctl get Interface <iface> statistics
+
EMC Insertion Probability
-------------------------
diff --git a/Documentation/topics/dpdk/phy.rst b/Documentation/topics/dpdk/phy.rst
index 93d74df452..9bf6e3112a 100644
--- a/Documentation/topics/dpdk/phy.rst
+++ b/Documentation/topics/dpdk/phy.rst
@@ -364,6 +364,8 @@ Jumbo Frames
DPDK physical ports can be configured to use Jumbo Frames. For more
information, refer to :doc:`jumbo-frames`.
+.. _lsc-detection:
+
Link State Change (LSC) detection configuration
-----------------------------------------------
diff --git a/Documentation/topics/dpdk/vhost-user.rst b/Documentation/topics/dpdk/vhost-user.rst
index 33361ec359..adef15a133 100644
--- a/Documentation/topics/dpdk/vhost-user.rst
+++ b/Documentation/topics/dpdk/vhost-user.rst
@@ -303,6 +303,31 @@ The default value is false.
.. _dpdk-testpmd:
+vhost-user-client tx retries config
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+For vhost-user-client interfaces, the max amount of retries can be changed from
+the default 8 by setting ``tx-retries-max``.
+
+The minimum is 0 which means there will be no retries and if any packets in
+each batch cannot be sent immediately they will be dropped. The maximum is 32,
+which would mean that after the first packet(s) in the batch was sent there
+could be a maximum of 32 more retries.
+
+Retries can help with avoiding packet loss when temporarily unable to send to a
+vhost interface because the virtqueue is full. However, spending more time
+retrying to send to one interface, will reduce the time available for rx/tx and
+processing packets on other interfaces, so some tuning may be required for best
+performance.
+
+Tx retries max can be set for vhost-user-client ports::
+
+ $ ovs-vsctl set Interface vhost-client-1 options:tx-retries-max=0
+
+.. note::
+
+ Configurable vhost tx retries are not supported with vhost-user ports.
+
DPDK in the Guest
-----------------
@@ -320,9 +345,9 @@ To begin, instantiate a guest as described in :ref:`dpdk-vhost-user` or
DPDK sources to VM and build DPDK::
$ cd /root/dpdk/
- $ wget http://fast.dpdk.org/rel/dpdk-18.11.2.tar.xz
- $ tar xf dpdk-18.11.2.tar.xz
- $ export DPDK_DIR=/root/dpdk/dpdk-stable-18.11.2
+ $ wget http://fast.dpdk.org/rel/dpdk-18.11.11.tar.xz
+ $ tar xf dpdk-18.11.11.tar.xz
+ $ export DPDK_DIR=/root/dpdk/dpdk-stable-18.11.11
$ export DPDK_TARGET=x86_64-native-linuxapp-gcc
$ export DPDK_BUILD=$DPDK_DIR/$DPDK_TARGET
$ cd $DPDK_DIR
@@ -437,6 +462,50 @@ Jumbo Frames
DPDK vHost User ports can be configured to use Jumbo Frames. For more
information, refer to :doc:`jumbo-frames`.
+vhost tx retries
+----------------
+
+When sending a batch of packets to a vhost-user or vhost-user-client interface,
+it may happen that some but not all of the packets in the batch are able to be
+sent to the guest. This is often because there is not enough free descriptors
+in the virtqueue for all the packets in the batch to be sent. In this case
+there will be a retry, with a default maximum of 8 occurring. If at any time no
+packets can be sent, it may mean the guest is not accepting packets, so there
+are no (more) retries.
+
+For information about configuring the maximum amount of tx retries for
+vhost-user-client interfaces see `vhost-user-client tx retries config`_.
+
+.. note::
+
+ Maximum vhost tx batch size is defined by NETDEV_MAX_BURST, and is currently
+ as 32.
+
+Tx Retries may be reduced or even avoided by some external configuration, such
+as increasing the virtqueue size through the ``rx_queue_size`` parameter
+introduced in QEMU 2.7.0 / libvirt 2.3.0::
+
+ <interface type='vhostuser'>
+ <mac address='56:48:4f:53:54:01'/>
+ <source type='unix' path='/tmp/dpdkvhostclient0' mode='server'/>
+ <model type='virtio'/>
+ <driver name='vhost' rx_queue_size='1024' tx_queue_size='1024'/>
+ <address type='pci' domain='0x0000' bus='0x00' slot='0x10' function='0x0'/>
+ </interface>
+
+The guest application will also need need to provide enough descriptors. For
+example with ``testpmd`` the command line argument can be used::
+
+ --rxd=1024 --txd=1024
+
+The guest should also have sufficient cores dedicated for consuming and
+processing packets at the required rate.
+
+The amount of Tx retries on a vhost-user or vhost-user-client interface can be
+shown with::
+
+ $ ovs-vsctl get Interface dpdkvhostclient0 statistics:ovs_tx_retries
+
vhost-user Dequeue Zero Copy (experimental)
-------------------------------------------
diff --git a/Documentation/topics/testing.rst b/Documentation/topics/testing.rst
index a8892e1c1c..b74653436d 100644
--- a/Documentation/topics/testing.rst
+++ b/Documentation/topics/testing.rst
@@ -372,45 +372,17 @@ You should invoke scan-view to view analysis results. The last line of output
from ``clang-analyze`` will list the command (containing results directory)
that you should invoke to view the results on a browser.
-Continuous Integration with Travis CI
--------------------------------------
+Continuous Integration with GitHub Actions
+------------------------------------------
-A .travis.yml file is provided to automatically build Open vSwitch with various
-build configurations and run the testsuite using Travis CI. Builds will be
-performed with gcc, sparse and clang with the -Werror compiler flag included,
-therefore the build will fail if a new warning has been introduced.
+A ``.github/workflows/*.yml`` files provided to automatically build
+Open vSwitch with various build configurations and run the testsuite using
+GitHub Actions. Builds will be performed with gcc, sparse and clang with the
+-Werror compiler flag included, therefore the build will fail if a new warning
+has been introduced.
The CI build is triggered via git push (regardless of the specific branch) or
-pull request against any Open vSwitch GitHub repository that is linked to
-travis-ci.
-
-Instructions to setup travis-ci for your GitHub repository:
-
-1. Go to https://travis-ci.org/ and sign in using your GitHub ID.
-2. Go to the "Repositories" tab and enable the ovs repository. You may disable
- builds for pushes or pull requests.
-3. In order to avoid forks sending build failures to the upstream mailing list,
- the notification email recipient is encrypted. If you want to receive email
- notification for build failures, replace the the encrypted string:
-
- 1. Install the travis-ci CLI (Requires ruby >=2.0): gem install travis
- 2. In your Open vSwitch repository: travis encrypt mylist@mydomain.org
- 3. Add/replace the notifications section in .travis.yml and fill in the
- secure string as returned by travis encrypt::
-
- notifications:
- email:
- recipients:
- - secure: "....."
-
- .. note::
- You may remove/omit the notifications section to fall back to default
- notification behaviour which is to send an email directly to the author and
- committer of the failing commit. Note that the email is only sent if the
- author/committer have commit rights for the particular GitHub repository.
-
-4. Pushing a commit to the repository which breaks the build or the
- testsuite will now trigger a email sent to mylist@mydomain.org
+pull request against any Open vSwitch GitHub repository.
vsperf
------
diff --git a/Makefile.am b/Makefile.am
index ff1f94b484..4f9f1866c0 100644
--- a/Makefile.am
+++ b/Makefile.am
@@ -76,12 +76,12 @@ EXTRA_DIST = \
MAINTAINERS.rst \
README.rst \
NOTICE \
+ .ci/linux-build.sh \
+ .ci/linux-prepare.sh \
+ .ci/osx-build.sh \
+ .ci/osx-prepare.sh \
.cirrus.yml \
- .travis.yml \
- .travis/linux-build.sh \
- .travis/linux-prepare.sh \
- .travis/osx-build.sh \
- .travis/osx-prepare.sh \
+ .github/workflows/build-and-test.yml \
appveyor.yml \
boot.sh \
poc/builders/Vagrantfile \
diff --git a/NEWS b/NEWS
index f177d7efc1..b8510e01ea 100644
--- a/NEWS
+++ b/NEWS
@@ -1,3 +1,39 @@
+v2.11.8 - xx xxx xxxx
+---------------------
+
+v2.11.7 - 05 Mar 2021
+---------------------
+ - Bug fixes
+ - DPDK
+ * OVS validated with DPDK 18.11.11. Due to this being the final release
+ in the DPDK 18.11 series it is recommended to be used.
+
+v2.11.6 - 10 Feb 2021
+---------------------
+ - Bug fixes
+ - Security:
+ * Fixed packet parsing vulnerability CVE-2020-35498.
+
+v2.11.5 - 13 Jan 2021
+---------------------
+ - Bug fixes
+ - LLDP:
+ * Security fixes for CVE-2015-8011 and CVE-2020-27827.
+ - OVSDB:
+ * Fixed SHA-1 hash computation for databases larger than 512 MB.
+ - DPDK:
+ * Fixed support of 'net_virtio' devices.
+
+v2.11.4 - 30 Jul 2020
+---------------------
+ - Bug fixes
+ - DPDK
+ * OVS validated with DPDK 18.11.9. Due to this being the latest LTS to
+ be validated and coupled with the inclusion of fixes for
+ CVE-2019-14818, CVE-2020-10722, CVE-2020-10723 and CVE-2020-10724
+ over the course of various LTS releases, this DPDK version is strongly
+ recommended to be used.
+
v2.11.3 - 06 Sep 2019
---------------------
- Fix compilation issue with Ubuntu kernel 4.15.60.
diff --git a/README.rst b/README.rst
index 54d06d04be..37d7685c88 100644
--- a/README.rst
+++ b/README.rst
@@ -6,8 +6,8 @@
Open vSwitch
============
-.. image:: https://travis-ci.org/openvswitch/ovs.png
- :target: https://travis-ci.org/openvswitch/ovs
+.. image:: https://github.com/openvswitch/ovs/workflows/Build%20and%20Test/badge.svg
+ :target: https://github.com/openvswitch/ovs/actions
.. image:: https://ci.appveyor.com/api/projects/status/github/openvswitch/ovs?branch=master&svg=true&retina=true
:target: https://ci.appveyor.com/project/blp/ovs/history
diff --git a/acinclude.m4 b/acinclude.m4
index f15b1ff670..71813077c6 100644
--- a/acinclude.m4
+++ b/acinclude.m4
@@ -172,16 +172,30 @@ AC_DEFUN([OVS_CHECK_LINUX], [
AM_CONDITIONAL(LINUX_ENABLED, test -n "$KBUILD")
])
+dnl OVS_CHECK_LINUX_NETLINK
+dnl
+dnl Configure Linux netlink compat.
+AC_DEFUN([OVS_CHECK_LINUX_NETLINK], [
+ AC_COMPILE_IFELSE([
+ AC_LANG_PROGRAM([#include <linux/netlink.h>], [
+ struct nla_bitfield32 x = { 0 };
+ ])],
+ [AC_DEFINE([HAVE_NLA_BITFIELD32], [1],
+ [Define to 1 if struct nla_bitfield32 is available.])])
+])
+
dnl OVS_CHECK_LINUX_TC
dnl
dnl Configure Linux tc compat.
AC_DEFUN([OVS_CHECK_LINUX_TC], [
AC_COMPILE_IFELSE([
AC_LANG_PROGRAM([#include <linux/pkt_cls.h>], [
- int x = TCA_FLOWER_KEY_ENC_IP_TTL_MASK;
+ int x = TCA_ACT_FLAGS;
])],
- [AC_DEFINE([HAVE_TCA_FLOWER_KEY_ENC_IP_TTL_MASK], [1],
- [Define to 1 if TCA_FLOWER_KEY_ENC_IP_TTL_MASK is available.])])
+ [AC_DEFINE([HAVE_TCA_ACT_FLAGS], [1],
+ [Define to 1 if TCA_ACT_FLAGS is available.])])
+
+ AC_CHECK_MEMBERS([struct tcf_t.firstuse], [], [], [#include <linux/pkt_cls.h>])
AC_COMPILE_IFELSE([
AC_LANG_PROGRAM([#include <linux/tc_act/tc_vlan.h>], [
@@ -685,6 +699,10 @@ AC_DEFUN([OVS_CHECK_LINUX_COMPAT], [
OVS_GREP_IFELSE([$KSRC/include/linux/random.h], [prandom_u32])
OVS_GREP_IFELSE([$KSRC/include/linux/random.h], [prandom_u32_max])
+ OVS_GREP_IFELSE([$KSRC/include/linux/prandom.h],
+ [prandom_u32[[\(]]],
+ [OVS_DEFINE([HAVE_PRANDOM_U32])])
+ OVS_GREP_IFELSE([$KSRC/include/linux/prandom.h], [prandom_u32_max])
OVS_GREP_IFELSE([$KSRC/include/net/rtnetlink.h], [get_link_net])
OVS_GREP_IFELSE([$KSRC/include/net/rtnetlink.h], [name_assign_type])
@@ -834,8 +852,6 @@ AC_DEFUN([OVS_CHECK_LINUX_COMPAT], [
OVS_GREP_IFELSE([$KSRC/include/net/sock.h], [sk_no_check_tx])
OVS_GREP_IFELSE([$KSRC/include/linux/udp.h], [no_check6_tx])
- OVS_GREP_IFELSE([$KSRC/include/linux/utsrelease.h], [el6],
- [OVS_DEFINE([HAVE_RHEL6_PER_CPU])])
OVS_FIND_PARAM_IFELSE([$KSRC/include/net/protocol.h],
[udp_add_offload], [net],
[OVS_DEFINE([HAVE_UDP_ADD_OFFLOAD_TAKES_NET])])
@@ -967,6 +983,8 @@ AC_DEFUN([OVS_CHECK_LINUX_COMPAT], [
[OVS_DEFINE([HAVE_NF_CONNTRACK_IN_TAKES_NF_HOOK_STATE])])
OVS_GREP_IFELSE([$KSRC/include/net/ipv6_frag.h], [IP6_DEFRAG_CONNTRACK_IN],
[OVS_DEFINE([HAVE_IPV6_FRAG_H])])
+ OVS_GREP_IFELSE([$KSRC/include/net/dst_ops.h], [bool confirm_neigh],
+ [OVS_DEFINE([HAVE_DST_OPS_CONFIRM_NEIGH])])
if cmp -s datapath/linux/kcompat.h.new \
datapath/linux/kcompat.h >/dev/null 2>&1; then
diff --git a/build-aux/dist-docs b/build-aux/dist-docs
index 9f6ca7b2cb..85641745ee 100755
--- a/build-aux/dist-docs
+++ b/build-aux/dist-docs
@@ -43,7 +43,7 @@ rm -rf $distdir
mkdir $distdir
# Install manpages.
-${MAKE-make} install-man mandir="$abs_distdir"/man
+${MAKE-make} install-man install-man-rst mandir="$abs_distdir"/man
(cd $distdir && mv `find man -type f` . && rm -rf man)
manpages=`cd $distdir && echo *`
diff --git a/configure.ac b/configure.ac
index 45ff8cb07e..86fb44d19b 100644
--- a/configure.ac
+++ b/configure.ac
@@ -13,7 +13,7 @@
# limitations under the License.
AC_PREREQ(2.63)
-AC_INIT(openvswitch, 2.11.3, bugs@openvswitch.org)
+AC_INIT(openvswitch, 2.11.8, bugs@openvswitch.org)
AC_CONFIG_SRCDIR([datapath/datapath.c])
AC_CONFIG_MACRO_DIR([m4])
AC_CONFIG_AUX_DIR([build-aux])
@@ -185,6 +185,7 @@ OVS_CTAGS_IDENTIFIERS
AC_ARG_VAR(KARCH, [Kernel Architecture String])
AC_SUBST(KARCH)
OVS_CHECK_LINUX
+OVS_CHECK_LINUX_NETLINK
OVS_CHECK_LINUX_TC
OVS_CHECK_DPDK
OVS_CHECK_PRAGMA_MESSAGE
diff --git a/datapath-windows/ovsext/Actions.c b/datapath-windows/ovsext/Actions.c
index 5c9b5c3a0c..c709699bc7 100644
--- a/datapath-windows/ovsext/Actions.c
+++ b/datapath-windows/ovsext/Actions.c
@@ -1112,9 +1112,9 @@ OvsPopFieldInPacketBuf(OvsForwardingContext *ovsFwdCtx,
* should split the function and refactor. */
if (!bufferData) {
EthHdr *ethHdr = (EthHdr *)bufferStart;
- /* If the frame is not VLAN make it a no op */
if (ethHdr->Type != ETH_TYPE_802_1PQ_NBO) {
- return NDIS_STATUS_SUCCESS;
+ OVS_LOG_ERROR("Invalid ethHdr type %u, nbl %p", ethHdr->Type, ovsFwdCtx->curNbl);
+ return NDIS_STATUS_INVALID_PACKET;
}
}
RtlMoveMemory(bufferStart + shiftLength, bufferStart, shiftOffset);
@@ -1137,6 +1137,9 @@ OvsPopFieldInPacketBuf(OvsForwardingContext *ovsFwdCtx,
static __inline NDIS_STATUS
OvsPopVlanInPktBuf(OvsForwardingContext *ovsFwdCtx)
{
+ NDIS_STATUS status;
+ OVS_PACKET_HDR_INFO* layers = &ovsFwdCtx->layers;
+
/*
* Declare a dummy vlanTag structure since we need to compute the size
* of shiftLength. The NDIS one is a unionized structure.
@@ -1145,7 +1148,15 @@ OvsPopVlanInPktBuf(OvsForwardingContext *ovsFwdCtx)
UINT32 shiftLength = sizeof(vlanTag.TagHeader);
UINT32 shiftOffset = sizeof(DL_EUI48) + sizeof(DL_EUI48);
- return OvsPopFieldInPacketBuf(ovsFwdCtx, shiftOffset, shiftLength, NULL);
+ status = OvsPopFieldInPacketBuf(ovsFwdCtx, shiftOffset, shiftLength,
+ NULL);
+
+ if (status == NDIS_STATUS_SUCCESS) {
+ layers->l3Offset -= (UINT16) shiftLength;
+ layers->l4Offset -= (UINT16) shiftLength;
+ }
+
+ return status;
}
@@ -1259,6 +1270,7 @@ OvsActionMplsPush(OvsForwardingContext *ovsFwdCtx,
*/
static __inline NDIS_STATUS
OvsUpdateEthHeader(OvsForwardingContext *ovsFwdCtx,
+ OvsFlowKey *key,
const struct ovs_key_ethernet *ethAttr)
{
PNET_BUFFER curNb;
@@ -1285,9 +1297,11 @@ OvsUpdateEthHeader(OvsForwardingContext *ovsFwdCtx,
}
ethHdr = (EthHdr *)(bufferStart + NET_BUFFER_CURRENT_MDL_OFFSET(curNb));
- RtlCopyMemory(ethHdr->Destination, ethAttr->eth_dst,
- sizeof ethHdr->Destination);
- RtlCopyMemory(ethHdr->Source, ethAttr->eth_src, sizeof ethHdr->Source);
+ RtlCopyMemory(ethHdr->Destination, ethAttr->eth_dst, ETH_ADDR_LENGTH);
+ RtlCopyMemory(ethHdr->Source, ethAttr->eth_src, ETH_ADDR_LENGTH);
+ /* Update l2 flow key */
+ RtlCopyMemory(key->l2.dlDst, ethAttr->eth_dst, ETH_ADDR_LENGTH);
+ RtlCopyMemory(key->l2.dlSrc, ethAttr->eth_src, ETH_ADDR_LENGTH);
return NDIS_STATUS_SUCCESS;
}
@@ -1376,6 +1390,7 @@ PUINT8 OvsGetHeaderBySize(OvsForwardingContext *ovsFwdCtx,
*/
NDIS_STATUS
OvsUpdateUdpPorts(OvsForwardingContext *ovsFwdCtx,
+ OvsFlowKey *key,
const struct ovs_key_udp *udpAttr)
{
PUINT8 bufferStart;
@@ -1400,15 +1415,19 @@ OvsUpdateUdpPorts(OvsForwardingContext *ovsFwdCtx,
udpHdr->check = ChecksumUpdate16(udpHdr->check, udpHdr->source,
udpAttr->udp_src);
udpHdr->source = udpAttr->udp_src;
+ key->ipKey.l4.tpSrc = udpAttr->udp_src;
}
if (udpHdr->dest != udpAttr->udp_dst) {
udpHdr->check = ChecksumUpdate16(udpHdr->check, udpHdr->dest,
udpAttr->udp_dst);
udpHdr->dest = udpAttr->udp_dst;
+ key->ipKey.l4.tpDst = udpAttr->udp_dst;
}
} else {
udpHdr->source = udpAttr->udp_src;
+ key->ipKey.l4.tpSrc = udpAttr->udp_src;
udpHdr->dest = udpAttr->udp_dst;
+ key->ipKey.l4.tpDst = udpAttr->udp_dst;
}
return NDIS_STATUS_SUCCESS;
@@ -1423,6 +1442,7 @@ OvsUpdateUdpPorts(OvsForwardingContext *ovsFwdCtx,
*/
NDIS_STATUS
OvsUpdateTcpPorts(OvsForwardingContext *ovsFwdCtx,
+ OvsFlowKey *key,
const struct ovs_key_tcp *tcpAttr)
{
PUINT8 bufferStart;
@@ -1447,11 +1467,13 @@ OvsUpdateTcpPorts(OvsForwardingContext *ovsFwdCtx,
tcpHdr->check = ChecksumUpdate16(tcpHdr->check, tcpHdr->source,
tcpAttr->tcp_src);
tcpHdr->source = tcpAttr->tcp_src;
+ key->ipKey.l4.tpSrc = tcpAttr->tcp_src;
}
if (tcpHdr->dest != tcpAttr->tcp_dst) {
tcpHdr->check = ChecksumUpdate16(tcpHdr->check, tcpHdr->dest,
tcpAttr->tcp_dst);
tcpHdr->dest = tcpAttr->tcp_dst;
+ key->ipKey.l4.tpDst = tcpAttr->tcp_dst;
}
return NDIS_STATUS_SUCCESS;
@@ -1579,6 +1601,7 @@ OvsUpdateAddressAndPort(OvsForwardingContext *ovsFwdCtx,
*/
NDIS_STATUS
OvsUpdateIPv4Header(OvsForwardingContext *ovsFwdCtx,
+ OvsFlowKey *key,
const struct ovs_key_ipv4 *ipAttr)
{
PUINT8 bufferStart;
@@ -1632,6 +1655,7 @@ OvsUpdateIPv4Header(OvsForwardingContext *ovsFwdCtx,
ipAttr->ipv4_src);
}
ipHdr->saddr = ipAttr->ipv4_src;
+ key->ipKey.nwSrc = ipAttr->ipv4_src;
}
if (ipHdr->daddr != ipAttr->ipv4_dst) {
if (tcpHdr) {
@@ -1647,6 +1671,7 @@ OvsUpdateIPv4Header(OvsForwardingContext *ovsFwdCtx,
ipAttr->ipv4_dst);
}
ipHdr->daddr = ipAttr->ipv4_dst;
+ key->ipKey.nwDst = ipAttr->ipv4_dst;
}
if (ipHdr->protocol != ipAttr->ipv4_proto) {
UINT16 oldProto = (ipHdr->protocol << 16) & 0xff00;
@@ -1661,6 +1686,7 @@ OvsUpdateIPv4Header(OvsForwardingContext *ovsFwdCtx,
ipHdr->check = ChecksumUpdate16(ipHdr->check, oldProto, newProto);
}
ipHdr->protocol = ipAttr->ipv4_proto;
+ key->ipKey.nwProto = ipAttr->ipv4_proto;
}
if (ipHdr->ttl != ipAttr->ipv4_ttl) {
UINT16 oldTtl = (ipHdr->ttl) & 0xff;
@@ -1669,6 +1695,7 @@ OvsUpdateIPv4Header(OvsForwardingContext *ovsFwdCtx,
ipHdr->check = ChecksumUpdate16(ipHdr->check, oldTtl, newTtl);
}
ipHdr->ttl = ipAttr->ipv4_ttl;
+ key->ipKey.nwTtl = ipAttr->ipv4_ttl;
}
return NDIS_STATUS_SUCCESS;
@@ -1691,12 +1718,12 @@ OvsExecuteSetAction(OvsForwardingContext *ovsFwdCtx,
switch (type) {
case OVS_KEY_ATTR_ETHERNET:
- status = OvsUpdateEthHeader(ovsFwdCtx,
+ status = OvsUpdateEthHeader(ovsFwdCtx, key,
NlAttrGetUnspec(a, sizeof(struct ovs_key_ethernet)));
break;
case OVS_KEY_ATTR_IPV4:
- status = OvsUpdateIPv4Header(ovsFwdCtx,
+ status = OvsUpdateIPv4Header(ovsFwdCtx, key,
NlAttrGetUnspec(a, sizeof(struct ovs_key_ipv4)));
break;
@@ -1709,16 +1736,17 @@ OvsExecuteSetAction(OvsForwardingContext *ovsFwdCtx,
status = SUCCEEDED(convertStatus) ? NDIS_STATUS_SUCCESS : NDIS_STATUS_FAILURE;
ASSERT(status == NDIS_STATUS_SUCCESS);
RtlCopyMemory(&ovsFwdCtx->tunKey, &tunKey, sizeof ovsFwdCtx->tunKey);
+ RtlCopyMemory(&key->tunKey, &tunKey, sizeof key->tunKey);
break;
}
case OVS_KEY_ATTR_UDP:
- status = OvsUpdateUdpPorts(ovsFwdCtx,
+ status = OvsUpdateUdpPorts(ovsFwdCtx, key,
NlAttrGetUnspec(a, sizeof(struct ovs_key_udp)));
break;
case OVS_KEY_ATTR_TCP:
- status = OvsUpdateTcpPorts(ovsFwdCtx,
+ status = OvsUpdateTcpPorts(ovsFwdCtx, key,
NlAttrGetUnspec(a, sizeof(struct ovs_key_tcp)));
break;
@@ -2053,6 +2081,7 @@ OvsDoExecuteActions(POVS_SWITCH_CONTEXT switchContext,
*/
status = OvsPopVlanInPktBuf(&ovsFwdCtx);
if (status != NDIS_STATUS_SUCCESS) {
+ OVS_LOG_ERROR("OVS-pop vlan action failed status = %lu", status);
dropReason = L"OVS-pop vlan action failed";
goto dropit;
}
diff --git a/datapath-windows/ovsext/Actions.h b/datapath-windows/ovsext/Actions.h
index fd050d5dd8..bc12e1166d 100644
--- a/datapath-windows/ovsext/Actions.h
+++ b/datapath-windows/ovsext/Actions.h
@@ -115,14 +115,17 @@ PUINT8 OvsGetHeaderBySize(OvsForwardingContext *ovsFwdCtx,
NDIS_STATUS
OvsUpdateUdpPorts(OvsForwardingContext *ovsFwdCtx,
+ OvsFlowKey *key,
const struct ovs_key_udp *udpAttr);
NDIS_STATUS
OvsUpdateTcpPorts(OvsForwardingContext *ovsFwdCtx,
+ OvsFlowKey *key,
const struct ovs_key_tcp *tcpAttr);
NDIS_STATUS
OvsUpdateIPv4Header(OvsForwardingContext *ovsFwdCtx,
+ OvsFlowKey *key,
const struct ovs_key_ipv4 *ipAttr);
NDIS_STATUS
diff --git a/datapath/conntrack.c b/datapath/conntrack.c
index 83840f9579..974387addb 100644
--- a/datapath/conntrack.c
+++ b/datapath/conntrack.c
@@ -1895,7 +1895,8 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net)
struct hlist_head *head = &info->limits[i];
struct ovs_ct_limit *ct_limit;
- hlist_for_each_entry_rcu(ct_limit, head, hlist_node)
+ hlist_for_each_entry_rcu(ct_limit, head, hlist_node,
+ lockdep_ovsl_is_held())
kfree_rcu(ct_limit, rcu);
}
kfree(ovs_net->ct_limit_info->limits);
diff --git a/datapath/datapath.c b/datapath/datapath.c
index 2febcb3f2a..c645c2b797 100644
--- a/datapath/datapath.c
+++ b/datapath/datapath.c
@@ -2383,8 +2383,10 @@ static void __net_exit ovs_exit_net(struct net *dnet)
ovs_netns_frags6_exit(dnet);
ovs_netns_frags_exit(dnet);
- ovs_ct_exit(dnet);
ovs_lock();
+
+ ovs_ct_exit(dnet);
+
list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node)
__dp_destroy(dp);
diff --git a/datapath/linux/compat/include/linux/openvswitch.h b/datapath/linux/compat/include/linux/openvswitch.h
index 9b087f1b06..3369c8630d 100644
--- a/datapath/linux/compat/include/linux/openvswitch.h
+++ b/datapath/linux/compat/include/linux/openvswitch.h
@@ -404,6 +404,28 @@ enum ovs_tunnel_key_attr {
#define OVS_TUNNEL_KEY_ATTR_MAX (__OVS_TUNNEL_KEY_ATTR_MAX - 1)
+/**
+ * enum xlate_error - Different types of error during translation
+ */
+
+#ifndef __KERNEL__
+enum xlate_error {
+ XLATE_OK = 0,
+ XLATE_BRIDGE_NOT_FOUND,
+ XLATE_RECURSION_TOO_DEEP,
+ XLATE_TOO_MANY_RESUBMITS,
+ XLATE_STACK_TOO_DEEP,
+ XLATE_NO_RECIRCULATION_CONTEXT,
+ XLATE_RECIRCULATION_CONFLICT,
+ XLATE_TOO_MANY_MPLS_LABELS,
+ XLATE_INVALID_TUNNEL_METADATA,
+ XLATE_UNSUPPORTED_PACKET_TYPE,
+ XLATE_CONGESTION_DROP,
+ XLATE_FORWARDING_DISABLED,
+ XLATE_MAX,
+};
+#endif
+
/**
* enum ovs_frag_type - IPv4 and IPv6 fragment type
* @OVS_FRAG_TYPE_NONE: Packet is not a fragment.
@@ -855,6 +877,24 @@ enum ovs_nat_attr {
#define OVS_NAT_ATTR_MAX (__OVS_NAT_ATTR_MAX - 1)
+/*
+ * enum ovs_check_pkt_len_attr - Attributes for %OVS_ACTION_ATTR_CHECK_PKT_LEN.
+ *
+ * @OVS_CHECK_PKT_LEN_ATTR_PKT_LEN: u16 Packet length to check for.
+ * @OVS_CHECK_PKT_LEN_ATTR_USERSPACE_COND: u8 comparison condition to send
+ * the packet to userspace. One of OVS_CHECK_PKT_LEN_COND_*.
+ * @OVS_CHECK_PKT_LEN_ATTR_USERPACE - Nested OVS_USERSPACE_ATTR_* actions.
+ */
+enum ovs_check_pkt_len_attr {
+ OVS_CHECK_PKT_LEN_ATTR_UNSPEC,
+ OVS_CHECK_PKT_LEN_ATTR_PKT_LEN,
+ OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER,
+ OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL,
+ __OVS_CHECK_PKT_LEN_ATTR_MAX,
+};
+
+#define OVS_CHECK_PKT_LEN_ATTR_MAX (__OVS_CHECK_PKT_LEN_ATTR_MAX - 1)
+
/**
* enum ovs_action_attr - Action types.
*
@@ -911,6 +951,10 @@ enum ovs_nat_attr {
* packet, or modify the packet (e.g., change the DSCP field).
* @OVS_ACTION_ATTR_CLONE: make a copy of the packet and execute a list of
* actions without affecting the original packet and key.
+ * @OVS_ACTION_ATTR_CHECK_PKT_LEN: Check the packet length and execute a set
+ * of actions if greater than the specified packet length, else execute
+ * another set of actions.
+ * @OVS_ACTION_ATTR_DROP: Explicit drop action.
*/
enum ovs_action_attr {
@@ -938,10 +982,12 @@ enum ovs_action_attr {
OVS_ACTION_ATTR_POP_NSH, /* No argument. */
OVS_ACTION_ATTR_METER, /* u32 meter number. */
OVS_ACTION_ATTR_CLONE, /* Nested OVS_CLONE_ATTR_*. */
+ OVS_ACTION_ATTR_CHECK_PKT_LEN, /* Nested OVS_CHECK_PKT_LEN_ATTR_*. */
#ifndef __KERNEL__
OVS_ACTION_ATTR_TUNNEL_PUSH, /* struct ovs_action_push_tnl*/
OVS_ACTION_ATTR_TUNNEL_POP, /* u32 port number. */
+ OVS_ACTION_ATTR_DROP, /* u32 xlate_error. */
#endif
__OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted
* from userspace. */
diff --git a/datapath/linux/compat/include/linux/percpu.h b/datapath/linux/compat/include/linux/percpu.h
index 7c346aa31a..a039142e22 100644
--- a/datapath/linux/compat/include/linux/percpu.h
+++ b/datapath/linux/compat/include/linux/percpu.h
@@ -7,12 +7,6 @@
#define this_cpu_ptr(ptr) per_cpu_ptr(ptr, smp_processor_id())
#endif
-#ifdef HAVE_RHEL6_PER_CPU
-#undef this_cpu_read
-#undef this_cpu_inc
-#undef this_cpu_dec
-#endif
-
#if !defined this_cpu_read
#define this_cpu_read(ptr) percpu_read(ptr)
#endif
diff --git a/datapath/linux/compat/include/linux/rculist.h b/datapath/linux/compat/include/linux/rculist.h
index 8df8ad8a27..40fd5e1710 100644
--- a/datapath/linux/compat/include/linux/rculist.h
+++ b/datapath/linux/compat/include/linux/rculist.h
@@ -9,9 +9,28 @@
#define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev)))
#endif
+/*
+ * Check during list traversal that we are within an RCU reader
+ */
+
+#define check_arg_count_one(dummy)
+
+#ifdef CONFIG_PROVE_RCU_LIST
+#define __list_check_rcu(dummy, cond, extra...) \
+ ({ \
+ check_arg_count_one(extra); \
+ RCU_LOCKDEP_WARN(!cond && !rcu_read_lock_any_held(), \
+ "RCU-list traversed in non-reader section!"); \
+ })
+#else
+#define __list_check_rcu(dummy, cond, extra...) \
+ ({ check_arg_count_one(extra); })
+#endif
+
#undef hlist_for_each_entry_rcu
-#define hlist_for_each_entry_rcu(pos, head, member) \
- for (pos = hlist_entry_safe (rcu_dereference_raw(hlist_first_rcu(head)),\
+#define hlist_for_each_entry_rcu(pos, head, member, cond...) \
+ for (__list_check_rcu(dummy, ## cond, 0), \
+ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\
typeof(*(pos)), member); \
pos; \
pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\
diff --git a/datapath/linux/compat/include/linux/skbuff.h b/datapath/linux/compat/include/linux/skbuff.h
index 4a6ac2384c..9828f811d9 100644
--- a/datapath/linux/compat/include/linux/skbuff.h
+++ b/datapath/linux/compat/include/linux/skbuff.h
@@ -278,7 +278,7 @@ static inline void skb_clear_hash(struct sk_buff *skb)
#ifdef HAVE_RXHASH
skb->rxhash = 0;
#endif
-#if defined(HAVE_L4_RXHASH) && !defined(HAVE_RHEL_OVS_HOOK)
+#if defined(HAVE_L4_RXHASH)
skb->l4_rxhash = 0;
#endif
}
diff --git a/datapath/linux/compat/ip6_gre.c b/datapath/linux/compat/ip6_gre.c
index 2ffdda5e1d..aa6cf3e7fc 100644
--- a/datapath/linux/compat/ip6_gre.c
+++ b/datapath/linux/compat/ip6_gre.c
@@ -1196,7 +1196,11 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
/* TooBig packet may have updated dst->dev's mtu */
if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
+#ifndef HAVE_DST_OPS_CONFIRM_NEIGH
dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu);
+#else
+ dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false);
+#endif
err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
NEXTHDR_GRE);
@@ -2550,7 +2554,7 @@ static struct rtnl_link_ops ip6gre_link_ops __read_mostly = {
};
static struct rtnl_link_ops ip6gre_tap_ops __read_mostly = {
- .kind = "ip6gre",
+ .kind = "ip6gretap",
.maxtype = RPL_IFLA_GRE_MAX,
.policy = ip6gre_policy,
.priv_size = sizeof(struct ip6_tnl),
diff --git a/datapath/linux/compat/ip_tunnel.c b/datapath/linux/compat/ip_tunnel.c
index d16e60fbfe..f1c8ba7cdc 100644
--- a/datapath/linux/compat/ip_tunnel.c
+++ b/datapath/linux/compat/ip_tunnel.c
@@ -266,7 +266,12 @@ static int rpl_tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
if (skb_dst(skb))
+#ifndef HAVE_DST_OPS_CONFIRM_NEIGH
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
+#else
+ skb_dst(skb)->ops->update_pmtu(skb_dst(skb),
+ NULL, skb, mtu, false);
+#endif
if (skb->protocol == htons(ETH_P_IP)) {
if (!skb_is_gso(skb) &&
diff --git a/datapath/linux/compat/nf_conntrack_reasm.c b/datapath/linux/compat/nf_conntrack_reasm.c
index 9d77d98271..715388d838 100644
--- a/datapath/linux/compat/nf_conntrack_reasm.c
+++ b/datapath/linux/compat/nf_conntrack_reasm.c
@@ -56,10 +56,13 @@
#include <net/netns/generic.h>
#include "datapath.h"
-#ifdef OVS_NF_DEFRAG6_BACKPORT
+#if defined(HAVE_INET_FRAGS_WITH_FRAGS_WORK) || !defined(HAVE_INET_FRAGS_RND)
static const char nf_frags_cache_name[] = "ovs-frag6";
+#endif
+
+#ifdef OVS_NF_DEFRAG6_BACKPORT
struct nf_ct_frag6_skb_cb
{
struct inet6_skb_parm h;
diff --git a/debian/changelog b/debian/changelog
index d08cfbfd91..5b1d53da32 100644
--- a/debian/changelog
+++ b/debian/changelog
@@ -1,3 +1,33 @@
+openvswitch (2.11.8-1) unstable; urgency=low
+ [ Open vSwitch team ]
+ * New upstream version
+
+ -- Open vSwitch team <dev@openvswitch.org> Fri, 05 Mar 2021 16:27:47 +0100
+
+openvswitch (2.11.7-1) unstable; urgency=low
+ [ Open vSwitch team ]
+ * New upstream version
+
+ -- Open vSwitch team <dev@openvswitch.org> Fri, 05 Mar 2021 16:27:47 +0100
+
+openvswitch (2.11.6-1) unstable; urgency=low
+ [ Open vSwitch team ]
+ * New upstream version
+
+ -- Open vSwitch team <dev@openvswitch.org> Wed, 10 Feb 2021 16:07:06 +0100
+
+openvswitch (2.11.5-1) unstable; urgency=low
+ [ Open vSwitch team ]
+ * New upstream version
+
+ -- Open vSwitch team <dev@openvswitch.org> Wed, 13 Jan 2021 11:26:35 -0500
+
+openvswitch (2.11.4-1) unstable; urgency=low
+ [ Open vSwitch team ]
+ * New upstream version
+
+ -- Open vSwitch team <dev@openvswitch.org> Thu, 30 Jul 2020 00:25:16 +0200
+
openvswitch (2.11.3-1) unstable; urgency=low
[ Open vSwitch team ]
* New upstream version
diff --git a/dpdk/app/test-crypto-perf/main.c b/dpdk/app/test-crypto-perf/main.c
index 921394799a..8affc5dc95 100644
--- a/dpdk/app/test-crypto-perf/main.c
+++ b/dpdk/app/test-crypto-perf/main.c
@@ -544,7 +544,8 @@ main(int argc, char **argv)
goto err;
}
- if (!opts.silent)
+ if (!opts.silent && opts.test != CPERF_TEST_TYPE_THROUGHPUT &&
+ opts.test != CPERF_TEST_TYPE_LATENCY)
show_test_vector(t_vec);
total_nb_qps = nb_cryptodevs * opts.nb_qps;
diff --git a/dpdk/app/test-eventdev/test_pipeline_common.c b/dpdk/app/test-eventdev/test_pipeline_common.c
index c988da28c9..b586804090 100644
--- a/dpdk/app/test-eventdev/test_pipeline_common.c
+++ b/dpdk/app/test-eventdev/test_pipeline_common.c
@@ -366,12 +366,16 @@ pipeline_event_tx_adapter_setup(struct evt_options *opt,
if (!(cap & RTE_EVENT_ETH_TX_ADAPTER_CAP_INTERNAL_PORT)) {
uint32_t service_id;
- rte_event_eth_tx_adapter_service_id_get(consm,
- &service_id);
+ ret = rte_event_eth_tx_adapter_service_id_get(consm,
+ &service_id);
+ if (ret != -ESRCH && ret != 0) {
+ evt_err("Failed to get Tx adptr service ID");
+ return ret;
+ }
ret = evt_service_setup(service_id);
if (ret) {
evt_err("Failed to setup service core"
- " for Tx adapter\n");
+ " for Tx adapter");
return ret;
}
}
diff --git a/dpdk/app/test-pmd/Makefile b/dpdk/app/test-pmd/Makefile
index d5258eae4a..f36137fd44 100644
--- a/dpdk/app/test-pmd/Makefile
+++ b/dpdk/app/test-pmd/Makefile
@@ -15,6 +15,12 @@ CFLAGS += -O3
CFLAGS += $(WERROR_FLAGS)
CFLAGS += -Wno-deprecated-declarations
+ifeq ($(CONFIG_RTE_TOOLCHAIN_GCC),y)
+ifeq ($(shell test $(GCC_VERSION) -ge 100 && echo 1), 1)
+CFLAGS += -fcommon
+endif
+endif
+
#
# all source are stored in SRCS-y
#
diff --git a/dpdk/app/test-pmd/cmdline.c b/dpdk/app/test-pmd/cmdline.c
index 26295130c5..abf803418c 100644
--- a/dpdk/app/test-pmd/cmdline.c
+++ b/dpdk/app/test-pmd/cmdline.c
@@ -101,7 +101,7 @@ static void cmd_help_brief_parsed(__attribute__((unused)) void *parsed_result,
" help ports : Configuring ports.\n"
" help registers : Reading and setting port registers.\n"
" help filters : Filters configuration help.\n"
- " help traffic_management : Traffic Management commmands.\n"
+ " help traffic_management : Traffic Management commands.\n"
" help all : All of the above sections.\n\n"
);
@@ -4932,7 +4932,7 @@ cmd_gso_size_parsed(void *parsed_result,
if (test_done == 0) {
printf("Before setting GSO segsz, please first"
- " stop fowarding\n");
+ " stop forwarding\n");
return;
}
@@ -16459,8 +16459,10 @@ cmd_ddp_get_list_parsed(
#ifdef RTE_LIBRTE_I40E_PMD
size = PROFILE_INFO_SIZE * MAX_PROFILE_NUM + 4;
p_list = (struct rte_pmd_i40e_profile_list *)malloc(size);
- if (!p_list)
+ if (!p_list) {
printf("%s: Failed to malloc buffer\n", __func__);
+ return;
+ }
if (ret == -ENOTSUP)
ret = rte_pmd_i40e_get_ddp_list(res->port_id,
diff --git a/dpdk/app/test-pmd/config.c b/dpdk/app/test-pmd/config.c
index 6e9a2042c2..0e5d77159d 100644
--- a/dpdk/app/test-pmd/config.c
+++ b/dpdk/app/test-pmd/config.c
@@ -204,11 +204,26 @@ nic_stats_display(portid_t port_id)
void
nic_stats_clear(portid_t port_id)
{
+ int ret;
+
if (port_id_is_invalid(port_id, ENABLED_WARN)) {
print_valid_ports();
return;
}
- rte_eth_stats_reset(port_id);
+
+ ret = rte_eth_stats_reset(port_id);
+ if (ret != 0) {
+ printf("%s: Error: failed to reset stats (port %u): %s",
+ __func__, port_id, strerror(ret));
+ return;
+ }
+
+ ret = rte_eth_stats_get(port_id, &ports[port_id].stats);
+ if (ret != 0) {
+ printf("%s: Error: failed to get stats (port %u): %s",
+ __func__, port_id, strerror(ret));
+ return;
+ }
printf("\n NIC statistics for port %d cleared\n", port_id);
}
@@ -278,11 +293,20 @@ nic_xstats_display(portid_t port_id)
void
nic_xstats_clear(portid_t port_id)
{
+ int ret;
+
if (port_id_is_invalid(port_id, ENABLED_WARN)) {
print_valid_ports();
return;
}
rte_eth_xstats_reset(port_id);
+
+ ret = rte_eth_stats_get(port_id, &ports[port_id].stats);
+ if (ret != 0) {
+ printf("%s: Error: failed to get stats (port %u): %s",
+ __func__, port_id, strerror(ret));
+ return;
+ }
}
void
diff --git a/dpdk/app/test-pmd/csumonly.c b/dpdk/app/test-pmd/csumonly.c
index 46eb52d5b8..b0d528d98c 100644
--- a/dpdk/app/test-pmd/csumonly.c
+++ b/dpdk/app/test-pmd/csumonly.c
@@ -138,21 +138,23 @@ parse_ipv6(struct ipv6_hdr *ipv6_hdr, struct testpmd_offload_info *info)
/*
* Parse an ethernet header to fill the ethertype, l2_len, l3_len and
- * ipproto. This function is able to recognize IPv4/IPv6 with one optional vlan
- * header. The l4_len argument is only set in case of TCP (useful for TSO).
+ * ipproto. This function is able to recognize IPv4/IPv6 with optional VLAN
+ * headers. The l4_len argument is only set in case of TCP (useful for TSO).
*/
static void
parse_ethernet(struct ether_hdr *eth_hdr, struct testpmd_offload_info *info)
{
struct ipv4_hdr *ipv4_hdr;
struct ipv6_hdr *ipv6_hdr;
+ struct vlan_hdr *vlan_hdr;
info->l2_len = sizeof(struct ether_hdr);
info->ethertype = eth_hdr->ether_type;
- if (info->ethertype == _htons(ETHER_TYPE_VLAN)) {
- struct vlan_hdr *vlan_hdr = (struct vlan_hdr *)(eth_hdr + 1);
-
+ while (info->ethertype == _htons(ETHER_TYPE_VLAN) ||
+ info->ethertype == _htons(ETHER_TYPE_QINQ)) {
+ vlan_hdr = (struct vlan_hdr *)
+ ((char *)eth_hdr + info->l2_len);
info->l2_len += sizeof(struct vlan_hdr);
info->ethertype = vlan_hdr->eth_proto;
}
diff --git a/dpdk/app/test-pmd/meson.build b/dpdk/app/test-pmd/meson.build
index 6006c60f99..adeeeeedba 100644
--- a/dpdk/app/test-pmd/meson.build
+++ b/dpdk/app/test-pmd/meson.build
@@ -5,6 +5,11 @@
name = 'testpmd'
allow_experimental_apis = true
cflags += '-Wno-deprecated-declarations'
+
+if (toolchain == 'gcc' and cc.version().version_compare('>=10.0.0'))
+ cflags += '-fcommon'
+endif
+
sources = files('cmdline.c',
'cmdline_flow.c',
'cmdline_mtr.c',
diff --git a/dpdk/app/test-pmd/parameters.c b/dpdk/app/test-pmd/parameters.c
index 4d5e28970c..57028c313f 100644
--- a/dpdk/app/test-pmd/parameters.c
+++ b/dpdk/app/test-pmd/parameters.c
@@ -52,7 +52,7 @@
static void
usage(char* progname)
{
- printf("usage: %s "
+ printf("usage: %s [EAL options] -- "
#ifdef RTE_LIBRTE_CMDLINE
"[--interactive|-i] "
"[--cmdline-file=FILENAME] "
diff --git a/dpdk/app/test-pmd/testpmd.c b/dpdk/app/test-pmd/testpmd.c
index a910c06dc2..a32eae750c 100644
--- a/dpdk/app/test-pmd/testpmd.c
+++ b/dpdk/app/test-pmd/testpmd.c
@@ -2500,7 +2500,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up. speed %u Mbps- %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
@@ -2934,6 +2934,8 @@ get_eth_dcb_conf(portid_t pid, struct rte_eth_conf *eth_conf,
struct rte_eth_dcb_tx_conf *tx_conf =
ð_conf->tx_adv_conf.dcb_tx_conf;
+ memset(&rss_conf, 0, sizeof(struct rte_eth_rss_conf));
+
rc = rte_eth_dev_rss_hash_conf_get(pid, &rss_conf);
if (rc != 0)
return rc;
diff --git a/dpdk/config/meson.build b/dpdk/config/meson.build
index 616af97466..88742ce9db 100644
--- a/dpdk/config/meson.build
+++ b/dpdk/config/meson.build
@@ -111,6 +111,10 @@ warning_flags = [
'-Wcast-qual',
'-Wno-address-of-packed-member'
]
+if cc.get_id() == 'gcc' and cc.version().version_compare('>=10.0')
+# FIXME: Bugzilla 396
+ warning_flags += '-Wno-zero-length-bounds'
+endif
if not dpdk_conf.get('RTE_ARCH_64')
# for 32-bit, don't warn about casting a 32-bit pointer to 64-bit int - it's fine!!
warning_flags += '-Wno-pointer-to-int-cast'
diff --git a/dpdk/devtools/check-symbol-change.sh b/dpdk/devtools/check-symbol-change.sh
index f6f79a883b..2d4f05fdd2 100755
--- a/dpdk/devtools/check-symbol-change.sh
+++ b/dpdk/devtools/check-symbol-change.sh
@@ -17,13 +17,11 @@ build_map_changes()
# map files are altered, and all section/symbol names
# appearing between a triggering of this rule and the
# next trigger of this rule are associated with this file
- /[-+] a\/.*\.map/ {map=$2; in_map=1}
+ /[-+] [ab]\/.*\.map/ {map=$2; in_map=1; next}
- # Same pattern as above, only it matches on anything that
- # does not end in 'map', indicating we have left the map chunk.
- # When we hit this, turn off the in_map variable, which
- # supresses the subordonate rules below
- /[-+] a\/.*\.[^map]/ {in_map=0}
+ # The previous rule catches all .map files, anything else
+ # indicates we left the map chunk.
+ /[-+] [ab]\// {in_map=0}
# Triggering this rule, which starts a line and ends it
# with a { identifies a versioned section. The section name is
diff --git a/dpdk/devtools/checkpatches.sh b/dpdk/devtools/checkpatches.sh
index c471731d45..acff1843af 100755
--- a/dpdk/devtools/checkpatches.sh
+++ b/dpdk/devtools/checkpatches.sh
@@ -56,6 +56,14 @@ check_forbidden_additions() { # <patch>
-f $(dirname $(readlink -e $0))/check-forbidden-tokens.awk \
"$1" || res=1
+ # links must prefer https over http
+ awk -v FOLDERS='doc' \
+ -v EXPRESSIONS='http://.*dpdk.org' \
+ -v RET_ON_FAIL=1 \
+ -v MESSAGE='Using non https link to dpdk.org' \
+ -f $(dirname $(readlink -f $0))/check-forbidden-tokens.awk \
+ "$1" || res=1
+
return $res
}
diff --git a/dpdk/doc/api/doxy-api-index.md b/dpdk/doc/api/doxy-api-index.md
index e27874c5ae..a380f44fbd 100644
--- a/dpdk/doc/api/doxy-api-index.md
+++ b/dpdk/doc/api/doxy-api-index.md
@@ -1,4 +1,4 @@
-API {#index}
+API
===
<!--
diff --git a/dpdk/doc/api/doxy-api.conf.in b/dpdk/doc/api/doxy-api.conf.in
index 77ba327a88..f0da8bd9e5 100644
--- a/dpdk/doc/api/doxy-api.conf.in
+++ b/dpdk/doc/api/doxy-api.conf.in
@@ -3,6 +3,7 @@
PROJECT_NAME = DPDK
PROJECT_NUMBER = @VERSION@
+USE_MDFILE_AS_MAINPAGE = @TOPDIR@/doc/api/doxy-api-index.md
INPUT = @TOPDIR@/doc/api/doxy-api-index.md \
@TOPDIR@/drivers/crypto/scheduler \
@TOPDIR@/drivers/mempool/dpaa2 \
diff --git a/dpdk/doc/guides/conf.py b/dpdk/doc/guides/conf.py
index 2ebbf50c60..5fc597cbe7 100644
--- a/dpdk/doc/guides/conf.py
+++ b/dpdk/doc/guides/conf.py
@@ -318,16 +318,22 @@ def print_table_css(outfile, table_id):
cursor: default;
overflow: hidden;
}
+ table#idx p {
+ margin: 0;
+ line-height: inherit;
+ }
table#idx th, table#idx td {
text-align: center;
+ border: solid 1px #ddd;
}
table#idx th {
- font-size: 72%;
+ padding: 0.5em 0;
+ }
+ table#idx th, table#idx th p {
+ font-size: 11px;
white-space: pre-wrap;
vertical-align: top;
- padding: 0.5em 0;
min-width: 0.9em;
- width: 2em;
}
table#idx col:first-child {
width: 0;
@@ -336,9 +342,11 @@ def print_table_css(outfile, table_id):
vertical-align: bottom;
}
table#idx td {
- font-size: 70%;
padding: 1px;
}
+ table#idx td, table#idx td p {
+ font-size: 11px;
+ }
table#idx td:first-child {
padding-left: 1em;
text-align: left;
@@ -414,4 +422,8 @@ def setup(app):
# Process the numref references once the doctree has been created.
app.connect('doctree-resolved', process_numref)
- app.add_stylesheet('css/custom.css')
+ try:
+ # New function in sphinx 1.8
+ app.add_css_file('css/custom.css')
+ except:
+ app.add_stylesheet('css/custom.css')
diff --git a/dpdk/doc/guides/contributing/documentation.rst b/dpdk/doc/guides/contributing/documentation.rst
index a45b62bad3..8c782531d9 100644
--- a/dpdk/doc/guides/contributing/documentation.rst
+++ b/dpdk/doc/guides/contributing/documentation.rst
@@ -83,7 +83,7 @@ added to by the developer.
* **API documentation**
The API documentation explains how to use the public DPDK functions.
- The `API index page <http://doc.dpdk.org/api/>`_ shows the generated API documentation with related groups of functions.
+ The `API index page <https://doc.dpdk.org/api/>`_ shows the generated API documentation with related groups of functions.
The API documentation should be updated via Doxygen comments when new functions are added.
@@ -562,14 +562,14 @@ Hyperlinks
~~~~~~~~~~
* Links to external websites can be plain URLs.
- The following is rendered as http://dpdk.org::
+ The following is rendered as https://dpdk.org::
- http://dpdk.org
+ https://dpdk.org
* They can contain alternative text.
- The following is rendered as `Check out DPDK <http://dpdk.org>`_::
+ The following is rendered as `Check out DPDK <https://dpdk.org>`_::
- `Check out DPDK <http://dpdk.org>`_
+ `Check out DPDK <https://dpdk.org>`_
* An internal link can be generated by placing labels in the document with the format ``.. _label_name``.
@@ -667,7 +667,7 @@ The following are some guidelines for use of Doxygen in the DPDK API documentati
*/
In the API documentation the functions will be rendered as links, see the
- `online section of the rte_ethdev.h docs <http://doc.dpdk.org/api/rte__ethdev_8h.html>`_ that contains the above text.
+ `online section of the rte_ethdev.h docs <https://doc.dpdk.org/api/rte__ethdev_8h.html>`_ that contains the above text.
* The ``@see`` keyword can be used to create a *see also* link to another file or library.
This directive should be placed on one line at the bottom of the documentation section.
diff --git a/dpdk/doc/guides/contributing/patches.rst b/dpdk/doc/guides/contributing/patches.rst
index 02cd0555a4..28d4b67d66 100644
--- a/dpdk/doc/guides/contributing/patches.rst
+++ b/dpdk/doc/guides/contributing/patches.rst
@@ -28,9 +28,9 @@ The DPDK development process has the following features:
* All sub-repositories are merged into main repository for ``-rc1`` and ``-rc2`` versions of the release.
* After the ``-rc2`` release all patches should target the main repository.
-The mailing list for DPDK development is `dev@dpdk.org <http://mails.dpdk.org/archives/dev/>`_.
-Contributors will need to `register for the mailing list <http://mails.dpdk.org/listinfo/dev>`_ in order to submit patches.
-It is also worth registering for the DPDK `Patchwork <http://patches.dpdk.org/project/dpdk/list/>`_
+The mailing list for DPDK development is `dev@dpdk.org <https://mails.dpdk.org/archives/dev/>`_.
+Contributors will need to `register for the mailing list <https://mails.dpdk.org/listinfo/dev>`_ in order to submit patches.
+It is also worth registering for the DPDK `Patchwork <https://patches.dpdk.org/project/dpdk/list/>`_
If you are using the GitHub service, you can link your repository to
the ``travis-ci.org`` build service. When you push patches to your GitHub
@@ -132,12 +132,12 @@ The source code can be cloned using either of the following:
main repository::
git clone git://dpdk.org/dpdk
- git clone http://dpdk.org/git/dpdk
+ git clone https://dpdk.org/git/dpdk
-sub-repositories (`list <http://git.dpdk.org/next>`_)::
+sub-repositories (`list <https://git.dpdk.org/next>`_)::
git clone git://dpdk.org/next/dpdk-next-*
- git clone http://dpdk.org/git/next/dpdk-next-*
+ git clone https://dpdk.org/git/next/dpdk-next-*
Make your Changes
-----------------
@@ -174,7 +174,7 @@ A good way of thinking about whether a patch should be split is to consider whet
applied without dependencies as a backport.
It is better to keep the related documentation changes in the same patch
-file as the code, rather than one big documentation patch at then end of a
+file as the code, rather than one big documentation patch at the end of a
patchset. This makes it easier for future maintenance and development of the
code.
@@ -312,7 +312,7 @@ Patch for Stable Releases
~~~~~~~~~~~~~~~~~~~~~~~~~
All fix patches to the master branch that are candidates for backporting
-should also be CCed to the `stable@dpdk.org <http://mails.dpdk.org/listinfo/stable>`_
+should also be CCed to the `stable@dpdk.org <https://mails.dpdk.org/listinfo/stable>`_
mailing list.
In the commit message body the Cc: stable@dpdk.org should be inserted as follows::
@@ -406,7 +406,7 @@ files, in order of preference::
~/.config/dpdk/devel.config
/etc/dpdk/devel.config.
-Once the environment variable the script can be run as follows::
+Once the environment variable is set, the script can be run as follows::
devtools/checkpatches.sh ~/patch/
@@ -513,7 +513,7 @@ If the patch is in relation to a previous email thread you can add it to the sam
git send-email --to dev@dpdk.org --in-reply-to <1234-foo@bar.com> 000*.patch
The Message ID can be found in the raw text of emails or at the top of each Patchwork patch,
-`for example <http://patches.dpdk.org/patch/7646/>`_.
+`for example <https://patches.dpdk.org/patch/7646/>`_.
Shallow threading (``--thread --no-chain-reply-to``) is preferred for a patch series.
Once submitted your patches will appear on the mailing list and in Patchwork.
diff --git a/dpdk/doc/guides/contributing/stable.rst b/dpdk/doc/guides/contributing/stable.rst
index 2ac4f0a88b..88b46aee24 100644
--- a/dpdk/doc/guides/contributing/stable.rst
+++ b/dpdk/doc/guides/contributing/stable.rst
@@ -96,7 +96,7 @@ The Stable and LTS release are coordinated on the stable@dpdk.org mailing
list.
All fix patches to the master branch that are candidates for backporting
-should also be CCed to the `stable@dpdk.org <http://mails.dpdk.org/listinfo/stable>`_
+should also be CCed to the `stable@dpdk.org <https://mails.dpdk.org/listinfo/stable>`_
mailing list.
@@ -107,10 +107,10 @@ A Stable Release will be released by:
* Tagging the release with YY.MM.n (year, month, number).
* Uploading a tarball of the release to dpdk.org.
-* Sending an announcement to the `announce@dpdk.org <http://mails.dpdk.org/listinfo/announce>`_
+* Sending an announcement to the `announce@dpdk.org <https://mails.dpdk.org/listinfo/announce>`_
list.
-Stable releases are available on the `dpdk.org download page <http://core.dpdk.org/download/>`_.
+Stable releases are available on the `dpdk.org download page <https://core.dpdk.org/download/>`_.
ABI
diff --git a/dpdk/doc/guides/cryptodevs/aesni_gcm.rst b/dpdk/doc/guides/cryptodevs/aesni_gcm.rst
index fb74179b84..77f45b8a26 100644
--- a/dpdk/doc/guides/cryptodevs/aesni_gcm.rst
+++ b/dpdk/doc/guides/cryptodevs/aesni_gcm.rst
@@ -45,6 +45,20 @@ can be downloaded in `<https://github.com/01org/intel-ipsec-mb/archive/v0.50.zip
make
make install
+The library requires NASM to be built. Depending on the library version, it might
+require a minimum NASM version (e.g. v0.54 requires at least NASM 2.14).
+
+NASM is packaged for different OS. However, on some OS the version is too old,
+so a manual installation is required. In that case, NASM can be downloaded from
+`NASM website <https://www.nasm.us/pub/nasm/releasebuilds/?C=M;O=D>`_.
+Once it is downloaded, extract it and follow these steps:
+
+.. code-block:: console
+
+ ./configure
+ make
+ make install
+
As a reference, the following table shows a mapping between the past DPDK versions
and the external crypto libraries supported by them:
diff --git a/dpdk/doc/guides/cryptodevs/aesni_mb.rst b/dpdk/doc/guides/cryptodevs/aesni_mb.rst
index 2c8ccc3d45..012726b3c7 100644
--- a/dpdk/doc/guides/cryptodevs/aesni_mb.rst
+++ b/dpdk/doc/guides/cryptodevs/aesni_mb.rst
@@ -69,6 +69,20 @@ can be downloaded from `<https://github.com/01org/intel-ipsec-mb/archive/v0.51.z
make
make install
+The library requires NASM to be built. Depending on the library version, it might
+require a minimum NASM version (e.g. v0.54 requires at least NASM 2.14).
+
+NASM is packaged for different OS. However, on some OS the version is too old,
+so a manual installation is required. In that case, NASM can be downloaded from
+`NASM website <https://www.nasm.us/pub/nasm/releasebuilds/?C=M;O=D>`_.
+Once it is downloaded, extract it and follow these steps:
+
+.. code-block:: console
+
+ ./configure
+ make
+ make install
+
As a reference, the following table shows a mapping between the past DPDK versions
and the Multi-Buffer library version supported by them:
diff --git a/dpdk/doc/guides/eventdevs/index.rst b/dpdk/doc/guides/eventdevs/index.rst
index f7382dc8a3..ce8b73cb86 100644
--- a/dpdk/doc/guides/eventdevs/index.rst
+++ b/dpdk/doc/guides/eventdevs/index.rst
@@ -5,7 +5,7 @@ Event Device Drivers
====================
The following are a list of event device PMDs, which can be used from an
-application trough the eventdev API.
+application through the eventdev API.
.. toctree::
:maxdepth: 2
diff --git a/dpdk/doc/guides/freebsd_gsg/install_from_ports.rst b/dpdk/doc/guides/freebsd_gsg/install_from_ports.rst
index 253328eb10..2ac27f115c 100644
--- a/dpdk/doc/guides/freebsd_gsg/install_from_ports.rst
+++ b/dpdk/doc/guides/freebsd_gsg/install_from_ports.rst
@@ -62,7 +62,7 @@ environmental variables should be set as below:
.. note::
To install a copy of the DPDK compiled using gcc, please download the
- official DPDK package from http://core.dpdk.org/download/ and install manually using
+ official DPDK package from https://core.dpdk.org/download/ and install manually using
the instructions given in the next chapter, :ref:`building_from_source`
An example application can therefore be copied to a user's home directory and
diff --git a/dpdk/doc/guides/linux_gsg/eal_args.include.rst b/dpdk/doc/guides/linux_gsg/eal_args.include.rst
index cf421a56eb..7251fe9c2f 100644
--- a/dpdk/doc/guides/linux_gsg/eal_args.include.rst
+++ b/dpdk/doc/guides/linux_gsg/eal_args.include.rst
@@ -126,7 +126,7 @@ Debugging options
Specify log level for a specific component. For example::
- --log-level eal:8
+ --log-level lib.eal:debug
Can be specified multiple times.
diff --git a/dpdk/doc/guides/linux_gsg/nic_perf_intel_platform.rst b/dpdk/doc/guides/linux_gsg/nic_perf_intel_platform.rst
index 4e9afbdbc1..5fa6e3899d 100644
--- a/dpdk/doc/guides/linux_gsg/nic_perf_intel_platform.rst
+++ b/dpdk/doc/guides/linux_gsg/nic_perf_intel_platform.rst
@@ -64,7 +64,7 @@ This aligns with the previous output which showed that each channel has one memo
Network Interface Card Requirements
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-Use a `DPDK supported <http://core.dpdk.org/supported/>`_ high end NIC such as the Intel XL710 40GbE.
+Use a `DPDK supported <https://core.dpdk.org/supported/>`_ high end NIC such as the Intel XL710 40GbE.
Make sure each NIC has been flashed the latest version of NVM/firmware.
diff --git a/dpdk/doc/guides/nics/enic.rst b/dpdk/doc/guides/nics/enic.rst
index 773f13b0fc..c06363fc27 100644
--- a/dpdk/doc/guides/nics/enic.rst
+++ b/dpdk/doc/guides/nics/enic.rst
@@ -14,7 +14,7 @@ How to obtain ENIC PMD integrated DPDK
--------------------------------------
ENIC PMD support is integrated into the DPDK suite. dpdk-<version>.tar.gz
-should be downloaded from http://core.dpdk.org/download/
+should be downloaded from https://core.dpdk.org/download/
Configuration information
diff --git a/dpdk/doc/guides/nics/fail_safe.rst b/dpdk/doc/guides/nics/fail_safe.rst
index 6c02d7ef6d..60bbf40f7f 100644
--- a/dpdk/doc/guides/nics/fail_safe.rst
+++ b/dpdk/doc/guides/nics/fail_safe.rst
@@ -49,7 +49,7 @@ The Fail-safe PMD can be used like most other DPDK virtual devices, by passing a
``--vdev`` parameter to the EAL when starting the application. The device name
must start with the *net_failsafe* prefix, followed by numbers or letters. This
name must be unique for each device. Each fail-safe instance must have at least one
-sub-device, up to ``RTE_MAX_ETHPORTS-1``.
+sub-device, and at most two.
A sub-device can be any legal DPDK device, including possibly another fail-safe
instance.
diff --git a/dpdk/doc/guides/nics/features/avf.ini b/dpdk/doc/guides/nics/features/avf.ini
index 35ceada24f..28d072f37e 100644
--- a/dpdk/doc/guides/nics/features/avf.ini
+++ b/dpdk/doc/guides/nics/features/avf.ini
@@ -15,7 +15,6 @@ TSO = Y
Promiscuous mode = Y
Allmulticast mode = Y
Unicast MAC filter = Y
-Multicast MAC filter = Y
RSS hash = Y
RSS key update = Y
RSS reta update = Y
diff --git a/dpdk/doc/guides/nics/features/avf_vec.ini b/dpdk/doc/guides/nics/features/avf_vec.ini
index 3050bc4a60..3b051f0d6f 100644
--- a/dpdk/doc/guides/nics/features/avf_vec.ini
+++ b/dpdk/doc/guides/nics/features/avf_vec.ini
@@ -15,7 +15,6 @@ TSO = Y
Promiscuous mode = Y
Allmulticast mode = Y
Unicast MAC filter = Y
-Multicast MAC filter = Y
RSS hash = Y
RSS key update = Y
RSS reta update = Y
diff --git a/dpdk/doc/guides/nics/features/i40e.ini b/dpdk/doc/guides/nics/features/i40e.ini
index 16eab7f43b..b0a9c20e6a 100644
--- a/dpdk/doc/guides/nics/features/i40e.ini
+++ b/dpdk/doc/guides/nics/features/i40e.ini
@@ -17,7 +17,6 @@ TSO = Y
Promiscuous mode = Y
Allmulticast mode = Y
Unicast MAC filter = Y
-Multicast MAC filter = Y
RSS hash = Y
RSS key update = Y
RSS reta update = Y
diff --git a/dpdk/doc/guides/nics/features/igb.ini b/dpdk/doc/guides/nics/features/igb.ini
index c53fd0757e..b66aa1de19 100644
--- a/dpdk/doc/guides/nics/features/igb.ini
+++ b/dpdk/doc/guides/nics/features/igb.ini
@@ -15,6 +15,7 @@ TSO = Y
Promiscuous mode = Y
Allmulticast mode = Y
Unicast MAC filter = Y
+Multicast MAC filter = Y
RSS hash = Y
RSS key update = Y
RSS reta update = Y
diff --git a/dpdk/doc/guides/nics/features/ixgbe.ini b/dpdk/doc/guides/nics/features/ixgbe.ini
index 4143111769..2ec3552599 100644
--- a/dpdk/doc/guides/nics/features/ixgbe.ini
+++ b/dpdk/doc/guides/nics/features/ixgbe.ini
@@ -17,6 +17,7 @@ TSO = Y
Promiscuous mode = Y
Allmulticast mode = Y
Unicast MAC filter = Y
+Multicast MAC filter = Y
RSS hash = Y
RSS key update = Y
RSS reta update = Y
diff --git a/dpdk/doc/guides/nics/i40e.rst b/dpdk/doc/guides/nics/i40e.rst
index 62e90d9fd2..01fa817a6d 100644
--- a/dpdk/doc/guides/nics/i40e.rst
+++ b/dpdk/doc/guides/nics/i40e.rst
@@ -642,6 +642,15 @@ Use 16 Bytes RX Descriptor Size
As i40e PMD supports both 16 and 32 bytes RX descriptor sizes, and 16 bytes size can provide helps to high performance of small packets.
Configuration of ``CONFIG_RTE_LIBRTE_I40E_16BYTE_RX_DESC`` in config files can be changed to use 16 bytes size RX descriptors.
+Input set requirement of each pctype for FDIR
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Each PCTYPE can only have one specific FDIR input set at one time.
+For example, if creating 2 rte_flow rules with different input set for one PCTYPE,
+it will fail and return the info "Conflict with the first rule's input set",
+which means the current rule's input set conflicts with the first rule's.
+Remove the first rule if want to change the input set of the PCTYPE.
+
Example of getting best performance with l3fwd example
------------------------------------------------------
diff --git a/dpdk/doc/guides/prog_guide/cryptodev_lib.rst b/dpdk/doc/guides/prog_guide/cryptodev_lib.rst
index 7a95053ad5..53d797bcc1 100644
--- a/dpdk/doc/guides/prog_guide/cryptodev_lib.rst
+++ b/dpdk/doc/guides/prog_guide/cryptodev_lib.rst
@@ -1043,4 +1043,4 @@ Asymmetric Crypto Device API
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The cryptodev Library API is described in the
-`DPDK API Reference <http://doc.dpdk.org/api/>`_
+`DPDK API Reference <https://doc.dpdk.org/api/>`_
diff --git a/dpdk/doc/guides/prog_guide/env_abstraction_layer.rst b/dpdk/doc/guides/prog_guide/env_abstraction_layer.rst
index a7536a80e1..67e65491a3 100644
--- a/dpdk/doc/guides/prog_guide/env_abstraction_layer.rst
+++ b/dpdk/doc/guides/prog_guide/env_abstraction_layer.rst
@@ -344,6 +344,37 @@ Misc Functions
Locks and atomic operations are per-architecture (i686 and x86_64).
+IOVA Mode Detection
+~~~~~~~~~~~~~~~~~~~
+
+IOVA Mode is selected by considering what the current usable Devices on the
+system require and/or support.
+
+Below is the 2-step heuristic for this choice.
+
+For the first step, EAL asks each bus its requirement in terms of IOVA mode
+and decides on a preferred IOVA mode.
+
+- if all buses report RTE_IOVA_PA, then the preferred IOVA mode is RTE_IOVA_PA,
+- if all buses report RTE_IOVA_VA, then the preferred IOVA mode is RTE_IOVA_VA,
+- if all buses report RTE_IOVA_DC, no bus expressed a preferrence, then the
+ preferred mode is RTE_IOVA_DC,
+- if the buses disagree (at least one wants RTE_IOVA_PA and at least one wants
+ RTE_IOVA_VA), then the preferred IOVA mode is RTE_IOVA_DC (see below with the
+ check on Physical Addresses availability),
+
+The second step checks if the preferred mode complies with the Physical
+Addresses availability since those are only available to root user in recent
+kernels.
+
+- if the preferred mode is RTE_IOVA_PA but there is no access to Physical
+ Addresses, then EAL init fails early, since later probing of the devices
+ would fail anyway,
+- if the preferred mode is RTE_IOVA_DC then based on the Physical Addresses
+ availability, the preferred mode is adjusted to RTE_IOVA_PA or RTE_IOVA_VA.
+ In the case when the buses had disagreed on the IOVA Mode at the first step,
+ part of the buses won't work because of this decision.
+
IOVA Mode Configuration
~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/dpdk/doc/guides/rel_notes/release_18_11.rst b/dpdk/doc/guides/rel_notes/release_18_11.rst
index 9e3686bed1..b2d3851c1c 100644
--- a/dpdk/doc/guides/rel_notes/release_18_11.rst
+++ b/dpdk/doc/guides/rel_notes/release_18_11.rst
@@ -2964,3 +2964,457 @@ Fixes skipped and status unresolved
* 207b1c813 test: fix build without ring PMD
* 819d0d1d5 net/ixgbe: fix blocking system events
* 050bfe033 net/mlx5: fix tunnel flow priority
+
+18.11.8 Release Notes
+---------------------
+
+18.11.8 Fixes
+~~~~~~~~~~~~~
+
+* vhost: check log mmap offset and size overflow
+* vhost/crypto: validate keys lengths
+* vhost: fix vring index check
+
+18.11.8 Validation
+~~~~~~~~~~~~~~~~~~
+
+* Red Hat(R) Testing
+
+ * RHEL 8
+ * Functionality
+
+ * PF assignment
+ * VF assignment
+ * vhost single/multi queues and cross-NUMA
+ * vhostclient reconnect
+ * vhost live migration with single/multi queues and cross-NUMA
+ * OVS PVP
+
+ * Tested NICs
+
+ * X540-AT2 NIC(ixgbe, 10G)
+
+* Intel(R) Testing
+
+ * Virtio features
+
+ * vhost/virtio loopback test with virtio user as server mode
+ * loopback multi queues
+ * loopback multi paths port restart
+ * vhost/virtio pvp multi-paths performance
+ * pvp multi-queues and port restart
+ * vhost dequeue zero copy
+ * pvp share lib
+ * pvp vhost user reconnect
+ * pvp test with 4k pages
+ * pvp test with 2M hugepages
+ * pvp virtio bonding
+ * pvp test with diff qemu version
+ * vhost enqueue interrupt
+ * vhost event idx interrupt
+ * vhost virtio pmd interrupt
+ * vhost virtio user interrupt
+ * virtio event idx interrupt
+ * virtio user for container networking
+ * virtio user as exceptional path
+ * vhost xstats
+ * virtio-pmd multi-process
+ * vm2vm virtio pmd
+ * vm2vm virtio-net iperf
+ * vm2vm virtio-user
+ * vhost user live migration
+
+18.11.8 Known Issues
+~~~~~~~~~~~~~~~~~~~~
+
+* DPDK 18.11.8 contains fixes up to DPDK v20.02 and fixes for CVE-2020-10722, CVE-2020-10723 and CVE-2020-10724
+* Issues identified/fixed in DPDK master branch after DPDK v20.02 may be present in DPDK 18.11.8
+
+18.11.8 Fixes skipped and status unresolved
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+* dcfbc594f net/iavf: fix queue interrupt for ice
+* b149a7064 eal/freebsd: add config reattach in secondary process
+* a135e050a examples/ipsec-secgw: fix packet length
+* 9d10f53e4 test/metrics: fix second run
+* ea81c1b81 net/mlx5: fix NVGRE matching
+* 721c95301 net/mlx5: fix Rx scatter mode validation
+* be048a1aa net/virtio: fix descriptor addressed in Tx
+* 6080796f6 mem: make base address hint OS specific
+* 6d3f9917f eal: fix memory config allocation for multi-process
+* 1526dd053 net/virtio: fix Tx checksum offloads
+* f0617163b mempool/dpaa2: report error on endless loop in mbuf release
+* 05817057f net/ena: fix indication of bad L4 Rx checksums
+* 9e0d81c1a net/mlx5: fix selection between encap and decap
+* 7392ad06f app/testpmd: use better randomness for Tx split
+* dcd05da0a app/testpmd: fix GENEVE flow item
+* 2e02a2aff ethdev: fix VLAN offloads set if no driver callback
+* ec8615607 crypto/dpaa_sec: fix IOVA conversions
+* 06387be8e net/mlx5: fix encap/decap validation
+* 7593cf1d3 net/mlx5: fix legacy multi-packet write session
+* e21492a51 net/mlx: fix overlinking with meson and glue dlopen
+* 150c9ac2d app/testpmd: update Rx offload after setting MTU
+* 207b1c813 test: fix build without ring PMD
+* 819d0d1d5 net/ixgbe: fix blocking system events
+* 050bfe033 net/mlx5: fix tunnel flow priority
+
+18.11.9 Release Notes
+---------------------
+
+18.11.9 Fixes
+~~~~~~~~~~~~~
+
+* app/crypto-perf: fix display of sample test vector
+* app/eventdev: check Tx adapter service ID
+* app: fix usage help of options separated by dashes
+* app/pipeline: fix build with gcc 10
+* app: remove extra new line after link duplex
+* app/testpmd: add parsing for QinQ VLAN headers
+* app/testpmd: disable gcc 10 -fno-common build errors
+* app/testpmd: fix DCB set
+* app/testpmd: fix memory failure handling for i40e DDP
+* app/testpmd: fix statistics after reset
+* bbdev: fix doxygen comments
+* build: disable gcc 10 zero-length-bounds warning
+* bus/fslmc: fix dereferencing null pointer
+* bus/fslmc: fix size of qman fq descriptor
+* bus/pci: fix devargs on probing again
+* bus/pci: fix UIO resource access from secondary process
+* bus/pci: fix VF memory access
+* bus/vmbus: fix comment spelling
+* contigmem: cleanup properly when load fails
+* crypto/caam_jr: fix check of file descriptors
+* crypto/caam_jr: fix IRQ functions return type
+* crypto/ccp: fix fd leak on probe failure
+* cryptodev: fix SHA-1 digest enum comment
+* crypto/kasumi: fix extern declaration
+* crypto/octeontx: fix build with gcc 10
+* crypto/octeontx: fix gcc 10 -fno-common build errors
+* crypto/openssl: fix out-of-place encryption
+* crypto/qat: fix cipher descriptor for ZUC and SNOW
+* devtools: fix symbol map change check
+* doc: add i40e limitation for flow director
+* doc: add NASM installation steps
+* doc: fix API index
+* doc: fix build with doxygen 1.8.18
+* doc: fix log level example in Linux guide
+* doc: fix matrix CSS for recent sphinx
+* doc: fix multicast filter feature announcement
+* doc: fix number of failsafe sub-devices
+* doc: fix sphinx compatibility
+* doc: fix typo in contributors guide
+* doc: fix typo in contributors guide
+* doc: prefer https when pointing to dpdk.org
+* drivers: add crypto as dependency for event drivers
+* drivers/crypto: disable gcc 10 fno-common errors
+* drivers/crypto: fix log type variables for -fno-common
+* drivers: fix log type variables for -fno-common
+* eal/arm64: fix precise TSC
+* eal: fix C++17 compilation
+* eal: fix comments spelling
+* eal: fix log message print for regex
+* eal: fix typo in endian conversion macros
+* eal/ppc: fix build with gcc 9.3
+* eal/x86: ignore gcc 10 stringop-overflow warnings
+* ethdev: fix build when vtune profiling is on
+* ethdev: fix spelling
+* eventdev: fix probe and remove for secondary process
+* event/dsw: avoid reusing previously recorded events
+* event/dsw: fix enqueue burst return value
+* event/dsw: remove redundant control ring poll
+* event/dsw: remove unnecessary read barrier
+* examples/eventdev: fix build with gcc 10
+* examples/eventdev: fix crash on exit
+* examples/ip_pipeline: remove check of null response
+* examples/kni: fix crash during MTU set
+* examples/kni: fix MTU change to setup Tx queue
+* examples/l2fwd-keepalive: fix mbuf pool size
+* examples: remove extra new line after link duplex
+* examples/vmdq: fix output of pools/queues
+* examples/vmdq: fix RSS configuration
+* examples/vm_power: drop Unix path limit redefinition
+* examples/vm_power: fix build because of missing include
+* examples/vm_power: fix build with -fno-common
+* fix same typo in multiple places
+* fix various typos found by Lintian
+* kni: fix ethtool build with kernel 5.6
+* kni: fix ethtool dev_open build error
+* kni: fix ethtool maybe-uninitialized warnings
+* kni: fix ethtool pointer type build error
+* kni: fix gcc 10 ethtool build error
+* kvargs: fix buffer overflow when parsing list
+* kvargs: fix invalid token parsing on FreeBSD
+* kvargs: fix strcmp helper documentation
+* log: fix level picked with globbing on type register
+* lpm6: fix comments spelling
+* lpm6: fix size of tbl8 group
+* mem: fix overflow on allocation
+* mem: mark pages as not accessed when freeing memory
+* mem: mark pages as not accessed when reserving VA
+* mempool/dpaa2: install missing header with meson
+* mlx5: fix build with -fno-common
+* net/avp: fix gcc 10 maybe-uninitialized warning
+* net/bnxt: do not use PMD log type
+* net/bnxt: fix error log for command timeout
+* net/bnxt: fix FW version query
+* net/bnxt: fix using RSS config struct
+* net/bnxt: fix VLAN add when port is stopped
+* net/dpaa2: fix 10G port negotiation
+* net/dpaa: use dynamic log type
+* net/e1000: fix port hotplug for multi-process
+* net/ena/base: fix documentation of functions
+* net/ena/base: fix indentation in CQ polling
+* net/ena/base: fix indentation of multiple defines
+* net/ena/base: fix testing for supported hash function
+* net/ena/base: make allocation macros thread-safe
+* net/ena/base: prevent allocation of zero sized memory
+* net/ena: set IO ring size to valid value
+* net/failsafe: fix fd leak
+* net/i40e/base: update copyright
+* net/i40e: fix flow director for ARP packets
+* net/i40e: fix flush of flow director filter
+* net/i40e: fix queue related exception handling
+* net/i40e: fix setting L2TAG
+* net/i40e: fix wild pointer
+* net/i40e: fix X722 performance
+* net/i40e: relax barrier in Tx for NEON
+* net/iavf: fix setting L2TAG
+* net/iavf: fix stats query error code
+* net/ixgbe/base: update copyright
+* net/ixgbe: check driver type in MACsec API
+* net/ixgbe: fix link status synchronization on BSD
+* net/ixgbe: fix statistics in flow control mode
+* net/mlx4: fix build with -fno-common
+* net/mlx4: fix drop queue error handling
+* net/mlx4: remove device register remap
+* net/mlx5: fix CVLAN tag set in IP item translation
+* net/mlx5: fix mask used for IPv6 item validation
+* net/mlx5: fix matching for UDP tunnels with Verbs
+* net/mlx5: fix mlx5 devices port naming
+* net/mlx5: fix recursive inclusion of header file
+* net/mlx5: fix RSS enablement
+* net/mlx5: fix Tx queue release debug log timing
+* net/mlx5: fix validation of VXLAN/VXLAN-GPE specs
+* net/mlx5: remove device register remap
+* net/mvneta: do not use PMD log type
+* net/mvpp2: fix build with gcc 10
+* net/netvsc: avoid possible live lock
+* net/netvsc: fix comment spelling
+* net/netvsc: fix memory free on device close
+* net/netvsc: handle Rx packets during multi-channel setup
+* net/netvsc: handle Tx completions based on burst size
+* net/netvsc: propagate descriptor limits from VF
+* net/netvsc: remove process event optimization
+* net/netvsc: split send buffers from Tx descriptors
+* net/null: fix secondary burst function selection
+* net/null: remove redundant check
+* net/octeontx: fix dangling pointer on init failure
+* net/octeontx: fix meson build for disabled drivers
+* net/qede: fix link state configuration
+* net/qede: fix port reconfiguration
+* net/ring: fix device pointer on allocation
+* net/sfc/base: fix manual filter delete in EF10
+* net/sfc/base: handle manual and auto filter clashes in EF10
+* net/sfc/base: reduce filter priorities to implemented only
+* net/sfc/base: refactor filter lookup loop in EF10
+* net/sfc/base: reject automatic filter creation by users
+* net/sfc: fix initialization error path
+* net/sfc: fix reported promiscuous/multicast mode
+* net/sfc: fix Rx queue start failure path
+* net/softnic: fix memory leak for thread
+* net/softnic: fix resource leak for pipeline
+* net/tap: do not use PMD log type
+* net/tap: fix check for mbuf number of segment
+* net/tap: fix crash in flow destroy
+* net/tap: fix fd leak on creation failure
+* net/tap: fix file close on remove
+* net/tap: fix mbuf and mem leak during queue release
+* net/tap: fix mbuf double free when writev fails
+* net/tap: fix queues fd check before close
+* net/tap: fix unexpected link handler
+* net/tap: remove unused assert
+* net/thunderx: use dynamic log type
+* net/vhost: fix potential memory leak on close
+* net/virtio: do not use PMD log type
+* net/virtio: fix outdated comment
+* net/virtio-user: fix devargs parsing
+* net/vmxnet3: handle bad host framing
+* pci: accept 32-bit domain numbers
+* pci: fix build on ppc
+* pci: reject negative values in PCI id
+* remove references to private PCI probe function
+* security: fix crash at accessing non-implemented ops
+* security: fix return types in documentation
+* security: fix session counter
+* security: fix verification of parameters
+* service: fix crash on exit
+* service: fix identification of service running on other lcore
+* service: fix race condition for MT unsafe service
+* service: remove rte prefix from static functions
+* test/crypto: fix flag check
+* test/flow_classify: enable multi-sockets system
+* test/kvargs: fix invalid cases check
+* test/kvargs: fix to consider empty elements as valid
+* test: remove redundant macro
+* test: skip some subtests in no-huge mode
+* usertools: check for pci.ids in /usr/share/misc
+* version: 18.11.9-rc1
+* version: 18.11.9-rc2
+* vfio: fix race condition with sysfs
+* vfio: fix use after free with multiprocess
+* vhost/crypto: add missing user protocol flag
+* vhost: fix peer close check
+* vhost: fix zero-copy server mode
+* vhost: make IOTLB cache name unique among processes
+* vhost: prevent zero-copy with incompatible client mode
+* vhost: remove unused variable
+* vhost: remove zero-copy and client mode restriction
+
+18.11.9 Validation
+~~~~~~~~~~~~~~~~~~
+
+* Intel(R) Testing
+
+ * Basic Intel(R) NIC(ixgbe and i40e) testing
+
+ * PF (i40e)
+ * PF (ixgbe)
+ * VF (i40e)
+ * Compile Testing
+ * Intel NIC single core/NIC performance
+
+ * Basic cryptodev and virtio testing
+
+ * vhost/virtio basic loopback, PVP and performance test
+ * cryptodev function
+ * cryptodev performance
+
+* Red Hat(R) Testing
+
+ * RHEL 8
+ * QEMU 5.0
+ * Functionality
+
+ * PF assignment
+ * VF assignment
+ * vhost single/multi queues and cross-NUMA
+ * vhostclient reconnect
+ * vhost live migration with single/multi queues and cross-NUMA
+ * OVS PVP
+
+ * Tested NICs
+
+ * X540-AT2 NIC(ixgbe, 10G)
+
+* Mellanox(R) Testing
+
+ * Basic functionality with testpmd
+
+ * Tx/Rx
+ * xstats
+ * Timestamps
+ * Link status
+ * RTE flow and flow_director
+ * RSS
+ * VLAN stripping and insertion
+ * Checksum/TSO
+ * ptype
+
+ * l3fwd-power example app tests
+ * Multi-process
+
+ * ConnectX-4 Lx
+
+ * RHEL 7.4
+ * Driver MLNX_OFED_LINUX-5.0-2.1.8.0
+ * fw 14.27.1016
+
+ * ConnectX-5
+
+ * RHEL 7.4
+ * Driver MLNX_OFED_LINUX-5.0-1.0.0.0
+ * fw 16.27.2008
+
+* Intel(R) Testing with Open vSwitch
+
+ * OVS testing with OVS branches 2.12 and 2.11 with VSPERF
+
+ * Tested NICs
+
+ * i40e (X710)
+ * ixgbe (82599ES)
+
+ * Functionality
+
+ * P2P throughput
+ * P2P multiqueue
+ * PVP RSS
+ * Vhostuserclient reconnect
+ * Flow Control
+
+18.11.9 Known Issues
+~~~~~~~~~~~~~~~~~~~~
+
+* DPDK 18.11.9 contains fixes up to DPDK 20.05
+* Issues identified/fixed in DPDK master branch after DPDK 20.05 may be present in DPDK 18.11.9
+
+18.11.9 Fixes skipped and status unresolved
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+* dcfbc594f net/iavf: fix queue interrupt for ice
+* b149a7064 eal/freebsd: add config reattach in secondary process
+* a135e050a examples/ipsec-secgw: fix packet length
+* 9d10f53e4 test/metrics: fix second run
+* ea81c1b81 net/mlx5: fix NVGRE matching
+* 721c95301 net/mlx5: fix Rx scatter mode validation
+* be048a1aa net/virtio: fix descriptor addressed in Tx
+* 6080796f6 mem: make base address hint OS specific
+* 6d3f9917f eal: fix memory config allocation for multi-process
+* 1526dd053 net/virtio: fix Tx checksum offloads
+* f0617163b mempool/dpaa2: report error on endless loop in mbuf release
+* 05817057f net/ena: fix indication of bad L4 Rx checksums
+* 9e0d81c1a net/mlx5: fix selection between encap and decap
+* 7392ad06f app/testpmd: use better randomness for Tx split
+* dcd05da0a app/testpmd: fix GENEVE flow item
+* 2e02a2aff (Xavier) ethdev: fix VLAN offloads set if no driver callback
+* ec8615607 crypto/dpaa_sec: fix IOVA conversions
+* 06387be8e net/mlx5: fix encap/decap validation
+* 7593cf1d3 net/mlx5: fix legacy multi-packet write session
+* e21492a51 net/mlx: fix overlinking with meson and glue dlopen
+* 150c9ac2d (Xavier) app/testpmd: update Rx offload after setting MTU
+* 207b1c813 test: fix build without ring PMD
+* 819d0d1d5 net/ixgbe: fix blocking system events
+* 050bfe033 net/mlx5: fix tunnel flow priority
+* bade47a75 net/i40e: relax barrier in Tx
+* 48f9faddc net/bnxt: fix MAC address setting when port is stopped
+* f6752f660 net/sfc: set priority of created filters to manual
+* 27fb5dd28 test: skip some subtests in no-huge mode
+* 4236694f0 mem: preallocate VA space in no-huge mode
+* 4448a202b eal: remove useless makefiles
+* efa8c72f1 net/ixgbe: fix link status inconsistencies
+* 9c4971e52 net/mlx5: update VLAN and encap actions validation
+* 00437823c net/mlx5: use open/read/close for ib stats query
+* 24cb500c1 net/tap: fix mbuf double free when writev fails
+* ae08c73e6 net/i40e: fix flow director initialisation
+* d68ab7a9f net/ixgbe: fix resource leak after thread exits normally
+* 036d82365 mempool: remove inline functions from export list
+* d256c73c1 net/bnxt: fix memory leak during queue restart
+* bc75bdb60 net/bnxt: fix VNIC Rx queue count on VNIC free
+* 90ecace4f examples/fips_validation: fix parsing of algorithms
+* d70a869db net/ixgbe: fix link state timing on fiber ports
+* 92818d839 net/mlx5: fix match on empty VLAN item in DV mode
+* 29fdc5bf4 test/crypto: fix statistics case
+* 3ae4beb07 vhost: check log mmap offset and size overflow
+* ff55182ce net/mlx5: fix VLAN flow action with wildcard VLAN item
+* a60704d1a net/qede: fix assignment of Rx/Tx handlers
+* 205b74295 net/bnxt: fix allocation of LED config info
+* 96477b5dd net/bnxt: fix allocation of COS queue info
+* 986fa3ba8 net/bnxt: fix allocation of link info struct
+* e8fe0e067 net/bnxt: fix allocation of PF info struct
+* 86421846c net/bnxt: fix storing MAC address twice
+* da7018ec2 net/i40e: fix queue region in RSS flow
+* 3acf10719 common/mlx5: fix netlink buffer allocation from stack
+* 20cb28a0e net/bnxt: fix Rx ring producer index
+* 24cb500c1 net/tap: fix mbuf double free when writev fails
+* be4ef2e0d net/i40e: fix flow director enabling
+* f6e63e59e app/testpmd: fix global variable multiple definitions
diff --git a/dpdk/doc/guides/sample_app_ug/l2_forward_real_virtual.rst b/dpdk/doc/guides/sample_app_ug/l2_forward_real_virtual.rst
index 87653ec7bd..9729095872 100644
--- a/dpdk/doc/guides/sample_app_ug/l2_forward_real_virtual.rst
+++ b/dpdk/doc/guides/sample_app_ug/l2_forward_real_virtual.rst
@@ -194,9 +194,6 @@ in the *DPDK Programmer's Guide* - Rel 1.4 EAR and the *DPDK API Reference*.
.. code-block:: c
- if (rte_pci_probe() < 0)
- rte_exit(EXIT_FAILURE, "Cannot probe PCI\n");
-
/* reset l2fwd_dst_ports */
for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++)
@@ -226,12 +223,6 @@ in the *DPDK Programmer's Guide* - Rel 1.4 EAR and the *DPDK API Reference*.
rte_eth_dev_info_get((uint8_t) portid, &dev_info);
}
-Observe that:
-
-* rte_igb_pmd_init_all() simultaneously registers the driver as a PCI driver and as an Ethernet* Poll Mode Driver.
-
-* rte_pci_probe() parses the devices on the PCI bus and initializes recognized devices.
-
The next step is to configure the RX and TX queues.
For each port, there is only one RX queue (only one lcore is able to poll a given port).
The number of TX queues depends on the number of available lcores.
diff --git a/dpdk/doc/guides/sample_app_ug/link_status_intr.rst b/dpdk/doc/guides/sample_app_ug/link_status_intr.rst
index 695c088e88..45f2439a32 100644
--- a/dpdk/doc/guides/sample_app_ug/link_status_intr.rst
+++ b/dpdk/doc/guides/sample_app_ug/link_status_intr.rst
@@ -88,9 +88,6 @@ To fully understand this code, it is recommended to study the chapters that rela
.. code-block:: c
- if (rte_pci_probe() < 0)
- rte_exit(EXIT_FAILURE, "Cannot probe PCI\n");
-
/*
* Each logical core is assigned a dedicated TX queue on each port.
*/
@@ -115,10 +112,6 @@ To fully understand this code, it is recommended to study the chapters that rela
rte_eth_dev_info_get((uint8_t) portid, &dev_info);
}
-Observe that:
-
-* rte_pci_probe() parses the devices on the PCI bus and initializes recognized devices.
-
The next step is to configure the RX and TX queues.
For each port, there is only one RX queue (only one lcore is able to poll a given port).
The number of TX queues depends on the number of available lcores.
diff --git a/dpdk/doc/guides/sample_app_ug/multi_process.rst b/dpdk/doc/guides/sample_app_ug/multi_process.rst
index 9c374da6f7..f2a79a6397 100644
--- a/dpdk/doc/guides/sample_app_ug/multi_process.rst
+++ b/dpdk/doc/guides/sample_app_ug/multi_process.rst
@@ -209,7 +209,7 @@ How the Application Works
^^^^^^^^^^^^^^^^^^^^^^^^^
The initialization calls in both the primary and secondary instances are the same for the most part,
-calling the rte_eal_init(), 1 G and 10 G driver initialization and then rte_pci_probe() functions.
+calling the rte_eal_init(), 1 G and 10 G driver initialization and then probing devices.
Thereafter, the initialization done depends on whether the process is configured as a primary or secondary instance.
In the primary instance, a memory pool is created for the packet mbufs and the network ports to be used are initialized -
diff --git a/dpdk/doc/guides/testpmd_app_ug/testpmd_funcs.rst b/dpdk/doc/guides/testpmd_app_ug/testpmd_funcs.rst
index c327d1f4df..0d71e20c64 100644
--- a/dpdk/doc/guides/testpmd_app_ug/testpmd_funcs.rst
+++ b/dpdk/doc/guides/testpmd_app_ug/testpmd_funcs.rst
@@ -238,7 +238,7 @@ Display the RSS hash functions and RSS hash key of a port::
clear port
~~~~~~~~~~
-Clear the port statistics for a given port or for all ports::
+Clear the port statistics and forward engine statistics for a given port or for all ports::
testpmd> clear port (info|stats|xstats|fdir|stat_qmap) (port_id|all)
diff --git a/dpdk/drivers/Makefile b/dpdk/drivers/Makefile
index 7d5da5d9f5..cfc24b2d0b 100644
--- a/dpdk/drivers/Makefile
+++ b/dpdk/drivers/Makefile
@@ -19,7 +19,7 @@ DEPDIRS-common/qat := bus mempool
DIRS-$(CONFIG_RTE_LIBRTE_COMPRESSDEV) += compress
DEPDIRS-compress := bus mempool
DIRS-$(CONFIG_RTE_LIBRTE_EVENTDEV) += event
-DEPDIRS-event := common bus mempool net
+DEPDIRS-event := common bus mempool net crypto
DIRS-$(CONFIG_RTE_LIBRTE_RAWDEV) += raw
DEPDIRS-raw := common bus mempool net event
diff --git a/dpdk/drivers/bus/fslmc/qbman/qbman_debug.c b/dpdk/drivers/bus/fslmc/qbman/qbman_debug.c
index 0bb2ce880f..34374ae4b6 100644
--- a/dpdk/drivers/bus/fslmc/qbman/qbman_debug.c
+++ b/dpdk/drivers/bus/fslmc/qbman/qbman_debug.c
@@ -20,26 +20,27 @@ struct qbman_fq_query_desc {
uint8_t verb;
uint8_t reserved[3];
uint32_t fqid;
- uint8_t reserved2[57];
+ uint8_t reserved2[56];
};
int qbman_fq_query_state(struct qbman_swp *s, uint32_t fqid,
struct qbman_fq_query_np_rslt *r)
{
struct qbman_fq_query_desc *p;
+ struct qbman_fq_query_np_rslt *var;
p = (struct qbman_fq_query_desc *)qbman_swp_mc_start(s);
if (!p)
return -EBUSY;
p->fqid = fqid;
- *r = *(struct qbman_fq_query_np_rslt *)qbman_swp_mc_complete(s, p,
- QBMAN_FQ_QUERY_NP);
- if (!r) {
+ var = qbman_swp_mc_complete(s, p, QBMAN_FQ_QUERY_NP);
+ if (!var) {
pr_err("qbman: Query FQID %d NP fields failed, no response\n",
fqid);
return -EIO;
}
+ *r = *var;
/* Decode the outcome */
QBMAN_BUG_ON((r->verb & QBMAN_RESPONSE_VERB_MASK) != QBMAN_FQ_QUERY_NP);
diff --git a/dpdk/drivers/bus/ifpga/ifpga_bus.c b/dpdk/drivers/bus/ifpga/ifpga_bus.c
index 55d3abf9fe..1fddde60a5 100644
--- a/dpdk/drivers/bus/ifpga/ifpga_bus.c
+++ b/dpdk/drivers/bus/ifpga/ifpga_bus.c
@@ -24,6 +24,7 @@
#include <rte_kvargs.h>
#include <rte_alarm.h>
#include <rte_string_fns.h>
+#include <rte_debug.h>
#include "rte_rawdev.h"
#include "rte_rawdev_pmd.h"
diff --git a/dpdk/drivers/bus/pci/bsd/pci.c b/dpdk/drivers/bus/pci/bsd/pci.c
index d09f8ee5a6..42f435334a 100644
--- a/dpdk/drivers/bus/pci/bsd/pci.c
+++ b/dpdk/drivers/bus/pci/bsd/pci.c
@@ -376,13 +376,20 @@ rte_pci_scan(void)
return -1;
}
-/*
- * Get iommu class of PCI devices on the bus.
- */
+bool
+pci_device_iommu_support_va(__rte_unused const struct rte_pci_device *dev)
+{
+ return false;
+}
+
enum rte_iova_mode
-rte_pci_get_iommu_class(void)
+pci_device_iova_mode(const struct rte_pci_driver *pdrv __rte_unused,
+ const struct rte_pci_device *pdev)
{
/* Supports only RTE_KDRV_NIC_UIO */
+ if (pdev->kdrv != RTE_KDRV_NIC_UIO)
+ RTE_LOG(DEBUG, EAL, "Unsupported kernel driver? Defaulting to IOVA as 'PA'\n");
+
return RTE_IOVA_PA;
}
diff --git a/dpdk/drivers/bus/pci/linux/pci.c b/dpdk/drivers/bus/pci/linux/pci.c
index 9b1c7c839a..f50c7090e4 100644
--- a/dpdk/drivers/bus/pci/linux/pci.c
+++ b/dpdk/drivers/bus/pci/linux/pci.c
@@ -378,6 +378,11 @@ pci_scan_one(const char *dirname, const struct rte_pci_addr *addr)
*/
RTE_LOG(ERR, EAL, "Unexpected device scan at %s!\n",
filename);
+ else if (dev2->device.devargs !=
+ dev->device.devargs) {
+ rte_devargs_remove(dev2->device.devargs);
+ pci_name_set(dev2);
+ }
}
free(dev);
}
@@ -497,93 +502,13 @@ rte_pci_scan(void)
return -1;
}
-/*
- * Is pci device bound to any kdrv
- */
-static inline int
-pci_one_device_is_bound(void)
-{
- struct rte_pci_device *dev = NULL;
- int ret = 0;
-
- FOREACH_DEVICE_ON_PCIBUS(dev) {
- if (dev->kdrv == RTE_KDRV_UNKNOWN ||
- dev->kdrv == RTE_KDRV_NONE) {
- continue;
- } else {
- ret = 1;
- break;
- }
- }
- return ret;
-}
-
-/*
- * Any one of the device bound to uio
- */
-static inline int
-pci_one_device_bound_uio(void)
-{
- struct rte_pci_device *dev = NULL;
- struct rte_devargs *devargs;
- int need_check;
-
- FOREACH_DEVICE_ON_PCIBUS(dev) {
- devargs = dev->device.devargs;
-
- need_check = 0;
- switch (rte_pci_bus.bus.conf.scan_mode) {
- case RTE_BUS_SCAN_WHITELIST:
- if (devargs && devargs->policy == RTE_DEV_WHITELISTED)
- need_check = 1;
- break;
- case RTE_BUS_SCAN_UNDEFINED:
- case RTE_BUS_SCAN_BLACKLIST:
- if (devargs == NULL ||
- devargs->policy != RTE_DEV_BLACKLISTED)
- need_check = 1;
- break;
- }
-
- if (!need_check)
- continue;
-
- if (dev->kdrv == RTE_KDRV_IGB_UIO ||
- dev->kdrv == RTE_KDRV_UIO_GENERIC) {
- return 1;
- }
- }
- return 0;
-}
-
-/*
- * Any one of the device has iova as va
- */
-static inline int
-pci_one_device_has_iova_va(void)
-{
- struct rte_pci_device *dev = NULL;
- struct rte_pci_driver *drv = NULL;
-
- FOREACH_DRIVER_ON_PCIBUS(drv) {
- if (drv && drv->drv_flags & RTE_PCI_DRV_IOVA_AS_VA) {
- FOREACH_DEVICE_ON_PCIBUS(dev) {
- if (dev->kdrv == RTE_KDRV_VFIO &&
- rte_pci_match(drv, dev))
- return 1;
- }
- }
- }
- return 0;
-}
-
#if defined(RTE_ARCH_X86)
-static bool
-pci_one_device_iommu_support_va(struct rte_pci_device *dev)
+bool
+pci_device_iommu_support_va(const struct rte_pci_device *dev)
{
#define VTD_CAP_MGAW_SHIFT 16
#define VTD_CAP_MGAW_MASK (0x3fULL << VTD_CAP_MGAW_SHIFT)
- struct rte_pci_addr *addr = &dev->addr;
+ const struct rte_pci_addr *addr = &dev->addr;
char filename[PATH_MAX];
FILE *fp;
uint64_t mgaw, vtd_cap_reg = 0;
@@ -627,81 +552,55 @@ pci_one_device_iommu_support_va(struct rte_pci_device *dev)
return true;
}
#elif defined(RTE_ARCH_PPC_64)
-static bool
-pci_one_device_iommu_support_va(__rte_unused struct rte_pci_device *dev)
+bool
+pci_device_iommu_support_va(__rte_unused const struct rte_pci_device *dev)
{
return false;
}
#else
-static bool
-pci_one_device_iommu_support_va(__rte_unused struct rte_pci_device *dev)
+bool
+pci_device_iommu_support_va(__rte_unused const struct rte_pci_device *dev)
{
return true;
}
#endif
-/*
- * All devices IOMMUs support VA as IOVA
- */
-static bool
-pci_devices_iommu_support_va(void)
+enum rte_iova_mode
+pci_device_iova_mode(const struct rte_pci_driver *pdrv,
+ const struct rte_pci_device *pdev)
{
- struct rte_pci_device *dev = NULL;
- struct rte_pci_driver *drv = NULL;
+ enum rte_iova_mode iova_mode = RTE_IOVA_DC;
- FOREACH_DRIVER_ON_PCIBUS(drv) {
- FOREACH_DEVICE_ON_PCIBUS(dev) {
- if (!rte_pci_match(drv, dev))
- continue;
- /*
- * just one PCI device needs to be checked out because
- * the IOMMU hardware is the same for all of them.
- */
- return pci_one_device_iommu_support_va(dev);
+ switch (pdev->kdrv) {
+ case RTE_KDRV_VFIO: {
+#ifdef VFIO_PRESENT
+ static int is_vfio_noiommu_enabled = -1;
+
+ if (is_vfio_noiommu_enabled == -1) {
+ if (rte_vfio_noiommu_is_enabled() == 1)
+ is_vfio_noiommu_enabled = 1;
+ else
+ is_vfio_noiommu_enabled = 0;
}
+ if (is_vfio_noiommu_enabled != 0)
+ iova_mode = RTE_IOVA_PA;
+ else if ((pdrv->drv_flags & RTE_PCI_DRV_IOVA_AS_VA) != 0)
+ iova_mode = RTE_IOVA_VA;
+#endif
+ break;
}
- return true;
-}
-/*
- * Get iommu class of PCI devices on the bus.
- */
-enum rte_iova_mode
-rte_pci_get_iommu_class(void)
-{
- bool is_bound;
- bool is_vfio_noiommu_enabled = true;
- bool has_iova_va;
- bool is_bound_uio;
- bool iommu_no_va;
-
- is_bound = pci_one_device_is_bound();
- if (!is_bound)
- return RTE_IOVA_DC;
-
- has_iova_va = pci_one_device_has_iova_va();
- is_bound_uio = pci_one_device_bound_uio();
- iommu_no_va = !pci_devices_iommu_support_va();
-#ifdef VFIO_PRESENT
- is_vfio_noiommu_enabled = rte_vfio_noiommu_is_enabled() == true ?
- true : false;
-#endif
+ case RTE_KDRV_IGB_UIO:
+ case RTE_KDRV_UIO_GENERIC:
+ iova_mode = RTE_IOVA_PA;
+ break;
- if (has_iova_va && !is_bound_uio && !is_vfio_noiommu_enabled &&
- !iommu_no_va)
- return RTE_IOVA_VA;
-
- if (has_iova_va) {
- RTE_LOG(WARNING, EAL, "Some devices want iova as va but pa will be used because.. ");
- if (is_vfio_noiommu_enabled)
- RTE_LOG(WARNING, EAL, "vfio-noiommu mode configured\n");
- if (is_bound_uio)
- RTE_LOG(WARNING, EAL, "few device bound to UIO\n");
- if (iommu_no_va)
- RTE_LOG(WARNING, EAL, "IOMMU does not support IOVA as VA\n");
+ default:
+ if ((pdrv->drv_flags & RTE_PCI_DRV_IOVA_AS_VA) != 0)
+ iova_mode = RTE_IOVA_VA;
+ break;
}
-
- return RTE_IOVA_PA;
+ return iova_mode;
}
/* Read PCI config space. */
diff --git a/dpdk/drivers/bus/pci/linux/pci_vfio.c b/dpdk/drivers/bus/pci/linux/pci_vfio.c
index 366d2ab2ff..cf61032a5d 100644
--- a/dpdk/drivers/bus/pci/linux/pci_vfio.c
+++ b/dpdk/drivers/bus/pci/linux/pci_vfio.c
@@ -149,6 +149,38 @@ pci_vfio_get_msix_bar(int fd, struct pci_msix_table *msix_table)
return 0;
}
+/* enable PCI bus memory space */
+static int
+pci_vfio_enable_bus_memory(int dev_fd)
+{
+ uint16_t cmd;
+ int ret;
+
+ ret = pread64(dev_fd, &cmd, sizeof(cmd),
+ VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
+ PCI_COMMAND);
+
+ if (ret != sizeof(cmd)) {
+ RTE_LOG(ERR, EAL, "Cannot read command from PCI config space!\n");
+ return -1;
+ }
+
+ if (cmd & PCI_COMMAND_MEMORY)
+ return 0;
+
+ cmd |= PCI_COMMAND_MEMORY;
+ ret = pwrite64(dev_fd, &cmd, sizeof(cmd),
+ VFIO_GET_REGION_ADDR(VFIO_PCI_CONFIG_REGION_INDEX) +
+ PCI_COMMAND);
+
+ if (ret != sizeof(cmd)) {
+ RTE_LOG(ERR, EAL, "Cannot write command to PCI config space!\n");
+ return -1;
+ }
+
+ return 0;
+}
+
/* set PCI bus mastering */
static int
pci_vfio_set_bus_master(int dev_fd, bool op)
@@ -427,6 +459,11 @@ pci_rte_vfio_setup_device(struct rte_pci_device *dev, int vfio_dev_fd)
return -1;
}
+ if (pci_vfio_enable_bus_memory(vfio_dev_fd)) {
+ RTE_LOG(ERR, EAL, "Cannot enable bus memory!\n");
+ return -1;
+ }
+
/* set bus mastering for the device */
if (pci_vfio_set_bus_master(vfio_dev_fd, true)) {
RTE_LOG(ERR, EAL, "Cannot set up bus mastering!\n");
diff --git a/dpdk/drivers/bus/pci/pci_common.c b/dpdk/drivers/bus/pci/pci_common.c
index 6276e5d695..954d638a99 100644
--- a/dpdk/drivers/bus/pci/pci_common.c
+++ b/dpdk/drivers/bus/pci/pci_common.c
@@ -169,8 +169,22 @@ rte_pci_probe_one_driver(struct rte_pci_driver *dr,
* This needs to be before rte_pci_map_device(), as it enables to use
* driver flags for adjusting configuration.
*/
- if (!already_probed)
+ if (!already_probed) {
+ enum rte_iova_mode dev_iova_mode;
+ enum rte_iova_mode iova_mode;
+
+ dev_iova_mode = pci_device_iova_mode(dr, dev);
+ iova_mode = rte_eal_iova_mode();
+ if (dev_iova_mode != RTE_IOVA_DC &&
+ dev_iova_mode != iova_mode) {
+ RTE_LOG(ERR, EAL, " Expecting '%s' IOVA mode but current mode is '%s', not initializing\n",
+ dev_iova_mode == RTE_IOVA_PA ? "PA" : "VA",
+ iova_mode == RTE_IOVA_PA ? "PA" : "VA");
+ return -EINVAL;
+ }
+
dev->driver = dr;
+ }
if (!already_probed && (dr->drv_flags & RTE_PCI_DRV_NEED_MAPPING)) {
/* map resources for devices that use igb_uio */
@@ -273,8 +287,8 @@ pci_probe_all_drivers(struct rte_pci_device *dev)
* all registered drivers that have a matching entry in its id_table
* for discovered devices.
*/
-int
-rte_pci_probe(void)
+static int
+pci_probe(void)
{
struct rte_pci_device *dev = NULL;
size_t probed = 0, failed = 0;
@@ -528,10 +542,93 @@ pci_unplug(struct rte_device *dev)
return ret;
}
+static bool
+pci_ignore_device(const struct rte_pci_device *dev)
+{
+ struct rte_devargs *devargs = dev->device.devargs;
+
+ switch (rte_pci_bus.bus.conf.scan_mode) {
+ case RTE_BUS_SCAN_WHITELIST:
+ if (devargs && devargs->policy == RTE_DEV_WHITELISTED)
+ return false;
+ break;
+ case RTE_BUS_SCAN_UNDEFINED:
+ case RTE_BUS_SCAN_BLACKLIST:
+ if (devargs == NULL ||
+ devargs->policy != RTE_DEV_BLACKLISTED)
+ return false;
+ break;
+ }
+ return true;
+}
+
+enum rte_iova_mode
+rte_pci_get_iommu_class(void)
+{
+ enum rte_iova_mode iova_mode = RTE_IOVA_DC;
+ const struct rte_pci_device *dev;
+ const struct rte_pci_driver *drv;
+ bool devices_want_va = false;
+ bool devices_want_pa = false;
+ int iommu_no_va = -1;
+
+ FOREACH_DEVICE_ON_PCIBUS(dev) {
+ /*
+ * We can check this only once, because the IOMMU hardware is
+ * the same for all of them.
+ */
+ if (iommu_no_va == -1)
+ iommu_no_va = pci_device_iommu_support_va(dev)
+ ? 0 : 1;
+ if (pci_ignore_device(dev))
+ continue;
+ if (dev->kdrv == RTE_KDRV_UNKNOWN ||
+ dev->kdrv == RTE_KDRV_NONE)
+ continue;
+ FOREACH_DRIVER_ON_PCIBUS(drv) {
+ enum rte_iova_mode dev_iova_mode;
+
+ if (!rte_pci_match(drv, dev))
+ continue;
+
+ dev_iova_mode = pci_device_iova_mode(drv, dev);
+ RTE_LOG(DEBUG, EAL, "PCI driver %s for device "
+ PCI_PRI_FMT " wants IOVA as '%s'\n",
+ drv->driver.name,
+ dev->addr.domain, dev->addr.bus,
+ dev->addr.devid, dev->addr.function,
+ dev_iova_mode == RTE_IOVA_DC ? "DC" :
+ (dev_iova_mode == RTE_IOVA_PA ? "PA" : "VA"));
+ if (dev_iova_mode == RTE_IOVA_PA)
+ devices_want_pa = true;
+ else if (dev_iova_mode == RTE_IOVA_VA)
+ devices_want_va = true;
+ }
+ }
+ if (iommu_no_va == 1) {
+ iova_mode = RTE_IOVA_PA;
+ if (devices_want_va) {
+ RTE_LOG(WARNING, EAL, "Some devices want 'VA' but IOMMU does not support 'VA'.\n");
+ RTE_LOG(WARNING, EAL, "The devices that want 'VA' won't initialize.\n");
+ }
+ } else if (devices_want_va && !devices_want_pa) {
+ iova_mode = RTE_IOVA_VA;
+ } else if (devices_want_pa && !devices_want_va) {
+ iova_mode = RTE_IOVA_PA;
+ } else {
+ iova_mode = RTE_IOVA_DC;
+ if (devices_want_va) {
+ RTE_LOG(WARNING, EAL, "Some devices want 'VA' but forcing 'DC' because other devices want 'PA'.\n");
+ RTE_LOG(WARNING, EAL, "Depending on the final decision by the EAL, not all devices may be able to initialize.\n");
+ }
+ }
+ return iova_mode;
+}
+
struct rte_pci_bus rte_pci_bus = {
.bus = {
.scan = rte_pci_scan,
- .probe = rte_pci_probe,
+ .probe = pci_probe,
.find_device = pci_find_device,
.plug = pci_plug,
.unplug = pci_unplug,
diff --git a/dpdk/drivers/bus/pci/pci_common_uio.c b/dpdk/drivers/bus/pci/pci_common_uio.c
index 7ea73dbc5b..f4dca9da91 100644
--- a/dpdk/drivers/bus/pci/pci_common_uio.c
+++ b/dpdk/drivers/bus/pci/pci_common_uio.c
@@ -70,6 +70,7 @@ pci_uio_map_secondary(struct rte_pci_device *dev)
}
return -1;
}
+ dev->mem_resource[i].addr = mapaddr;
}
return 0;
}
diff --git a/dpdk/drivers/bus/pci/private.h b/dpdk/drivers/bus/pci/private.h
index 13c3324bb0..af1c7ae5fe 100644
--- a/dpdk/drivers/bus/pci/private.h
+++ b/dpdk/drivers/bus/pci/private.h
@@ -17,16 +17,6 @@ struct rte_pci_device;
extern struct rte_pci_bus rte_pci_bus;
-/**
- * Probe the PCI bus
- *
- * @return
- * - 0 on success.
- * - !0 on error.
- */
-int
-rte_pci_probe(void);
-
/**
* Scan the content of the PCI bus, and the devices in the devices
* list
@@ -172,6 +162,17 @@ int
rte_pci_match(const struct rte_pci_driver *pci_drv,
const struct rte_pci_device *pci_dev);
+/**
+ * OS specific callbacks for rte_pci_get_iommu_class
+ *
+ */
+bool
+pci_device_iommu_support_va(const struct rte_pci_device *dev);
+
+enum rte_iova_mode
+pci_device_iova_mode(const struct rte_pci_driver *pci_drv,
+ const struct rte_pci_device *pci_dev);
+
/**
* Get iommu class of PCI devices on the bus.
* And return their preferred iova mapping mode.
diff --git a/dpdk/drivers/bus/pci/rte_bus_pci.h b/dpdk/drivers/bus/pci/rte_bus_pci.h
index f0d6d81c00..f0fa3a17f3 100644
--- a/dpdk/drivers/bus/pci/rte_bus_pci.h
+++ b/dpdk/drivers/bus/pci/rte_bus_pci.h
@@ -147,8 +147,8 @@ struct rte_pci_bus {
#define RTE_PCI_DRV_INTR_RMV 0x0010
/** Device driver needs to keep mapped resources if unsupported dev detected */
#define RTE_PCI_DRV_KEEP_MAPPED_RES 0x0020
-/** Device driver supports IOVA as VA */
-#define RTE_PCI_DRV_IOVA_AS_VA 0X0040
+/** Device driver only supports IOVA as VA and cannot work with IOVA as PA */
+#define RTE_PCI_DRV_IOVA_AS_VA 0x0040
/**
* Map the PCI device resources in user space virtual memory address
diff --git a/dpdk/drivers/bus/vmbus/linux/vmbus_uio.c b/dpdk/drivers/bus/vmbus/linux/vmbus_uio.c
index 7cab5c19f4..308ba00893 100644
--- a/dpdk/drivers/bus/vmbus/linux/vmbus_uio.c
+++ b/dpdk/drivers/bus/vmbus/linux/vmbus_uio.c
@@ -166,7 +166,7 @@ vmbus_uio_map_resource_by_index(struct rte_vmbus_device *dev, int idx,
dev->resource[idx].addr = mapaddr;
vmbus_map_addr = RTE_PTR_ADD(mapaddr, size);
- /* Record result of sucessful mapping for use by secondary */
+ /* Record result of successful mapping for use by secondary */
maps[idx].addr = mapaddr;
maps[idx].size = size;
diff --git a/dpdk/drivers/bus/vmbus/vmbus_common.c b/dpdk/drivers/bus/vmbus/vmbus_common.c
index 48a219f735..3adef01c95 100644
--- a/dpdk/drivers/bus/vmbus/vmbus_common.c
+++ b/dpdk/drivers/bus/vmbus/vmbus_common.c
@@ -131,7 +131,7 @@ vmbus_probe_one_driver(struct rte_vmbus_driver *dr,
}
/*
- * IF device class GUID mathces, call the probe function of
+ * If device class GUID matches, call the probe function of
* registere drivers for the vmbus device.
* Return -1 if initialization failed,
* and 1 if no driver found for this device.
diff --git a/dpdk/drivers/common/cpt/cpt_pmd_logs.h b/dpdk/drivers/common/cpt/cpt_pmd_logs.h
index 4cbec4e36c..2681d12869 100644
--- a/dpdk/drivers/common/cpt/cpt_pmd_logs.h
+++ b/dpdk/drivers/common/cpt/cpt_pmd_logs.h
@@ -45,6 +45,6 @@
* cpt_logtype will be used for common logging. This field would be initialized
* by otx_* driver routines during PCI probe.
*/
-int cpt_logtype;
+extern int cpt_logtype;
#endif /* _CPT_PMD_LOGS_H_ */
diff --git a/dpdk/drivers/compress/octeontx/otx_zip_pmd.c b/dpdk/drivers/compress/octeontx/otx_zip_pmd.c
index 9e00c86630..bff8ef035e 100644
--- a/dpdk/drivers/compress/octeontx/otx_zip_pmd.c
+++ b/dpdk/drivers/compress/octeontx/otx_zip_pmd.c
@@ -406,7 +406,7 @@ zip_pmd_qp_setup(struct rte_compressdev *dev, uint16_t qp_id,
qp->name = name;
- /* Create completion queue upto max_inflight_ops */
+ /* Create completion queue up to max_inflight_ops */
qp->processed_pkts = zip_pmd_qp_create_processed_pkts_ring(qp,
max_inflight_ops, socket_id);
if (qp->processed_pkts == NULL)
diff --git a/dpdk/drivers/compress/zlib/zlib_pmd.c b/dpdk/drivers/compress/zlib/zlib_pmd.c
index 19f9200c22..e39be2ed86 100644
--- a/dpdk/drivers/compress/zlib/zlib_pmd.c
+++ b/dpdk/drivers/compress/zlib/zlib_pmd.c
@@ -7,6 +7,8 @@
#include "zlib_pmd_private.h"
+int zlib_logtype_driver;
+
/** Compute next mbuf in the list, assign data buffer and length,
* returns 0 if mbuf is NULL
*/
diff --git a/dpdk/drivers/compress/zlib/zlib_pmd_private.h b/dpdk/drivers/compress/zlib/zlib_pmd_private.h
index 2c6e83d45c..05e80d94ef 100644
--- a/dpdk/drivers/compress/zlib/zlib_pmd_private.h
+++ b/dpdk/drivers/compress/zlib/zlib_pmd_private.h
@@ -14,7 +14,7 @@
#define DEF_MEM_LEVEL 8
-int zlib_logtype_driver;
+extern int zlib_logtype_driver;
#define ZLIB_PMD_LOG(level, fmt, args...) \
rte_log(RTE_LOG_ ## level, zlib_logtype_driver, "%s(): "fmt "\n", \
__func__, ##args)
diff --git a/dpdk/drivers/crypto/aesni_gcm/aesni_gcm_pmd.c b/dpdk/drivers/crypto/aesni_gcm/aesni_gcm_pmd.c
index ebdf7c35a8..1975ad09d2 100644
--- a/dpdk/drivers/crypto/aesni_gcm/aesni_gcm_pmd.c
+++ b/dpdk/drivers/crypto/aesni_gcm/aesni_gcm_pmd.c
@@ -13,6 +13,8 @@
#include "aesni_gcm_pmd_private.h"
+int aesni_gcm_logtype_driver;
+
static uint8_t cryptodev_driver_id;
/** Parse crypto xform chain and set private session parameters */
diff --git a/dpdk/drivers/crypto/aesni_gcm/aesni_gcm_pmd_private.h b/dpdk/drivers/crypto/aesni_gcm/aesni_gcm_pmd_private.h
index 92b0413547..20a619f1a9 100644
--- a/dpdk/drivers/crypto/aesni_gcm/aesni_gcm_pmd_private.h
+++ b/dpdk/drivers/crypto/aesni_gcm/aesni_gcm_pmd_private.h
@@ -20,7 +20,7 @@
/**< AES-NI GCM PMD device name */
/** AES-NI GCM PMD LOGTYPE DRIVER */
-int aesni_gcm_logtype_driver;
+extern int aesni_gcm_logtype_driver;
#define AESNI_GCM_LOG(level, fmt, ...) \
rte_log(RTE_LOG_ ## level, aesni_gcm_logtype_driver, \
"%s() line %u: "fmt "\n", __func__, __LINE__, \
diff --git a/dpdk/drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c b/dpdk/drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c
index 45dd86a756..19652469e7 100644
--- a/dpdk/drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c
+++ b/dpdk/drivers/crypto/aesni_mb/rte_aesni_mb_pmd.c
@@ -14,6 +14,8 @@
#include "rte_aesni_mb_pmd_private.h"
+int aesni_mb_logtype_driver;
+
#define AES_CCM_DIGEST_MIN_LEN 4
#define AES_CCM_DIGEST_MAX_LEN 16
#define HMAC_MAX_BLOCK_SIZE 128
diff --git a/dpdk/drivers/crypto/aesni_mb/rte_aesni_mb_pmd_private.h b/dpdk/drivers/crypto/aesni_mb/rte_aesni_mb_pmd_private.h
index d8021cdaa2..a7a417b6b5 100644
--- a/dpdk/drivers/crypto/aesni_mb/rte_aesni_mb_pmd_private.h
+++ b/dpdk/drivers/crypto/aesni_mb/rte_aesni_mb_pmd_private.h
@@ -11,7 +11,7 @@
/**< AES-NI Multi buffer PMD device name */
/** AESNI_MB PMD LOGTYPE DRIVER */
-int aesni_mb_logtype_driver;
+extern int aesni_mb_logtype_driver;
#define AESNI_MB_LOG(level, fmt, ...) \
rte_log(RTE_LOG_ ## level, aesni_mb_logtype_driver, \
diff --git a/dpdk/drivers/crypto/caam_jr/Makefile b/dpdk/drivers/crypto/caam_jr/Makefile
index 88cdf74108..c78901f5bb 100644
--- a/dpdk/drivers/crypto/caam_jr/Makefile
+++ b/dpdk/drivers/crypto/caam_jr/Makefile
@@ -16,6 +16,13 @@ CFLAGS += -D _GNU_SOURCE
CFLAGS += -O3
CFLAGS += $(WERROR_FLAGS)
+# FIXME: temporary solution for Bugzilla 469
+ifeq ($(CONFIG_RTE_TOOLCHAIN_GCC),y)
+ifeq ($(shell test $(GCC_VERSION) -ge 100 && echo 1), 1)
+CFLAGS += -fcommon
+endif
+endif
+
CFLAGS += -I$(RTE_SDK)/drivers/bus/dpaa/include
CFLAGS += -I$(RTE_SDK)/drivers/crypto/caam_jr
#sharing the hw flib headers from dpaa2_sec pmd
diff --git a/dpdk/drivers/crypto/caam_jr/caam_jr.c b/dpdk/drivers/crypto/caam_jr/caam_jr.c
index a4e70babf4..7aca8d6fbd 100644
--- a/dpdk/drivers/crypto/caam_jr/caam_jr.c
+++ b/dpdk/drivers/crypto/caam_jr/caam_jr.c
@@ -2110,7 +2110,7 @@ static void
close_job_ring(struct sec_job_ring_t *job_ring)
{
PMD_INIT_FUNC_TRACE();
- if (job_ring->irq_fd) {
+ if (job_ring->irq_fd != -1) {
/* Producer index is frozen. If consumer index is not equal
* with producer index, then we have descs to flush.
*/
@@ -2119,7 +2119,7 @@ close_job_ring(struct sec_job_ring_t *job_ring)
/* free the uio job ring */
free_job_ring(job_ring->irq_fd);
- job_ring->irq_fd = 0;
+ job_ring->irq_fd = -1;
caam_jr_dma_free(job_ring->input_ring);
caam_jr_dma_free(job_ring->output_ring);
g_job_rings_no--;
@@ -2223,7 +2223,7 @@ caam_jr_dev_uninit(struct rte_cryptodev *dev)
*
*/
static void *
-init_job_ring(void *reg_base_addr, uint32_t irq_id)
+init_job_ring(void *reg_base_addr, int irq_id)
{
struct sec_job_ring_t *job_ring = NULL;
int i, ret = 0;
@@ -2233,7 +2233,7 @@ init_job_ring(void *reg_base_addr, uint32_t irq_id)
int irq_coalescing_count = 0;
for (i = 0; i < MAX_SEC_JOB_RINGS; i++) {
- if (g_job_rings[i].irq_fd == 0) {
+ if (g_job_rings[i].irq_fd == -1) {
job_ring = &g_job_rings[i];
g_job_rings_no++;
break;
@@ -2486,6 +2486,15 @@ cryptodev_caam_jr_remove(struct rte_vdev_device *vdev)
return rte_cryptodev_pmd_destroy(cryptodev);
}
+static void
+sec_job_rings_init(void)
+{
+ int i;
+
+ for (i = 0; i < MAX_SEC_JOB_RINGS; i++)
+ g_job_rings[i].irq_fd = -1;
+}
+
static struct rte_vdev_driver cryptodev_caam_jr_drv = {
.probe = cryptodev_caam_jr_probe,
.remove = cryptodev_caam_jr_remove
@@ -2500,6 +2509,12 @@ RTE_PMD_REGISTER_PARAM_STRING(CRYPTODEV_NAME_CAAM_JR_PMD,
RTE_PMD_REGISTER_CRYPTO_DRIVER(caam_jr_crypto_drv, cryptodev_caam_jr_drv.driver,
cryptodev_driver_id);
+RTE_INIT(caam_jr_init)
+{
+ sec_uio_job_rings_init();
+ sec_job_rings_init();
+}
+
RTE_INIT(caam_jr_init_log)
{
caam_jr_logtype = rte_log_register("pmd.crypto.caam");
diff --git a/dpdk/drivers/crypto/caam_jr/caam_jr_hw_specific.h b/dpdk/drivers/crypto/caam_jr/caam_jr_hw_specific.h
index 5f58a585d7..bbe8bc3f90 100644
--- a/dpdk/drivers/crypto/caam_jr/caam_jr_hw_specific.h
+++ b/dpdk/drivers/crypto/caam_jr/caam_jr_hw_specific.h
@@ -360,7 +360,7 @@ struct sec_job_ring_t {
* bitwise operations.
*/
- uint32_t irq_fd; /* The file descriptor used for polling from
+ int irq_fd; /* The file descriptor used for polling from
* user space for interrupts notifications
*/
uint32_t jr_mode; /* Model used by SEC Driver to receive
diff --git a/dpdk/drivers/crypto/caam_jr/caam_jr_pvt.h b/dpdk/drivers/crypto/caam_jr/caam_jr_pvt.h
index 9f1adabc7d..579aacbb38 100644
--- a/dpdk/drivers/crypto/caam_jr/caam_jr_pvt.h
+++ b/dpdk/drivers/crypto/caam_jr/caam_jr_pvt.h
@@ -215,7 +215,7 @@ calc_chksum(void *buffer, int len)
}
struct uio_job_ring {
uint32_t jr_id;
- uint32_t uio_fd;
+ int uio_fd;
void *register_base_addr;
int map_size;
int uio_minor_number;
@@ -223,8 +223,9 @@ struct uio_job_ring {
int sec_cleanup(void);
int sec_configure(void);
+void sec_uio_job_rings_init(void);
struct uio_job_ring *config_job_ring(void);
-void free_job_ring(uint32_t uio_fd);
+void free_job_ring(int uio_fd);
/* For Dma memory allocation of specified length and alignment */
static inline void *
@@ -273,7 +274,7 @@ static inline rte_iova_t caam_jr_dma_vtop(void *ptr)
* @retval 0 for success
* @retval -1 value for error
*/
-uint32_t caam_jr_enable_irqs(uint32_t uio_fd);
+int caam_jr_enable_irqs(int uio_fd);
/** @brief Request to SEC kernel driver to disable interrupts for descriptor
* finished processing
@@ -286,6 +287,6 @@ uint32_t caam_jr_enable_irqs(uint32_t uio_fd);
* @retval -1 value for error
*
*/
-uint32_t caam_jr_disable_irqs(uint32_t uio_fd);
+int caam_jr_disable_irqs(int uio_fd);
#endif
diff --git a/dpdk/drivers/crypto/caam_jr/caam_jr_uio.c b/dpdk/drivers/crypto/caam_jr/caam_jr_uio.c
index afd75c9a62..913f5f10a1 100644
--- a/dpdk/drivers/crypto/caam_jr/caam_jr_uio.c
+++ b/dpdk/drivers/crypto/caam_jr/caam_jr_uio.c
@@ -150,7 +150,7 @@ file_read_first_line(const char root[], const char subdir[],
"%s/%s/%s", root, subdir, filename);
fd = open(absolute_file_name, O_RDONLY);
- SEC_ASSERT(fd > 0, fd, "Error opening file %s",
+ SEC_ASSERT(fd >= 0, fd, "Error opening file %s",
absolute_file_name);
/* read UIO device name from first line in file */
@@ -184,7 +184,7 @@ file_read_first_line(const char root[], const char subdir[],
* kernel driver as well. No special return values are used.
*/
static int
-sec_uio_send_command(uint32_t uio_fd, int32_t uio_command)
+sec_uio_send_command(int uio_fd, int32_t uio_command)
{
int ret;
@@ -206,8 +206,8 @@ sec_uio_send_command(uint32_t uio_fd, int32_t uio_command)
* @retval 0 for success
* @retval -1 value for error
*/
-uint32_t
-caam_jr_enable_irqs(uint32_t uio_fd)
+int
+caam_jr_enable_irqs(int uio_fd)
{
int ret;
@@ -237,8 +237,8 @@ caam_jr_enable_irqs(uint32_t uio_fd)
* @retval -1 value for error
*
*/
-uint32_t
-caam_jr_disable_irqs(uint32_t uio_fd)
+int
+caam_jr_disable_irqs(int uio_fd)
{
int ret;
@@ -327,12 +327,12 @@ uio_map_registers(int uio_device_fd, int uio_device_id,
}
void
-free_job_ring(uint32_t uio_fd)
+free_job_ring(int uio_fd)
{
struct uio_job_ring *job_ring = NULL;
int i;
- if (!uio_fd)
+ if (uio_fd == -1)
return;
for (i = 0; i < MAX_SEC_JOB_RINGS; i++) {
@@ -352,7 +352,7 @@ free_job_ring(uint32_t uio_fd)
job_ring->jr_id, job_ring->uio_fd);
close(job_ring->uio_fd);
g_uio_jr_num--;
- job_ring->uio_fd = 0;
+ job_ring->uio_fd = -1;
if (job_ring->register_base_addr == NULL)
return;
@@ -375,7 +375,7 @@ uio_job_ring *config_job_ring(void)
int i;
for (i = 0; i < MAX_SEC_JOB_RINGS; i++) {
- if (g_uio_job_ring[i].uio_fd == 0) {
+ if (g_uio_job_ring[i].uio_fd == -1) {
job_ring = &g_uio_job_ring[i];
g_uio_jr_num++;
break;
@@ -394,7 +394,7 @@ uio_job_ring *config_job_ring(void)
/* Open device file */
job_ring->uio_fd = open(uio_device_file_name, O_RDWR);
- SEC_ASSERT(job_ring->uio_fd > 0, NULL,
+ SEC_ASSERT(job_ring->uio_fd >= 0, NULL,
"Failed to open UIO device file for job ring %d",
job_ring->jr_id);
@@ -493,12 +493,22 @@ sec_cleanup(void)
/* I need to close the fd after shutdown UIO commands need to be
* sent using the fd
*/
- if (job_ring->uio_fd != 0) {
+ if (job_ring->uio_fd != -1) {
CAAM_JR_INFO(
"Closed device file for job ring %d , fd = %d",
job_ring->jr_id, job_ring->uio_fd);
close(job_ring->uio_fd);
+ job_ring->uio_fd = -1;
}
}
return 0;
}
+
+void
+sec_uio_job_rings_init(void)
+{
+ int i;
+
+ for (i = 0; i < MAX_SEC_JOB_RINGS; i++)
+ g_uio_job_ring[i].uio_fd = -1;
+}
diff --git a/dpdk/drivers/crypto/caam_jr/meson.build b/dpdk/drivers/crypto/caam_jr/meson.build
index 99b71aef15..ead7f42ff3 100644
--- a/dpdk/drivers/crypto/caam_jr/meson.build
+++ b/dpdk/drivers/crypto/caam_jr/meson.build
@@ -11,6 +11,11 @@ sources = files('caam_jr_capabilities.c',
'caam_jr_uio.c',
'caam_jr.c')
+# FIXME: temporary solution for Bugzilla 469
+if (toolchain == 'gcc' and cc.version().version_compare('>=10.0.0'))
+ cflags += '-fcommon'
+endif
+
allow_experimental_apis = true
includes += include_directories('../dpaa2_sec/')
diff --git a/dpdk/drivers/crypto/ccp/ccp_dev.c b/dpdk/drivers/crypto/ccp/ccp_dev.c
index 80fe6a4533..7d98b2eb25 100644
--- a/dpdk/drivers/crypto/ccp/ccp_dev.c
+++ b/dpdk/drivers/crypto/ccp/ccp_dev.c
@@ -760,7 +760,7 @@ ccp_probe_device(const char *dirname, uint16_t domain,
return 0;
fail:
CCP_LOG_ERR("CCP Device probe failed");
- if (uio_fd > 0)
+ if (uio_fd >= 0)
close(uio_fd);
if (ccp_dev)
rte_free(ccp_dev);
diff --git a/dpdk/drivers/crypto/dpaa2_sec/Makefile b/dpdk/drivers/crypto/dpaa2_sec/Makefile
index f537f76a6f..0da83bfc16 100644
--- a/dpdk/drivers/crypto/dpaa2_sec/Makefile
+++ b/dpdk/drivers/crypto/dpaa2_sec/Makefile
@@ -20,6 +20,13 @@ CFLAGS += -Wno-implicit-fallthrough
endif
endif
+# FIXME: temporary solution for Bugzilla 469
+ifeq ($(CONFIG_RTE_TOOLCHAIN_GCC),y)
+ifeq ($(shell test $(GCC_VERSION) -ge 100 && echo 1), 1)
+CFLAGS += -fcommon
+endif
+endif
+
CFLAGS += -I$(RTE_SDK)/drivers/crypto/dpaa2_sec/
CFLAGS += -I$(RTE_SDK)/drivers/crypto/dpaa2_sec/mc
CFLAGS += -I$(RTE_SDK)/drivers/bus/fslmc/
diff --git a/dpdk/drivers/crypto/dpaa2_sec/meson.build b/dpdk/drivers/crypto/dpaa2_sec/meson.build
index 8fa4827edb..b999bbe433 100644
--- a/dpdk/drivers/crypto/dpaa2_sec/meson.build
+++ b/dpdk/drivers/crypto/dpaa2_sec/meson.build
@@ -11,6 +11,11 @@ deps += ['security', 'mempool_dpaa2']
sources = files('dpaa2_sec_dpseci.c',
'mc/dpseci.c')
+# FIXME: temporary solution for Bugzilla 469
+if (toolchain == 'gcc' and cc.version().version_compare('>=10.0.0'))
+ cflags += '-fcommon'
+endif
+
allow_experimental_apis = true
includes += include_directories('mc', 'hw')
diff --git a/dpdk/drivers/crypto/dpaa_sec/Makefile b/dpdk/drivers/crypto/dpaa_sec/Makefile
index 5ce95c23fd..ed47f92b2b 100644
--- a/dpdk/drivers/crypto/dpaa_sec/Makefile
+++ b/dpdk/drivers/crypto/dpaa_sec/Makefile
@@ -14,6 +14,13 @@ CFLAGS += -DALLOW_EXPERIMENTAL_API
CFLAGS += -O3
CFLAGS += $(WERROR_FLAGS)
+# FIXME: temporary solution for Bugzilla 469
+ifeq ($(CONFIG_RTE_TOOLCHAIN_GCC),y)
+ifeq ($(shell test $(GCC_VERSION) -ge 100 && echo 1), 1)
+CFLAGS += -fcommon
+endif
+endif
+
CFLAGS += -I$(RTE_SDK)/drivers/bus/dpaa
CFLAGS += -I$(RTE_SDK)/drivers/bus/dpaa/include
CFLAGS += -I$(RTE_SDK)/drivers/crypto/dpaa_sec/
diff --git a/dpdk/drivers/crypto/dpaa_sec/meson.build b/dpdk/drivers/crypto/dpaa_sec/meson.build
index 8a5709846e..e3daddbfd7 100644
--- a/dpdk/drivers/crypto/dpaa_sec/meson.build
+++ b/dpdk/drivers/crypto/dpaa_sec/meson.build
@@ -8,6 +8,11 @@ endif
deps += ['bus_dpaa', 'security']
sources = files('dpaa_sec.c')
+# FIXME: temporary solution for Bugzilla 469
+if (toolchain == 'gcc' and cc.version().version_compare('>=10.0.0'))
+ cflags += '-fcommon'
+endif
+
allow_experimental_apis = true
includes += include_directories('../dpaa2_sec/')
diff --git a/dpdk/drivers/crypto/kasumi/rte_kasumi_pmd.c b/dpdk/drivers/crypto/kasumi/rte_kasumi_pmd.c
index 239a1cf441..2d33f14e76 100644
--- a/dpdk/drivers/crypto/kasumi/rte_kasumi_pmd.c
+++ b/dpdk/drivers/crypto/kasumi/rte_kasumi_pmd.c
@@ -17,6 +17,7 @@
#define KASUMI_MAX_BURST 4
#define BYTE_LEN 8
+int kasumi_logtype_driver;
static uint8_t cryptodev_driver_id;
/** Get xform chain order. */
diff --git a/dpdk/drivers/crypto/kasumi/rte_kasumi_pmd_private.h b/dpdk/drivers/crypto/kasumi/rte_kasumi_pmd_private.h
index 488777ca87..d26a86b62c 100644
--- a/dpdk/drivers/crypto/kasumi/rte_kasumi_pmd_private.h
+++ b/dpdk/drivers/crypto/kasumi/rte_kasumi_pmd_private.h
@@ -11,7 +11,7 @@
/**< KASUMI PMD device name */
/** KASUMI PMD LOGTYPE DRIVER */
-int kasumi_logtype_driver;
+extern int kasumi_logtype_driver;
#define KASUMI_LOG(level, fmt, ...) \
rte_log(RTE_LOG_ ## level, kasumi_logtype_driver, \
@@ -70,6 +70,6 @@ kasumi_set_session_parameters(struct kasumi_session *sess,
/** device specific operations function pointer structure */
-struct rte_cryptodev_ops *rte_kasumi_pmd_ops;
+extern struct rte_cryptodev_ops *rte_kasumi_pmd_ops;
#endif /* _RTE_KASUMI_PMD_PRIVATE_H_ */
diff --git a/dpdk/drivers/crypto/mvsam/rte_mrvl_pmd.c b/dpdk/drivers/crypto/mvsam/rte_mrvl_pmd.c
index 41301d7ec0..661e187e37 100644
--- a/dpdk/drivers/crypto/mvsam/rte_mrvl_pmd.c
+++ b/dpdk/drivers/crypto/mvsam/rte_mrvl_pmd.c
@@ -19,6 +19,7 @@
#define MRVL_PMD_MAX_NB_SESS_ARG ("max_nb_sessions")
#define MRVL_PMD_DEFAULT_MAX_NB_SESSIONS 2048
+int mrvl_logtype_driver;
static uint8_t cryptodev_driver_id;
struct mrvl_pmd_init_params {
diff --git a/dpdk/drivers/crypto/mvsam/rte_mrvl_pmd_private.h b/dpdk/drivers/crypto/mvsam/rte_mrvl_pmd_private.h
index 6f8cf56248..200254cca6 100644
--- a/dpdk/drivers/crypto/mvsam/rte_mrvl_pmd_private.h
+++ b/dpdk/drivers/crypto/mvsam/rte_mrvl_pmd_private.h
@@ -13,7 +13,7 @@
/**< Marvell PMD device name */
/** MRVL PMD LOGTYPE DRIVER */
-int mrvl_logtype_driver;
+extern int mrvl_logtype_driver;
#define MRVL_LOG(level, fmt, ...) \
rte_log(RTE_LOG_ ## level, mrvl_logtype_driver, \
diff --git a/dpdk/drivers/crypto/octeontx/otx_cryptodev.c b/dpdk/drivers/crypto/octeontx/otx_cryptodev.c
index c3076487f7..d334fbfdd5 100644
--- a/dpdk/drivers/crypto/octeontx/otx_cryptodev.c
+++ b/dpdk/drivers/crypto/octeontx/otx_cryptodev.c
@@ -17,6 +17,10 @@
static int otx_cryptodev_logtype;
+uint8_t otx_cryptodev_driver_id;
+
+int cpt_logtype;
+
static struct rte_pci_id pci_id_cpt_table[] = {
{
RTE_PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, CPT_81XX_PCI_VF_DEVICE_ID),
diff --git a/dpdk/drivers/crypto/octeontx/otx_cryptodev.h b/dpdk/drivers/crypto/octeontx/otx_cryptodev.h
index 6c2871d712..0b204320a2 100644
--- a/dpdk/drivers/crypto/octeontx/otx_cryptodev.h
+++ b/dpdk/drivers/crypto/octeontx/otx_cryptodev.h
@@ -15,6 +15,6 @@
/*
* Crypto device driver ID
*/
-uint8_t otx_cryptodev_driver_id;
+extern uint8_t otx_cryptodev_driver_id;
#endif /* _OTX_CRYPTODEV_H_ */
diff --git a/dpdk/drivers/crypto/openssl/rte_openssl_pmd.c b/dpdk/drivers/crypto/openssl/rte_openssl_pmd.c
index 36122a43ce..a73c92ffd3 100644
--- a/dpdk/drivers/crypto/openssl/rte_openssl_pmd.c
+++ b/dpdk/drivers/crypto/openssl/rte_openssl_pmd.c
@@ -18,6 +18,7 @@
#define DES_BLOCK_SIZE 8
+int openssl_logtype_driver;
static uint8_t cryptodev_driver_id;
#if (OPENSSL_VERSION_NUMBER < 0x10100000L)
@@ -1997,6 +1998,26 @@ process_asym_op(struct openssl_qp *qp, struct rte_crypto_op *op,
return retval;
}
+static void
+copy_plaintext(struct rte_mbuf *m_src, struct rte_mbuf *m_dst,
+ struct rte_crypto_op *op)
+{
+ uint8_t *p_src, *p_dst;
+
+ p_src = rte_pktmbuf_mtod(m_src, uint8_t *);
+ p_dst = rte_pktmbuf_mtod(m_dst, uint8_t *);
+
+ /**
+ * Copy the content between cipher offset and auth offset
+ * for generating correct digest.
+ */
+ if (op->sym->cipher.data.offset > op->sym->auth.data.offset)
+ memcpy(p_dst + op->sym->auth.data.offset,
+ p_src + op->sym->auth.data.offset,
+ op->sym->cipher.data.offset -
+ op->sym->auth.data.offset);
+}
+
/** Process crypto operation for mbuf */
static int
process_op(struct openssl_qp *qp, struct rte_crypto_op *op,
@@ -2019,6 +2040,9 @@ process_op(struct openssl_qp *qp, struct rte_crypto_op *op,
break;
case OPENSSL_CHAIN_CIPHER_AUTH:
process_openssl_cipher_op(op, sess, msrc, mdst);
+ /* OOP */
+ if (msrc != mdst)
+ copy_plaintext(msrc, mdst, op);
process_openssl_auth_op(qp, op, sess, mdst, mdst);
break;
case OPENSSL_CHAIN_AUTH_CIPHER:
diff --git a/dpdk/drivers/crypto/openssl/rte_openssl_pmd_private.h b/dpdk/drivers/crypto/openssl/rte_openssl_pmd_private.h
index a8f2c8482b..2a9302bc19 100644
--- a/dpdk/drivers/crypto/openssl/rte_openssl_pmd_private.h
+++ b/dpdk/drivers/crypto/openssl/rte_openssl_pmd_private.h
@@ -16,7 +16,7 @@
/**< Open SSL Crypto PMD device name */
/** OPENSSL PMD LOGTYPE DRIVER */
-int openssl_logtype_driver;
+extern int openssl_logtype_driver;
#define OPENSSL_LOG(level, fmt, ...) \
rte_log(RTE_LOG_ ## level, openssl_logtype_driver, \
"%s() line %u: " fmt "\n", __func__, __LINE__, \
diff --git a/dpdk/drivers/crypto/qat/qat_sym_session.c b/dpdk/drivers/crypto/qat/qat_sym_session.c
index e147572e12..c4f39280c6 100644
--- a/dpdk/drivers/crypto/qat/qat_sym_session.c
+++ b/dpdk/drivers/crypto/qat/qat_sym_session.c
@@ -1432,7 +1432,7 @@ int qat_sym_session_aead_create_cd_auth(struct qat_sym_session *cdesc,
(struct icp_qat_fw_la_auth_req_params *)
((char *)&req_tmpl->serv_specif_rqpars +
sizeof(struct icp_qat_fw_la_cipher_req_params));
- uint16_t state1_size = 0, state2_size = 0;
+ uint16_t state1_size = 0, state2_size = 0, cd_extra_size = 0;
uint16_t hash_offset, cd_size;
uint32_t *aad_len = NULL;
uint32_t wordIndex = 0;
@@ -1608,7 +1608,7 @@ int qat_sym_session_aead_create_cd_auth(struct qat_sym_session *cdesc,
memcpy(cipherconfig->key, authkey, authkeylen);
memset(cipherconfig->key + authkeylen,
0, ICP_QAT_HW_SNOW_3G_UEA2_IV_SZ);
- cdesc->cd_cur_ptr += sizeof(struct icp_qat_hw_cipher_config) +
+ cd_extra_size += sizeof(struct icp_qat_hw_cipher_config) +
authkeylen + ICP_QAT_HW_SNOW_3G_UEA2_IV_SZ;
auth_param->hash_state_sz = ICP_QAT_HW_SNOW_3G_UEA2_IV_SZ >> 3;
break;
@@ -1624,8 +1624,7 @@ int qat_sym_session_aead_create_cd_auth(struct qat_sym_session *cdesc,
+ ICP_QAT_HW_ZUC_3G_EEA3_IV_SZ);
memcpy(cdesc->cd_cur_ptr + state1_size, authkey, authkeylen);
- cdesc->cd_cur_ptr += state1_size + state2_size
- + ICP_QAT_HW_ZUC_3G_EEA3_IV_SZ;
+ cd_extra_size += ICP_QAT_HW_ZUC_3G_EEA3_IV_SZ;
auth_param->hash_state_sz = ICP_QAT_HW_ZUC_3G_EEA3_IV_SZ >> 3;
cdesc->min_qat_dev_gen = QAT_GEN2;
@@ -1711,7 +1710,7 @@ int qat_sym_session_aead_create_cd_auth(struct qat_sym_session *cdesc,
RTE_ALIGN_CEIL(hash_cd_ctrl->inner_state1_sz, 8))
>> 3);
- cdesc->cd_cur_ptr += state1_size + state2_size;
+ cdesc->cd_cur_ptr += state1_size + state2_size + cd_extra_size;
cd_size = cdesc->cd_cur_ptr-(uint8_t *)&cdesc->cd;
cd_pars->u.s.content_desc_addr = cdesc->cd_paddr;
diff --git a/dpdk/drivers/crypto/snow3g/rte_snow3g_pmd.c b/dpdk/drivers/crypto/snow3g/rte_snow3g_pmd.c
index a17536b777..aa3277ff57 100644
--- a/dpdk/drivers/crypto/snow3g/rte_snow3g_pmd.c
+++ b/dpdk/drivers/crypto/snow3g/rte_snow3g_pmd.c
@@ -16,6 +16,7 @@
#define SNOW3G_MAX_BURST 8
#define BYTE_LEN 8
+int snow3g_logtype_driver;
static uint8_t cryptodev_driver_id;
/** Get xform chain order. */
diff --git a/dpdk/drivers/crypto/snow3g/rte_snow3g_pmd_private.h b/dpdk/drivers/crypto/snow3g/rte_snow3g_pmd_private.h
index b7807b6216..debe0516b0 100644
--- a/dpdk/drivers/crypto/snow3g/rte_snow3g_pmd_private.h
+++ b/dpdk/drivers/crypto/snow3g/rte_snow3g_pmd_private.h
@@ -11,7 +11,7 @@
/**< SNOW 3G PMD device name */
/** SNOW 3G PMD LOGTYPE DRIVER */
-int snow3g_logtype_driver;
+extern int snow3g_logtype_driver;
#define SNOW3G_LOG(level, fmt, ...) \
rte_log(RTE_LOG_ ## level, snow3g_logtype_driver, \
diff --git a/dpdk/drivers/crypto/zuc/rte_zuc_pmd.c b/dpdk/drivers/crypto/zuc/rte_zuc_pmd.c
index 313f4590bf..64a0d7a812 100644
--- a/dpdk/drivers/crypto/zuc/rte_zuc_pmd.c
+++ b/dpdk/drivers/crypto/zuc/rte_zuc_pmd.c
@@ -14,6 +14,7 @@
#define ZUC_MAX_BURST 4
#define BYTE_LEN 8
+int zuc_logtype_driver;
static uint8_t cryptodev_driver_id;
/** Get xform chain order. */
diff --git a/dpdk/drivers/crypto/zuc/rte_zuc_pmd_private.h b/dpdk/drivers/crypto/zuc/rte_zuc_pmd_private.h
index 5e5906ddb5..3d827052a5 100644
--- a/dpdk/drivers/crypto/zuc/rte_zuc_pmd_private.h
+++ b/dpdk/drivers/crypto/zuc/rte_zuc_pmd_private.h
@@ -8,10 +8,10 @@
#include <sso_zuc.h>
#define CRYPTODEV_NAME_ZUC_PMD crypto_zuc
-/**< KASUMI PMD device name */
+/**< ZUC PMD device name */
/** ZUC PMD LOGTYPE DRIVER */
-int zuc_logtype_driver;
+extern int zuc_logtype_driver;
#define ZUC_LOG(level, fmt, ...) \
rte_log(RTE_LOG_ ## level, zuc_logtype_driver, \
"%s()... line %u: " fmt "\n", __func__, __LINE__, \
diff --git a/dpdk/drivers/event/dpaa2/dpaa2_eventdev.c b/dpdk/drivers/event/dpaa2/dpaa2_eventdev.c
index b8cb437a0c..270ebbe850 100644
--- a/dpdk/drivers/event/dpaa2/dpaa2_eventdev.c
+++ b/dpdk/drivers/event/dpaa2/dpaa2_eventdev.c
@@ -379,7 +379,7 @@ dpaa2_eventdev_info_get(struct rte_eventdev *dev,
dev_info->max_event_priority_levels =
DPAA2_EVENT_MAX_EVENT_PRIORITY_LEVELS;
dev_info->max_event_ports = rte_fslmc_get_device_count(DPAA2_IO);
- /* we only support dpio upto number of cores*/
+ /* we only support dpio up to number of cores */
if (dev_info->max_event_ports > rte_lcore_count())
dev_info->max_event_ports = rte_lcore_count();
dev_info->max_event_port_dequeue_depth =
diff --git a/dpdk/drivers/event/dsw/dsw_event.c b/dpdk/drivers/event/dsw/dsw_event.c
index eae53b2404..0df9209e4f 100644
--- a/dpdk/drivers/event/dsw/dsw_event.c
+++ b/dpdk/drivers/event/dsw/dsw_event.c
@@ -658,6 +658,9 @@ dsw_port_consider_migration(struct dsw_evdev *dsw,
if (dsw->num_ports == 1)
return;
+ if (seen_events_len < DSW_MAX_EVENTS_RECORDED)
+ return;
+
DSW_LOG_DP_PORT(DEBUG, source_port->id, "Considering migration.\n");
/* Randomize interval to avoid having all threads considering
@@ -930,11 +933,6 @@ dsw_port_ctl_process(struct dsw_evdev *dsw, struct dsw_port *port)
{
struct dsw_ctl_msg msg;
- /* So any table loads happens before the ring dequeue, in the
- * case of a 'paus' message.
- */
- rte_smp_rmb();
-
if (dsw_port_ctl_dequeue(port, &msg) == 0) {
switch (msg.type) {
case DSW_CTL_PAUS_REQ:
@@ -1099,7 +1097,7 @@ dsw_event_enqueue_burst_generic(struct dsw_port *source_port,
DSW_LOG_DP_PORT(DEBUG, source_port->id, "%d non-release events "
"accepted.\n", num_non_release);
- return num_non_release;
+ return (num_non_release + num_release);
}
uint16_t
@@ -1194,11 +1192,6 @@ static uint16_t
dsw_port_dequeue_burst(struct dsw_port *port, struct rte_event *events,
uint16_t num)
{
- struct dsw_port *source_port = port;
- struct dsw_evdev *dsw = source_port->dsw;
-
- dsw_port_ctl_process(dsw, source_port);
-
if (unlikely(port->in_buffer_len > 0)) {
uint16_t dequeued = RTE_MIN(num, port->in_buffer_len);
diff --git a/dpdk/drivers/mempool/dpaa2/meson.build b/dpdk/drivers/mempool/dpaa2/meson.build
index 6b6ead617e..cdec39ddda 100644
--- a/dpdk/drivers/mempool/dpaa2/meson.build
+++ b/dpdk/drivers/mempool/dpaa2/meson.build
@@ -12,3 +12,5 @@ sources = files('dpaa2_hw_mempool.c')
# depends on fslmc bus which uses experimental API
allow_experimental_apis = true
+
+install_headers('rte_dpaa2_mempool.h')
diff --git a/dpdk/drivers/net/atlantic/atl_ethdev.c b/dpdk/drivers/net/atlantic/atl_ethdev.c
index 761347fb59..9c98bd7f91 100644
--- a/dpdk/drivers/net/atlantic/atl_ethdev.c
+++ b/dpdk/drivers/net/atlantic/atl_ethdev.c
@@ -152,8 +152,7 @@ static const struct rte_pci_id pci_id_atl_map[] = {
static struct rte_pci_driver rte_atl_pmd = {
.id_table = pci_id_atl_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_atl_pci_probe,
.remove = eth_atl_pci_remove,
};
diff --git a/dpdk/drivers/net/avf/avf_ethdev.c b/dpdk/drivers/net/avf/avf_ethdev.c
index e67621e4a9..3924289d8d 100644
--- a/dpdk/drivers/net/avf/avf_ethdev.c
+++ b/dpdk/drivers/net/avf/avf_ethdev.c
@@ -998,7 +998,7 @@ avf_dev_stats_get(struct rte_eth_dev *dev, struct rte_eth_stats *stats)
} else {
PMD_DRV_LOG(ERR, "Get statistics failed");
}
- return -EIO;
+ return ret;
}
static int
@@ -1330,8 +1330,7 @@ static int eth_avf_pci_remove(struct rte_pci_device *pci_dev)
/* Adaptive virtual function driver struct */
static struct rte_pci_driver rte_avf_pmd = {
.id_table = pci_id_avf_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_avf_pci_probe,
.remove = eth_avf_pci_remove,
};
diff --git a/dpdk/drivers/net/avf/avf_rxtx_vec_common.h b/dpdk/drivers/net/avf/avf_rxtx_vec_common.h
index 8057b9682d..b97ea5f2b7 100644
--- a/dpdk/drivers/net/avf/avf_rxtx_vec_common.h
+++ b/dpdk/drivers/net/avf/avf_rxtx_vec_common.h
@@ -33,6 +33,7 @@ reassemble_packets(struct avf_rx_queue *rxq, struct rte_mbuf **rx_bufs,
if (!split_flags[buf_idx]) {
/* it's the last packet of the set */
start->hash = end->hash;
+ start->vlan_tci = end->vlan_tci;
start->ol_flags = end->ol_flags;
/* we need to strip crc for the whole packet */
start->pkt_len -= rxq->crc_len;
diff --git a/dpdk/drivers/net/avp/avp_ethdev.c b/dpdk/drivers/net/avp/avp_ethdev.c
index 09388d05f8..c5dfb3cab7 100644
--- a/dpdk/drivers/net/avp/avp_ethdev.c
+++ b/dpdk/drivers/net/avp/avp_ethdev.c
@@ -1697,7 +1697,7 @@ avp_xmit_scattered_pkts(void *tx_queue,
uint16_t nb_pkts)
{
struct rte_avp_desc *avp_bufs[(AVP_MAX_TX_BURST *
- RTE_AVP_MAX_MBUF_SEGMENTS)];
+ RTE_AVP_MAX_MBUF_SEGMENTS)] = {};
struct avp_queue *txq = (struct avp_queue *)tx_queue;
struct rte_avp_desc *tx_bufs[AVP_MAX_TX_BURST];
struct avp_dev *avp = txq->avp;
diff --git a/dpdk/drivers/net/bnxt/bnxt.h b/dpdk/drivers/net/bnxt/bnxt.h
index 140089d37e..5e5f91d730 100644
--- a/dpdk/drivers/net/bnxt/bnxt.h
+++ b/dpdk/drivers/net/bnxt/bnxt.h
@@ -296,7 +296,6 @@ struct bnxt {
void *bar0;
struct rte_eth_dev *eth_dev;
- struct rte_eth_rss_conf rss_conf;
struct rte_pci_device *pdev;
void *doorbell_base;
diff --git a/dpdk/drivers/net/bnxt/bnxt_ethdev.c b/dpdk/drivers/net/bnxt/bnxt_ethdev.c
index 90139bc837..223f98f9e9 100644
--- a/dpdk/drivers/net/bnxt/bnxt_ethdev.c
+++ b/dpdk/drivers/net/bnxt/bnxt_ethdev.c
@@ -1029,7 +1029,9 @@ static int bnxt_rss_hash_update_op(struct rte_eth_dev *eth_dev,
}
bp->flags |= BNXT_FLAG_UPDATE_HASH;
- memcpy(&bp->rss_conf, rss_conf, sizeof(*rss_conf));
+ memcpy(ð_dev->data->dev_conf.rx_adv_conf.rss_conf,
+ rss_conf,
+ sizeof(*rss_conf));
if (rss_conf->rss_hf & ETH_RSS_IPV4)
hash_type |= HWRM_VNIC_RSS_CFG_INPUT_HASH_TYPE_IPV4;
@@ -1111,7 +1113,7 @@ static int bnxt_rss_hash_conf_get_op(struct rte_eth_dev *eth_dev,
}
if (hash_types) {
PMD_DRV_LOG(ERR,
- "Unknwon RSS config from firmware (%08x), RSS disabled",
+ "Unknown RSS config from firmware (%08x), RSS disabled",
vnic->hash_type);
return -ENOTSUP;
}
@@ -1418,6 +1420,11 @@ static int bnxt_vlan_filter_set_op(struct rte_eth_dev *eth_dev,
{
struct bnxt *bp = eth_dev->data->dev_private;
+ if (!eth_dev->data->dev_started) {
+ PMD_DRV_LOG(ERR, "port must be started before setting vlan\n");
+ return -EINVAL;
+ }
+
/* These operations apply to ALL existing MAC/VLAN filters */
if (on)
return bnxt_add_vlan_filter(bp, vlan_id);
@@ -1544,10 +1551,11 @@ bnxt_fw_version_get(struct rte_eth_dev *dev, char *fw_version, size_t fw_size)
uint8_t fw_major = (bp->fw_ver >> 24) & 0xff;
uint8_t fw_minor = (bp->fw_ver >> 16) & 0xff;
uint8_t fw_updt = (bp->fw_ver >> 8) & 0xff;
+ uint8_t fw_rsvd = bp->fw_ver & 0xff;
int ret;
- ret = snprintf(fw_version, fw_size, "%d.%d.%d",
- fw_major, fw_minor, fw_updt);
+ ret = snprintf(fw_version, fw_size, "%d.%d.%d.%d",
+ fw_major, fw_minor, fw_updt, fw_rsvd);
ret += 1; /* add the size of '\0' */
if (fw_size < (uint32_t)ret)
@@ -3537,8 +3545,7 @@ static int bnxt_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver bnxt_rte_pmd = {
.id_table = bnxt_pci_id_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING |
- RTE_PCI_DRV_INTR_LSC | RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = bnxt_pci_probe,
.remove = bnxt_pci_remove,
};
diff --git a/dpdk/drivers/net/bnxt/bnxt_hwrm.c b/dpdk/drivers/net/bnxt/bnxt_hwrm.c
index 6e6d47751e..cfb4cb63ad 100644
--- a/dpdk/drivers/net/bnxt/bnxt_hwrm.c
+++ b/dpdk/drivers/net/bnxt/bnxt_hwrm.c
@@ -141,8 +141,9 @@ static int bnxt_hwrm_send_message(struct bnxt *bp, void *msg,
}
if (i >= timeout) {
- PMD_DRV_LOG(ERR, "Error(timeout) sending msg 0x%04x\n",
- req->req_type);
+ PMD_DRV_LOG(ERR,
+ "Error(timeout) sending msg 0x%04x, seq_id %d\n",
+ req->req_type, req->seq_id);
return -ETIMEDOUT;
}
return 0;
diff --git a/dpdk/drivers/net/bnxt/bnxt_ring.c b/dpdk/drivers/net/bnxt/bnxt_ring.c
index 85bb7a623d..40edfe52df 100644
--- a/dpdk/drivers/net/bnxt/bnxt_ring.c
+++ b/dpdk/drivers/net/bnxt/bnxt_ring.c
@@ -331,7 +331,7 @@ int bnxt_alloc_hwrm_rx_ring(struct bnxt *bp, int queue_index)
if (rxq->rx_started) {
if (bnxt_init_one_rx_ring(rxq)) {
- RTE_LOG(ERR, PMD,
+ PMD_DRV_LOG(ERR,
"bnxt_init_one_rx_ring failed!\n");
bnxt_rx_queue_release_op(rxq);
rc = -ENOMEM;
diff --git a/dpdk/drivers/net/bnxt/bnxt_rxq.c b/dpdk/drivers/net/bnxt/bnxt_rxq.c
index 005c9f2c2c..d1664dbc09 100644
--- a/dpdk/drivers/net/bnxt/bnxt_rxq.c
+++ b/dpdk/drivers/net/bnxt/bnxt_rxq.c
@@ -160,10 +160,8 @@ int bnxt_mq_rx_configure(struct bnxt *bp)
struct rte_eth_rss_conf *rss = &dev_conf->rx_adv_conf.rss_conf;
uint16_t hash_type = 0;
- if (bp->flags & BNXT_FLAG_UPDATE_HASH) {
- rss = &bp->rss_conf;
+ if (bp->flags & BNXT_FLAG_UPDATE_HASH)
bp->flags &= ~BNXT_FLAG_UPDATE_HASH;
- }
if (rss->rss_hf & ETH_RSS_IPV4)
hash_type |= HWRM_VNIC_RSS_CFG_INPUT_HASH_TYPE_IPV4;
diff --git a/dpdk/drivers/net/cxgbe/cxgbe_flow.c b/dpdk/drivers/net/cxgbe/cxgbe_flow.c
index b6250a2a90..d2466f29e4 100644
--- a/dpdk/drivers/net/cxgbe/cxgbe_flow.c
+++ b/dpdk/drivers/net/cxgbe/cxgbe_flow.c
@@ -156,7 +156,7 @@ ch_rte_parsetype_port(const void *dmask, const struct rte_flow_item *item,
if (val->index > 0x7)
return rte_flow_error_set(e, EINVAL, RTE_FLOW_ERROR_TYPE_ITEM,
item,
- "port index upto 0x7 is supported");
+ "port index up to 0x7 is supported");
CXGBE_FILL_FS(val->index, mask->index, iport);
diff --git a/dpdk/drivers/net/dpaa/dpaa_ethdev.c b/dpdk/drivers/net/dpaa/dpaa_ethdev.c
index f41a01e113..adbf5f6074 100644
--- a/dpdk/drivers/net/dpaa/dpaa_ethdev.c
+++ b/dpdk/drivers/net/dpaa/dpaa_ethdev.c
@@ -827,8 +827,8 @@ dpaa_dev_rx_queue_count(struct rte_eth_dev *dev, uint16_t rx_queue_id)
PMD_INIT_FUNC_TRACE();
if (qman_query_fq_frm_cnt(rxq, &frm_cnt) == 0) {
- RTE_LOG(DEBUG, PMD, "RX frame count for q(%d) is %u\n",
- rx_queue_id, frm_cnt);
+ DPAA_PMD_DEBUG("RX frame count for q(%d) is %u",
+ rx_queue_id, frm_cnt);
}
return frm_cnt;
}
@@ -942,8 +942,7 @@ dpaa_dev_add_mac_addr(struct rte_eth_dev *dev,
ret = fman_if_add_mac_addr(dpaa_intf->fif, addr->addr_bytes, index);
if (ret)
- RTE_LOG(ERR, PMD, "error: Adding the MAC ADDR failed:"
- " err = %d", ret);
+ DPAA_PMD_ERR("Adding the MAC ADDR failed: err = %d", ret);
return 0;
}
@@ -969,7 +968,7 @@ dpaa_dev_set_mac_addr(struct rte_eth_dev *dev,
ret = fman_if_add_mac_addr(dpaa_intf->fif, addr->addr_bytes, 0);
if (ret)
- RTE_LOG(ERR, PMD, "error: Setting the MAC ADDR failed %d", ret);
+ DPAA_PMD_ERR("Setting the MAC ADDR failed %d", ret);
return ret;
}
@@ -1219,6 +1218,7 @@ dpaa_dev_init(struct rte_eth_dev *eth_dev)
struct fman_if *fman_intf;
struct fman_if_bpool *bp, *tmp_bp;
uint32_t cgrid[DPAA_MAX_NUM_PCD_QUEUES];
+ char eth_buf[ETHER_ADDR_FMT_SIZE];
PMD_INIT_FUNC_TRACE();
@@ -1365,15 +1365,9 @@ dpaa_dev_init(struct rte_eth_dev *eth_dev)
/* copy the primary mac address */
ether_addr_copy(&fman_intf->mac_addr, ð_dev->data->mac_addrs[0]);
+ ether_format_addr(eth_buf, sizeof(eth_buf), &fman_intf->mac_addr);
- RTE_LOG(INFO, PMD, "net: dpaa: %s: %02x:%02x:%02x:%02x:%02x:%02x\n",
- dpaa_device->name,
- fman_intf->mac_addr.addr_bytes[0],
- fman_intf->mac_addr.addr_bytes[1],
- fman_intf->mac_addr.addr_bytes[2],
- fman_intf->mac_addr.addr_bytes[3],
- fman_intf->mac_addr.addr_bytes[4],
- fman_intf->mac_addr.addr_bytes[5]);
+ DPAA_PMD_INFO("net: dpaa: %s: %s", dpaa_device->name, eth_buf);
/* Disable RX mode */
fman_if_discard_rx_errors(fman_intf);
@@ -1500,8 +1494,7 @@ rte_dpaa_probe(struct rte_dpaa_driver *dpaa_drv __rte_unused,
}
if (access("/tmp/fmc.bin", F_OK) == -1) {
- RTE_LOG(INFO, PMD,
- "* FMC not configured.Enabling default mode\n");
+ DPAA_PMD_INFO("* FMC not configured.Enabling default mode");
default_q = 1;
}
diff --git a/dpdk/drivers/net/dpaa2/dpaa2_ethdev.c b/dpdk/drivers/net/dpaa2/dpaa2_ethdev.c
index e50467285e..c801d922cf 100644
--- a/dpdk/drivers/net/dpaa2/dpaa2_ethdev.c
+++ b/dpdk/drivers/net/dpaa2/dpaa2_ethdev.c
@@ -436,9 +436,6 @@ dpaa2_eth_dev_configure(struct rte_eth_dev *dev)
if (rx_offloads & DEV_RX_OFFLOAD_VLAN_FILTER)
dpaa2_vlan_offload_set(dev, ETH_VLAN_FILTER_MASK);
- /* update the current status */
- dpaa2_dev_link_update(dev, 0);
-
return 0;
}
@@ -1480,6 +1477,7 @@ dpaa2_dev_set_link_up(struct rte_eth_dev *dev)
/* changing tx burst function to start enqueues */
dev->tx_pkt_burst = dpaa2_dev_tx;
dev->data->dev_link.link_status = state.up;
+ dev->data->dev_link.link_speed = state.rate;
if (state.up)
DPAA2_PMD_INFO("Port %d Link is Up", dev->data->port_id);
diff --git a/dpdk/drivers/net/e1000/em_ethdev.c b/dpdk/drivers/net/e1000/em_ethdev.c
index 28637c4945..db8eef9b49 100644
--- a/dpdk/drivers/net/e1000/em_ethdev.c
+++ b/dpdk/drivers/net/e1000/em_ethdev.c
@@ -320,7 +320,7 @@ eth_em_dev_uninit(struct rte_eth_dev *eth_dev)
PMD_INIT_FUNC_TRACE();
if (rte_eal_process_type() != RTE_PROC_PRIMARY)
- return -EPERM;
+ return 0;
if (adapter->stopped == 0)
eth_em_close(eth_dev);
@@ -351,8 +351,7 @@ static int eth_em_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_em_pmd = {
.id_table = pci_id_em_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_em_pci_probe,
.remove = eth_em_pci_remove,
};
diff --git a/dpdk/drivers/net/e1000/igb_ethdev.c b/dpdk/drivers/net/e1000/igb_ethdev.c
index 2c1f2314e8..5b69f3646f 100644
--- a/dpdk/drivers/net/e1000/igb_ethdev.c
+++ b/dpdk/drivers/net/e1000/igb_ethdev.c
@@ -923,7 +923,7 @@ eth_igb_dev_uninit(struct rte_eth_dev *eth_dev)
PMD_INIT_FUNC_TRACE();
if (rte_eal_process_type() != RTE_PROC_PRIMARY)
- return -EPERM;
+ return 0;
hw = E1000_DEV_PRIVATE_TO_HW(eth_dev->data->dev_private);
pci_dev = RTE_ETH_DEV_TO_PCI(eth_dev);
@@ -1083,7 +1083,7 @@ eth_igbvf_dev_uninit(struct rte_eth_dev *eth_dev)
PMD_INIT_FUNC_TRACE();
if (rte_eal_process_type() != RTE_PROC_PRIMARY)
- return -EPERM;
+ return 0;
if (adapter->stopped == 0)
igbvf_dev_close(eth_dev);
@@ -1115,8 +1115,7 @@ static int eth_igb_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_igb_pmd = {
.id_table = pci_id_igb_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_igb_pci_probe,
.remove = eth_igb_pci_remove,
};
@@ -1139,7 +1138,7 @@ static int eth_igbvf_pci_remove(struct rte_pci_device *pci_dev)
*/
static struct rte_pci_driver rte_igbvf_pmd = {
.id_table = pci_id_igbvf_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING,
.probe = eth_igbvf_pci_probe,
.remove = eth_igbvf_pci_remove,
};
diff --git a/dpdk/drivers/net/ena/base/ena_com.c b/dpdk/drivers/net/ena/base/ena_com.c
index f22d67cd4d..19eec493ed 100644
--- a/dpdk/drivers/net/ena/base/ena_com.c
+++ b/dpdk/drivers/net/ena/base/ena_com.c
@@ -532,11 +532,11 @@ static int ena_com_wait_and_process_admin_cq_polling(struct ena_comp_ctx *comp_c
timeout = ENA_GET_SYSTEM_TIMEOUT(admin_queue->completion_timeout);
while (1) {
- ENA_SPINLOCK_LOCK(admin_queue->q_lock, flags);
- ena_com_handle_admin_completion(admin_queue);
- ENA_SPINLOCK_UNLOCK(admin_queue->q_lock, flags);
+ ENA_SPINLOCK_LOCK(admin_queue->q_lock, flags);
+ ena_com_handle_admin_completion(admin_queue);
+ ENA_SPINLOCK_UNLOCK(admin_queue->q_lock, flags);
- if (comp_ctx->status != ENA_CMD_SUBMITTED)
+ if (comp_ctx->status != ENA_CMD_SUBMITTED)
break;
if (ENA_TIME_EXPIRE(timeout)) {
@@ -2098,12 +2098,14 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
enum ena_admin_hash_functions func,
const u8 *key, u16 key_len, u32 init_val)
{
- struct ena_rss *rss = &ena_dev->rss;
+ struct ena_admin_feature_rss_flow_hash_control *hash_key;
struct ena_admin_get_feat_resp get_resp;
- struct ena_admin_feature_rss_flow_hash_control *hash_key =
- rss->hash_key;
+ enum ena_admin_hash_functions old_func;
+ struct ena_rss *rss = &ena_dev->rss;
int rc;
+ hash_key = rss->hash_key;
+
/* Make sure size is a mult of DWs */
if (unlikely(key_len & 0x3))
return ENA_COM_INVAL;
@@ -2115,7 +2117,7 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
if (unlikely(rc))
return rc;
- if (!((1 << func) & get_resp.u.flow_hash_func.supported_func)) {
+ if (!(BIT(func) & get_resp.u.flow_hash_func.supported_func)) {
ena_trc_err("Flow hash function %d isn't supported\n", func);
return ENA_COM_UNSUPPORTED;
}
@@ -2140,11 +2142,12 @@ int ena_com_fill_hash_function(struct ena_com_dev *ena_dev,
return ENA_COM_INVAL;
}
+ old_func = rss->hash_func;
rc = ena_com_set_hash_function(ena_dev);
/* Restore the old function */
if (unlikely(rc))
- ena_com_get_hash_function(ena_dev, NULL, NULL);
+ rss->hash_func = old_func;
return rc;
}
@@ -2166,7 +2169,11 @@ int ena_com_get_hash_function(struct ena_com_dev *ena_dev,
if (unlikely(rc))
return rc;
- rss->hash_func = get_resp.u.flow_hash_func.selected_func;
+ /* ENA_FFS returns 1 in case the lsb is set */
+ rss->hash_func = ENA_FFS(get_resp.u.flow_hash_func.selected_func);
+ if (rss->hash_func)
+ rss->hash_func--;
+
if (func)
*func = rss->hash_func;
diff --git a/dpdk/drivers/net/ena/base/ena_com.h b/dpdk/drivers/net/ena/base/ena_com.h
index f58cd86a87..f373d50c50 100644
--- a/dpdk/drivers/net/ena/base/ena_com.h
+++ b/dpdk/drivers/net/ena/base/ena_com.h
@@ -37,9 +37,9 @@
#include "ena_plat.h"
#include "ena_includes.h"
-#define ENA_MAX_NUM_IO_QUEUES 128U
+#define ENA_MAX_NUM_IO_QUEUES 128U
/* We need to queues for each IO (on for Tx and one for Rx) */
-#define ENA_TOTAL_NUM_QUEUES (2 * (ENA_MAX_NUM_IO_QUEUES))
+#define ENA_TOTAL_NUM_QUEUES (2 * (ENA_MAX_NUM_IO_QUEUES))
#define ENA_MAX_HANDLERS 256
@@ -84,7 +84,7 @@
#define ENA_INTR_MODER_LEVEL_STRIDE 1
#define ENA_INTR_BYTE_COUNT_NOT_SUPPORTED 0xFFFFFF
-#define ENA_HW_HINTS_NO_TIMEOUT 0xFFFF
+#define ENA_HW_HINTS_NO_TIMEOUT 0xFFFF
enum ena_intr_moder_level {
ENA_INTR_MODER_LOWEST = 0,
@@ -380,7 +380,7 @@ extern "C" {
*/
int ena_com_mmio_reg_read_request_init(struct ena_com_dev *ena_dev);
-/* ena_com_set_mmio_read_mode - Enable/disable the mmio reg read mechanism
+/* ena_com_set_mmio_read_mode - Enable/disable the indirect mmio reg read mechanism
* @ena_dev: ENA communication layer struct
* @readless_supported: readless mode (enable/disable)
*/
@@ -506,7 +506,7 @@ bool ena_com_get_ena_admin_polling_mode(struct ena_com_dev *ena_dev);
/* ena_com_admin_q_comp_intr_handler - admin queue interrupt handler
* @ena_dev: ENA communication layer struct
*
- * This method go over the admin completion queue and wake up all the pending
+ * This method goes over the admin completion queue and wakes up all the pending
* threads that wait on the commands wait event.
*
* @note: Should be called after MSI-X interrupt.
@@ -516,7 +516,7 @@ void ena_com_admin_q_comp_intr_handler(struct ena_com_dev *ena_dev);
/* ena_com_aenq_intr_handler - AENQ interrupt handler
* @ena_dev: ENA communication layer struct
*
- * This method go over the async event notification queue and call the proper
+ * This method goes over the async event notification queue and calls the proper
* aenq handler.
*/
void ena_com_aenq_intr_handler(struct ena_com_dev *dev, void *data);
@@ -533,14 +533,14 @@ void ena_com_abort_admin_commands(struct ena_com_dev *ena_dev);
/* ena_com_wait_for_abort_completion - Wait for admin commands abort.
* @ena_dev: ENA communication layer struct
*
- * This method wait until all the outstanding admin commands will be completed.
+ * This method waits until all the outstanding admin commands are completed.
*/
void ena_com_wait_for_abort_completion(struct ena_com_dev *ena_dev);
/* ena_com_validate_version - Validate the device parameters
* @ena_dev: ENA communication layer struct
*
- * This method validate the device parameters are the same as the saved
+ * This method verifies the device parameters are the same as the saved
* parameters in ena_dev.
* This method is useful after device reset, to validate the device mac address
* and the device offloads are the same as before the reset.
@@ -717,7 +717,7 @@ int ena_com_set_hash_ctrl(struct ena_com_dev *ena_dev);
*
* Retrieve the hash control from the device.
*
- * @note, If the caller called ena_com_fill_hash_ctrl but didn't flash
+ * @note: If the caller called ena_com_fill_hash_ctrl but didn't flash
* it to the device, the new configuration will be lost.
*
* @return: 0 on Success and negative value otherwise.
@@ -769,7 +769,7 @@ int ena_com_indirect_table_set(struct ena_com_dev *ena_dev);
*
* Retrieve the RSS indirection table from the device.
*
- * @note: If the caller called ena_com_indirect_table_fill_entry but didn't flash
+ * @note: If the caller called ena_com_indirect_table_fill_entry but didn't flush
* it to the device, the new configuration will be lost.
*
* @return: 0 on Success and negative value otherwise.
@@ -795,14 +795,14 @@ int ena_com_allocate_debug_area(struct ena_com_dev *ena_dev,
/* ena_com_delete_debug_area - Free the debug area resources.
* @ena_dev: ENA communication layer struct
*
- * Free the allocate debug area.
+ * Free the allocated debug area.
*/
void ena_com_delete_debug_area(struct ena_com_dev *ena_dev);
/* ena_com_delete_host_info - Free the host info resources.
* @ena_dev: ENA communication layer struct
*
- * Free the allocate host info.
+ * Free the allocated host info.
*/
void ena_com_delete_host_info(struct ena_com_dev *ena_dev);
@@ -843,9 +843,9 @@ int ena_com_destroy_io_cq(struct ena_com_dev *ena_dev,
* @cmd_completion: command completion return value.
* @cmd_comp_size: command completion size.
- * Submit an admin command and then wait until the device will return a
+ * Submit an admin command and then wait until the device returns a
* completion.
- * The completion will be copyed into cmd_comp.
+ * The completion will be copied into cmd_comp.
*
* @return - 0 on success, negative value on failure.
*/
@@ -1027,7 +1027,7 @@ static inline void ena_com_calculate_interrupt_delay(struct ena_com_dev *ena_dev
* @intr_reg: interrupt register to update.
* @rx_delay_interval: Rx interval in usecs
* @tx_delay_interval: Tx interval in usecs
- * @unmask: unask enable/disable
+ * @unmask: unmask enable/disable
*
* Prepare interrupt update register with the supplied parameters.
*/
diff --git a/dpdk/drivers/net/ena/base/ena_plat_dpdk.h b/dpdk/drivers/net/ena/base/ena_plat_dpdk.h
index 900ba1a6b0..03ea2cd0dd 100644
--- a/dpdk/drivers/net/ena/base/ena_plat_dpdk.h
+++ b/dpdk/drivers/net/ena/base/ena_plat_dpdk.h
@@ -1,35 +1,7 @@
-/*-
-* BSD LICENSE
-*
-* Copyright (c) 2015-2016 Amazon.com, Inc. or its affiliates.
-* All rights reserved.
-*
-* Redistribution and use in source and binary forms, with or without
-* modification, are permitted provided that the following conditions
-* are met:
-*
-* * Redistributions of source code must retain the above copyright
-* notice, this list of conditions and the following disclaimer.
-* * Redistributions in binary form must reproduce the above copyright
-* notice, this list of conditions and the following disclaimer in
-* the documentation and/or other materials provided with the
-* distribution.
-* * Neither the name of copyright holder nor the names of its
-* contributors may be used to endorse or promote products derived
-* from this software without specific prior written permission.
-*
-* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
-* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
-* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
-* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
-* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-*/
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright (c) 2015-2020 Amazon.com, Inc. or its affiliates.
+ * All rights reserved.
+ */
#ifndef DPDK_ENA_COM_ENA_PLAT_DPDK_H_
#define DPDK_ENA_COM_ENA_PLAT_DPDK_H_
@@ -201,18 +173,22 @@ do { \
* Each rte_memzone should have unique name.
* To satisfy it, count number of allocations and add it to name.
*/
-extern uint32_t ena_alloc_cnt;
+extern rte_atomic32_t ena_alloc_cnt;
#define ENA_MEM_ALLOC_COHERENT(dmadev, size, virt, phys, handle) \
do { \
- const struct rte_memzone *mz; \
- char z_name[RTE_MEMZONE_NAMESIZE]; \
+ const struct rte_memzone *mz = NULL; \
ENA_TOUCH(dmadev); ENA_TOUCH(handle); \
- snprintf(z_name, sizeof(z_name), \
- "ena_alloc_%d", ena_alloc_cnt++); \
- mz = rte_memzone_reserve(z_name, size, SOCKET_ID_ANY, \
- RTE_MEMZONE_IOVA_CONTIG); \
- handle = mz; \
+ if (size > 0) { \
+ char z_name[RTE_MEMZONE_NAMESIZE]; \
+ snprintf(z_name, sizeof(z_name), \
+ "ena_alloc_%d", \
+ rte_atomic32_add_return(&ena_alloc_cnt, 1)); \
+ mz = rte_memzone_reserve(z_name, size, \
+ SOCKET_ID_ANY, \
+ RTE_MEMZONE_IOVA_CONTIG); \
+ handle = mz; \
+ } \
if (mz == NULL) { \
virt = NULL; \
phys = 0; \
@@ -230,14 +206,17 @@ extern uint32_t ena_alloc_cnt;
#define ENA_MEM_ALLOC_COHERENT_NODE( \
dmadev, size, virt, phys, mem_handle, node, dev_node) \
do { \
- const struct rte_memzone *mz; \
- char z_name[RTE_MEMZONE_NAMESIZE]; \
+ const struct rte_memzone *mz = NULL; \
ENA_TOUCH(dmadev); ENA_TOUCH(dev_node); \
- snprintf(z_name, sizeof(z_name), \
- "ena_alloc_%d", ena_alloc_cnt++); \
- mz = rte_memzone_reserve(z_name, size, node, \
+ if (size > 0) { \
+ char z_name[RTE_MEMZONE_NAMESIZE]; \
+ snprintf(z_name, sizeof(z_name), \
+ "ena_alloc_%d", \
+ rte_atomic32_add_return(&ena_alloc_cnt, 1)); \
+ mz = rte_memzone_reserve(z_name, size, node, \
RTE_MEMZONE_IOVA_CONTIG); \
- mem_handle = mz; \
+ mem_handle = mz; \
+ } \
if (mz == NULL) { \
virt = NULL; \
phys = 0; \
@@ -283,4 +262,6 @@ extern uint32_t ena_alloc_cnt;
#define READ_ONCE(var) (*((volatile typeof(var) *)(&(var))))
#endif
+#define ENA_FFS(x) ffs(x)
+
#endif /* DPDK_ENA_COM_ENA_PLAT_DPDK_H_ */
diff --git a/dpdk/drivers/net/ena/ena_ethdev.c b/dpdk/drivers/net/ena/ena_ethdev.c
index 0779bb7713..8afd82bc87 100644
--- a/dpdk/drivers/net/ena/ena_ethdev.c
+++ b/dpdk/drivers/net/ena/ena_ethdev.c
@@ -120,7 +120,7 @@ struct ena_stats {
* Each rte_memzone should have unique name.
* To satisfy it, count number of allocation and add it to name.
*/
-uint32_t ena_alloc_cnt;
+rte_atomic32_t ena_alloc_cnt;
static const struct ena_stats ena_stats_global_strings[] = {
ENA_STAT_GLOBAL_ENTRY(tx_timeout),
@@ -1043,16 +1043,15 @@ static int ena_create_io_queue(struct ena_ring *ring)
ena_qid = ENA_IO_TXQ_IDX(ring->id);
ctx.direction = ENA_COM_IO_QUEUE_DIRECTION_TX;
ctx.mem_queue_type = ena_dev->tx_mem_queue_type;
- ctx.queue_size = adapter->tx_ring_size;
for (i = 0; i < ring->ring_size; i++)
ring->empty_tx_reqs[i] = i;
} else {
ena_qid = ENA_IO_RXQ_IDX(ring->id);
ctx.direction = ENA_COM_IO_QUEUE_DIRECTION_RX;
- ctx.queue_size = adapter->rx_ring_size;
for (i = 0; i < ring->ring_size; i++)
ring->empty_rx_reqs[i] = i;
}
+ ctx.queue_size = ring->ring_size;
ctx.qid = ena_qid;
ctx.msix_vector = -1; /* interrupts not used */
ctx.numa_node = ring->numa_socket_id;
diff --git a/dpdk/drivers/net/enic/enic_ethdev.c b/dpdk/drivers/net/enic/enic_ethdev.c
index ed6dd70c84..5efaa4de43 100644
--- a/dpdk/drivers/net/enic/enic_ethdev.c
+++ b/dpdk/drivers/net/enic/enic_ethdev.c
@@ -1082,8 +1082,7 @@ static int eth_enic_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_enic_pmd = {
.id_table = pci_id_enic_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_enic_pci_probe,
.remove = eth_enic_pci_remove,
};
diff --git a/dpdk/drivers/net/failsafe/failsafe.c b/dpdk/drivers/net/failsafe/failsafe.c
index 06e859e9fd..0180954123 100644
--- a/dpdk/drivers/net/failsafe/failsafe.c
+++ b/dpdk/drivers/net/failsafe/failsafe.c
@@ -182,6 +182,7 @@ fs_eth_dev_create(struct rte_vdev_device *vdev)
}
priv = PRIV(dev);
priv->dev = dev;
+ priv->rxp = FS_RX_PROXY_INIT;
dev->dev_ops = &failsafe_ops;
dev->data->mac_addrs = &PRIV(dev)->mac_addrs[0];
dev->data->dev_link = eth_link;
diff --git a/dpdk/drivers/net/failsafe/failsafe_intr.c b/dpdk/drivers/net/failsafe/failsafe_intr.c
index 1c2cb71c41..de229b2c2f 100644
--- a/dpdk/drivers/net/failsafe/failsafe_intr.c
+++ b/dpdk/drivers/net/failsafe/failsafe_intr.c
@@ -394,7 +394,7 @@ fs_rx_event_proxy_uninstall(struct fs_priv *priv)
free(priv->rxp.evec);
priv->rxp.evec = NULL;
}
- if (priv->rxp.efd > 0) {
+ if (priv->rxp.efd >= 0) {
close(priv->rxp.efd);
priv->rxp.efd = -1;
}
diff --git a/dpdk/drivers/net/failsafe/failsafe_ops.c b/dpdk/drivers/net/failsafe/failsafe_ops.c
index 595278bbf7..a3c30c25a9 100644
--- a/dpdk/drivers/net/failsafe/failsafe_ops.c
+++ b/dpdk/drivers/net/failsafe/failsafe_ops.c
@@ -379,7 +379,7 @@ fs_rx_queue_release(void *queue)
rxq = queue;
dev = rxq->priv->dev;
fs_lock(dev, 0);
- if (rxq->event_fd > 0)
+ if (rxq->event_fd >= 0)
close(rxq->event_fd);
FOREACH_SUBDEV_STATE(sdev, i, dev, DEV_ACTIVE) {
if (ETH(sdev)->data->rx_queues != NULL &&
diff --git a/dpdk/drivers/net/failsafe/failsafe_private.h b/dpdk/drivers/net/failsafe/failsafe_private.h
index 3264bff2f8..cfe29c3f33 100644
--- a/dpdk/drivers/net/failsafe/failsafe_private.h
+++ b/dpdk/drivers/net/failsafe/failsafe_private.h
@@ -58,6 +58,14 @@ struct rx_proxy {
enum rxp_service_state sstate;
};
+#define FS_RX_PROXY_INIT (struct rx_proxy){ \
+ .efd = -1, \
+ .evec = NULL, \
+ .sid = 0, \
+ .scid = 0, \
+ .sstate = SS_NO_SERVICE, \
+}
+
struct rxq {
struct fs_priv *priv;
uint16_t qid;
diff --git a/dpdk/drivers/net/fm10k/fm10k_ethdev.c b/dpdk/drivers/net/fm10k/fm10k_ethdev.c
index f64d07bbad..b90eda7d83 100644
--- a/dpdk/drivers/net/fm10k/fm10k_ethdev.c
+++ b/dpdk/drivers/net/fm10k/fm10k_ethdev.c
@@ -3267,8 +3267,7 @@ static const struct rte_pci_id pci_id_fm10k_map[] = {
static struct rte_pci_driver rte_pmd_fm10k = {
.id_table = pci_id_fm10k_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_fm10k_pci_probe,
.remove = eth_fm10k_pci_remove,
};
diff --git a/dpdk/drivers/net/i40e/base/README b/dpdk/drivers/net/i40e/base/README
index 84f191fad1..b46593566b 100644
--- a/dpdk/drivers/net/i40e/base/README
+++ b/dpdk/drivers/net/i40e/base/README
@@ -1,34 +1,6 @@
-..
- BSD LICENSE
-
- Copyright(c) 2017 Intel Corporation. All rights reserved.
- All rights reserved.
-
- Redistribution and use in source and binary forms, with or without
- modification, are permitted provided that the following conditions
- are met:
-
- * Redistributions of source code must retain the above copyright
- notice, this list of conditions and the following disclaimer.
- * Redistributions in binary form must reproduce the above copyright
- notice, this list of conditions and the following disclaimer in
- the documentation and/or other materials provided with the
- distribution.
- * Neither the name of Intel Corporation nor the names of its
- contributors may be used to endorse or promote products derived
- from this software without specific prior written permission.
-
- THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2017-2020 Intel Corporation
+ */
Intel® I40E driver
==================
diff --git a/dpdk/drivers/net/i40e/base/i40e_adminq.c b/dpdk/drivers/net/i40e/base/i40e_adminq.c
index b2fc6f5900..584da0383c 100644
--- a/dpdk/drivers/net/i40e/base/i40e_adminq.c
+++ b/dpdk/drivers/net/i40e/base/i40e_adminq.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "i40e_status.h"
diff --git a/dpdk/drivers/net/i40e/base/i40e_adminq.h b/dpdk/drivers/net/i40e/base/i40e_adminq.h
index 769d84809e..6ce262ad4b 100644
--- a/dpdk/drivers/net/i40e/base/i40e_adminq.h
+++ b/dpdk/drivers/net/i40e/base/i40e_adminq.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_ADMINQ_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_adminq_cmd.h b/dpdk/drivers/net/i40e/base/i40e_adminq_cmd.h
index cf6ef63e39..ec1ba7825b 100644
--- a/dpdk/drivers/net/i40e/base/i40e_adminq_cmd.h
+++ b/dpdk/drivers/net/i40e/base/i40e_adminq_cmd.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_ADMINQ_CMD_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_alloc.h b/dpdk/drivers/net/i40e/base/i40e_alloc.h
index 4fc1860155..ae14e4d932 100644
--- a/dpdk/drivers/net/i40e/base/i40e_alloc.h
+++ b/dpdk/drivers/net/i40e/base/i40e_alloc.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_ALLOC_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_common.c b/dpdk/drivers/net/i40e/base/i40e_common.c
index 1f8bb603df..b256fb47d3 100644
--- a/dpdk/drivers/net/i40e/base/i40e_common.c
+++ b/dpdk/drivers/net/i40e/base/i40e_common.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "i40e_type.h"
diff --git a/dpdk/drivers/net/i40e/base/i40e_dcb.c b/dpdk/drivers/net/i40e/base/i40e_dcb.c
index a26f82b3a6..d99bd6e3f8 100644
--- a/dpdk/drivers/net/i40e/base/i40e_dcb.c
+++ b/dpdk/drivers/net/i40e/base/i40e_dcb.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "i40e_adminq.h"
diff --git a/dpdk/drivers/net/i40e/base/i40e_dcb.h b/dpdk/drivers/net/i40e/base/i40e_dcb.h
index 85b0eed3ad..8d36fce430 100644
--- a/dpdk/drivers/net/i40e/base/i40e_dcb.h
+++ b/dpdk/drivers/net/i40e/base/i40e_dcb.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_DCB_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_devids.h b/dpdk/drivers/net/i40e/base/i40e_devids.h
index 8b667c2afb..545e35d243 100644
--- a/dpdk/drivers/net/i40e/base/i40e_devids.h
+++ b/dpdk/drivers/net/i40e/base/i40e_devids.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_DEVIDS_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_diag.c b/dpdk/drivers/net/i40e/base/i40e_diag.c
index 3ccbea4829..b3c4cfd3aa 100644
--- a/dpdk/drivers/net/i40e/base/i40e_diag.c
+++ b/dpdk/drivers/net/i40e/base/i40e_diag.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "i40e_diag.h"
diff --git a/dpdk/drivers/net/i40e/base/i40e_diag.h b/dpdk/drivers/net/i40e/base/i40e_diag.h
index 4434fc960b..cb59285d9c 100644
--- a/dpdk/drivers/net/i40e/base/i40e_diag.h
+++ b/dpdk/drivers/net/i40e/base/i40e_diag.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_DIAG_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_hmc.c b/dpdk/drivers/net/i40e/base/i40e_hmc.c
index 11c9ae2072..a47d6e0d79 100644
--- a/dpdk/drivers/net/i40e/base/i40e_hmc.c
+++ b/dpdk/drivers/net/i40e/base/i40e_hmc.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "i40e_osdep.h"
diff --git a/dpdk/drivers/net/i40e/base/i40e_hmc.h b/dpdk/drivers/net/i40e/base/i40e_hmc.h
index 289264ed99..f9aad7dc31 100644
--- a/dpdk/drivers/net/i40e/base/i40e_hmc.h
+++ b/dpdk/drivers/net/i40e/base/i40e_hmc.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_HMC_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_lan_hmc.c b/dpdk/drivers/net/i40e/base/i40e_lan_hmc.c
index 0afee49b13..d3969396f0 100644
--- a/dpdk/drivers/net/i40e/base/i40e_lan_hmc.c
+++ b/dpdk/drivers/net/i40e/base/i40e_lan_hmc.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "i40e_osdep.h"
diff --git a/dpdk/drivers/net/i40e/base/i40e_lan_hmc.h b/dpdk/drivers/net/i40e/base/i40e_lan_hmc.h
index e531ec490a..aa5dceb792 100644
--- a/dpdk/drivers/net/i40e/base/i40e_lan_hmc.h
+++ b/dpdk/drivers/net/i40e/base/i40e_lan_hmc.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_LAN_HMC_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_nvm.c b/dpdk/drivers/net/i40e/base/i40e_nvm.c
index 6c8ca87718..d87a6e56ff 100644
--- a/dpdk/drivers/net/i40e/base/i40e_nvm.c
+++ b/dpdk/drivers/net/i40e/base/i40e_nvm.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "i40e_prototype.h"
diff --git a/dpdk/drivers/net/i40e/base/i40e_osdep.h b/dpdk/drivers/net/i40e/base/i40e_osdep.h
index 8a2d82a8d0..64b15e1b61 100644
--- a/dpdk/drivers/net/i40e/base/i40e_osdep.h
+++ b/dpdk/drivers/net/i40e/base/i40e_osdep.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_OSDEP_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_prototype.h b/dpdk/drivers/net/i40e/base/i40e_prototype.h
index 0cf006dadc..055b38e73d 100644
--- a/dpdk/drivers/net/i40e/base/i40e_prototype.h
+++ b/dpdk/drivers/net/i40e/base/i40e_prototype.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_PROTOTYPE_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_register.h b/dpdk/drivers/net/i40e/base/i40e_register.h
index e93ec3f58f..2408dcb117 100644
--- a/dpdk/drivers/net/i40e/base/i40e_register.h
+++ b/dpdk/drivers/net/i40e/base/i40e_register.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_REGISTER_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_status.h b/dpdk/drivers/net/i40e/base/i40e_status.h
index 1dad4f4b83..cd72169f14 100644
--- a/dpdk/drivers/net/i40e/base/i40e_status.h
+++ b/dpdk/drivers/net/i40e/base/i40e_status.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_STATUS_H_
diff --git a/dpdk/drivers/net/i40e/base/i40e_type.h b/dpdk/drivers/net/i40e/base/i40e_type.h
index 1a637e40e8..3a46e3e1fa 100644
--- a/dpdk/drivers/net/i40e/base/i40e_type.h
+++ b/dpdk/drivers/net/i40e/base/i40e_type.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _I40E_TYPE_H_
diff --git a/dpdk/drivers/net/i40e/base/meson.build b/dpdk/drivers/net/i40e/base/meson.build
index d4c8f872d5..07aa91c08f 100644
--- a/dpdk/drivers/net/i40e/base/meson.build
+++ b/dpdk/drivers/net/i40e/base/meson.build
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: BSD-3-Clause
-# Copyright(c) 2017 Intel Corporation
+# Copyright(c) 2017-2020 Intel Corporation
sources = [
'i40e_adminq.c',
diff --git a/dpdk/drivers/net/i40e/base/virtchnl.h b/dpdk/drivers/net/i40e/base/virtchnl.h
index 88096cb45c..483020d4e5 100644
--- a/dpdk/drivers/net/i40e/base/virtchnl.h
+++ b/dpdk/drivers/net/i40e/base/virtchnl.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _VIRTCHNL_H_
diff --git a/dpdk/drivers/net/i40e/i40e_ethdev.c b/dpdk/drivers/net/i40e/i40e_ethdev.c
index 040bedfad9..8f372d1c09 100644
--- a/dpdk/drivers/net/i40e/i40e_ethdev.c
+++ b/dpdk/drivers/net/i40e/i40e_ethdev.c
@@ -694,8 +694,7 @@ static int eth_i40e_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_i40e_pmd = {
.id_table = pci_id_i40e_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_i40e_pci_probe,
.remove = eth_i40e_pci_remove,
};
@@ -2241,6 +2240,7 @@ i40e_dev_start(struct rte_eth_dev *dev)
struct rte_intr_handle *intr_handle = &pci_dev->intr_handle;
uint32_t intr_vector = 0;
struct i40e_vsi *vsi;
+ uint16_t nb_rxq, nb_txq;
hw->adapter_stopped = 0;
@@ -2279,7 +2279,7 @@ i40e_dev_start(struct rte_eth_dev *dev)
ret = i40e_dev_rxtx_init(pf);
if (ret != I40E_SUCCESS) {
PMD_DRV_LOG(ERR, "Failed to init rx/tx queues");
- goto err_up;
+ return ret;
}
/* Map queues with MSIX interrupt */
@@ -2304,10 +2304,16 @@ i40e_dev_start(struct rte_eth_dev *dev)
}
/* Enable all queues which have been configured */
- ret = i40e_dev_switch_queues(pf, TRUE);
- if (ret != I40E_SUCCESS) {
- PMD_DRV_LOG(ERR, "Failed to enable VSI");
- goto err_up;
+ for (nb_rxq = 0; nb_rxq < dev->data->nb_rx_queues; nb_rxq++) {
+ ret = i40e_dev_rx_queue_start(dev, nb_rxq);
+ if (ret)
+ goto rx_err;
+ }
+
+ for (nb_txq = 0; nb_txq < dev->data->nb_tx_queues; nb_txq++) {
+ ret = i40e_dev_tx_queue_start(dev, nb_txq);
+ if (ret)
+ goto tx_err;
}
/* Enable receiving broadcast packets */
@@ -2337,7 +2343,7 @@ i40e_dev_start(struct rte_eth_dev *dev)
ret = i40e_aq_set_lb_modes(hw, dev->data->dev_conf.lpbk_mode, NULL);
if (ret != I40E_SUCCESS) {
PMD_DRV_LOG(ERR, "fail to set loopback link");
- goto err_up;
+ goto tx_err;
}
}
@@ -2345,7 +2351,7 @@ i40e_dev_start(struct rte_eth_dev *dev)
ret = i40e_apply_link_speed(dev);
if (I40E_SUCCESS != ret) {
PMD_DRV_LOG(ERR, "Fail to apply link setting");
- goto err_up;
+ goto tx_err;
}
if (!rte_intr_allow_others(intr_handle)) {
@@ -2388,9 +2394,12 @@ i40e_dev_start(struct rte_eth_dev *dev)
return I40E_SUCCESS;
-err_up:
- i40e_dev_switch_queues(pf, FALSE);
- i40e_dev_clear_queues(dev);
+tx_err:
+ for (i = 0; i < nb_txq; i++)
+ i40e_dev_tx_queue_stop(dev, i);
+rx_err:
+ for (i = 0; i < nb_rxq; i++)
+ i40e_dev_rx_queue_stop(dev, i);
return ret;
}
@@ -2414,7 +2423,11 @@ i40e_dev_stop(struct rte_eth_dev *dev)
}
/* Disable all queues */
- i40e_dev_switch_queues(pf, FALSE);
+ for (i = 0; i < dev->data->nb_tx_queues; i++)
+ i40e_dev_tx_queue_stop(dev, i);
+
+ for (i = 0; i < dev->data->nb_rx_queues; i++)
+ i40e_dev_rx_queue_stop(dev, i);
/* un-map queues with interrupt registers */
i40e_vsi_disable_queues_intr(main_vsi);
@@ -4806,6 +4819,7 @@ i40e_res_pool_free(struct i40e_res_pool_info *pool,
{
struct pool_entry *entry, *next, *prev, *valid_entry = NULL;
uint32_t pool_offset;
+ uint16_t len;
int insert;
if (pool == NULL) {
@@ -4844,12 +4858,13 @@ i40e_res_pool_free(struct i40e_res_pool_info *pool,
}
insert = 0;
+ len = valid_entry->len;
/* Try to merge with next one*/
if (next != NULL) {
/* Merge with next one */
- if (valid_entry->base + valid_entry->len == next->base) {
+ if (valid_entry->base + len == next->base) {
next->base = valid_entry->base;
- next->len += valid_entry->len;
+ next->len += len;
rte_free(valid_entry);
valid_entry = next;
insert = 1;
@@ -4859,13 +4874,15 @@ i40e_res_pool_free(struct i40e_res_pool_info *pool,
if (prev != NULL) {
/* Merge with previous one */
if (prev->base + prev->len == valid_entry->base) {
- prev->len += valid_entry->len;
+ prev->len += len;
/* If it merge with next one, remove next node */
if (insert == 1) {
LIST_REMOVE(valid_entry, next);
rte_free(valid_entry);
+ valid_entry = NULL;
} else {
rte_free(valid_entry);
+ valid_entry = NULL;
insert = 1;
}
}
@@ -4881,8 +4898,8 @@ i40e_res_pool_free(struct i40e_res_pool_info *pool,
LIST_INSERT_HEAD(&pool->free_list, valid_entry, next);
}
- pool->num_free += valid_entry->len;
- pool->num_alloc -= valid_entry->len;
+ pool->num_free += len;
+ pool->num_alloc -= len;
return 0;
}
@@ -6153,33 +6170,6 @@ i40e_switch_tx_queue(struct i40e_hw *hw, uint16_t q_idx, bool on)
return I40E_SUCCESS;
}
-/* Swith on or off the tx queues */
-static int
-i40e_dev_switch_tx_queues(struct i40e_pf *pf, bool on)
-{
- struct rte_eth_dev_data *dev_data = pf->dev_data;
- struct i40e_tx_queue *txq;
- struct rte_eth_dev *dev = pf->adapter->eth_dev;
- uint16_t i;
- int ret;
-
- for (i = 0; i < dev_data->nb_tx_queues; i++) {
- txq = dev_data->tx_queues[i];
- /* Don't operate the queue if not configured or
- * if starting only per queue */
- if (!txq || !txq->q_set || (on && txq->tx_deferred_start))
- continue;
- if (on)
- ret = i40e_dev_tx_queue_start(dev, i);
- else
- ret = i40e_dev_tx_queue_stop(dev, i);
- if ( ret != I40E_SUCCESS)
- return ret;
- }
-
- return I40E_SUCCESS;
-}
-
int
i40e_switch_rx_queue(struct i40e_hw *hw, uint16_t q_idx, bool on)
{
@@ -6231,59 +6221,6 @@ i40e_switch_rx_queue(struct i40e_hw *hw, uint16_t q_idx, bool on)
return I40E_SUCCESS;
}
-/* Switch on or off the rx queues */
-static int
-i40e_dev_switch_rx_queues(struct i40e_pf *pf, bool on)
-{
- struct rte_eth_dev_data *dev_data = pf->dev_data;
- struct i40e_rx_queue *rxq;
- struct rte_eth_dev *dev = pf->adapter->eth_dev;
- uint16_t i;
- int ret;
-
- for (i = 0; i < dev_data->nb_rx_queues; i++) {
- rxq = dev_data->rx_queues[i];
- /* Don't operate the queue if not configured or
- * if starting only per queue */
- if (!rxq || !rxq->q_set || (on && rxq->rx_deferred_start))
- continue;
- if (on)
- ret = i40e_dev_rx_queue_start(dev, i);
- else
- ret = i40e_dev_rx_queue_stop(dev, i);
- if (ret != I40E_SUCCESS)
- return ret;
- }
-
- return I40E_SUCCESS;
-}
-
-/* Switch on or off all the rx/tx queues */
-int
-i40e_dev_switch_queues(struct i40e_pf *pf, bool on)
-{
- int ret;
-
- if (on) {
- /* enable rx queues before enabling tx queues */
- ret = i40e_dev_switch_rx_queues(pf, on);
- if (ret) {
- PMD_DRV_LOG(ERR, "Failed to switch rx queues");
- return ret;
- }
- ret = i40e_dev_switch_tx_queues(pf, on);
- } else {
- /* Stop tx queues before stopping rx queues */
- ret = i40e_dev_switch_tx_queues(pf, on);
- if (ret) {
- PMD_DRV_LOG(ERR, "Failed to switch tx queues");
- return ret;
- }
- ret = i40e_dev_switch_rx_queues(pf, on);
- }
-
- return ret;
-}
/* Initialize VSI for TX */
static int
@@ -10276,6 +10213,7 @@ i40e_get_swr_pm_cfg(struct i40e_hw *hw, uint32_t *value)
{ I40E_GL_SWR_PM_EF_DEVICE(I40E_DEV_ID_KX_C) },
{ I40E_GL_SWR_PM_EF_DEVICE(I40E_DEV_ID_10G_BASE_T) },
{ I40E_GL_SWR_PM_EF_DEVICE(I40E_DEV_ID_10G_BASE_T4) },
+ { I40E_GL_SWR_PM_EF_DEVICE(I40E_DEV_ID_SFP_X722) },
{ I40E_GL_SWR_PM_SF_DEVICE(I40E_DEV_ID_KX_B) },
{ I40E_GL_SWR_PM_SF_DEVICE(I40E_DEV_ID_QSFP_A) },
diff --git a/dpdk/drivers/net/i40e/i40e_ethdev_vf.c b/dpdk/drivers/net/i40e/i40e_ethdev_vf.c
index 16d67b5938..ee2d8540ca 100644
--- a/dpdk/drivers/net/i40e/i40e_ethdev_vf.c
+++ b/dpdk/drivers/net/i40e/i40e_ethdev_vf.c
@@ -738,7 +738,6 @@ i40evf_stop_queues(struct rte_eth_dev *dev)
for (i = 0; i < dev->data->nb_tx_queues; i++) {
if (i40evf_dev_tx_queue_stop(dev, i) != 0) {
PMD_DRV_LOG(ERR, "Fail to stop queue %u", i);
- return -1;
}
}
@@ -746,7 +745,6 @@ i40evf_stop_queues(struct rte_eth_dev *dev)
for (i = 0; i < dev->data->nb_rx_queues; i++) {
if (i40evf_dev_rx_queue_stop(dev, i) != 0) {
PMD_DRV_LOG(ERR, "Fail to stop queue %u", i);
- return -1;
}
}
@@ -1511,7 +1509,7 @@ static int eth_i40evf_pci_remove(struct rte_pci_device *pci_dev)
*/
static struct rte_pci_driver rte_i40evf_pmd = {
.id_table = pci_id_i40evf_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING,
.probe = eth_i40evf_pci_probe,
.remove = eth_i40evf_pci_remove,
};
@@ -2094,10 +2092,6 @@ i40evf_dev_promiscuous_enable(struct rte_eth_dev *dev)
struct i40e_vf *vf = I40EVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
int ret;
- /* If enabled, just return */
- if (vf->promisc_unicast_enabled)
- return;
-
ret = i40evf_config_promisc(dev, 1, vf->promisc_multicast_enabled);
if (ret == 0)
vf->promisc_unicast_enabled = TRUE;
@@ -2109,10 +2103,6 @@ i40evf_dev_promiscuous_disable(struct rte_eth_dev *dev)
struct i40e_vf *vf = I40EVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
int ret;
- /* If disabled, just return */
- if (!vf->promisc_unicast_enabled)
- return;
-
ret = i40evf_config_promisc(dev, 0, vf->promisc_multicast_enabled);
if (ret == 0)
vf->promisc_unicast_enabled = FALSE;
@@ -2124,10 +2114,6 @@ i40evf_dev_allmulticast_enable(struct rte_eth_dev *dev)
struct i40e_vf *vf = I40EVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
int ret;
- /* If enabled, just return */
- if (vf->promisc_multicast_enabled)
- return;
-
ret = i40evf_config_promisc(dev, vf->promisc_unicast_enabled, 1);
if (ret == 0)
vf->promisc_multicast_enabled = TRUE;
@@ -2139,10 +2125,6 @@ i40evf_dev_allmulticast_disable(struct rte_eth_dev *dev)
struct i40e_vf *vf = I40EVF_DEV_PRIVATE_TO_VF(dev->data->dev_private);
int ret;
- /* If enabled, just return */
- if (!vf->promisc_multicast_enabled)
- return;
-
ret = i40evf_config_promisc(dev, vf->promisc_unicast_enabled, 0);
if (ret == 0)
vf->promisc_multicast_enabled = FALSE;
diff --git a/dpdk/drivers/net/i40e/i40e_flow.c b/dpdk/drivers/net/i40e/i40e_flow.c
index 642532ba96..088b92fdd1 100644
--- a/dpdk/drivers/net/i40e/i40e_flow.c
+++ b/dpdk/drivers/net/i40e/i40e_flow.c
@@ -2543,7 +2543,6 @@ i40e_flow_parse_fdir_pattern(struct rte_eth_dev *dev,
if (next_type == RTE_FLOW_ITEM_TYPE_VLAN ||
ether_type == ETHER_TYPE_IPv4 ||
ether_type == ETHER_TYPE_IPv6 ||
- ether_type == ETHER_TYPE_ARP ||
ether_type == outer_tpid) {
rte_flow_error_set(error, EINVAL,
RTE_FLOW_ERROR_TYPE_ITEM,
@@ -2588,7 +2587,6 @@ i40e_flow_parse_fdir_pattern(struct rte_eth_dev *dev,
if (ether_type == ETHER_TYPE_IPv4 ||
ether_type == ETHER_TYPE_IPv6 ||
- ether_type == ETHER_TYPE_ARP ||
ether_type == outer_tpid) {
rte_flow_error_set(error, EINVAL,
RTE_FLOW_ERROR_TYPE_ITEM,
@@ -4768,7 +4766,6 @@ i40e_flow_destroy(struct rte_eth_dev *dev,
/* If the last flow is destroyed, disable fdir. */
if (!ret && TAILQ_EMPTY(&pf->fdir.fdir_list)) {
- i40e_fdir_teardown(pf);
dev->data->dev_conf.fdir_conf.mode =
RTE_FDIR_MODE_NONE;
}
@@ -4964,8 +4961,6 @@ i40e_flow_flush_fdir_filter(struct i40e_pf *pf)
pf->fdir.inset_flag[pctype] = 0;
}
- i40e_fdir_teardown(pf);
-
return ret;
}
diff --git a/dpdk/drivers/net/i40e/i40e_rxtx.c b/dpdk/drivers/net/i40e/i40e_rxtx.c
index e4a314f4ab..7c620a76b0 100644
--- a/dpdk/drivers/net/i40e/i40e_rxtx.c
+++ b/dpdk/drivers/net/i40e/i40e_rxtx.c
@@ -1586,6 +1586,15 @@ i40e_dev_rx_queue_start(struct rte_eth_dev *dev, uint16_t rx_queue_id)
PMD_INIT_FUNC_TRACE();
rxq = dev->data->rx_queues[rx_queue_id];
+ if (!rxq || !rxq->q_set) {
+ PMD_DRV_LOG(ERR, "RX queue %u not available or setup",
+ rx_queue_id);
+ return -EINVAL;
+ }
+
+ if (rxq->rx_deferred_start)
+ PMD_DRV_LOG(WARNING, "RX queue %u is deferrd start",
+ rx_queue_id);
err = i40e_alloc_rx_queue_mbufs(rxq);
if (err) {
@@ -1620,6 +1629,11 @@ i40e_dev_rx_queue_stop(struct rte_eth_dev *dev, uint16_t rx_queue_id)
struct i40e_hw *hw = I40E_DEV_PRIVATE_TO_HW(dev->data->dev_private);
rxq = dev->data->rx_queues[rx_queue_id];
+ if (!rxq || !rxq->q_set) {
+ PMD_DRV_LOG(ERR, "RX queue %u not available or setup",
+ rx_queue_id);
+ return -EINVAL;
+ }
/*
* rx_queue_id is queue id application refers to, while
@@ -1648,6 +1662,15 @@ i40e_dev_tx_queue_start(struct rte_eth_dev *dev, uint16_t tx_queue_id)
PMD_INIT_FUNC_TRACE();
txq = dev->data->tx_queues[tx_queue_id];
+ if (!txq || !txq->q_set) {
+ PMD_DRV_LOG(ERR, "TX queue %u is not available or setup",
+ tx_queue_id);
+ return -EINVAL;
+ }
+
+ if (txq->tx_deferred_start)
+ PMD_DRV_LOG(WARNING, "TX queue %u is deferrd start",
+ tx_queue_id);
/*
* tx_queue_id is queue id application refers to, while
@@ -1672,6 +1695,11 @@ i40e_dev_tx_queue_stop(struct rte_eth_dev *dev, uint16_t tx_queue_id)
struct i40e_hw *hw = I40E_DEV_PRIVATE_TO_HW(dev->data->dev_private);
txq = dev->data->tx_queues[tx_queue_id];
+ if (!txq || !txq->q_set) {
+ PMD_DRV_LOG(ERR, "TX queue %u is not available or setup",
+ tx_queue_id);
+ return -EINVAL;
+ }
/*
* tx_queue_id is queue id application refers to, while
diff --git a/dpdk/drivers/net/i40e/i40e_rxtx_vec_common.h b/dpdk/drivers/net/i40e/i40e_rxtx_vec_common.h
index 0e6ffa0078..31f73f6054 100644
--- a/dpdk/drivers/net/i40e/i40e_rxtx_vec_common.h
+++ b/dpdk/drivers/net/i40e/i40e_rxtx_vec_common.h
@@ -33,6 +33,7 @@ reassemble_packets(struct i40e_rx_queue *rxq, struct rte_mbuf **rx_bufs,
if (!split_flags[buf_idx]) {
/* it's the last packet of the set */
start->hash = end->hash;
+ start->vlan_tci = end->vlan_tci;
start->ol_flags = end->ol_flags;
/* we need to strip crc for the whole packet */
start->pkt_len -= rxq->crc_len;
diff --git a/dpdk/drivers/net/i40e/i40e_rxtx_vec_neon.c b/dpdk/drivers/net/i40e/i40e_rxtx_vec_neon.c
index deb185fe2f..4376d8911c 100644
--- a/dpdk/drivers/net/i40e/i40e_rxtx_vec_neon.c
+++ b/dpdk/drivers/net/i40e/i40e_rxtx_vec_neon.c
@@ -72,8 +72,9 @@ i40e_rxq_rearm(struct i40e_rx_queue *rxq)
rx_id = (uint16_t)((rxq->rxrearm_start == 0) ?
(rxq->nb_rx_desc - 1) : (rxq->rxrearm_start - 1));
+ rte_cio_wmb();
/* Update the tail pointer on the NIC */
- I40E_PCI_REG_WRITE(rxq->qrx_tail, rx_id);
+ I40E_PCI_REG_WRITE_RELAXED(rxq->qrx_tail, rx_id);
}
static inline void
@@ -564,7 +565,8 @@ i40e_xmit_fixed_burst_vec(void *tx_queue, struct rte_mbuf **tx_pkts,
txq->tx_tail = tx_id;
- I40E_PCI_REG_WRITE(txq->qtx_tail, txq->tx_tail);
+ rte_cio_wmb();
+ I40E_PCI_REG_WRITE_RELAXED(txq->qtx_tail, tx_id);
return nb_pkts;
}
diff --git a/dpdk/drivers/net/ixgbe/base/README b/dpdk/drivers/net/ixgbe/base/README
index 431be0260e..a48b14ed27 100644
--- a/dpdk/drivers/net/ixgbe/base/README
+++ b/dpdk/drivers/net/ixgbe/base/README
@@ -1,34 +1,6 @@
-..
- BSD LICENSE
-
- Copyright(c) 2010-2018 Intel Corporation. All rights reserved.
- All rights reserved.
-
- Redistribution and use in source and binary forms, with or without
- modification, are permitted provided that the following conditions
- are met:
-
- * Redistributions of source code must retain the above copyright
- notice, this list of conditions and the following disclaimer.
- * Redistributions in binary form must reproduce the above copyright
- notice, this list of conditions and the following disclaimer in
- the documentation and/or other materials provided with the
- distribution.
- * Neither the name of Intel Corporation nor the names of its
- contributors may be used to endorse or promote products derived
- from this software without specific prior written permission.
-
- THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2020 Intel Corporation
+ */
Intel® IXGBE driver
===================
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_82598.c b/dpdk/drivers/net/ixgbe/base/ixgbe_82598.c
index 245ff75d55..c83e1c6b30 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_82598.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_82598.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "ixgbe_type.h"
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_82598.h b/dpdk/drivers/net/ixgbe/base/ixgbe_82598.h
index 8013f495ec..7bad5e12d3 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_82598.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_82598.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_82598_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_82599.c b/dpdk/drivers/net/ixgbe/base/ixgbe_82599.c
index 96bdde62c8..9cd0b1428c 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_82599.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_82599.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "ixgbe_type.h"
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_82599.h b/dpdk/drivers/net/ixgbe/base/ixgbe_82599.h
index a32eb1f517..238481983f 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_82599.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_82599.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_82599_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_api.c b/dpdk/drivers/net/ixgbe/base/ixgbe_api.c
index 873c07999c..0a22df3d06 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_api.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_api.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "ixgbe_api.h"
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_api.h b/dpdk/drivers/net/ixgbe/base/ixgbe_api.h
index ff8f7b2611..33e7c3c215 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_api.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_api.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_API_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_common.c b/dpdk/drivers/net/ixgbe/base/ixgbe_common.c
index 62ff767230..4eb98dc198 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_common.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_common.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "ixgbe_common.h"
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_common.h b/dpdk/drivers/net/ixgbe/base/ixgbe_common.h
index 3bb2475119..7a31f088c4 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_common.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_common.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_COMMON_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb.c b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb.c
index a590e0e07c..53def2146e 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb.h b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb.h
index 503d06018f..c2a1013ac0 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_DCB_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82598.c b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82598.c
index d87cb58857..bb309e28fd 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82598.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82598.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82598.h b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82598.h
index 1a14744482..8f36881378 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82598.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82598.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_DCB_82598_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82599.c b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82599.c
index f4f0ff0190..04e0d1fb7d 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82599.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82599.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82599.h b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82599.h
index 085ada27f7..7bd1d6a325 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82599.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_dcb_82599.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_DCB_82599_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_hv_vf.c b/dpdk/drivers/net/ixgbe/base/ixgbe_hv_vf.c
index 67a124d8d1..6005c4ac93 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_hv_vf.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_hv_vf.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "ixgbe_vf.h"
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_hv_vf.h b/dpdk/drivers/net/ixgbe/base/ixgbe_hv_vf.h
index 9664f3bdbf..dd2e1eee4e 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_hv_vf.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_hv_vf.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_HV_VF_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_mbx.c b/dpdk/drivers/net/ixgbe/base/ixgbe_mbx.c
index cb82942dfa..13bdb5f68f 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_mbx.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_mbx.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "ixgbe_type.h"
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_mbx.h b/dpdk/drivers/net/ixgbe/base/ixgbe_mbx.h
index 5d32cbc074..1a45e49c2f 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_mbx.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_mbx.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_MBX_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_osdep.h b/dpdk/drivers/net/ixgbe/base/ixgbe_osdep.h
index ea8dc1cbe5..a4eb71777c 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_osdep.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_osdep.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_OS_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_phy.c b/dpdk/drivers/net/ixgbe/base/ixgbe_phy.c
index dd118f9170..a8243fa974 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_phy.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_phy.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "ixgbe_api.h"
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_phy.h b/dpdk/drivers/net/ixgbe/base/ixgbe_phy.h
index f1605f2cc9..a06c3be170 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_phy.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_phy.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_PHY_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_type.h b/dpdk/drivers/net/ixgbe/base/ixgbe_type.h
index 077b8f01c7..15e9370105 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_type.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_type.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_TYPE_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_vf.c b/dpdk/drivers/net/ixgbe/base/ixgbe_vf.c
index aac37822e4..7f69ece107 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_vf.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_vf.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_vf.h b/dpdk/drivers/net/ixgbe/base/ixgbe_vf.h
index dba643fced..be58b4f76e 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_vf.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_vf.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_VF_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_x540.c b/dpdk/drivers/net/ixgbe/base/ixgbe_x540.c
index f00f0eae7e..d65f47c181 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_x540.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_x540.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "ixgbe_x540.h"
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_x540.h b/dpdk/drivers/net/ixgbe/base/ixgbe_x540.h
index 231dfe56e5..ba79847d11 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_x540.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_x540.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_X540_H_
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_x550.c b/dpdk/drivers/net/ixgbe/base/ixgbe_x550.c
index a920a146e7..f2c8e5425e 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_x550.c
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_x550.c
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#include "ixgbe_x550.h"
diff --git a/dpdk/drivers/net/ixgbe/base/ixgbe_x550.h b/dpdk/drivers/net/ixgbe/base/ixgbe_x550.h
index 3bd98f243d..10086ab423 100644
--- a/dpdk/drivers/net/ixgbe/base/ixgbe_x550.h
+++ b/dpdk/drivers/net/ixgbe/base/ixgbe_x550.h
@@ -1,5 +1,5 @@
/* SPDX-License-Identifier: BSD-3-Clause
- * Copyright(c) 2001-2018
+ * Copyright(c) 2001-2020 Intel Corporation
*/
#ifndef _IXGBE_X550_H_
diff --git a/dpdk/drivers/net/ixgbe/base/meson.build b/dpdk/drivers/net/ixgbe/base/meson.build
index 21ac64bf5c..e4807e59a5 100644
--- a/dpdk/drivers/net/ixgbe/base/meson.build
+++ b/dpdk/drivers/net/ixgbe/base/meson.build
@@ -1,5 +1,5 @@
# SPDX-License-Identifier: BSD-3-Clause
-# Copyright(c) 2017 Intel Corporation
+# Copyright(c) 2017-2020 Intel Corporation
sources = [
'ixgbe_82598.c',
diff --git a/dpdk/drivers/net/ixgbe/ixgbe_ethdev.c b/dpdk/drivers/net/ixgbe/ixgbe_ethdev.c
index 2d49ea011b..aa0e90a13c 100644
--- a/dpdk/drivers/net/ixgbe/ixgbe_ethdev.c
+++ b/dpdk/drivers/net/ixgbe/ixgbe_ethdev.c
@@ -1866,8 +1866,7 @@ static int eth_ixgbe_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_ixgbe_pmd = {
.id_table = pci_id_ixgbe_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_ixgbe_pci_probe,
.remove = eth_ixgbe_pci_remove,
};
@@ -1889,7 +1888,7 @@ static int eth_ixgbevf_pci_remove(struct rte_pci_device *pci_dev)
*/
static struct rte_pci_driver rte_ixgbevf_pmd = {
.id_table = pci_id_ixgbevf_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING,
.probe = eth_ixgbevf_pci_probe,
.remove = eth_ixgbevf_pci_remove,
};
@@ -2580,6 +2579,8 @@ ixgbe_flow_ctrl_enable(struct rte_eth_dev *dev, struct ixgbe_hw *hw)
int err;
uint32_t mflcn;
+ ixgbe_setup_fc(hw);
+
err = ixgbe_fc_enable(hw);
/* Not negotiated is not an error case */
@@ -4187,6 +4188,11 @@ ixgbe_dev_link_update_share(struct rte_eth_dev *dev,
if (wait_to_complete == 0 || dev->data->dev_conf.intr_conf.lsc != 0)
wait = 0;
+/* BSD has no interrupt mechanism, so force NIC status synchronization. */
+#ifdef RTE_EXEC_ENV_FREEBSD
+ wait = 1;
+#endif
+
if (vf)
diag = ixgbevf_check_link(hw, &link_speed, &link_up, wait);
else
diff --git a/dpdk/drivers/net/ixgbe/rte_pmd_ixgbe.c b/dpdk/drivers/net/ixgbe/rte_pmd_ixgbe.c
index b946808bc2..62376bdad7 100644
--- a/dpdk/drivers/net/ixgbe/rte_pmd_ixgbe.c
+++ b/dpdk/drivers/net/ixgbe/rte_pmd_ixgbe.c
@@ -521,6 +521,9 @@ rte_pmd_ixgbe_macsec_enable(uint16_t port, uint8_t en, uint8_t rp)
dev = &rte_eth_devices[port];
+ if (!is_ixgbe_supported(dev))
+ return -ENOTSUP;
+
macsec_setting.offload_en = 1;
macsec_setting.encrypt_en = en;
macsec_setting.replayprotect_en = rp;
@@ -541,6 +544,9 @@ rte_pmd_ixgbe_macsec_disable(uint16_t port)
dev = &rte_eth_devices[port];
+ if (!is_ixgbe_supported(dev))
+ return -ENOTSUP;
+
ixgbe_dev_macsec_setting_reset(dev);
ixgbe_dev_macsec_register_disable(dev);
diff --git a/dpdk/drivers/net/mlx4/mlx4.c b/dpdk/drivers/net/mlx4/mlx4.c
index 4428edf108..5e22ee4381 100644
--- a/dpdk/drivers/net/mlx4/mlx4.c
+++ b/dpdk/drivers/net/mlx4/mlx4.c
@@ -48,6 +48,10 @@
#include "mlx4_rxtx.h"
#include "mlx4_utils.h"
+#ifdef MLX4_GLUE
+const struct mlx4_glue *mlx4_glue;
+#endif
+
struct mlx4_dev_list mlx4_mem_event_cb_list =
LIST_HEAD_INITIALIZER(mlx4_mem_event_cb_list);
@@ -69,6 +73,53 @@ const char *pmd_mlx4_init_params[] = {
static void mlx4_dev_stop(struct rte_eth_dev *dev);
+/**
+ * Initialize process private data structure.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+mlx4_proc_priv_init(struct rte_eth_dev *dev)
+{
+ struct mlx4_proc_priv *ppriv;
+ size_t ppriv_size;
+
+ /*
+ * UAR register table follows the process private structure. BlueFlame
+ * registers for Tx queues are stored in the table.
+ */
+ ppriv_size = sizeof(struct mlx4_proc_priv) +
+ RTE_MAX_QUEUES_PER_PORT * sizeof(void *);
+ ppriv = rte_malloc_socket("mlx4_proc_priv", ppriv_size,
+ RTE_CACHE_LINE_SIZE, dev->device->numa_node);
+ if (!ppriv) {
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
+ ppriv->uar_table_sz = ppriv_size;
+ dev->process_private = ppriv;
+ return 0;
+}
+
+/**
+ * Un-initialize process private data structure.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ */
+static void
+mlx4_proc_priv_uninit(struct rte_eth_dev *dev)
+{
+ if (!dev->process_private)
+ return;
+ rte_free(dev->process_private);
+ dev->process_private = NULL;
+}
+
/**
* DPDK callback for Ethernet device configuration.
*
@@ -95,9 +146,17 @@ mlx4_dev_configure(struct rte_eth_dev *dev)
goto exit;
}
ret = mlx4_intr_install(priv);
- if (ret)
+ if (ret) {
ERROR("%p: interrupt handler installation failed",
(void *)dev);
+ goto exit;
+ }
+ ret = mlx4_proc_priv_init(dev);
+ if (ret) {
+ ERROR("%p: process private data allocation failed",
+ (void *)dev);
+ goto exit;
+ }
exit:
return ret;
}
@@ -209,6 +268,7 @@ mlx4_dev_close(struct rte_eth_dev *dev)
mlx4_rx_queue_release(dev->data->rx_queues[i]);
for (i = 0; i != dev->data->nb_tx_queues; ++i)
mlx4_tx_queue_release(dev->data->tx_queues[i]);
+ mlx4_proc_priv_uninit(dev);
mlx4_mr_release(dev);
if (priv->pd != NULL) {
assert(priv->ctx != NULL);
diff --git a/dpdk/drivers/net/mlx4/mlx4.h b/dpdk/drivers/net/mlx4/mlx4.h
index 758b7aa435..8454a5fcec 100644
--- a/dpdk/drivers/net/mlx4/mlx4.h
+++ b/dpdk/drivers/net/mlx4/mlx4.h
@@ -75,6 +75,17 @@ struct rte_flow;
LIST_HEAD(mlx4_dev_list, mlx4_priv);
LIST_HEAD(mlx4_mr_list, mlx4_mr);
+/* Per-process private structure. */
+struct mlx4_proc_priv {
+ size_t uar_table_sz;
+ /* Size of UAR register table. */
+ void *uar_table[];
+ /* Table of UAR registers for each process. */
+};
+
+#define MLX4_PROC_PRIV(port_id) \
+ ((struct mlx4_proc_priv *)rte_eth_devices[port_id].process_private)
+
/** Private data structure. */
struct mlx4_priv {
LIST_ENTRY(mlx4_priv) mem_event_cb;
diff --git a/dpdk/drivers/net/mlx4/mlx4_flow.c b/dpdk/drivers/net/mlx4/mlx4_flow.c
index 5136d136ff..dfdc790aaf 100644
--- a/dpdk/drivers/net/mlx4/mlx4_flow.c
+++ b/dpdk/drivers/net/mlx4/mlx4_flow.c
@@ -976,12 +976,13 @@ mlx4_drop_get(struct mlx4_priv *priv)
priv->drop = drop;
return drop;
error:
- if (drop->qp)
- claim_zero(mlx4_glue->destroy_qp(drop->qp));
- if (drop->cq)
- claim_zero(mlx4_glue->destroy_cq(drop->cq));
- if (drop)
+ if (drop) {
+ if (drop->qp)
+ claim_zero(mlx4_glue->destroy_qp(drop->qp));
+ if (drop->cq)
+ claim_zero(mlx4_glue->destroy_cq(drop->cq));
rte_free(drop);
+ }
rte_errno = ENOMEM;
return NULL;
}
diff --git a/dpdk/drivers/net/mlx4/mlx4_glue.h b/dpdk/drivers/net/mlx4/mlx4_glue.h
index 668ca86700..5d9e985495 100644
--- a/dpdk/drivers/net/mlx4/mlx4_glue.h
+++ b/dpdk/drivers/net/mlx4/mlx4_glue.h
@@ -84,6 +84,6 @@ struct mlx4_glue {
void *attr);
};
-const struct mlx4_glue *mlx4_glue;
+extern const struct mlx4_glue *mlx4_glue;
#endif /* MLX4_GLUE_H_ */
diff --git a/dpdk/drivers/net/mlx4/mlx4_prm.h b/dpdk/drivers/net/mlx4/mlx4_prm.h
index aef77ba06e..16ae6db82d 100644
--- a/dpdk/drivers/net/mlx4/mlx4_prm.h
+++ b/dpdk/drivers/net/mlx4/mlx4_prm.h
@@ -77,7 +77,8 @@ struct mlx4_sq {
uint32_t owner_opcode;
/**< Default owner opcode with HW valid owner bit. */
uint32_t stamp; /**< Stamp value with an invalid HW owner bit. */
- volatile uint32_t *db; /**< Pointer to the doorbell. */
+ uint32_t *db; /**< Pointer to the doorbell. */
+ off_t uar_mmap_offset; /* UAR mmap offset for non-primary process. */
uint32_t doorbell_qpn; /**< qp number to write to the doorbell. */
};
diff --git a/dpdk/drivers/net/mlx4/mlx4_rxtx.c b/dpdk/drivers/net/mlx4/mlx4_rxtx.c
index 8c88effcd1..d5290162dc 100644
--- a/dpdk/drivers/net/mlx4/mlx4_rxtx.c
+++ b/dpdk/drivers/net/mlx4/mlx4_rxtx.c
@@ -1048,7 +1048,7 @@ mlx4_tx_burst(void *dpdk_txq, struct rte_mbuf **pkts, uint16_t pkts_n)
/* Make sure that descriptors are written before doorbell record. */
rte_wmb();
/* Ring QP doorbell. */
- rte_write32(txq->msq.doorbell_qpn, txq->msq.db);
+ rte_write32(txq->msq.doorbell_qpn, MLX4_TX_BFREG(txq));
txq->elts_head += i;
return i;
}
diff --git a/dpdk/drivers/net/mlx4/mlx4_rxtx.h b/dpdk/drivers/net/mlx4/mlx4_rxtx.h
index 29389f1ea7..7a7cc36cd4 100644
--- a/dpdk/drivers/net/mlx4/mlx4_rxtx.h
+++ b/dpdk/drivers/net/mlx4/mlx4_rxtx.h
@@ -97,6 +97,7 @@ struct mlx4_txq_stats {
struct txq {
struct mlx4_sq msq; /**< Info for directly manipulating the SQ. */
struct mlx4_cq mcq; /**< Info for directly manipulating the CQ. */
+ uint16_t port_id; /**< Port ID of device. */
unsigned int elts_head; /**< Current index in (*elts)[]. */
unsigned int elts_tail; /**< First element awaiting completion. */
int elts_comp_cd; /**< Countdown for next completion. */
@@ -118,9 +119,12 @@ struct txq {
uint8_t data[]; /**< Remaining queue resources. */
};
+#define MLX4_TX_BFREG(txq) \
+ (MLX4_PROC_PRIV((txq)->port_id)->uar_table[(txq)->stats.idx])
+
/* mlx4_rxq.c */
-uint8_t mlx4_rss_hash_key_default[MLX4_RSS_HASH_KEY_SIZE];
+extern uint8_t mlx4_rss_hash_key_default[MLX4_RSS_HASH_KEY_SIZE];
int mlx4_rss_init(struct mlx4_priv *priv);
void mlx4_rss_deinit(struct mlx4_priv *priv);
struct mlx4_rss *mlx4_rss_get(struct mlx4_priv *priv, uint64_t fields,
diff --git a/dpdk/drivers/net/mlx4/mlx4_txq.c b/dpdk/drivers/net/mlx4/mlx4_txq.c
index 352700820d..92c9c03d36 100644
--- a/dpdk/drivers/net/mlx4/mlx4_txq.c
+++ b/dpdk/drivers/net/mlx4/mlx4_txq.c
@@ -37,6 +37,23 @@
#include "mlx4_rxtx.h"
#include "mlx4_utils.h"
+/**
+ * Initialize Tx UAR registers for primary process.
+ *
+ * @param txq
+ * Pointer to Tx queue structure.
+ */
+static void
+txq_uar_init(struct txq *txq)
+{
+ struct mlx4_priv *priv = txq->priv;
+ struct mlx4_proc_priv *ppriv = MLX4_PROC_PRIV(PORT_ID(priv));
+
+ assert(rte_eal_process_type() == RTE_PROC_PRIMARY);
+ assert(ppriv);
+ ppriv->uar_table[txq->stats.idx] = txq->msq.db;
+}
+
/**
* Free Tx queue elements.
*
@@ -89,6 +106,7 @@ mlx4_txq_fill_dv_obj_info(struct txq *txq, struct mlx4dv_obj *mlxdv)
sq->owner_opcode = MLX4_OPCODE_SEND | (0u << MLX4_SQ_OWNER_BIT);
sq->stamp = rte_cpu_to_be_32(MLX4_SQ_STAMP_VAL |
(0u << MLX4_SQ_OWNER_BIT));
+ sq->uar_mmap_offset = -1; /* Make mmap() fail. */
sq->db = dqp->sdb;
sq->doorbell_qpn = dqp->doorbell_qpn;
cq->buf = dcq->buf.buf;
@@ -214,6 +232,7 @@ mlx4_tx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
}
*txq = (struct txq){
.priv = priv,
+ .port_id = dev->data->port_id,
.stats = {
.idx = idx,
},
@@ -319,6 +338,7 @@ mlx4_tx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
goto error;
}
mlx4_txq_fill_dv_obj_info(txq, &mlxdv);
+ txq_uar_init(txq);
/* Save first wqe pointer in the first element. */
(&(*txq->elts)[0])->wqe =
(volatile struct mlx4_wqe_ctrl_seg *)txq->msq.buf;
diff --git a/dpdk/drivers/net/mlx5/mlx5.c b/dpdk/drivers/net/mlx5/mlx5.c
index 29370f58f0..01fff19224 100644
--- a/dpdk/drivers/net/mlx5/mlx5.c
+++ b/dpdk/drivers/net/mlx5/mlx5.c
@@ -131,6 +131,10 @@ static rte_spinlock_t mlx5_shared_data_lock = RTE_SPINLOCK_INITIALIZER;
/** Driver-specific log messages type. */
int mlx5_logtype;
+#ifdef MLX5_GLUE
+const struct mlx5_glue *mlx5_glue;
+#endif
+
/**
* Prepare shared data between primary and secondary process.
*/
@@ -238,6 +242,53 @@ mlx5_free_verbs_buf(void *ptr, void *data __rte_unused)
rte_free(ptr);
}
+/**
+ * Initialize process private data structure.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_proc_priv_init(struct rte_eth_dev *dev)
+{
+ struct mlx5_proc_priv *ppriv;
+ size_t ppriv_size;
+
+ /*
+ * UAR register table follows the process private structure. BlueFlame
+ * registers for Tx queues are stored in the table.
+ */
+ ppriv_size = sizeof(struct mlx5_proc_priv) +
+ RTE_MAX_QUEUES_PER_PORT * sizeof(void *);
+ ppriv = rte_malloc_socket("mlx5_proc_priv", ppriv_size,
+ RTE_CACHE_LINE_SIZE, dev->device->numa_node);
+ if (!ppriv) {
+ rte_errno = ENOMEM;
+ return -rte_errno;
+ }
+ ppriv->uar_table_sz = ppriv_size;
+ dev->process_private = ppriv;
+ return 0;
+}
+
+/**
+ * Un-initialize process private data structure.
+ *
+ * @param dev
+ * Pointer to Ethernet device structure.
+ */
+static void
+mlx5_proc_priv_uninit(struct rte_eth_dev *dev)
+{
+ if (!dev->process_private)
+ return;
+ rte_free(dev->process_private);
+ dev->process_private = NULL;
+}
+
/**
* DPDK callback to close the device.
*
@@ -279,6 +330,7 @@ mlx5_dev_close(struct rte_eth_dev *dev)
priv->txqs_n = 0;
priv->txqs = NULL;
}
+ mlx5_proc_priv_uninit(dev);
mlx5_mprq_free_mp(dev);
mlx5_mr_release(dev);
if (priv->pd != NULL) {
@@ -596,121 +648,6 @@ mlx5_args(struct mlx5_dev_config *config, struct rte_devargs *devargs)
static struct rte_pci_driver mlx5_driver;
-/*
- * Reserved UAR address space for TXQ UAR(hw doorbell) mapping, process
- * local resource used by both primary and secondary to avoid duplicate
- * reservation.
- * The space has to be available on both primary and secondary process,
- * TXQ UAR maps to this area using fixed mmap w/o double check.
- */
-static void *uar_base;
-
-static int
-find_lower_va_bound(const struct rte_memseg_list *msl,
- const struct rte_memseg *ms, void *arg)
-{
- void **addr = arg;
-
- if (msl->external)
- return 0;
- if (*addr == NULL)
- *addr = ms->addr;
- else
- *addr = RTE_MIN(*addr, ms->addr);
-
- return 0;
-}
-
-/**
- * Reserve UAR address space for primary process.
- *
- * @param[in] dev
- * Pointer to Ethernet device.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-static int
-mlx5_uar_init_primary(struct rte_eth_dev *dev)
-{
- struct mlx5_priv *priv = dev->data->dev_private;
- void *addr = (void *)0;
-
- if (uar_base) { /* UAR address space mapped. */
- priv->uar_base = uar_base;
- return 0;
- }
- /* find out lower bound of hugepage segments */
- rte_memseg_walk(find_lower_va_bound, &addr);
-
- /* keep distance to hugepages to minimize potential conflicts. */
- addr = RTE_PTR_SUB(addr, (uintptr_t)(MLX5_UAR_OFFSET + MLX5_UAR_SIZE));
- /* anonymous mmap, no real memory consumption. */
- addr = mmap(addr, MLX5_UAR_SIZE,
- PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
- if (addr == MAP_FAILED) {
- DRV_LOG(ERR,
- "port %u failed to reserve UAR address space, please"
- " adjust MLX5_UAR_SIZE or try --base-virtaddr",
- dev->data->port_id);
- rte_errno = ENOMEM;
- return -rte_errno;
- }
- /* Accept either same addr or a new addr returned from mmap if target
- * range occupied.
- */
- DRV_LOG(INFO, "port %u reserved UAR address space: %p",
- dev->data->port_id, addr);
- priv->uar_base = addr; /* for primary and secondary UAR re-mmap. */
- uar_base = addr; /* process local, don't reserve again. */
- return 0;
-}
-
-/**
- * Reserve UAR address space for secondary process, align with
- * primary process.
- *
- * @param[in] dev
- * Pointer to Ethernet device.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-static int
-mlx5_uar_init_secondary(struct rte_eth_dev *dev)
-{
- struct mlx5_priv *priv = dev->data->dev_private;
- void *addr;
-
- assert(priv->uar_base);
- if (uar_base) { /* already reserved. */
- assert(uar_base == priv->uar_base);
- return 0;
- }
- /* anonymous mmap, no real memory consumption. */
- addr = mmap(priv->uar_base, MLX5_UAR_SIZE,
- PROT_NONE, MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
- if (addr == MAP_FAILED) {
- DRV_LOG(ERR, "port %u UAR mmap failed: %p size: %llu",
- dev->data->port_id, priv->uar_base, MLX5_UAR_SIZE);
- rte_errno = ENXIO;
- return -rte_errno;
- }
- if (priv->uar_base != addr) {
- DRV_LOG(ERR,
- "port %u UAR address %p size %llu occupied, please"
- " adjust MLX5_UAR_OFFSET or try EAL parameter"
- " --base-virtaddr",
- dev->data->port_id, priv->uar_base, MLX5_UAR_SIZE);
- rte_errno = ENXIO;
- return -rte_errno;
- }
- uar_base = addr; /* process local, don't reserve again */
- DRV_LOG(INFO, "port %u reserved UAR address space: %p",
- dev->data->port_id, addr);
- return 0;
-}
-
/**
* Spawn an Ethernet device from Verbs information.
*
@@ -916,7 +853,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
}
eth_dev->device = dpdk_dev;
eth_dev->dev_ops = &mlx5_dev_sec_ops;
- err = mlx5_uar_init_secondary(eth_dev);
+ err = mlx5_proc_priv_init(eth_dev);
if (err) {
err = rte_errno;
goto error;
@@ -928,7 +865,7 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
goto error;
}
/* Remap UAR for Tx queues. */
- err = mlx5_tx_uar_remap(eth_dev, err);
+ err = mlx5_tx_uar_init_secondary(eth_dev, err);
if (err) {
err = rte_errno;
goto error;
@@ -1143,11 +1080,6 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
priv->dev_data = eth_dev->data;
eth_dev->data->mac_addrs = priv->mac;
eth_dev->device = dpdk_dev;
- err = mlx5_uar_init_primary(eth_dev);
- if (err) {
- err = rte_errno;
- goto error;
- }
/* Configure the first MAC address by default. */
if (mlx5_get_mac(eth_dev, &mac.addr_bytes)) {
DRV_LOG(ERR,
@@ -1278,12 +1210,11 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
if (own_domain_id)
claim_zero(rte_eth_switch_domain_free(priv->domain_id));
rte_free(priv);
- if (eth_dev != NULL)
- eth_dev->data->dev_private = NULL;
}
if (pd)
claim_zero(mlx5_glue->dealloc_pd(pd));
if (eth_dev != NULL) {
+ mlx5_proc_priv_uninit(eth_dev);
/* mac_addrs must not be freed alone because part of dev_private */
eth_dev->data->mac_addrs = NULL;
rte_eth_dev_release_port(eth_dev);
@@ -1497,6 +1428,8 @@ mlx5_pci_probe(struct rte_pci_driver *pci_drv __rte_unused,
for (i = 0; i != n; ++i) {
uint32_t restore;
+ if (!list[i].ifindex)
+ continue;
list[i].eth_dev = mlx5_dev_spawn(&pci_dev->device,
list[i].ibv_dev, dev_config,
&list[i].info, list[i].ifindex);
diff --git a/dpdk/drivers/net/mlx5/mlx5.h b/dpdk/drivers/net/mlx5/mlx5.h
index 26cbdbc389..cf38b6544d 100644
--- a/dpdk/drivers/net/mlx5/mlx5.h
+++ b/dpdk/drivers/net/mlx5/mlx5.h
@@ -33,7 +33,6 @@
#include "mlx5_utils.h"
#include "mlx5_mr.h"
-#include "mlx5_rxtx.h"
#include "mlx5_autoconf.h"
#include "mlx5_defs.h"
@@ -54,10 +53,22 @@ enum {
PCI_DEVICE_ID_MELLANOX_CONNECTX5BFVF = 0xa2d3,
};
+/* Recognized Infiniband device physical port name types. */
+enum mlx5_nl_phys_port_name_type {
+ MLX5_PHYS_PORT_NAME_TYPE_NOTSET = 0, /* Not set. */
+ MLX5_PHYS_PORT_NAME_TYPE_LEGACY, /* before kernel ver < 5.0 */
+ MLX5_PHYS_PORT_NAME_TYPE_UPLINK, /* p0, kernel ver >= 5.0 */
+ MLX5_PHYS_PORT_NAME_TYPE_PFVF, /* pf0vf0, kernel ver >= 5.0 */
+ MLX5_PHYS_PORT_NAME_TYPE_UNKNOWN, /* Unrecognized. */
+};
+
+
/** Switch information returned by mlx5_nl_switch_info(). */
struct mlx5_switch_info {
uint32_t master:1; /**< Master device. */
uint32_t representor:1; /**< Representor device. */
+ enum mlx5_nl_phys_port_name_type name_type; /** < Port name type. */
+ int32_t pf_num; /**< PF number (valid for pfxvfx format only). */
int32_t port_name; /**< Representor port name. */
uint64_t switch_id; /**< Switch identifier. */
};
@@ -177,6 +188,17 @@ struct mlx5_drop {
struct mlx5_flow_tcf_context;
+/* Per-process private structure. */
+struct mlx5_proc_priv {
+ size_t uar_table_sz;
+ /* Size of UAR register table. */
+ void *uar_table[];
+ /* Table of UAR registers for each process. */
+};
+
+#define MLX5_PROC_PRIV(port_id) \
+ ((struct mlx5_proc_priv *)rte_eth_devices[port_id].process_private)
+
struct mlx5_priv {
LIST_ENTRY(mlx5_priv) mem_event_cb;
/**< Called by memory event callback. */
@@ -255,6 +277,7 @@ struct mlx5_priv {
/* mlx5.c */
int mlx5_getenv_int(const char *);
+int mlx5_proc_priv_init(struct rte_eth_dev *dev);
/* mlx5_ethdev.c */
@@ -290,6 +313,8 @@ unsigned int mlx5_dev_to_port_id(const struct rte_device *dev,
unsigned int port_list_n);
int mlx5_sysfs_switch_info(unsigned int ifindex,
struct mlx5_switch_info *info);
+void mlx5_translate_port_name(const char *port_name_in,
+ struct mlx5_switch_info *port_info_out);
/* mlx5_mac.c */
diff --git a/dpdk/drivers/net/mlx5/mlx5_defs.h b/dpdk/drivers/net/mlx5/mlx5_defs.h
index 480b33c812..13801a5c2d 100644
--- a/dpdk/drivers/net/mlx5/mlx5_defs.h
+++ b/dpdk/drivers/net/mlx5/mlx5_defs.h
@@ -92,16 +92,6 @@
/* Timeout in seconds to get a valid link status. */
#define MLX5_LINK_STATUS_TIMEOUT 10
-/* Reserved address space for UAR mapping. */
-#define MLX5_UAR_SIZE (1ULL << (sizeof(uintptr_t) * 4))
-
-/* Offset of reserved UAR address space to hugepage memory. Offset is used here
- * to minimize possibility of address next to hugepage being used by other code
- * in either primary or secondary process, failing to map TX UAR would make TX
- * packets invisible to HW.
- */
-#define MLX5_UAR_OFFSET (1ULL << (sizeof(uintptr_t) * 4))
-
/* Maximum number of UAR pages used by a port,
* These are the size and mask for an array of mutexes used to synchronize
* the access to port's UARs on platforms that do not support 64 bit writes.
diff --git a/dpdk/drivers/net/mlx5/mlx5_ethdev.c b/dpdk/drivers/net/mlx5/mlx5_ethdev.c
index d49cb59b34..e35ff327c8 100644
--- a/dpdk/drivers/net/mlx5/mlx5_ethdev.c
+++ b/dpdk/drivers/net/mlx5/mlx5_ethdev.c
@@ -446,6 +446,9 @@ mlx5_dev_configure(struct rte_eth_dev *dev)
if (++j == rxqs_n)
j = 0;
}
+ ret = mlx5_proc_priv_init(dev);
+ if (ret)
+ return ret;
return 0;
}
@@ -1311,6 +1314,110 @@ mlx5_dev_to_port_id(const struct rte_device *dev, uint16_t *port_list,
return n;
}
+/**
+ * Extract port name, as a number, from sysfs or netlink information.
+ *
+ * @param[in] port_name_in
+ * String representing the port name.
+ * @param[out] port_info_out
+ * Port information, including port name as a number and port name
+ * type if recognized
+ *
+ * @return
+ * port_name field set according to recognized name format.
+ */
+void
+mlx5_translate_port_name(const char *port_name_in,
+ struct mlx5_switch_info *port_info_out)
+{
+ char pf_c1, pf_c2, vf_c1, vf_c2;
+ char *end;
+ int sc_items;
+
+ /*
+ * Check for port-name as a string of the form pf0vf0
+ * (support kernel ver >= 5.0 or OFED ver >= 4.6).
+ */
+ sc_items = sscanf(port_name_in, "%c%c%d%c%c%d",
+ &pf_c1, &pf_c2, &port_info_out->pf_num,
+ &vf_c1, &vf_c2, &port_info_out->port_name);
+ if (sc_items == 6 &&
+ pf_c1 == 'p' && pf_c2 == 'f' &&
+ vf_c1 == 'v' && vf_c2 == 'f') {
+ port_info_out->name_type = MLX5_PHYS_PORT_NAME_TYPE_PFVF;
+ return;
+ }
+ /*
+ * Check for port-name as a string of the form p0
+ * (support kernel ver >= 5.0, or OFED ver >= 4.6).
+ */
+ sc_items = sscanf(port_name_in, "%c%d",
+ &pf_c1, &port_info_out->port_name);
+ if (sc_items == 2 && pf_c1 == 'p') {
+ port_info_out->name_type = MLX5_PHYS_PORT_NAME_TYPE_UPLINK;
+ return;
+ }
+ /* Check for port-name as a number (support kernel ver < 5.0 */
+ errno = 0;
+ port_info_out->port_name = strtol(port_name_in, &end, 0);
+ if (!errno &&
+ (size_t)(end - port_name_in) == strlen(port_name_in)) {
+ port_info_out->name_type = MLX5_PHYS_PORT_NAME_TYPE_LEGACY;
+ return;
+ }
+ port_info_out->name_type = MLX5_PHYS_PORT_NAME_TYPE_UNKNOWN;
+}
+
+/**
+ * Analyze gathered port parameters via sysfs to recognize master
+ * and representor devices for E-Switch configuration.
+ *
+ * @param[in] device_dir
+ * flag of presence of "device" directory under port device key.
+ * @param[inout] switch_info
+ * Port information, including port name as a number and port name
+ * type if recognized
+ *
+ * @return
+ * master and representor flags are set in switch_info according to
+ * recognized parameters (if any).
+ */
+static void
+mlx5_sysfs_check_switch_info(bool device_dir,
+ struct mlx5_switch_info *switch_info)
+{
+ switch (switch_info->name_type) {
+ case MLX5_PHYS_PORT_NAME_TYPE_UNKNOWN:
+ /*
+ * Name is not recognized, assume the master,
+ * check the device directory presence.
+ */
+ switch_info->master = device_dir;
+ break;
+ case MLX5_PHYS_PORT_NAME_TYPE_NOTSET:
+ /*
+ * Name is not set, this assumes the legacy naming
+ * schema for master, just check if there is
+ * a device directory.
+ */
+ switch_info->master = device_dir;
+ break;
+ case MLX5_PHYS_PORT_NAME_TYPE_UPLINK:
+ /* New uplink naming schema recognized. */
+ switch_info->master = 1;
+ break;
+ case MLX5_PHYS_PORT_NAME_TYPE_LEGACY:
+ /* Legacy representors naming schema. */
+ switch_info->representor = !device_dir;
+ break;
+ case MLX5_PHYS_PORT_NAME_TYPE_PFVF:
+ /* New representors naming schema. */
+ switch_info->representor = 1;
+ break;
+ }
+}
+
+
/**
* Get switch information associated with network interface.
*
@@ -1326,11 +1433,20 @@ int
mlx5_sysfs_switch_info(unsigned int ifindex, struct mlx5_switch_info *info)
{
char ifname[IF_NAMESIZE];
+ char port_name[IF_NAMESIZE];
FILE *file;
- struct mlx5_switch_info data = { .master = 0, };
- bool port_name_set = false;
+ struct mlx5_switch_info data = {
+ .master = 0,
+ .representor = 0,
+ .name_type = MLX5_PHYS_PORT_NAME_TYPE_NOTSET,
+ .port_name = 0,
+ .switch_id = 0,
+ };
+ DIR *dir;
bool port_switch_id_set = false;
+ bool device_dir = false;
char c;
+ int ret;
if (!if_indextoname(ifindex, ifname)) {
rte_errno = errno;
@@ -1341,13 +1457,15 @@ mlx5_sysfs_switch_info(unsigned int ifindex, struct mlx5_switch_info *info)
ifname);
MKSTR(phys_switch_id, "/sys/class/net/%s/phys_switch_id",
ifname);
+ MKSTR(pci_device, "/sys/class/net/%s/device",
+ ifname);
file = fopen(phys_port_name, "rb");
if (file != NULL) {
- port_name_set =
- fscanf(file, "%d%c", &data.port_name, &c) == 2 &&
- c == '\n';
+ ret = fscanf(file, "%s", port_name);
fclose(file);
+ if (ret == 1)
+ mlx5_translate_port_name(port_name, &data);
}
file = fopen(phys_switch_id, "rb");
if (file == NULL) {
@@ -1358,8 +1476,22 @@ mlx5_sysfs_switch_info(unsigned int ifindex, struct mlx5_switch_info *info)
fscanf(file, "%" SCNx64 "%c", &data.switch_id, &c) == 2 &&
c == '\n';
fclose(file);
- data.master = port_switch_id_set && !port_name_set;
- data.representor = port_switch_id_set && port_name_set;
+ dir = opendir(pci_device);
+ if (dir != NULL) {
+ closedir(dir);
+ device_dir = true;
+ }
+ if (port_switch_id_set) {
+ /* We have some E-Switch configuration. */
+ mlx5_sysfs_check_switch_info(device_dir, &data);
+ }
*info = data;
+ assert(!(data.master && data.representor));
+ if (data.master && data.representor) {
+ DRV_LOG(ERR, "ifindex %u device is recognized as master"
+ " and as representor", ifindex);
+ rte_errno = ENODEV;
+ return -rte_errno;
+ }
return 0;
}
diff --git a/dpdk/drivers/net/mlx5/mlx5_flow.c b/dpdk/drivers/net/mlx5/mlx5_flow.c
index 7f518fcd26..30d5b66e64 100644
--- a/dpdk/drivers/net/mlx5/mlx5_flow.c
+++ b/dpdk/drivers/net/mlx5/mlx5_flow.c
@@ -31,8 +31,9 @@
#include "mlx5.h"
#include "mlx5_defs.h"
#include "mlx5_prm.h"
-#include "mlx5_glue.h"
#include "mlx5_flow.h"
+#include "mlx5_glue.h"
+#include "mlx5_rxtx.h"
/* Dev ops structure defined in mlx5.c */
extern const struct eth_dev_ops mlx5_dev_ops;
@@ -1266,7 +1267,6 @@ mlx5_flow_validate_item_ipv6(const struct rte_flow_item *item,
"\xff\xff\xff\xff\xff\xff\xff\xff",
.vtc_flow = RTE_BE32(0xffffffff),
.proto = 0xff,
- .hop_limits = 0xff,
},
};
const int tunnel = !!(item_flags & MLX5_FLOW_LAYER_TUNNEL);
@@ -1441,7 +1441,6 @@ mlx5_flow_validate_item_vxlan(const struct rte_flow_item *item,
uint32_t vlan_id;
uint8_t vni[4];
} id = { .vlan_id = 0, };
- uint32_t vlan_id = 0;
if (item_flags & MLX5_FLOW_LAYER_TUNNEL)
@@ -1468,23 +1467,8 @@ mlx5_flow_validate_item_vxlan(const struct rte_flow_item *item,
return ret;
if (spec) {
memcpy(&id.vni[1], spec->vni, 3);
- vlan_id = id.vlan_id;
memcpy(&id.vni[1], mask->vni, 3);
- vlan_id &= id.vlan_id;
}
- /*
- * Tunnel id 0 is equivalent as not adding a VXLAN layer, if
- * only this layer is defined in the Verbs specification it is
- * interpreted as wildcard and all packets will match this
- * rule, if it follows a full stack layer (ex: eth / ipv4 /
- * udp), all packets matching the layers before will also
- * match this rule. To avoid such situation, VNI 0 is
- * currently refused.
- */
- if (!vlan_id)
- return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ITEM, item,
- "VXLAN vni cannot be 0");
if (!(item_flags & MLX5_FLOW_LAYER_OUTER))
return rte_flow_error_set(error, ENOTSUP,
RTE_FLOW_ERROR_TYPE_ITEM, item,
@@ -1523,7 +1507,6 @@ mlx5_flow_validate_item_vxlan_gpe(const struct rte_flow_item *item,
uint32_t vlan_id;
uint8_t vni[4];
} id = { .vlan_id = 0, };
- uint32_t vlan_id = 0;
if (!priv->config.l3_vxlan_en)
return rte_flow_error_set(error, ENOTSUP,
@@ -1561,22 +1544,8 @@ mlx5_flow_validate_item_vxlan_gpe(const struct rte_flow_item *item,
"VxLAN-GPE protocol"
" not supported");
memcpy(&id.vni[1], spec->vni, 3);
- vlan_id = id.vlan_id;
memcpy(&id.vni[1], mask->vni, 3);
- vlan_id &= id.vlan_id;
}
- /*
- * Tunnel id 0 is equivalent as not adding a VXLAN layer, if only this
- * layer is defined in the Verbs specification it is interpreted as
- * wildcard and all packets will match this rule, if it follows a full
- * stack layer (ex: eth / ipv4 / udp), all packets matching the layers
- * before will also match this rule. To avoid such situation, VNI 0
- * is currently refused.
- */
- if (!vlan_id)
- return rte_flow_error_set(error, ENOTSUP,
- RTE_FLOW_ERROR_TYPE_ITEM, item,
- "VXLAN-GPE vni cannot be 0");
if (!(item_flags & MLX5_FLOW_LAYER_OUTER))
return rte_flow_error_set(error, ENOTSUP,
RTE_FLOW_ERROR_TYPE_ITEM, item,
@@ -2377,6 +2346,8 @@ mlx5_ctrl_flow_vlan(struct rte_eth_dev *dev,
rte_errno = EINVAL;
return -rte_errno;
}
+ if (!(dev->data->dev_conf.rxmode.mq_mode & ETH_MQ_RX_RSS_FLAG))
+ action_rss.types = 0;
for (i = 0; i != priv->reta_idx_n; ++i)
queue[i] = (*priv->reta_idx)[i];
flow = flow_list_create(dev, &priv->ctrl_flows,
diff --git a/dpdk/drivers/net/mlx5/mlx5_flow_dv.c b/dpdk/drivers/net/mlx5/mlx5_flow_dv.c
index 54b8770ffc..460461ab0d 100644
--- a/dpdk/drivers/net/mlx5/mlx5_flow_dv.c
+++ b/dpdk/drivers/net/mlx5/mlx5_flow_dv.c
@@ -29,9 +29,10 @@
#include "mlx5.h"
#include "mlx5_defs.h"
-#include "mlx5_prm.h"
#include "mlx5_glue.h"
+#include "mlx5_prm.h"
#include "mlx5_flow.h"
+#include "mlx5_rxtx.h"
#ifdef HAVE_IBV_FLOW_DV_SUPPORT
@@ -1307,6 +1308,13 @@ flow_dv_translate_item_ipv4(void *matcher, void *key,
}
MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_version, 0xf);
MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_version, 4);
+ /*
+ * On outer header (which must contains L2), or inner header with L2,
+ * set cvlan_tag mask bit to mark this packet as untagged.
+ * This should be done even if item->spec is empty.
+ */
+ if (!inner || item_flags & MLX5_FLOW_LAYER_INNER_L2)
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, cvlan_tag, 1);
if (!ipv4_v)
return;
if (!ipv4_m)
@@ -1334,12 +1342,6 @@ flow_dv_translate_item_ipv4(void *matcher, void *key,
ipv4_m->hdr.next_proto_id);
MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
ipv4_v->hdr.next_proto_id & ipv4_m->hdr.next_proto_id);
- /*
- * On outer header (which must contains L2), or inner header with L2,
- * set cvlan_tag mask bit to mark this packet as untagged.
- */
- if (!inner || item_flags & MLX5_FLOW_LAYER_INNER_L2)
- MLX5_SET(fte_match_set_lyr_2_4, headers_m, cvlan_tag, 1);
}
/**
@@ -1399,6 +1401,13 @@ flow_dv_translate_item_ipv6(void *matcher, void *key,
}
MLX5_SET(fte_match_set_lyr_2_4, headers_m, ip_version, 0xf);
MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_version, 6);
+ /*
+ * On outer header (which must contains L2), or inner header with L2,
+ * set cvlan_tag mask bit to mark this packet as untagged.
+ * This should be done even if item->spec is empty.
+ */
+ if (!inner || item_flags & MLX5_FLOW_LAYER_INNER_L2)
+ MLX5_SET(fte_match_set_lyr_2_4, headers_m, cvlan_tag, 1);
if (!ipv6_v)
return;
if (!ipv6_m)
@@ -1442,12 +1451,6 @@ flow_dv_translate_item_ipv6(void *matcher, void *key,
ipv6_m->hdr.proto);
MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol,
ipv6_v->hdr.proto & ipv6_m->hdr.proto);
- /*
- * On outer header (which must contains L2), or inner header with L2,
- * set cvlan_tag mask bit to mark this packet as untagged.
- */
- if (!inner || item_flags & MLX5_FLOW_LAYER_INNER_L2)
- MLX5_SET(fte_match_set_lyr_2_4, headers_m, cvlan_tag, 1);
}
/**
diff --git a/dpdk/drivers/net/mlx5/mlx5_flow_tcf.c b/dpdk/drivers/net/mlx5/mlx5_flow_tcf.c
index e9c4fe9d75..8456e033d6 100644
--- a/dpdk/drivers/net/mlx5/mlx5_flow_tcf.c
+++ b/dpdk/drivers/net/mlx5/mlx5_flow_tcf.c
@@ -31,6 +31,7 @@
#include <rte_cycles.h>
#include "mlx5.h"
+#include "mlx5_prm.h"
#include "mlx5_flow.h"
#include "mlx5_autoconf.h"
diff --git a/dpdk/drivers/net/mlx5/mlx5_flow_verbs.c b/dpdk/drivers/net/mlx5/mlx5_flow_verbs.c
index 1a8a9e63ca..f4b43d50b9 100644
--- a/dpdk/drivers/net/mlx5/mlx5_flow_verbs.c
+++ b/dpdk/drivers/net/mlx5/mlx5_flow_verbs.c
@@ -30,8 +30,9 @@
#include "mlx5.h"
#include "mlx5_defs.h"
#include "mlx5_prm.h"
-#include "mlx5_glue.h"
#include "mlx5_flow.h"
+#include "mlx5_glue.h"
+#include "mlx5_rxtx.h"
#define VERBS_SPEC_INNER(item_flags) \
(!!((item_flags) & MLX5_FLOW_LAYER_TUNNEL) ? IBV_FLOW_SPEC_INNER : 0)
@@ -479,14 +480,12 @@ flow_verbs_translate_item_ipv6(struct mlx5_flow *dev_flow,
ipv6.val.traffic_class = (vtc_flow_val & IPV6_HDR_TC_MASK) >>
IPV6_HDR_TC_SHIFT;
ipv6.val.next_hdr = spec->hdr.proto;
- ipv6.val.hop_limit = spec->hdr.hop_limits;
ipv6.mask.flow_label =
rte_cpu_to_be_32((vtc_flow_mask & IPV6_HDR_FL_MASK) >>
IPV6_HDR_FL_SHIFT);
ipv6.mask.traffic_class = (vtc_flow_mask & IPV6_HDR_TC_MASK) >>
IPV6_HDR_TC_SHIFT;
ipv6.mask.next_hdr = mask->hdr.proto;
- ipv6.mask.hop_limit = mask->hdr.hop_limits;
/* Remove unwanted bits from values. */
for (i = 0; i < RTE_DIM(ipv6.val.src_ip); ++i) {
ipv6.val.src_ip[i] &= ipv6.mask.src_ip[i];
@@ -495,7 +494,6 @@ flow_verbs_translate_item_ipv6(struct mlx5_flow *dev_flow,
ipv6.val.flow_label &= ipv6.mask.flow_label;
ipv6.val.traffic_class &= ipv6.mask.traffic_class;
ipv6.val.next_hdr &= ipv6.mask.next_hdr;
- ipv6.val.hop_limit &= ipv6.mask.hop_limit;
}
flow_verbs_spec_add(&dev_flow->verbs, &ipv6, size);
}
@@ -575,6 +573,28 @@ flow_verbs_translate_item_udp(struct mlx5_flow *dev_flow,
udp.val.src_port &= udp.mask.src_port;
udp.val.dst_port &= udp.mask.dst_port;
}
+ item++;
+ while (item->type == RTE_FLOW_ITEM_TYPE_VOID)
+ item++;
+ if (!(udp.val.dst_port & udp.mask.dst_port)) {
+ switch ((item)->type) {
+ case RTE_FLOW_ITEM_TYPE_VXLAN:
+ udp.val.dst_port = htons(MLX5_UDP_PORT_VXLAN);
+ udp.mask.dst_port = 0xffff;
+ break;
+ case RTE_FLOW_ITEM_TYPE_VXLAN_GPE:
+ udp.val.dst_port = htons(MLX5_UDP_PORT_VXLAN_GPE);
+ udp.mask.dst_port = 0xffff;
+ break;
+ case RTE_FLOW_ITEM_TYPE_MPLS:
+ udp.val.dst_port = htons(MLX5_UDP_PORT_MPLS);
+ udp.mask.dst_port = 0xffff;
+ break;
+ default:
+ break;
+ }
+ }
+
flow_verbs_spec_add(&dev_flow->verbs, &udp, size);
}
diff --git a/dpdk/drivers/net/mlx5/mlx5_glue.h b/dpdk/drivers/net/mlx5/mlx5_glue.h
index 2d92ba8bcf..0ed754a070 100644
--- a/dpdk/drivers/net/mlx5/mlx5_glue.h
+++ b/dpdk/drivers/net/mlx5/mlx5_glue.h
@@ -166,6 +166,6 @@ struct mlx5_glue {
enum mlx5dv_flow_table_type ft_type);
};
-const struct mlx5_glue *mlx5_glue;
+extern const struct mlx5_glue *mlx5_glue;
#endif /* MLX5_GLUE_H_ */
diff --git a/dpdk/drivers/net/mlx5/mlx5_nl.c b/dpdk/drivers/net/mlx5/mlx5_nl.c
index fe5a27461e..7098d31322 100644
--- a/dpdk/drivers/net/mlx5/mlx5_nl.c
+++ b/dpdk/drivers/net/mlx5/mlx5_nl.c
@@ -84,6 +84,7 @@ struct mlx5_nl_ifindex_data {
const char *name; /**< IB device name (in). */
uint32_t ibindex; /**< IB device index (out). */
uint32_t ifindex; /**< Network interface index (out). */
+ uint32_t ibfound; /**< Found IB index for matching device. */
};
/**
@@ -695,7 +696,7 @@ mlx5_nl_ifindex_cb(struct nlmsghdr *nh, void *arg)
size_t off = NLMSG_HDRLEN;
uint32_t ibindex = 0;
uint32_t ifindex = 0;
- int found = 0;
+ uint32_t found = 0, ibfound = 0;
if (nh->nlmsg_type !=
RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET) &&
@@ -711,6 +712,7 @@ mlx5_nl_ifindex_cb(struct nlmsghdr *nh, void *arg)
switch (na->nla_type) {
case RDMA_NLDEV_ATTR_DEV_INDEX:
ibindex = *(uint32_t *)payload;
+ ibfound = 1;
break;
case RDMA_NLDEV_ATTR_DEV_NAME:
if (!strcmp(payload, data->name))
@@ -727,6 +729,7 @@ mlx5_nl_ifindex_cb(struct nlmsghdr *nh, void *arg)
if (found) {
data->ibindex = ibindex;
data->ifindex = ifindex;
+ data->ibfound = ibfound;
}
return 0;
error:
@@ -759,6 +762,7 @@ mlx5_nl_ifindex(int nl, const char *name)
.name = name,
.ibindex = 0, /* Determined during first pass. */
.ifindex = 0, /* Determined during second pass. */
+ .ibfound = 0,
};
union {
struct nlmsghdr nh;
@@ -782,7 +786,7 @@ mlx5_nl_ifindex(int nl, const char *name)
ret = mlx5_nl_recv(nl, seq, mlx5_nl_ifindex_cb, &data);
if (ret < 0)
return 0;
- if (!data.ibindex)
+ if (!data.ibfound)
goto error;
++seq;
req.nh.nlmsg_type = RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
@@ -813,6 +817,55 @@ mlx5_nl_ifindex(int nl, const char *name)
return 0;
}
+/**
+ * Analyze gathered port parameters via Netlink to recognize master
+ * and representor devices for E-Switch configuration.
+ *
+ * @param[in] num_vf_set
+ * flag of presence of number of VFs port attribute.
+ * @param[inout] switch_info
+ * Port information, including port name as a number and port name
+ * type if recognized
+ *
+ * @return
+ * master and representor flags are set in switch_info according to
+ * recognized parameters (if any).
+ */
+static void
+mlx5_nl_check_switch_info(bool num_vf_set,
+ struct mlx5_switch_info *switch_info)
+{
+ switch (switch_info->name_type) {
+ case MLX5_PHYS_PORT_NAME_TYPE_UNKNOWN:
+ /*
+ * Name is not recognized, assume the master,
+ * check the number of VFs key presence.
+ */
+ switch_info->master = num_vf_set;
+ break;
+ case MLX5_PHYS_PORT_NAME_TYPE_NOTSET:
+ /*
+ * Name is not set, this assumes the legacy naming
+ * schema for master, just check if there is a
+ * number of VFs key.
+ */
+ switch_info->master = num_vf_set;
+ break;
+ case MLX5_PHYS_PORT_NAME_TYPE_UPLINK:
+ /* New uplink naming schema recognized. */
+ switch_info->master = 1;
+ break;
+ case MLX5_PHYS_PORT_NAME_TYPE_LEGACY:
+ /* Legacy representors naming schema. */
+ switch_info->representor = !num_vf_set;
+ break;
+ case MLX5_PHYS_PORT_NAME_TYPE_PFVF:
+ /* New representors naming schema. */
+ switch_info->representor = 1;
+ break;
+ }
+}
+
/**
* Process switch information from Netlink message.
*
@@ -830,31 +883,29 @@ mlx5_nl_switch_info_cb(struct nlmsghdr *nh, void *arg)
struct mlx5_switch_info info = {
.master = 0,
.representor = 0,
+ .name_type = MLX5_PHYS_PORT_NAME_TYPE_NOTSET,
.port_name = 0,
.switch_id = 0,
};
size_t off = NLMSG_LENGTH(sizeof(struct ifinfomsg));
- bool port_name_set = false;
bool switch_id_set = false;
+ bool num_vf_set = false;
if (nh->nlmsg_type != RTM_NEWLINK)
goto error;
while (off < nh->nlmsg_len) {
struct rtattr *ra = (void *)((uintptr_t)nh + off);
void *payload = RTA_DATA(ra);
- char *end;
unsigned int i;
if (ra->rta_len > nh->nlmsg_len - off)
goto error;
switch (ra->rta_type) {
+ case IFLA_NUM_VF:
+ num_vf_set = true;
+ break;
case IFLA_PHYS_PORT_NAME:
- errno = 0;
- info.port_name = strtol(payload, &end, 0);
- if (errno ||
- (size_t)(end - (char *)payload) != strlen(payload))
- goto error;
- port_name_set = true;
+ mlx5_translate_port_name((char *)payload, &info);
break;
case IFLA_PHYS_SWITCH_ID:
info.switch_id = 0;
@@ -867,8 +918,11 @@ mlx5_nl_switch_info_cb(struct nlmsghdr *nh, void *arg)
}
off += RTA_ALIGN(ra->rta_len);
}
- info.master = switch_id_set && !port_name_set;
- info.representor = switch_id_set && port_name_set;
+ if (switch_id_set) {
+ /* We have some E-Switch configuration. */
+ mlx5_nl_check_switch_info(num_vf_set, &info);
+ }
+ assert(!(info.master && info.representor));
memcpy(arg, &info, sizeof(info));
return 0;
error:
@@ -890,15 +944,19 @@ mlx5_nl_switch_info_cb(struct nlmsghdr *nh, void *arg)
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-mlx5_nl_switch_info(int nl, unsigned int ifindex, struct mlx5_switch_info *info)
+mlx5_nl_switch_info(int nl, unsigned int ifindex,
+ struct mlx5_switch_info *info)
{
- uint32_t seq = random();
struct {
struct nlmsghdr nh;
struct ifinfomsg info;
+ struct rtattr rta;
+ uint32_t extmask;
} req = {
.nh = {
- .nlmsg_len = NLMSG_LENGTH(sizeof(req.info)),
+ .nlmsg_len = NLMSG_LENGTH
+ (sizeof(req.info) +
+ RTA_LENGTH(sizeof(uint32_t))),
.nlmsg_type = RTM_GETLINK,
.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK,
},
@@ -906,11 +964,23 @@ mlx5_nl_switch_info(int nl, unsigned int ifindex, struct mlx5_switch_info *info)
.ifi_family = AF_UNSPEC,
.ifi_index = ifindex,
},
+ .rta = {
+ .rta_type = IFLA_EXT_MASK,
+ .rta_len = RTA_LENGTH(sizeof(int32_t)),
+ },
+ .extmask = RTE_LE32(1),
};
+ uint32_t sn = random();
int ret;
- ret = mlx5_nl_send(nl, &req.nh, seq);
+ ret = mlx5_nl_send(nl, &req.nh, sn);
if (ret >= 0)
- ret = mlx5_nl_recv(nl, seq, mlx5_nl_switch_info_cb, info);
+ ret = mlx5_nl_recv(nl, sn, mlx5_nl_switch_info_cb, info);
+ if (info->master && info->representor) {
+ DRV_LOG(ERR, "ifindex %u device is recognized as master"
+ " and as representor", ifindex);
+ rte_errno = ENODEV;
+ ret = -rte_errno;
+ }
return ret;
}
diff --git a/dpdk/drivers/net/mlx5/mlx5_rxtx.h b/dpdk/drivers/net/mlx5/mlx5_rxtx.h
index 820675b824..dc2ca5e4ad 100644
--- a/dpdk/drivers/net/mlx5/mlx5_rxtx.h
+++ b/dpdk/drivers/net/mlx5/mlx5_rxtx.h
@@ -202,8 +202,9 @@ struct mlx5_txq_data {
volatile void *wqes; /* Work queue (use volatile to write into). */
volatile uint32_t *qp_db; /* Work queue doorbell. */
volatile uint32_t *cq_db; /* Completion queue doorbell. */
- volatile void *bf_reg; /* Blueflame register remapped. */
struct rte_mbuf *(*elts)[]; /* TX elements. */
+ uint16_t port_id; /* Port ID of device. */
+ uint16_t idx; /* Queue index. */
struct mlx5_txq_stats stats; /* TX queue counters. */
#ifndef RTE_ARCH_64
rte_spinlock_t *uar_lock;
@@ -231,10 +232,12 @@ struct mlx5_txq_ctrl {
struct mlx5_priv *priv; /* Back pointer to private data. */
struct mlx5_txq_data txq; /* Data path structure. */
off_t uar_mmap_offset; /* UAR mmap offset for non-primary process. */
- volatile void *bf_reg_orig; /* Blueflame register from verbs. */
- uint16_t idx; /* Queue index. */
+ void *bf_reg; /* BlueFlame register from Verbs. */
};
+#define MLX5_TX_BFREG(txq) \
+ (MLX5_PROC_PRIV((txq)->port_id)->uar_table[(txq)->idx])
+
/* mlx5_rxq.c */
extern uint8_t rss_hash_default_key[];
@@ -302,7 +305,7 @@ uint64_t mlx5_get_rx_queue_offloads(struct rte_eth_dev *dev);
int mlx5_tx_queue_setup(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
unsigned int socket, const struct rte_eth_txconf *conf);
void mlx5_tx_queue_release(void *dpdk_txq);
-int mlx5_tx_uar_remap(struct rte_eth_dev *dev, int fd);
+int mlx5_tx_uar_init_secondary(struct rte_eth_dev *dev, int fd);
struct mlx5_txq_ibv *mlx5_txq_ibv_new(struct rte_eth_dev *dev, uint16_t idx);
struct mlx5_txq_ibv *mlx5_txq_ibv_get(struct rte_eth_dev *dev, uint16_t idx);
int mlx5_txq_ibv_release(struct mlx5_txq_ibv *txq_ibv);
@@ -701,7 +704,7 @@ static __rte_always_inline void
mlx5_tx_dbrec_cond_wmb(struct mlx5_txq_data *txq, volatile struct mlx5_wqe *wqe,
int cond)
{
- uint64_t *dst = (uint64_t *)((uintptr_t)txq->bf_reg);
+ uint64_t *dst = MLX5_TX_BFREG(txq);
volatile uint64_t *src = ((volatile uint64_t *)wqe);
rte_cio_wmb();
diff --git a/dpdk/drivers/net/mlx5/mlx5_trigger.c b/dpdk/drivers/net/mlx5/mlx5_trigger.c
index 2137bdc461..6b0f8b2056 100644
--- a/dpdk/drivers/net/mlx5/mlx5_trigger.c
+++ b/dpdk/drivers/net/mlx5/mlx5_trigger.c
@@ -58,12 +58,6 @@ mlx5_txq_start(struct rte_eth_dev *dev)
goto error;
}
}
- ret = mlx5_tx_uar_remap(dev, priv->ctx->cmd_fd);
- if (ret) {
- /* Adjust index for rollback. */
- i = priv->txqs_n - 1;
- goto error;
- }
return 0;
error:
ret = rte_errno; /* Save rte_errno before cleanup. */
diff --git a/dpdk/drivers/net/mlx5/mlx5_txq.c b/dpdk/drivers/net/mlx5/mlx5_txq.c
index e6020fbcbf..42ab34aa77 100644
--- a/dpdk/drivers/net/mlx5/mlx5_txq.c
+++ b/dpdk/drivers/net/mlx5/mlx5_txq.c
@@ -49,7 +49,7 @@ txq_alloc_elts(struct mlx5_txq_ctrl *txq_ctrl)
for (i = 0; (i != elts_n); ++i)
(*txq_ctrl->txq.elts)[i] = NULL;
DRV_LOG(DEBUG, "port %u Tx queue %u allocated and configured %u WRs",
- PORT_ID(txq_ctrl->priv), txq_ctrl->idx, elts_n);
+ PORT_ID(txq_ctrl->priv), txq_ctrl->txq.idx, elts_n);
txq_ctrl->txq.elts_head = 0;
txq_ctrl->txq.elts_tail = 0;
txq_ctrl->txq.elts_comp = 0;
@@ -71,7 +71,7 @@ txq_free_elts(struct mlx5_txq_ctrl *txq_ctrl)
struct rte_mbuf *(*elts)[elts_n] = txq_ctrl->txq.elts;
DRV_LOG(DEBUG, "port %u Tx queue %u freeing WRs",
- PORT_ID(txq_ctrl->priv), txq_ctrl->idx);
+ PORT_ID(txq_ctrl->priv), txq_ctrl->txq.idx);
txq_ctrl->txq.elts_head = 0;
txq_ctrl->txq.elts_tail = 0;
txq_ctrl->txq.elts_comp = 0;
@@ -223,20 +223,107 @@ mlx5_tx_queue_release(void *dpdk_txq)
priv = txq_ctrl->priv;
for (i = 0; (i != priv->txqs_n); ++i)
if ((*priv->txqs)[i] == txq) {
- mlx5_txq_release(ETH_DEV(priv), i);
DRV_LOG(DEBUG, "port %u removing Tx queue %u from list",
- PORT_ID(priv), txq_ctrl->idx);
+ PORT_ID(priv), txq_ctrl->txq.idx);
+ mlx5_txq_release(ETH_DEV(priv), i);
break;
}
}
+/**
+ * Initialize Tx UAR registers for primary process.
+ *
+ * @param txq_ctrl
+ * Pointer to Tx queue control structure.
+ */
+static void
+txq_uar_init(struct mlx5_txq_ctrl *txq_ctrl)
+{
+ struct mlx5_priv *priv = txq_ctrl->priv;
+ struct mlx5_proc_priv *ppriv = MLX5_PROC_PRIV(PORT_ID(priv));
+#ifndef RTE_ARCH_64
+ unsigned int lock_idx;
+ const size_t page_size = sysconf(_SC_PAGESIZE);
+#endif
+
+ assert(rte_eal_process_type() == RTE_PROC_PRIMARY);
+ assert(ppriv);
+ ppriv->uar_table[txq_ctrl->txq.idx] = txq_ctrl->bf_reg;
+#ifndef RTE_ARCH_64
+ /* Assign an UAR lock according to UAR page number */
+ lock_idx = (txq_ctrl->uar_mmap_offset / page_size) &
+ MLX5_UAR_PAGE_NUM_MASK;
+ txq_ctrl->txq.uar_lock = &priv->uar_lock[lock_idx];
+#endif
+}
+
+/**
+ * Remap UAR register of a Tx queue for secondary process.
+ *
+ * Remapped address is stored at the table in the process private structure of
+ * the device, indexed by queue index.
+ *
+ * @param txq_ctrl
+ * Pointer to Tx queue control structure.
+ * @param fd
+ * Verbs file descriptor to map UAR pages.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+static int
+txq_uar_init_secondary(struct mlx5_txq_ctrl *txq_ctrl, int fd)
+{
+ struct mlx5_priv *priv = txq_ctrl->priv;
+ struct mlx5_proc_priv *ppriv = MLX5_PROC_PRIV(PORT_ID(priv));
+ struct mlx5_txq_data *txq = &txq_ctrl->txq;
+ void *addr;
+ uintptr_t uar_va;
+ uintptr_t offset;
+ const size_t page_size = sysconf(_SC_PAGESIZE);
+
+ assert(ppriv);
+ /*
+ * As rdma-core, UARs are mapped in size of OS page
+ * size. Ref to libmlx5 function: mlx5_init_context()
+ */
+ uar_va = (uintptr_t)txq_ctrl->bf_reg;
+ offset = uar_va & (page_size - 1); /* Offset in page. */
+ addr = mmap(NULL, page_size, PROT_WRITE, MAP_SHARED, fd,
+ txq_ctrl->uar_mmap_offset);
+ if (addr == MAP_FAILED) {
+ DRV_LOG(ERR,
+ "port %u mmap failed for BF reg of txq %u",
+ txq->port_id, txq->idx);
+ rte_errno = ENXIO;
+ return -rte_errno;
+ }
+ addr = RTE_PTR_ADD(addr, offset);
+ ppriv->uar_table[txq->idx] = addr;
+ return 0;
+}
+
+/**
+ * Unmap UAR register of a Tx queue for secondary process.
+ *
+ * @param txq_ctrl
+ * Pointer to Tx queue control structure.
+ */
+static void
+txq_uar_uninit_secondary(struct mlx5_txq_ctrl *txq_ctrl)
+{
+ struct mlx5_proc_priv *ppriv = MLX5_PROC_PRIV(PORT_ID(txq_ctrl->priv));
+ const size_t page_size = sysconf(_SC_PAGESIZE);
+ void *addr;
+
+ addr = ppriv->uar_table[txq_ctrl->txq.idx];
+ munmap(RTE_PTR_ALIGN_FLOOR(addr, page_size), page_size);
+}
/**
- * Mmap TX UAR(HW doorbell) pages into reserved UAR address space.
- * Both primary and secondary process do mmap to make UAR address
- * aligned.
+ * Initialize Tx UAR registers for secondary process.
*
- * @param[in] dev
+ * @param dev
* Pointer to Ethernet device.
* @param fd
* Verbs file descriptor to map UAR pages.
@@ -245,81 +332,36 @@ mlx5_tx_queue_release(void *dpdk_txq)
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
-mlx5_tx_uar_remap(struct rte_eth_dev *dev, int fd)
+mlx5_tx_uar_init_secondary(struct rte_eth_dev *dev, int fd)
{
struct mlx5_priv *priv = dev->data->dev_private;
- unsigned int i, j;
- uintptr_t pages[priv->txqs_n];
- unsigned int pages_n = 0;
- uintptr_t uar_va;
- uintptr_t off;
- void *addr;
- void *ret;
struct mlx5_txq_data *txq;
struct mlx5_txq_ctrl *txq_ctrl;
- int already_mapped;
- size_t page_size = sysconf(_SC_PAGESIZE);
-#ifndef RTE_ARCH_64
- unsigned int lock_idx;
-#endif
+ unsigned int i;
+ int ret;
- memset(pages, 0, priv->txqs_n * sizeof(uintptr_t));
- /*
- * As rdma-core, UARs are mapped in size of OS page size.
- * Use aligned address to avoid duplicate mmap.
- * Ref to libmlx5 function: mlx5_init_context()
- */
+ assert(rte_eal_process_type() == RTE_PROC_SECONDARY);
for (i = 0; i != priv->txqs_n; ++i) {
if (!(*priv->txqs)[i])
continue;
txq = (*priv->txqs)[i];
txq_ctrl = container_of(txq, struct mlx5_txq_ctrl, txq);
- assert(txq_ctrl->idx == (uint16_t)i);
- /* UAR addr form verbs used to find dup and offset in page. */
- uar_va = (uintptr_t)txq_ctrl->bf_reg_orig;
- off = uar_va & (page_size - 1); /* offset in page. */
- uar_va = RTE_ALIGN_FLOOR(uar_va, page_size); /* page addr. */
- already_mapped = 0;
- for (j = 0; j != pages_n; ++j) {
- if (pages[j] == uar_va) {
- already_mapped = 1;
- break;
- }
- }
- /* new address in reserved UAR address space. */
- addr = RTE_PTR_ADD(priv->uar_base,
- uar_va & (uintptr_t)(MLX5_UAR_SIZE - 1));
- if (!already_mapped) {
- pages[pages_n++] = uar_va;
- /* fixed mmap to specified address in reserved
- * address space.
- */
- ret = mmap(addr, page_size,
- PROT_WRITE, MAP_FIXED | MAP_SHARED, fd,
- txq_ctrl->uar_mmap_offset);
- if (ret != addr) {
- /* fixed mmap have to return same address */
- DRV_LOG(ERR,
- "port %u call to mmap failed on UAR"
- " for txq %u",
- dev->data->port_id, txq_ctrl->idx);
- rte_errno = ENXIO;
- return -rte_errno;
- }
- }
- if (rte_eal_process_type() == RTE_PROC_PRIMARY) /* save once */
- txq_ctrl->txq.bf_reg = RTE_PTR_ADD((void *)addr, off);
- else
- assert(txq_ctrl->txq.bf_reg ==
- RTE_PTR_ADD((void *)addr, off));
-#ifndef RTE_ARCH_64
- /* Assign a UAR lock according to UAR page number */
- lock_idx = (txq_ctrl->uar_mmap_offset / page_size) &
- MLX5_UAR_PAGE_NUM_MASK;
- txq->uar_lock = &priv->uar_lock[lock_idx];
-#endif
+ assert(txq->idx == (uint16_t)i);
+ ret = txq_uar_init_secondary(txq_ctrl, fd);
+ if (ret)
+ goto error;
}
return 0;
+error:
+ /* Rollback. */
+ do {
+ if (!(*priv->txqs)[i])
+ continue;
+ txq = (*priv->txqs)[i];
+ txq_ctrl = container_of(txq, struct mlx5_txq_ctrl, txq);
+ txq_uar_uninit_secondary(txq_ctrl);
+ } while (i--);
+ return -rte_errno;
}
/**
@@ -507,7 +549,6 @@ mlx5_txq_ibv_new(struct rte_eth_dev *dev, uint16_t idx)
txq_data->wqes = qp.sq.buf;
txq_data->wqe_n = log2above(qp.sq.wqe_cnt);
txq_data->qp_db = &qp.dbrec[MLX5_SND_DBR];
- txq_ctrl->bf_reg_orig = qp.bf.reg;
txq_data->cq_db = cq_info.dbrec;
txq_data->cqes =
(volatile struct mlx5_cqe (*)[])
@@ -521,6 +562,8 @@ mlx5_txq_ibv_new(struct rte_eth_dev *dev, uint16_t idx)
txq_ibv->qp = tmpl.qp;
txq_ibv->cq = tmpl.cq;
rte_atomic32_inc(&txq_ibv->refcnt);
+ txq_ctrl->bf_reg = qp.bf.reg;
+ txq_uar_init(txq_ctrl);
if (qp.comp_mask & MLX5DV_QP_MASK_UAR_MMAP_OFFSET) {
txq_ctrl->uar_mmap_offset = qp.uar_mmap_offset;
DRV_LOG(DEBUG, "port %u: uar_mmap_offset 0x%"PRIx64,
@@ -631,7 +674,7 @@ mlx5_txq_ibv_verify(struct rte_eth_dev *dev)
LIST_FOREACH(txq_ibv, &priv->txqsibv, next) {
DRV_LOG(DEBUG, "port %u Verbs Tx queue %u still referenced",
- dev->data->port_id, txq_ibv->txq_ctrl->idx);
+ dev->data->port_id, txq_ibv->txq_ctrl->txq.idx);
++ret;
}
return ret;
@@ -801,7 +844,8 @@ mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc,
tmpl->priv = priv;
tmpl->socket = socket;
tmpl->txq.elts_n = log2above(desc);
- tmpl->idx = idx;
+ tmpl->txq.port_id = dev->data->port_id;
+ tmpl->txq.idx = idx;
txq_set_params(tmpl);
if (txq_calc_wqebb_cnt(tmpl) >
priv->device_attr.orig_attr.max_qp_wr) {
@@ -866,16 +910,12 @@ mlx5_txq_release(struct rte_eth_dev *dev, uint16_t idx)
{
struct mlx5_priv *priv = dev->data->dev_private;
struct mlx5_txq_ctrl *txq;
- size_t page_size = sysconf(_SC_PAGESIZE);
if (!(*priv->txqs)[idx])
return 0;
txq = container_of((*priv->txqs)[idx], struct mlx5_txq_ctrl, txq);
if (txq->ibv && !mlx5_txq_ibv_release(txq->ibv))
txq->ibv = NULL;
- if (priv->uar_base)
- munmap((void *)RTE_ALIGN_FLOOR((uintptr_t)txq->txq.bf_reg,
- page_size), page_size);
if (rte_atomic32_dec_and_test(&txq->refcnt)) {
txq_free_elts(txq);
mlx5_mr_btree_free(&txq->txq.mr_ctrl.cache_bh);
@@ -928,7 +968,7 @@ mlx5_txq_verify(struct rte_eth_dev *dev)
LIST_FOREACH(txq, &priv->txqsctrl, next) {
DRV_LOG(DEBUG, "port %u Tx queue %u still referenced",
- dev->data->port_id, txq->idx);
+ dev->data->port_id, txq->txq.idx);
++ret;
}
return ret;
diff --git a/dpdk/drivers/net/mlx5/mlx5_vlan.c b/dpdk/drivers/net/mlx5/mlx5_vlan.c
index 6568a3a475..4004930942 100644
--- a/dpdk/drivers/net/mlx5/mlx5_vlan.c
+++ b/dpdk/drivers/net/mlx5/mlx5_vlan.c
@@ -27,10 +27,11 @@
#include <rte_ethdev_driver.h>
#include <rte_common.h>
-#include "mlx5_utils.h"
#include "mlx5.h"
#include "mlx5_autoconf.h"
#include "mlx5_glue.h"
+#include "mlx5_rxtx.h"
+#include "mlx5_utils.h"
/**
* DPDK callback to configure a VLAN filter.
diff --git a/dpdk/drivers/net/mvneta/mvneta_ethdev.c b/dpdk/drivers/net/mvneta/mvneta_ethdev.c
index 919856885a..950a4be75b 100644
--- a/dpdk/drivers/net/mvneta/mvneta_ethdev.c
+++ b/dpdk/drivers/net/mvneta/mvneta_ethdev.c
@@ -730,7 +730,7 @@ mvneta_stats_reset(struct rte_eth_dev *dev)
ret = mvneta_stats_get(dev, &priv->prev_stats);
if (unlikely(ret))
- RTE_LOG(ERR, PMD, "Failed to reset port statistics");
+ MVNETA_LOG(ERR, "Failed to reset port statistics");
}
diff --git a/dpdk/drivers/net/mvpp2/mrvl_flow.c b/dpdk/drivers/net/mvpp2/mrvl_flow.c
index ffd1dab9b5..8b1ec7e2bc 100644
--- a/dpdk/drivers/net/mvpp2/mrvl_flow.c
+++ b/dpdk/drivers/net/mvpp2/mrvl_flow.c
@@ -2511,14 +2511,14 @@ mrvl_create_cls_table(struct rte_eth_dev *dev, struct rte_flow *first_flow)
if (first_flow->pattern & F_UDP_SPORT) {
key->proto_field[key->num_fields].proto = MV_NET_PROTO_UDP;
- key->proto_field[key->num_fields].field.tcp = MV_NET_TCP_F_SP;
+ key->proto_field[key->num_fields].field.udp = MV_NET_UDP_F_SP;
key->key_size += 2;
key->num_fields += 1;
}
if (first_flow->pattern & F_UDP_DPORT) {
key->proto_field[key->num_fields].proto = MV_NET_PROTO_UDP;
- key->proto_field[key->num_fields].field.udp = MV_NET_TCP_F_DP;
+ key->proto_field[key->num_fields].field.udp = MV_NET_UDP_F_DP;
key->key_size += 2;
key->num_fields += 1;
}
diff --git a/dpdk/drivers/net/netvsc/hn_ethdev.c b/dpdk/drivers/net/netvsc/hn_ethdev.c
index 04efd092ec..55382907a4 100644
--- a/dpdk/drivers/net/netvsc/hn_ethdev.c
+++ b/dpdk/drivers/net/netvsc/hn_ethdev.c
@@ -118,8 +118,6 @@ eth_dev_vmbus_allocate(struct rte_vmbus_device *dev, size_t private_data_size)
static void
eth_dev_vmbus_release(struct rte_eth_dev *eth_dev)
{
- /* mac_addrs must not be freed alone because part of dev_private */
- eth_dev->data->mac_addrs = NULL;
/* free ether device */
rte_eth_dev_release_port(eth_dev);
@@ -240,6 +238,9 @@ static void hn_dev_info_get(struct rte_eth_dev *dev,
dev_info->max_rx_queues = hv->max_queues;
dev_info->max_tx_queues = hv->max_queues;
+ dev_info->tx_desc_lim.nb_min = 1;
+ dev_info->tx_desc_lim.nb_max = 4096;
+
if (rte_eal_process_type() != RTE_PROC_PRIMARY)
return;
@@ -728,9 +729,6 @@ eth_hn_dev_init(struct rte_eth_dev *eth_dev)
eth_dev->tx_pkt_burst = &hn_xmit_pkts;
eth_dev->rx_pkt_burst = &hn_recv_pkts;
- /* Since Hyper-V only supports one MAC address, just use local data */
- eth_dev->data->mac_addrs = &hv->mac_addr;
-
/*
* for secondary processes, we don't initialize any further as primary
* has already done this work.
@@ -738,6 +736,15 @@ eth_hn_dev_init(struct rte_eth_dev *eth_dev)
if (rte_eal_process_type() != RTE_PROC_PRIMARY)
return 0;
+ /* Since Hyper-V only supports one MAC address */
+ eth_dev->data->mac_addrs = rte_calloc("hv_mac", HN_MAX_MAC_ADDRS,
+ sizeof(struct ether_addr), 0);
+ if (eth_dev->data->mac_addrs == NULL) {
+ PMD_INIT_LOG(ERR,
+ "Failed to allocate memory store MAC addresses");
+ return -ENOMEM;
+ }
+
hv->vmbus = vmbus;
hv->rxbuf_res = &vmbus->resource[HV_RECV_BUF_MAP];
hv->chim_res = &vmbus->resource[HV_SEND_BUF_MAP];
@@ -776,11 +783,11 @@ eth_hn_dev_init(struct rte_eth_dev *eth_dev)
if (err)
goto failed;
- err = hn_tx_pool_init(eth_dev);
+ err = hn_chim_init(eth_dev);
if (err)
goto failed;
- err = hn_rndis_get_eaddr(hv, hv->mac_addr.addr_bytes);
+ err = hn_rndis_get_eaddr(hv, eth_dev->data->mac_addrs->addr_bytes);
if (err)
goto failed;
@@ -812,7 +819,7 @@ eth_hn_dev_init(struct rte_eth_dev *eth_dev)
failed:
PMD_INIT_LOG(NOTICE, "device init failed");
- hn_tx_pool_uninit(eth_dev);
+ hn_chim_uninit(eth_dev);
hn_detach(hv);
return err;
}
@@ -835,7 +842,7 @@ eth_hn_dev_uninit(struct rte_eth_dev *eth_dev)
eth_dev->rx_pkt_burst = NULL;
hn_detach(hv);
- hn_tx_pool_uninit(eth_dev);
+ hn_chim_uninit(eth_dev);
rte_vmbus_chan_close(hv->primary->chan);
rte_free(hv->primary);
rte_eth_dev_owner_delete(hv->owner.id);
diff --git a/dpdk/drivers/net/netvsc/hn_nvs.c b/dpdk/drivers/net/netvsc/hn_nvs.c
index d58770e045..76a7281f1b 100644
--- a/dpdk/drivers/net/netvsc/hn_nvs.c
+++ b/dpdk/drivers/net/netvsc/hn_nvs.c
@@ -54,7 +54,7 @@ static int hn_nvs_req_send(struct hn_data *hv,
}
static int
-hn_nvs_execute(struct hn_data *hv,
+__hn_nvs_execute(struct hn_data *hv,
void *req, uint32_t reqlen,
void *resp, uint32_t resplen,
uint32_t type)
@@ -62,6 +62,7 @@ hn_nvs_execute(struct hn_data *hv,
struct vmbus_channel *chan = hn_primary_chan(hv);
char buffer[NVS_RESPSIZE_MAX];
const struct hn_nvs_hdr *hdr;
+ uint64_t xactid;
uint32_t len;
int ret;
@@ -77,7 +78,7 @@ hn_nvs_execute(struct hn_data *hv,
retry:
len = sizeof(buffer);
- ret = rte_vmbus_chan_recv(chan, buffer, &len, NULL);
+ ret = rte_vmbus_chan_recv(chan, buffer, &len, &xactid);
if (ret == -EAGAIN) {
rte_delay_us(HN_CHAN_INTERVAL_US);
goto retry;
@@ -88,7 +89,20 @@ hn_nvs_execute(struct hn_data *hv,
return ret;
}
+ if (len < sizeof(*hdr)) {
+ PMD_DRV_LOG(ERR, "response missing NVS header");
+ return -EINVAL;
+ }
+
hdr = (struct hn_nvs_hdr *)buffer;
+
+ /* Silently drop received packets while waiting for response */
+ if (hdr->type == NVS_TYPE_RNDIS) {
+ hn_nvs_ack_rxbuf(chan, xactid);
+ --hv->rxbuf_outstanding;
+ goto retry;
+ }
+
if (hdr->type != type) {
PMD_DRV_LOG(ERR, "unexpected NVS resp %#x, expect %#x",
hdr->type, type);
@@ -108,6 +122,29 @@ hn_nvs_execute(struct hn_data *hv,
return 0;
}
+
+/*
+ * Execute one control command and get the response.
+ * Only one command can be active on a channel at once
+ * Unlike BSD, DPDK does not have an interrupt context
+ * so the polling is required to wait for response.
+ */
+static int
+hn_nvs_execute(struct hn_data *hv,
+ void *req, uint32_t reqlen,
+ void *resp, uint32_t resplen,
+ uint32_t type)
+{
+ struct hn_rx_queue *rxq = hv->primary;
+ int ret;
+
+ rte_spinlock_lock(&rxq->ring_lock);
+ ret = __hn_nvs_execute(hv, req, reqlen, resp, resplen, type);
+ rte_spinlock_unlock(&rxq->ring_lock);
+
+ return ret;
+}
+
static int
hn_nvs_doinit(struct hn_data *hv, uint32_t nvs_ver)
{
diff --git a/dpdk/drivers/net/netvsc/hn_nvs.h b/dpdk/drivers/net/netvsc/hn_nvs.h
index 2563fd8d86..015839e364 100644
--- a/dpdk/drivers/net/netvsc/hn_nvs.h
+++ b/dpdk/drivers/net/netvsc/hn_nvs.h
@@ -37,7 +37,7 @@
#define NVS_RNDIS_MTYPE_CTRL 1
/*
- * NVS message transacion status codes.
+ * NVS message transaction status codes.
*/
#define NVS_STATUS_OK 1
#define NVS_STATUS_FAILED 2
diff --git a/dpdk/drivers/net/netvsc/hn_rxtx.c b/dpdk/drivers/net/netvsc/hn_rxtx.c
index 5ffc0ee145..b526b490b2 100644
--- a/dpdk/drivers/net/netvsc/hn_rxtx.c
+++ b/dpdk/drivers/net/netvsc/hn_rxtx.c
@@ -18,6 +18,7 @@
#include <rte_memzone.h>
#include <rte_malloc.h>
#include <rte_atomic.h>
+#include <rte_bitmap.h>
#include <rte_branch_prediction.h>
#include <rte_ether.h>
#include <rte_common.h>
@@ -83,7 +84,7 @@ struct hn_txdesc {
struct rte_mbuf *m;
uint16_t queue_id;
- uint16_t chim_index;
+ uint32_t chim_index;
uint32_t chim_size;
uint32_t data_size;
uint32_t packets;
@@ -98,11 +99,13 @@ struct hn_txdesc {
RNDIS_PKTINFO_SIZE(NDIS_LSO2_INFO_SIZE) + \
RNDIS_PKTINFO_SIZE(NDIS_TXCSUM_INFO_SIZE))
+#define HN_RNDIS_PKT_ALIGNED RTE_ALIGN(HN_RNDIS_PKT_LEN, RTE_CACHE_LINE_SIZE)
+
/* Minimum space required for a packet */
#define HN_PKTSIZE_MIN(align) \
RTE_ALIGN(ETHER_MIN_LEN + HN_RNDIS_PKT_LEN, align)
-#define DEFAULT_TX_FREE_THRESH 32U
+#define DEFAULT_TX_FREE_THRESH 32
static void
hn_update_packet_stats(struct hn_stats *stats, const struct rte_mbuf *m)
@@ -150,63 +153,77 @@ hn_rndis_pktmsg_offset(uint32_t ofs)
static void hn_txd_init(struct rte_mempool *mp __rte_unused,
void *opaque, void *obj, unsigned int idx)
{
+ struct hn_tx_queue *txq = opaque;
struct hn_txdesc *txd = obj;
- struct rte_eth_dev *dev = opaque;
- struct rndis_packet_msg *pkt;
memset(txd, 0, sizeof(*txd));
- txd->chim_index = idx;
- pkt = rte_malloc_socket("RNDIS_TX", HN_RNDIS_PKT_LEN,
- rte_align32pow2(HN_RNDIS_PKT_LEN),
- dev->device->numa_node);
- if (!pkt)
- rte_exit(EXIT_FAILURE, "can not allocate RNDIS header");
-
- txd->rndis_pkt = pkt;
+ txd->queue_id = txq->queue_id;
+ txd->chim_index = NVS_CHIM_IDX_INVALID;
+ txd->rndis_pkt = (struct rndis_packet_msg *)(char *)txq->tx_rndis
+ + idx * HN_RNDIS_PKT_ALIGNED;
}
-/*
- * Unlike Linux and FreeBSD, this driver uses a mempool
- * to limit outstanding transmits and reserve buffers
- */
int
-hn_tx_pool_init(struct rte_eth_dev *dev)
+hn_chim_init(struct rte_eth_dev *dev)
{
struct hn_data *hv = dev->data->dev_private;
- char name[RTE_MEMPOOL_NAMESIZE];
- struct rte_mempool *mp;
+ uint32_t i, chim_bmp_size;
+
+ rte_spinlock_init(&hv->chim_lock);
+ chim_bmp_size = rte_bitmap_get_memory_footprint(hv->chim_cnt);
+ hv->chim_bmem = rte_zmalloc("hn_chim_bitmap", chim_bmp_size,
+ RTE_CACHE_LINE_SIZE);
+ if (hv->chim_bmem == NULL) {
+ PMD_INIT_LOG(ERR, "failed to allocate bitmap size %u",
+ chim_bmp_size);
+ return -1;
+ }
- snprintf(name, sizeof(name),
- "hn_txd_%u", dev->data->port_id);
-
- PMD_INIT_LOG(DEBUG, "create a TX send pool %s n=%u size=%zu socket=%d",
- name, hv->chim_cnt, sizeof(struct hn_txdesc),
- dev->device->numa_node);
-
- mp = rte_mempool_create(name, hv->chim_cnt, sizeof(struct hn_txdesc),
- HN_TXD_CACHE_SIZE, 0,
- NULL, NULL,
- hn_txd_init, dev,
- dev->device->numa_node, 0);
- if (!mp) {
- PMD_DRV_LOG(ERR,
- "mempool %s create failed: %d", name, rte_errno);
- return -rte_errno;
+ hv->chim_bmap = rte_bitmap_init(hv->chim_cnt,
+ hv->chim_bmem, chim_bmp_size);
+ if (hv->chim_bmap == NULL) {
+ PMD_INIT_LOG(ERR, "failed to init chim bitmap");
+ return -1;
}
- hv->tx_pool = mp;
+ for (i = 0; i < hv->chim_cnt; i++)
+ rte_bitmap_set(hv->chim_bmap, i);
+
return 0;
}
void
-hn_tx_pool_uninit(struct rte_eth_dev *dev)
+hn_chim_uninit(struct rte_eth_dev *dev)
{
struct hn_data *hv = dev->data->dev_private;
- if (hv->tx_pool) {
- rte_mempool_free(hv->tx_pool);
- hv->tx_pool = NULL;
+ rte_bitmap_free(hv->chim_bmap);
+ rte_free(hv->chim_bmem);
+ hv->chim_bmem = NULL;
+}
+
+static uint32_t hn_chim_alloc(struct hn_data *hv)
+{
+ uint32_t index = NVS_CHIM_IDX_INVALID;
+ uint64_t slab;
+
+ rte_spinlock_lock(&hv->chim_lock);
+ if (rte_bitmap_scan(hv->chim_bmap, &index, &slab))
+ rte_bitmap_clear(hv->chim_bmap, index);
+ rte_spinlock_unlock(&hv->chim_lock);
+
+ return index;
+}
+
+static void hn_chim_free(struct hn_data *hv, uint32_t chim_idx)
+{
+ if (chim_idx >= hv->chim_cnt) {
+ PMD_DRV_LOG(ERR, "Invalid chimney index %u", chim_idx);
+ } else {
+ rte_spinlock_lock(&hv->chim_lock);
+ rte_bitmap_set(hv->chim_bmap, chim_idx);
+ rte_spinlock_unlock(&hv->chim_lock);
}
}
@@ -220,15 +237,16 @@ static void hn_reset_txagg(struct hn_tx_queue *txq)
int
hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
- uint16_t queue_idx, uint16_t nb_desc __rte_unused,
+ uint16_t queue_idx, uint16_t nb_desc,
unsigned int socket_id,
const struct rte_eth_txconf *tx_conf)
{
struct hn_data *hv = dev->data->dev_private;
struct hn_tx_queue *txq;
+ char name[RTE_MEMPOOL_NAMESIZE];
uint32_t tx_free_thresh;
- int err;
+ int err = -ENOMEM;
PMD_INIT_FUNC_TRACE();
@@ -244,14 +262,42 @@ hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
tx_free_thresh = tx_conf->tx_free_thresh;
if (tx_free_thresh == 0)
- tx_free_thresh = RTE_MIN(hv->chim_cnt / 4,
+ tx_free_thresh = RTE_MIN(nb_desc / 4,
DEFAULT_TX_FREE_THRESH);
- if (tx_free_thresh >= hv->chim_cnt - 3)
- tx_free_thresh = hv->chim_cnt - 3;
+ if (tx_free_thresh + 3 >= nb_desc) {
+ PMD_INIT_LOG(ERR,
+ "tx_free_thresh must be less than the number of TX entries minus 3(%u)."
+ " (tx_free_thresh=%u port=%u queue=%u)\n",
+ nb_desc - 3,
+ tx_free_thresh, dev->data->port_id, queue_idx);
+ return -EINVAL;
+ }
txq->free_thresh = tx_free_thresh;
+ snprintf(name, sizeof(name),
+ "hn_txd_%u_%u", dev->data->port_id, queue_idx);
+
+ PMD_INIT_LOG(DEBUG, "TX descriptor pool %s n=%u size=%zu",
+ name, nb_desc, sizeof(struct hn_txdesc));
+
+ txq->tx_rndis = rte_calloc("hn_txq_rndis", nb_desc,
+ HN_RNDIS_PKT_ALIGNED, RTE_CACHE_LINE_SIZE);
+ if (txq->tx_rndis == NULL)
+ goto error;
+
+ txq->txdesc_pool = rte_mempool_create(name, nb_desc,
+ sizeof(struct hn_txdesc),
+ 0, 0, NULL, NULL,
+ hn_txd_init, txq,
+ dev->device->numa_node, 0);
+ if (txq->txdesc_pool == NULL) {
+ PMD_DRV_LOG(ERR,
+ "mempool %s create failed: %d", name, rte_errno);
+ goto error;
+ }
+
txq->agg_szmax = RTE_MIN(hv->chim_szmax, hv->rndis_agg_size);
txq->agg_pktmax = hv->rndis_agg_pkts;
txq->agg_align = hv->rndis_agg_align;
@@ -260,31 +306,57 @@ hn_dev_tx_queue_setup(struct rte_eth_dev *dev,
err = hn_vf_tx_queue_setup(dev, queue_idx, nb_desc,
socket_id, tx_conf);
- if (err) {
- rte_free(txq);
- return err;
+ if (err == 0) {
+ dev->data->tx_queues[queue_idx] = txq;
+ return 0;
}
- dev->data->tx_queues[queue_idx] = txq;
- return 0;
+error:
+ if (txq->txdesc_pool)
+ rte_mempool_free(txq->txdesc_pool);
+ rte_free(txq->tx_rndis);
+ rte_free(txq);
+ return err;
+}
+
+
+static struct hn_txdesc *hn_txd_get(struct hn_tx_queue *txq)
+{
+ struct hn_txdesc *txd;
+
+ if (rte_mempool_get(txq->txdesc_pool, (void **)&txd)) {
+ ++txq->stats.ring_full;
+ PMD_TX_LOG(DEBUG, "tx pool exhausted!");
+ return NULL;
+ }
+
+ txd->m = NULL;
+ txd->packets = 0;
+ txd->data_size = 0;
+ txd->chim_size = 0;
+
+ return txd;
+}
+
+static void hn_txd_put(struct hn_tx_queue *txq, struct hn_txdesc *txd)
+{
+ rte_mempool_put(txq->txdesc_pool, txd);
}
void
hn_dev_tx_queue_release(void *arg)
{
struct hn_tx_queue *txq = arg;
- struct hn_txdesc *txd;
PMD_INIT_FUNC_TRACE();
if (!txq)
return;
- /* If any pending data is still present just drop it */
- txd = txq->agg_txd;
- if (txd)
- rte_mempool_put(txq->hv->tx_pool, txd);
+ if (txq->txdesc_pool)
+ rte_mempool_free(txq->txdesc_pool);
+ rte_free(txq->tx_rndis);
rte_free(txq);
}
@@ -292,6 +364,7 @@ static void
hn_nvs_send_completed(struct rte_eth_dev *dev, uint16_t queue_id,
unsigned long xactid, const struct hn_nvs_rndis_ack *ack)
{
+ struct hn_data *hv = dev->data->dev_private;
struct hn_txdesc *txd = (struct hn_txdesc *)xactid;
struct hn_tx_queue *txq;
@@ -312,9 +385,11 @@ hn_nvs_send_completed(struct rte_eth_dev *dev, uint16_t queue_id,
++txq->stats.errors;
}
- rte_pktmbuf_free(txd->m);
+ if (txd->chim_index != NVS_CHIM_IDX_INVALID)
+ hn_chim_free(hv, txd->chim_index);
- rte_mempool_put(txq->hv->tx_pool, txd);
+ rte_pktmbuf_free(txd->m);
+ hn_txd_put(txq, txd);
}
/* Handle transmit completion events */
@@ -878,10 +953,6 @@ uint32_t hn_process_events(struct hn_data *hv, uint16_t queue_id,
rxq = queue_id == 0 ? hv->primary : dev->data->rx_queues[queue_id];
- /* If no pending data then nothing to do */
- if (rte_vmbus_chan_rx_empty(rxq->chan))
- return 0;
-
/*
* Since channel is shared between Rx and TX queue need to have a lock
* since DPDK does not force same CPU to be used for Rx/Tx.
@@ -945,9 +1016,6 @@ uint32_t hn_process_events(struct hn_data *hv, uint16_t queue_id,
if (tx_limit && tx_done >= tx_limit)
break;
-
- if (rxq->rx_ring && rte_ring_full(rxq->rx_ring))
- break;
}
if (bytes_read > 0)
@@ -1020,28 +1088,15 @@ static int hn_flush_txagg(struct hn_tx_queue *txq, bool *need_sig)
return ret;
}
-static struct hn_txdesc *hn_new_txd(struct hn_data *hv,
- struct hn_tx_queue *txq)
-{
- struct hn_txdesc *txd;
-
- if (rte_mempool_get(hv->tx_pool, (void **)&txd)) {
- ++txq->stats.ring_full;
- PMD_TX_LOG(DEBUG, "tx pool exhausted!");
- return NULL;
- }
-
- txd->m = NULL;
- txd->queue_id = txq->queue_id;
- txd->packets = 0;
- txd->data_size = 0;
- txd->chim_size = 0;
-
- return txd;
-}
-
+/*
+ * Try and find a place in a send chimney buffer to put
+ * the small packet. If space is available, this routine
+ * returns a pointer of where to place the data.
+ * If no space, caller should try direct transmit.
+ */
static void *
-hn_try_txagg(struct hn_data *hv, struct hn_tx_queue *txq, uint32_t pktsize)
+hn_try_txagg(struct hn_data *hv, struct hn_tx_queue *txq,
+ struct hn_txdesc *txd, uint32_t pktsize)
{
struct hn_txdesc *agg_txd = txq->agg_txd;
struct rndis_packet_msg *pkt;
@@ -1069,7 +1124,7 @@ hn_try_txagg(struct hn_data *hv, struct hn_tx_queue *txq, uint32_t pktsize)
}
chim = (uint8_t *)pkt + pkt->len;
-
+ txq->agg_prevpkt = chim;
txq->agg_pktleft--;
txq->agg_szleft -= pktsize;
if (txq->agg_szleft < HN_PKTSIZE_MIN(txq->agg_align)) {
@@ -1079,18 +1134,21 @@ hn_try_txagg(struct hn_data *hv, struct hn_tx_queue *txq, uint32_t pktsize)
*/
txq->agg_pktleft = 0;
}
- } else {
- agg_txd = hn_new_txd(hv, txq);
- if (!agg_txd)
- return NULL;
-
- chim = (uint8_t *)hv->chim_res->addr
- + agg_txd->chim_index * hv->chim_szmax;
- txq->agg_txd = agg_txd;
- txq->agg_pktleft = txq->agg_pktmax - 1;
- txq->agg_szleft = txq->agg_szmax - pktsize;
+ hn_txd_put(txq, txd);
+ return chim;
}
+
+ txd->chim_index = hn_chim_alloc(hv);
+ if (txd->chim_index == NVS_CHIM_IDX_INVALID)
+ return NULL;
+
+ chim = (uint8_t *)hv->chim_res->addr
+ + txd->chim_index * hv->chim_szmax;
+
+ txq->agg_txd = txd;
+ txq->agg_pktleft = txq->agg_pktmax - 1;
+ txq->agg_szleft = txq->agg_szmax - pktsize;
txq->agg_prevpkt = chim;
return chim;
@@ -1298,7 +1356,7 @@ hn_xmit_pkts(void *ptxq, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
struct hn_data *hv = txq->hv;
struct rte_eth_dev *vf_dev;
bool need_sig = false;
- uint16_t nb_tx;
+ uint16_t nb_tx, avail;
int ret;
if (unlikely(hv->closed))
@@ -1313,13 +1371,19 @@ hn_xmit_pkts(void *ptxq, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
return (*vf_dev->tx_pkt_burst)(sub_q, tx_pkts, nb_pkts);
}
- if (rte_mempool_avail_count(hv->tx_pool) <= txq->free_thresh)
+ avail = rte_mempool_avail_count(txq->txdesc_pool);
+ if (nb_pkts > avail || avail <= txq->free_thresh)
hn_process_events(hv, txq->queue_id, 0);
for (nb_tx = 0; nb_tx < nb_pkts; nb_tx++) {
struct rte_mbuf *m = tx_pkts[nb_tx];
uint32_t pkt_size = m->pkt_len + HN_RNDIS_PKT_LEN;
struct rndis_packet_msg *pkt;
+ struct hn_txdesc *txd;
+
+ txd = hn_txd_get(txq);
+ if (txd == NULL)
+ break;
/* For small packets aggregate them in chimney buffer */
if (m->pkt_len < HN_TXCOPY_THRESHOLD && pkt_size <= txq->agg_szmax) {
@@ -1330,7 +1394,8 @@ hn_xmit_pkts(void *ptxq, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
goto fail;
}
- pkt = hn_try_txagg(hv, txq, pkt_size);
+
+ pkt = hn_try_txagg(hv, txq, txd, pkt_size);
if (unlikely(!pkt))
break;
@@ -1344,21 +1409,13 @@ hn_xmit_pkts(void *ptxq, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
hn_flush_txagg(txq, &need_sig))
goto fail;
} else {
- struct hn_txdesc *txd;
-
- /* can send chimney data and large packet at once */
- txd = txq->agg_txd;
- if (txd) {
- hn_reset_txagg(txq);
- } else {
- txd = hn_new_txd(hv, txq);
- if (unlikely(!txd))
- break;
- }
+ /* Send any outstanding packets in buffer */
+ if (txq->agg_txd && hn_flush_txagg(txq, &need_sig))
+ goto fail;
pkt = txd->rndis_pkt;
txd->m = m;
- txd->data_size += m->pkt_len;
+ txd->data_size = m->pkt_len;
++txd->packets;
hn_encap(pkt, queue_id, m);
@@ -1367,7 +1424,7 @@ hn_xmit_pkts(void *ptxq, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
if (unlikely(ret != 0)) {
PMD_TX_LOG(NOTICE, "sg send failed: %d", ret);
++txq->stats.errors;
- rte_mempool_put(hv->tx_pool, txd);
+ hn_txd_put(txq, txd);
goto fail;
}
}
diff --git a/dpdk/drivers/net/netvsc/hn_var.h b/dpdk/drivers/net/netvsc/hn_var.h
index d10e164e68..5dcd53638a 100644
--- a/dpdk/drivers/net/netvsc/hn_var.h
+++ b/dpdk/drivers/net/netvsc/hn_var.h
@@ -52,6 +52,8 @@ struct hn_tx_queue {
uint16_t port_id;
uint16_t queue_id;
uint32_t free_thresh;
+ struct rte_mempool *txdesc_pool;
+ void *tx_rndis;
/* Applied packet transmission aggregation limits. */
uint32_t agg_szmax;
@@ -114,8 +116,10 @@ struct hn_data {
uint16_t num_queues;
uint64_t rss_offloads;
+ rte_spinlock_t chim_lock;
struct rte_mem_resource *chim_res; /* UIO resource for Tx */
- struct rte_mempool *tx_pool; /* Tx descriptors */
+ struct rte_bitmap *chim_bmap; /* Send buffer map */
+ void *chim_bmem;
uint32_t chim_szmax; /* Max size per buffer */
uint32_t chim_cnt; /* Max packets per buffer */
@@ -130,8 +134,6 @@ struct hn_data {
rte_atomic32_t rndis_req_id;
uint8_t rndis_resp[256];
- struct ether_addr mac_addr;
-
struct rte_eth_dev_owner owner;
struct rte_intr_handle vf_intr;
@@ -152,8 +154,8 @@ uint16_t hn_xmit_pkts(void *tx_queue, struct rte_mbuf **tx_pkts,
uint16_t hn_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts,
uint16_t nb_pkts);
-int hn_tx_pool_init(struct rte_eth_dev *dev);
-void hn_tx_pool_uninit(struct rte_eth_dev *dev);
+int hn_chim_init(struct rte_eth_dev *dev);
+void hn_chim_uninit(struct rte_eth_dev *dev);
int hn_dev_link_update(struct rte_eth_dev *dev, int wait);
int hn_dev_tx_queue_setup(struct rte_eth_dev *dev, uint16_t queue_idx,
uint16_t nb_desc, unsigned int socket_id,
diff --git a/dpdk/drivers/net/netvsc/hn_vf.c b/dpdk/drivers/net/netvsc/hn_vf.c
index 50f92a00ae..86485235ae 100644
--- a/dpdk/drivers/net/netvsc/hn_vf.c
+++ b/dpdk/drivers/net/netvsc/hn_vf.c
@@ -170,6 +170,17 @@ hn_nvs_handle_vfassoc(struct rte_eth_dev *dev,
hn_vf_remove(hv);
}
+static void
+hn_vf_merge_desc_lim(struct rte_eth_desc_lim *lim,
+ const struct rte_eth_desc_lim *vf_lim)
+{
+ lim->nb_max = RTE_MIN(vf_lim->nb_max, lim->nb_max);
+ lim->nb_min = RTE_MAX(vf_lim->nb_min, lim->nb_min);
+ lim->nb_align = RTE_MAX(vf_lim->nb_align, lim->nb_align);
+ lim->nb_seg_max = RTE_MIN(vf_lim->nb_seg_max, lim->nb_seg_max);
+ lim->nb_mtu_seg_max = RTE_MIN(vf_lim->nb_seg_max, lim->nb_seg_max);
+}
+
/*
* Merge the info from the VF and synthetic path.
* use the default config of the VF
@@ -196,11 +207,13 @@ static void hn_vf_info_merge(struct rte_eth_dev *vf_dev,
info->max_tx_queues);
info->tx_offload_capa &= vf_info.tx_offload_capa;
info->tx_queue_offload_capa &= vf_info.tx_queue_offload_capa;
+ hn_vf_merge_desc_lim(&info->tx_desc_lim, &vf_info.tx_desc_lim);
info->min_rx_bufsize = RTE_MAX(vf_info.min_rx_bufsize,
info->min_rx_bufsize);
info->max_rx_pktlen = RTE_MAX(vf_info.max_rx_pktlen,
info->max_rx_pktlen);
+ hn_vf_merge_desc_lim(&info->rx_desc_lim, &vf_info.rx_desc_lim);
}
void hn_vf_info_get(struct hn_data *hv, struct rte_eth_dev_info *info)
diff --git a/dpdk/drivers/net/nfp/nfp_net.c b/dpdk/drivers/net/nfp/nfp_net.c
index 68c853c94f..ddd9d9fca9 100644
--- a/dpdk/drivers/net/nfp/nfp_net.c
+++ b/dpdk/drivers/net/nfp/nfp_net.c
@@ -3297,16 +3297,14 @@ static int eth_nfp_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_nfp_net_pf_pmd = {
.id_table = pci_id_nfp_pf_net_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = nfp_pf_pci_probe,
.remove = eth_nfp_pci_remove,
};
static struct rte_pci_driver rte_nfp_net_vf_pmd = {
.id_table = pci_id_nfp_vf_net_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = eth_nfp_pci_probe,
.remove = eth_nfp_pci_remove,
};
diff --git a/dpdk/drivers/net/null/rte_eth_null.c b/dpdk/drivers/net/null/rte_eth_null.c
index 1067e6e4ea..1de26b0f69 100644
--- a/dpdk/drivers/net/null/rte_eth_null.c
+++ b/dpdk/drivers/net/null/rte_eth_null.c
@@ -613,6 +613,7 @@ rte_pmd_null_probe(struct rte_vdev_device *dev)
PMD_LOG(INFO, "Initializing pmd_null for %s", name);
if (rte_eal_process_type() == RTE_PROC_SECONDARY) {
+ struct pmd_internals *internals;
eth_dev = rte_eth_dev_attach_secondary(name);
if (!eth_dev) {
PMD_LOG(ERR, "Failed to probe %s", name);
@@ -621,7 +622,8 @@ rte_pmd_null_probe(struct rte_vdev_device *dev)
/* TODO: request info from primary to set up Rx and Tx */
eth_dev->dev_ops = &ops;
eth_dev->device = &dev->device;
- if (packet_copy) {
+ internals = eth_dev->data->dev_private;
+ if (internals->packet_copy) {
eth_dev->rx_pkt_burst = eth_null_copy_rx;
eth_dev->tx_pkt_burst = eth_null_copy_tx;
} else {
@@ -637,23 +639,18 @@ rte_pmd_null_probe(struct rte_vdev_device *dev)
if (kvlist == NULL)
return -1;
- if (rte_kvargs_count(kvlist, ETH_NULL_PACKET_SIZE_ARG) == 1) {
+ ret = rte_kvargs_process(kvlist,
+ ETH_NULL_PACKET_SIZE_ARG,
+ &get_packet_size_arg, &packet_size);
+ if (ret < 0)
+ goto free_kvlist;
- ret = rte_kvargs_process(kvlist,
- ETH_NULL_PACKET_SIZE_ARG,
- &get_packet_size_arg, &packet_size);
- if (ret < 0)
- goto free_kvlist;
- }
-
- if (rte_kvargs_count(kvlist, ETH_NULL_PACKET_COPY_ARG) == 1) {
- ret = rte_kvargs_process(kvlist,
- ETH_NULL_PACKET_COPY_ARG,
- &get_packet_copy_arg, &packet_copy);
- if (ret < 0)
- goto free_kvlist;
- }
+ ret = rte_kvargs_process(kvlist,
+ ETH_NULL_PACKET_COPY_ARG,
+ &get_packet_copy_arg, &packet_copy);
+ if (ret < 0)
+ goto free_kvlist;
}
PMD_LOG(INFO, "Configure pmd_null: packet size is %d, "
diff --git a/dpdk/drivers/net/octeontx/base/meson.build b/dpdk/drivers/net/octeontx/base/meson.build
index a06a2c89c9..e1060fc4ec 100644
--- a/dpdk/drivers/net/octeontx/base/meson.build
+++ b/dpdk/drivers/net/octeontx/base/meson.build
@@ -10,7 +10,10 @@ sources = [
depends = ['ethdev', 'mempool_octeontx']
static_objs = []
foreach d: depends
- static_objs += [get_variable('static_rte_' + d)]
+ if not is_variable('shared_rte_' + d)
+ subdir_done()
+ endif
+ static_objs += get_variable('static_rte_' + d)
endforeach
c_args = cflags
diff --git a/dpdk/drivers/net/octeontx/octeontx_ethdev.c b/dpdk/drivers/net/octeontx/octeontx_ethdev.c
index ac193ace43..17128da994 100644
--- a/dpdk/drivers/net/octeontx/octeontx_ethdev.c
+++ b/dpdk/drivers/net/octeontx/octeontx_ethdev.c
@@ -1106,6 +1106,7 @@ octeontx_create(struct rte_vdev_device *dev, int port, uint8_t evdev,
free_mac_addrs:
rte_free(data->mac_addrs);
+ data->mac_addrs = NULL;
err:
if (nic)
octeontx_port_close(nic);
diff --git a/dpdk/drivers/net/qede/qede_ethdev.c b/dpdk/drivers/net/qede/qede_ethdev.c
index 49f7b32056..d269e75cc0 100644
--- a/dpdk/drivers/net/qede/qede_ethdev.c
+++ b/dpdk/drivers/net/qede/qede_ethdev.c
@@ -1046,7 +1046,7 @@ static int qede_dev_start(struct rte_eth_dev *eth_dev)
qede_reset_queue_stats(qdev, true);
/* Newer SR-IOV PF driver expects RX/TX queues to be started before
- * enabling RSS. Hence RSS configuration is deferred upto this point.
+ * enabling RSS. Hence RSS configuration is deferred up to this point.
* Also, we would like to retain similar behavior in PF case, so we
* don't do PF/VF specific check here.
*/
@@ -1058,6 +1058,9 @@ static int qede_dev_start(struct rte_eth_dev *eth_dev)
if (qede_activate_vport(eth_dev, true))
goto err;
+ /* Bring-up the link */
+ qede_dev_set_link_state(eth_dev, true);
+
/* Update link status */
qede_link_update(eth_dev, 0);
@@ -1079,6 +1082,12 @@ static void qede_dev_stop(struct rte_eth_dev *eth_dev)
PMD_INIT_FUNC_TRACE(edev);
+ /* Bring the link down */
+ qede_dev_set_link_state(eth_dev, false);
+
+ /* Update link status */
+ qede_link_update(eth_dev, 0);
+
/* Disable vport */
if (qede_activate_vport(eth_dev, false))
return;
@@ -1164,6 +1173,8 @@ static int qede_dev_configure(struct rte_eth_dev *eth_dev)
struct qede_dev *qdev = QEDE_INIT_QDEV(eth_dev);
struct ecore_dev *edev = QEDE_INIT_EDEV(qdev);
struct rte_eth_rxmode *rxmode = ð_dev->data->dev_conf.rxmode;
+ uint8_t num_rxqs;
+ uint8_t num_txqs;
int ret;
PMD_INIT_FUNC_TRACE(edev);
@@ -1193,12 +1204,17 @@ static int qede_dev_configure(struct rte_eth_dev *eth_dev)
if (qede_check_fdir_support(eth_dev))
return -ENOTSUP;
- qede_dealloc_fp_resc(eth_dev);
- qdev->num_tx_queues = eth_dev->data->nb_tx_queues * edev->num_hwfns;
- qdev->num_rx_queues = eth_dev->data->nb_rx_queues * edev->num_hwfns;
-
- if (qede_alloc_fp_resc(qdev))
- return -ENOMEM;
+ /* Allocate/reallocate fastpath resources only for new queue config */
+ num_txqs = eth_dev->data->nb_tx_queues * edev->num_hwfns;
+ num_rxqs = eth_dev->data->nb_rx_queues * edev->num_hwfns;
+ if (qdev->num_tx_queues != num_txqs ||
+ qdev->num_rx_queues != num_rxqs) {
+ qede_dealloc_fp_resc(eth_dev);
+ qdev->num_tx_queues = num_txqs;
+ qdev->num_rx_queues = num_rxqs;
+ if (qede_alloc_fp_resc(qdev))
+ return -ENOMEM;
+ }
/* If jumbo enabled adjust MTU */
if (rxmode->offloads & DEV_RX_OFFLOAD_JUMBO_FRAME)
@@ -1451,8 +1467,6 @@ static void qede_dev_close(struct rte_eth_dev *eth_dev)
eth_dev->data->nb_rx_queues = 0;
eth_dev->data->nb_tx_queues = 0;
- /* Bring the link down */
- qede_dev_set_link_state(eth_dev, false);
qdev->ops->common->slowpath_stop(edev);
qdev->ops->common->remove(edev);
rte_intr_disable(&pci_dev->intr_handle);
@@ -2551,9 +2565,6 @@ static int qede_common_dev_init(struct rte_eth_dev *eth_dev, bool is_vf)
do_once = false;
}
- /* Bring-up the link */
- qede_dev_set_link_state(eth_dev, true);
-
adapter->num_tx_queues = 0;
adapter->num_rx_queues = 0;
SLIST_INIT(&adapter->arfs_info.arfs_list_head);
@@ -2702,8 +2713,7 @@ static int qedevf_eth_dev_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_qedevf_pmd = {
.id_table = pci_id_qedevf_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = qedevf_eth_dev_pci_probe,
.remove = qedevf_eth_dev_pci_remove,
};
@@ -2722,8 +2732,7 @@ static int qede_eth_dev_pci_remove(struct rte_pci_device *pci_dev)
static struct rte_pci_driver rte_qede_pmd = {
.id_table = pci_id_qede_map,
- .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC |
- RTE_PCI_DRV_IOVA_AS_VA,
+ .drv_flags = RTE_PCI_DRV_NEED_MAPPING | RTE_PCI_DRV_INTR_LSC,
.probe = qede_eth_dev_pci_probe,
.remove = qede_eth_dev_pci_remove,
};
diff --git a/dpdk/drivers/net/qede/qede_rxtx.c b/dpdk/drivers/net/qede/qede_rxtx.c
index 52ebc8b8b3..a72c9aa333 100644
--- a/dpdk/drivers/net/qede/qede_rxtx.c
+++ b/dpdk/drivers/net/qede/qede_rxtx.c
@@ -593,12 +593,14 @@ qede_alloc_mem_sb(struct qede_dev *qdev, struct ecore_sb_info *sb_info,
int qede_alloc_fp_resc(struct qede_dev *qdev)
{
- struct ecore_dev *edev = &qdev->edev;
+ struct ecore_dev *edev = QEDE_INIT_EDEV(qdev);
struct qede_fastpath *fp;
uint32_t num_sbs;
uint16_t sb_idx;
int i;
+ PMD_INIT_FUNC_TRACE(edev);
+
if (IS_VF(edev))
ecore_vf_get_num_sbs(ECORE_LEADING_HWFN(edev), &num_sbs);
else
diff --git a/dpdk/drivers/net/ring/rte_eth_ring.c b/dpdk/drivers/net/ring/rte_eth_ring.c
index 452114d0c5..7298ee93e2 100644
--- a/dpdk/drivers/net/ring/rte_eth_ring.c
+++ b/dpdk/drivers/net/ring/rte_eth_ring.c
@@ -251,6 +251,7 @@ static const struct eth_dev_ops ops = {
static int
do_eth_dev_ring_create(const char *name,
+ struct rte_vdev_device *vdev,
struct rte_ring * const rx_queues[],
const unsigned int nb_rx_queues,
struct rte_ring *const tx_queues[],
@@ -296,12 +297,15 @@ do_eth_dev_ring_create(const char *name,
}
/* now put it all together
+ * - store EAL device in eth_dev,
* - store queue data in internals,
* - store numa_node info in eth_dev_data
* - point eth_dev_data to internals
* - and point eth_dev structure to new eth_dev_data structure
*/
+ eth_dev->device = &vdev->device;
+
data = eth_dev->data;
data->rx_queues = rx_queues_local;
data->tx_queues = tx_queues_local;
@@ -411,7 +415,9 @@ rte_eth_from_ring(struct rte_ring *r)
}
static int
-eth_dev_ring_create(const char *name, const unsigned int numa_node,
+eth_dev_ring_create(const char *name,
+ struct rte_vdev_device *vdev,
+ const unsigned int numa_node,
enum dev_action action, struct rte_eth_dev **eth_dev)
{
/* rx and tx are so-called from point of view of first port.
@@ -441,7 +447,7 @@ eth_dev_ring_create(const char *name, const unsigned int numa_node,
return -1;
}
- if (do_eth_dev_ring_create(name, rxtx, num_rings, rxtx, num_rings,
+ if (do_eth_dev_ring_create(name, vdev, rxtx, num_rings, rxtx, num_rings,
numa_node, action, eth_dev) < 0)
return -1;
@@ -562,12 +568,12 @@ rte_pmd_ring_probe(struct rte_vdev_device *dev)
PMD_LOG(INFO, "Initializing pmd_ring for %s", name);
if (params == NULL || params[0] == '\0') {
- ret = eth_dev_ring_create(name, rte_socket_id(), DEV_CREATE,
+ ret = eth_dev_ring_create(name, dev, rte_socket_id(), DEV_CREATE,
ð_dev);
if (ret == -1) {
PMD_LOG(INFO,
"Attach to pmd_ring for %s", name);
- ret = eth_dev_ring_create(name, rte_socket_id(),
+ ret = eth_dev_ring_create(name, dev, rte_socket_id(),
DEV_ATTACH, ð_dev);
}
} else {
@@ -576,19 +582,16 @@ rte_pmd_ring_probe(struct rte_vdev_device *dev)
if (!kvlist) {
PMD_LOG(INFO,
"Ignoring unsupported parameters when creatingrings-backed ethernet device");
- ret = eth_dev_ring_create(name, rte_socket_id(),
+ ret = eth_dev_ring_create(name, dev, rte_socket_id(),
DEV_CREATE, ð_dev);
if (ret == -1) {
PMD_LOG(INFO,
"Attach to pmd_ring for %s",
name);
- ret = eth_dev_ring_create(name, rte_socket_id(),
+ ret = eth_dev_ring_create(name, dev, rte_socket_id(),
DEV_ATTACH, ð_dev);
}
- if (eth_dev)
- eth_dev->device = &dev->device;
-
return ret;
}
@@ -599,7 +602,7 @@ rte_pmd_ring_probe(struct rte_vdev_device *dev)
if (ret < 0)
goto out_free;
- ret = do_eth_dev_ring_create(name,
+ ret = do_eth_dev_ring_create(name, dev,
internal_args->rx_queues,
internal_args->nb_rx_queues,
internal_args->tx_queues,
@@ -629,6 +632,7 @@ rte_pmd_ring_probe(struct rte_vdev_device *dev)
for (info->count = 0; info->count < info->total; info->count++) {
ret = eth_dev_ring_create(info->list[info->count].name,
+ dev,
info->list[info->count].node,
info->list[info->count].action,
ð_dev);
@@ -637,7 +641,7 @@ rte_pmd_ring_probe(struct rte_vdev_device *dev)
PMD_LOG(INFO,
"Attach to pmd_ring for %s",
name);
- ret = eth_dev_ring_create(name,
+ ret = eth_dev_ring_create(name, dev,
info->list[info->count].node,
DEV_ATTACH,
ð_dev);
@@ -646,9 +650,6 @@ rte_pmd_ring_probe(struct rte_vdev_device *dev)
}
}
- if (eth_dev)
- eth_dev->device = &dev->device;
-
out_free:
rte_kvargs_free(kvlist);
rte_free(info);
diff --git a/dpdk/drivers/net/sfc/base/ef10_filter.c b/dpdk/drivers/net/sfc/base/ef10_filter.c
index afe4064d9f..cf3446805a 100644
--- a/dpdk/drivers/net/sfc/base/ef10_filter.c
+++ b/dpdk/drivers/net/sfc/base/ef10_filter.c
@@ -597,6 +597,231 @@ ef10_filter_restore(
return (rc);
}
+enum ef10_filter_add_action_e {
+ /* Insert a new filter */
+ EF10_FILTER_ADD_NEW,
+ /*
+ * Replace old filter with a new, overriding the old one
+ * if it has lower priority.
+ */
+ EF10_FILTER_ADD_REPLACE,
+ /* Store new, lower priority filter as overridden by old filter */
+ EF10_FILTER_ADD_STORE,
+ /* Special case for AUTO filters, remove AUTO_OLD flag */
+ EF10_FILTER_ADD_REFRESH,
+};
+
+static __checkReturn efx_rc_t
+ef10_filter_add_lookup_equal_spec(
+ __in efx_filter_spec_t *spec,
+ __in efx_filter_spec_t *probe_spec,
+ __in efx_filter_replacement_policy_t policy,
+ __out boolean_t *found)
+{
+ efx_rc_t rc;
+
+ /* Refreshing AUTO filter */
+ if (spec->efs_priority == EFX_FILTER_PRI_AUTO &&
+ probe_spec->efs_priority == EFX_FILTER_PRI_AUTO) {
+ *found = B_TRUE;
+ return (0);
+ }
+
+ /*
+ * With exclusive filters, higher priority ones
+ * override lower priority ones, and lower priority
+ * ones are stored in case the higher priority one
+ * is removed.
+ */
+ if (ef10_filter_is_exclusive(spec)) {
+ switch (policy) {
+ case EFX_FILTER_REPLACEMENT_HIGHER_OR_EQUAL_PRIORITY:
+ if (spec->efs_priority == probe_spec->efs_priority) {
+ *found = B_TRUE;
+ break;
+ }
+ /* Fall-through */
+ case EFX_FILTER_REPLACEMENT_HIGHER_PRIORITY:
+ if (spec->efs_priority > probe_spec->efs_priority) {
+ *found = B_TRUE;
+ break;
+ }
+ /* Fall-through */
+ case EFX_FILTER_REPLACEMENT_NEVER:
+ /*
+ * Lower priority filter needs to be
+ * stored. It does *not* replace the
+ * old one. That is why EEXIST is not
+ * returned in that case.
+ */
+ if (spec->efs_priority < probe_spec->efs_priority) {
+ *found = B_TRUE;
+ break;
+ } else {
+ rc = EEXIST;
+ goto fail1;
+ }
+ default:
+ EFSYS_ASSERT(0);
+ rc = EEXIST;
+ goto fail2;
+ }
+ } else {
+ *found = B_FALSE;
+ }
+
+ return (0);
+
+fail2:
+ EFSYS_PROBE(fail2);
+
+fail1:
+ EFSYS_PROBE1(fail1, efx_rc_t, rc);
+
+ return (rc);
+}
+
+
+static void
+ef10_filter_add_select_action(
+ __in efx_filter_spec_t *saved_spec,
+ __in efx_filter_spec_t *spec,
+ __out enum ef10_filter_add_action_e *action,
+ __out efx_filter_spec_t **overridden_spec)
+{
+ efx_filter_spec_t *overridden = NULL;
+
+ if (saved_spec == NULL) {
+ *action = EF10_FILTER_ADD_NEW;
+ } else if (ef10_filter_is_exclusive(spec) == B_FALSE) {
+ /*
+ * Non-exclusive filters are always stored in separate entries
+ * in the table. The only case involving a saved spec is
+ * refreshing an AUTO filter.
+ */
+ EFSYS_ASSERT(saved_spec->efs_overridden_spec == NULL);
+ EFSYS_ASSERT(spec->efs_priority == EFX_FILTER_PRI_AUTO);
+ EFSYS_ASSERT(saved_spec->efs_priority == EFX_FILTER_PRI_AUTO);
+ *action = EF10_FILTER_ADD_REFRESH;
+ } else {
+ /* Exclusive filters stored in the same entry */
+ if (spec->efs_priority > saved_spec->efs_priority) {
+ /*
+ * Insert a high priority filter over a lower priority
+ * one. Only two priority levels are implemented, so
+ * there must not already be an overridden filter.
+ */
+ EFX_STATIC_ASSERT(EFX_FILTER_NPRI == 2);
+ EFSYS_ASSERT(saved_spec->efs_overridden_spec == NULL);
+ overridden = saved_spec;
+ *action = EF10_FILTER_ADD_REPLACE;
+ } else if (spec->efs_priority == saved_spec->efs_priority) {
+ /* Replace in-place or refresh an existing filter */
+ if (spec->efs_priority == EFX_FILTER_PRI_AUTO)
+ *action = EF10_FILTER_ADD_REFRESH;
+ else
+ *action = EF10_FILTER_ADD_REPLACE;
+ } else {
+ /*
+ * Insert a lower priority filter, storing it in case
+ * the higher priority filter is removed.
+ *
+ * Currently there are only two priority levels, so this
+ * must be an AUTO filter.
+ */
+ EFX_STATIC_ASSERT(EFX_FILTER_NPRI == 2);
+ EFSYS_ASSERT(spec->efs_priority == EFX_FILTER_PRI_AUTO);
+ if (saved_spec->efs_overridden_spec != NULL) {
+ *action = EF10_FILTER_ADD_REFRESH;
+ } else {
+ overridden = spec;
+ *action = EF10_FILTER_ADD_STORE;
+ }
+ }
+ }
+
+ *overridden_spec = overridden;
+}
+
+static __checkReturn efx_rc_t
+ef10_filter_add_execute_action(
+ __in efx_nic_t *enp,
+ __in efx_filter_spec_t *saved_spec,
+ __in efx_filter_spec_t *spec,
+ __in efx_filter_spec_t *overridden_spec,
+ __in enum ef10_filter_add_action_e action,
+ __in int ins_index)
+{
+ ef10_filter_table_t *eftp = enp->en_filter.ef_ef10_filter_table;
+ efsys_lock_state_t state;
+ efx_rc_t rc;
+
+ EFSYS_LOCK(enp->en_eslp, state);
+
+ if (action == EF10_FILTER_ADD_REFRESH) {
+ ef10_filter_set_entry_not_auto_old(eftp, ins_index);
+ goto out_unlock;
+ } else if (action == EF10_FILTER_ADD_STORE) {
+ EFSYS_ASSERT(overridden_spec != NULL);
+ saved_spec->efs_overridden_spec = overridden_spec;
+ goto out_unlock;
+ }
+
+ EFSYS_UNLOCK(enp->en_eslp, state);
+
+ switch (action) {
+ case EF10_FILTER_ADD_REPLACE:
+ /*
+ * On replacing the filter handle may change after a
+ * successful replace operation.
+ */
+ rc = efx_mcdi_filter_op_add(enp, spec,
+ MC_CMD_FILTER_OP_IN_OP_REPLACE,
+ &eftp->eft_entry[ins_index].efe_handle);
+ break;
+ case EF10_FILTER_ADD_NEW:
+ if (ef10_filter_is_exclusive(spec)) {
+ rc = efx_mcdi_filter_op_add(enp, spec,
+ MC_CMD_FILTER_OP_IN_OP_INSERT,
+ &eftp->eft_entry[ins_index].efe_handle);
+ } else {
+ rc = efx_mcdi_filter_op_add(enp, spec,
+ MC_CMD_FILTER_OP_IN_OP_SUBSCRIBE,
+ &eftp->eft_entry[ins_index].efe_handle);
+ }
+ break;
+ default:
+ rc = EINVAL;
+ EFSYS_ASSERT(0);
+ break;
+ }
+ if (rc != 0)
+ goto fail1;
+
+ EFSYS_LOCK(enp->en_eslp, state);
+
+ if (action == EF10_FILTER_ADD_REPLACE) {
+ /* Update the fields that may differ */
+ saved_spec->efs_priority = spec->efs_priority;
+ saved_spec->efs_flags = spec->efs_flags;
+ saved_spec->efs_rss_context = spec->efs_rss_context;
+ saved_spec->efs_dmaq_id = spec->efs_dmaq_id;
+
+ if (overridden_spec != NULL)
+ saved_spec->efs_overridden_spec = overridden_spec;
+ }
+
+out_unlock:
+ EFSYS_UNLOCK(enp->en_eslp, state);
+
+ return (0);
+
+fail1:
+ EFSYS_PROBE1(fail1, efx_rc_t, rc);
+
+ return (rc);
+}
+
/*
* An arbitrary search limit for the software hash table. As per the linux net
* driver.
@@ -607,17 +832,17 @@ static __checkReturn efx_rc_t
ef10_filter_add_internal(
__in efx_nic_t *enp,
__inout efx_filter_spec_t *spec,
- __in boolean_t may_replace,
+ __in efx_filter_replacement_policy_t policy,
__out_opt uint32_t *filter_id)
{
efx_rc_t rc;
ef10_filter_table_t *eftp = enp->en_filter.ef_ef10_filter_table;
+ enum ef10_filter_add_action_e action;
+ efx_filter_spec_t *overridden_spec = NULL;
efx_filter_spec_t *saved_spec;
uint32_t hash;
unsigned int depth;
int ins_index;
- boolean_t replacing = B_FALSE;
- unsigned int i;
efsys_lock_state_t state;
boolean_t locked = B_FALSE;
@@ -625,6 +850,8 @@ ef10_filter_add_internal(
enp->en_family == EFX_FAMILY_MEDFORD ||
enp->en_family == EFX_FAMILY_MEDFORD2);
+ EFSYS_ASSERT(spec->efs_overridden_spec == NULL);
+
hash = ef10_filter_hash(spec);
/*
@@ -637,145 +864,136 @@ ef10_filter_add_internal(
* else a free slot to insert at. If any of them are busy,
* we have to wait and retry.
*/
- for (;;) {
- ins_index = -1;
- depth = 1;
- EFSYS_LOCK(enp->en_eslp, state);
- locked = B_TRUE;
+retry:
+ EFSYS_LOCK(enp->en_eslp, state);
+ locked = B_TRUE;
+
+ ins_index = -1;
+
+ for (depth = 1; depth <= EF10_FILTER_SEARCH_LIMIT; depth++) {
+ unsigned int probe_index;
+ efx_filter_spec_t *probe_spec;
- for (;;) {
- i = (hash + depth) & (EFX_EF10_FILTER_TBL_ROWS - 1);
- saved_spec = ef10_filter_entry_spec(eftp, i);
-
- if (!saved_spec) {
- if (ins_index < 0) {
- ins_index = i;
- }
- } else if (ef10_filter_equal(spec, saved_spec)) {
- if (ef10_filter_entry_is_busy(eftp, i))
- break;
- if (saved_spec->efs_priority
- == EFX_FILTER_PRI_AUTO) {
- ins_index = i;
- goto found;
- } else if (ef10_filter_is_exclusive(spec)) {
- if (may_replace) {
- ins_index = i;
- goto found;
- } else {
- rc = EEXIST;
- goto fail1;
- }
- }
-
- /* Leave existing */
+ probe_index = (hash + depth) & (EFX_EF10_FILTER_TBL_ROWS - 1);
+ probe_spec = ef10_filter_entry_spec(eftp, probe_index);
+
+ if (probe_spec == NULL) {
+ if (ins_index < 0)
+ ins_index = probe_index;
+ } else if (ef10_filter_equal(spec, probe_spec)) {
+ boolean_t found;
+
+ if (ef10_filter_entry_is_busy(eftp, probe_index)) {
+ EFSYS_UNLOCK(enp->en_eslp, state);
+ locked = B_FALSE;
+ goto retry;
}
- /*
- * Once we reach the maximum search depth, use
- * the first suitable slot or return EBUSY if
- * there was none.
- */
- if (depth == EF10_FILTER_SEARCH_LIMIT) {
- if (ins_index < 0) {
- rc = EBUSY;
- goto fail2;
- }
- goto found;
+ rc = ef10_filter_add_lookup_equal_spec(spec,
+ probe_spec, policy, &found);
+ if (rc != 0)
+ goto fail1;
+
+ if (found != B_FALSE) {
+ ins_index = probe_index;
+ break;
}
- depth++;
}
- EFSYS_UNLOCK(enp->en_eslp, state);
- locked = B_FALSE;
}
-found:
/*
- * Create a software table entry if necessary, and mark it
- * busy. We might yet fail to insert, but any attempt to
- * insert a conflicting filter while we're waiting for the
- * firmware must find the busy entry.
+ * Once we reach the maximum search depth, use the first suitable slot
+ * or return EBUSY if there was none.
*/
- saved_spec = ef10_filter_entry_spec(eftp, ins_index);
- if (saved_spec) {
- if (saved_spec->efs_priority == EFX_FILTER_PRI_AUTO) {
- /* This is a filter we are refreshing */
- ef10_filter_set_entry_not_auto_old(eftp, ins_index);
- goto out_unlock;
-
- }
- replacing = B_TRUE;
- } else {
- EFSYS_KMEM_ALLOC(enp->en_esip, sizeof (*spec), saved_spec);
- if (!saved_spec) {
- rc = ENOMEM;
- goto fail3;
- }
- *saved_spec = *spec;
- ef10_filter_set_entry(eftp, ins_index, saved_spec);
+ if (ins_index < 0) {
+ rc = EBUSY;
+ goto fail2;
}
+
+ /*
+ * Mark software table entry busy. We might yet fail to insert,
+ * but any attempt to insert a conflicting filter while we're
+ * waiting for the firmware must find the busy entry.
+ */
ef10_filter_set_entry_busy(eftp, ins_index);
- EFSYS_UNLOCK(enp->en_eslp, state);
- locked = B_FALSE;
+ saved_spec = ef10_filter_entry_spec(eftp, ins_index);
+ ef10_filter_add_select_action(saved_spec, spec, &action,
+ &overridden_spec);
/*
- * On replacing the filter handle may change after after a successful
- * replace operation.
+ * Allocate a new filter if found entry is empty or
+ * a filter should be overridden.
*/
- if (replacing) {
- rc = efx_mcdi_filter_op_add(enp, spec,
- MC_CMD_FILTER_OP_IN_OP_REPLACE,
- &eftp->eft_entry[ins_index].efe_handle);
- } else if (ef10_filter_is_exclusive(spec)) {
- rc = efx_mcdi_filter_op_add(enp, spec,
- MC_CMD_FILTER_OP_IN_OP_INSERT,
- &eftp->eft_entry[ins_index].efe_handle);
- } else {
- rc = efx_mcdi_filter_op_add(enp, spec,
- MC_CMD_FILTER_OP_IN_OP_SUBSCRIBE,
- &eftp->eft_entry[ins_index].efe_handle);
- }
-
- if (rc != 0)
- goto fail4;
+ if (overridden_spec != NULL || saved_spec == NULL) {
+ efx_filter_spec_t *new_spec;
- EFSYS_LOCK(enp->en_eslp, state);
- locked = B_TRUE;
+ EFSYS_UNLOCK(enp->en_eslp, state);
+ locked = B_FALSE;
- if (replacing) {
- /* Update the fields that may differ */
- saved_spec->efs_priority = spec->efs_priority;
- saved_spec->efs_flags = spec->efs_flags;
- saved_spec->efs_rss_context = spec->efs_rss_context;
- saved_spec->efs_dmaq_id = spec->efs_dmaq_id;
- }
+ EFSYS_KMEM_ALLOC(enp->en_esip, sizeof (*new_spec), new_spec);
+ if (new_spec == NULL) {
+ rc = ENOMEM;
+ overridden_spec = NULL;
+ goto fail3;
+ }
- ef10_filter_set_entry_not_busy(eftp, ins_index);
+ EFSYS_LOCK(enp->en_eslp, state);
+ locked = B_TRUE;
-out_unlock:
+ if (saved_spec == NULL) {
+ *new_spec = *spec;
+ ef10_filter_set_entry(eftp, ins_index, new_spec);
+ } else {
+ *new_spec = *overridden_spec;
+ overridden_spec = new_spec;
+ }
+ }
EFSYS_UNLOCK(enp->en_eslp, state);
locked = B_FALSE;
+ rc = ef10_filter_add_execute_action(enp, saved_spec, spec,
+ overridden_spec, action, ins_index);
+ if (rc != 0)
+ goto fail4;
+
if (filter_id)
*filter_id = ins_index;
+ EFSYS_LOCK(enp->en_eslp, state);
+ ef10_filter_set_entry_not_busy(eftp, ins_index);
+ EFSYS_UNLOCK(enp->en_eslp, state);
+
return (0);
fail4:
EFSYS_PROBE(fail4);
- if (!replacing) {
- EFSYS_KMEM_FREE(enp->en_esip, sizeof (*spec), saved_spec);
- saved_spec = NULL;
+ EFSYS_ASSERT(locked == B_FALSE);
+ EFSYS_LOCK(enp->en_eslp, state);
+
+ if (action == EF10_FILTER_ADD_NEW) {
+ EFSYS_KMEM_FREE(enp->en_esip, sizeof (*spec),
+ ef10_filter_entry_spec(eftp, ins_index));
+ ef10_filter_set_entry(eftp, ins_index, NULL);
}
- ef10_filter_set_entry_not_busy(eftp, ins_index);
- ef10_filter_set_entry(eftp, ins_index, NULL);
+
+ EFSYS_UNLOCK(enp->en_eslp, state);
+
+ if (overridden_spec != NULL)
+ EFSYS_KMEM_FREE(enp->en_esip, sizeof (*spec), overridden_spec);
fail3:
EFSYS_PROBE(fail3);
+ EFSYS_ASSERT(locked == B_FALSE);
+ EFSYS_LOCK(enp->en_eslp, state);
+
+ ef10_filter_set_entry_not_busy(eftp, ins_index);
+
+ EFSYS_UNLOCK(enp->en_eslp, state);
+
fail2:
EFSYS_PROBE(fail2);
@@ -792,11 +1010,11 @@ ef10_filter_add_internal(
ef10_filter_add(
__in efx_nic_t *enp,
__inout efx_filter_spec_t *spec,
- __in boolean_t may_replace)
+ __in enum efx_filter_replacement_policy_e policy)
{
efx_rc_t rc;
- rc = ef10_filter_add_internal(enp, spec, may_replace, NULL);
+ rc = ef10_filter_add_internal(enp, spec, policy, NULL);
if (rc != 0)
goto fail1;
@@ -808,11 +1026,15 @@ ef10_filter_add(
return (rc);
}
-
+/*
+ * Delete a filter by index from the filter table with priority
+ * that is not higher than specified.
+ */
static __checkReturn efx_rc_t
ef10_filter_delete_internal(
__in efx_nic_t *enp,
- __in uint32_t filter_id)
+ __in uint32_t filter_id,
+ __in efx_filter_priority_t priority)
{
efx_rc_t rc;
ef10_filter_table_t *table = enp->en_filter.ef_ef10_filter_table;
@@ -834,7 +1056,8 @@ ef10_filter_delete_internal(
EFSYS_LOCK(enp->en_eslp, state);
}
if ((spec = ef10_filter_entry_spec(table, filter_idx)) != NULL) {
- ef10_filter_set_entry_busy(table, filter_idx);
+ if (spec->efs_priority <= priority)
+ ef10_filter_set_entry_busy(table, filter_idx);
}
EFSYS_UNLOCK(enp->en_eslp, state);
@@ -843,31 +1066,53 @@ ef10_filter_delete_internal(
goto fail1;
}
- /*
- * Try to remove the hardware filter. This may fail if the MC has
- * rebooted (which frees all hardware filter resources).
- */
- if (ef10_filter_is_exclusive(spec)) {
- rc = efx_mcdi_filter_op_delete(enp,
- MC_CMD_FILTER_OP_IN_OP_REMOVE,
- &table->eft_entry[filter_idx].efe_handle);
+ if (spec->efs_priority > priority) {
+ /*
+ * Applied filter stays, but overridden filter is removed since
+ * next user request to delete the applied filter should not
+ * restore outdated filter.
+ */
+ if (spec->efs_overridden_spec != NULL) {
+ EFSYS_ASSERT(spec->efs_overridden_spec->efs_overridden_spec ==
+ NULL);
+ EFSYS_KMEM_FREE(enp->en_esip, sizeof (*spec),
+ spec->efs_overridden_spec);
+ spec->efs_overridden_spec = NULL;
+ }
} else {
- rc = efx_mcdi_filter_op_delete(enp,
- MC_CMD_FILTER_OP_IN_OP_UNSUBSCRIBE,
- &table->eft_entry[filter_idx].efe_handle);
- }
+ /*
+ * Try to remove the hardware filter or replace it with the
+ * saved automatic filter. This may fail if the MC has
+ * rebooted (which frees all hardware filter resources).
+ */
+ if (spec->efs_overridden_spec != NULL) {
+ rc = efx_mcdi_filter_op_add(enp,
+ spec->efs_overridden_spec,
+ MC_CMD_FILTER_OP_IN_OP_REPLACE,
+ &table->eft_entry[filter_idx].efe_handle);
+ } else if (ef10_filter_is_exclusive(spec)) {
+ rc = efx_mcdi_filter_op_delete(enp,
+ MC_CMD_FILTER_OP_IN_OP_REMOVE,
+ &table->eft_entry[filter_idx].efe_handle);
+ } else {
+ rc = efx_mcdi_filter_op_delete(enp,
+ MC_CMD_FILTER_OP_IN_OP_UNSUBSCRIBE,
+ &table->eft_entry[filter_idx].efe_handle);
+ }
- /* Free the software table entry */
- EFSYS_LOCK(enp->en_eslp, state);
- ef10_filter_set_entry_not_busy(table, filter_idx);
- ef10_filter_set_entry(table, filter_idx, NULL);
- EFSYS_UNLOCK(enp->en_eslp, state);
+ /* Free the software table entry */
+ EFSYS_LOCK(enp->en_eslp, state);
+ ef10_filter_set_entry_not_busy(table, filter_idx);
+ ef10_filter_set_entry(table, filter_idx,
+ spec->efs_overridden_spec);
+ EFSYS_UNLOCK(enp->en_eslp, state);
- EFSYS_KMEM_FREE(enp->en_esip, sizeof (*spec), spec);
+ EFSYS_KMEM_FREE(enp->en_esip, sizeof (*spec), spec);
- /* Check result of hardware filter removal */
- if (rc != 0)
- goto fail2;
+ /* Check result of hardware filter removal */
+ if (rc != 0)
+ goto fail2;
+ }
return (0);
@@ -880,6 +1125,25 @@ ef10_filter_delete_internal(
return (rc);
}
+static void
+ef10_filter_delete_auto(
+ __in efx_nic_t *enp,
+ __in uint32_t filter_id)
+{
+ ef10_filter_table_t *table = enp->en_filter.ef_ef10_filter_table;
+ uint32_t filter_idx = filter_id % EFX_EF10_FILTER_TBL_ROWS;
+
+ /*
+ * AUTO_OLD flag is cleared since the auto filter that is to be removed
+ * may not be the filter at the specified index itself, but the filter
+ * that is overridden by it.
+ */
+ ef10_filter_set_entry_not_auto_old(table, filter_idx);
+
+ (void) ef10_filter_delete_internal(enp, filter_idx,
+ EFX_FILTER_PRI_AUTO);
+}
+
__checkReturn efx_rc_t
ef10_filter_delete(
__in efx_nic_t *enp,
@@ -908,7 +1172,8 @@ ef10_filter_delete(
i = (hash + depth) & (EFX_EF10_FILTER_TBL_ROWS - 1);
saved_spec = ef10_filter_entry_spec(table, i);
if (saved_spec && ef10_filter_equal(spec, saved_spec) &&
- ef10_filter_same_dest(spec, saved_spec)) {
+ ef10_filter_same_dest(spec, saved_spec) &&
+ saved_spec->efs_priority == EFX_FILTER_PRI_MANUAL) {
break;
}
if (depth == EF10_FILTER_SEARCH_LIMIT) {
@@ -921,7 +1186,7 @@ ef10_filter_delete(
EFSYS_UNLOCK(enp->en_eslp, state);
locked = B_FALSE;
- rc = ef10_filter_delete_internal(enp, i);
+ rc = ef10_filter_delete_internal(enp, i, EFX_FILTER_PRI_MANUAL);
if (rc != 0)
goto fail2;
@@ -1146,7 +1411,7 @@ ef10_filter_insert_unicast(
if (rc != 0)
goto fail1;
- rc = ef10_filter_add_internal(enp, &spec, B_TRUE,
+ rc = ef10_filter_add_internal(enp, &spec, EFX_FILTER_REPLACEMENT_NEVER,
&eftp->eft_unicst_filter_indexes[eftp->eft_unicst_filter_count]);
if (rc != 0)
goto fail2;
@@ -1180,7 +1445,7 @@ ef10_filter_insert_all_unicast(
rc = efx_filter_spec_set_uc_def(&spec);
if (rc != 0)
goto fail1;
- rc = ef10_filter_add_internal(enp, &spec, B_TRUE,
+ rc = ef10_filter_add_internal(enp, &spec, EFX_FILTER_REPLACEMENT_NEVER,
&eftp->eft_unicst_filter_indexes[eftp->eft_unicst_filter_count]);
if (rc != 0)
goto fail2;
@@ -1250,8 +1515,8 @@ ef10_filter_insert_multicast_list(
}
}
- rc = ef10_filter_add_internal(enp, &spec, B_TRUE,
- &filter_index);
+ rc = ef10_filter_add_internal(enp, &spec,
+ EFX_FILTER_REPLACEMENT_NEVER, &filter_index);
if (rc == 0) {
eftp->eft_mulcst_filter_indexes[filter_count] =
@@ -1278,8 +1543,8 @@ ef10_filter_insert_multicast_list(
goto rollback;
}
- rc = ef10_filter_add_internal(enp, &spec, B_TRUE,
- &filter_index);
+ rc = ef10_filter_add_internal(enp, &spec,
+ EFX_FILTER_REPLACEMENT_NEVER, &filter_index);
if (rc == 0) {
eftp->eft_mulcst_filter_indexes[filter_count] =
@@ -1300,7 +1565,7 @@ ef10_filter_insert_multicast_list(
/* Remove any filters we have inserted */
i = filter_count;
while (i--) {
- (void) ef10_filter_delete_internal(enp,
+ ef10_filter_delete_auto(enp,
eftp->eft_mulcst_filter_indexes[i]);
}
eftp->eft_mulcst_filter_count = 0;
@@ -1328,7 +1593,7 @@ ef10_filter_insert_all_multicast(
if (rc != 0)
goto fail1;
- rc = ef10_filter_add_internal(enp, &spec, B_TRUE,
+ rc = ef10_filter_add_internal(enp, &spec, EFX_FILTER_REPLACEMENT_NEVER,
&eftp->eft_mulcst_filter_indexes[0]);
if (rc != 0)
goto fail2;
@@ -1431,8 +1696,9 @@ ef10_filter_insert_encap_filters(
if (rc != 0)
goto fail1;
- rc = ef10_filter_add_internal(enp, &spec, B_TRUE,
- &table->eft_encap_filter_indexes[
+ rc = ef10_filter_add_internal(enp, &spec,
+ EFX_FILTER_REPLACEMENT_NEVER,
+ &table->eft_encap_filter_indexes[
table->eft_encap_filter_count]);
if (rc != 0) {
if (rc != EACCES)
@@ -1461,7 +1727,7 @@ ef10_filter_remove_old(
for (i = 0; i < EFX_ARRAY_SIZE(table->eft_entry); i++) {
if (ef10_filter_entry_is_auto_old(table, i)) {
- (void) ef10_filter_delete_internal(enp, i);
+ ef10_filter_delete_auto(enp, i);
}
}
}
@@ -1536,19 +1802,19 @@ ef10_filter_reconfigure(
* has rebooted, which removes hardware filters).
*/
for (i = 0; i < table->eft_unicst_filter_count; i++) {
- (void) ef10_filter_delete_internal(enp,
+ ef10_filter_delete_auto(enp,
table->eft_unicst_filter_indexes[i]);
}
table->eft_unicst_filter_count = 0;
for (i = 0; i < table->eft_mulcst_filter_count; i++) {
- (void) ef10_filter_delete_internal(enp,
+ ef10_filter_delete_auto(enp,
table->eft_mulcst_filter_indexes[i]);
}
table->eft_mulcst_filter_count = 0;
for (i = 0; i < table->eft_encap_filter_count; i++) {
- (void) ef10_filter_delete_internal(enp,
+ ef10_filter_delete_auto(enp,
table->eft_encap_filter_indexes[i]);
}
table->eft_encap_filter_count = 0;
diff --git a/dpdk/drivers/net/sfc/base/ef10_impl.h b/dpdk/drivers/net/sfc/base/ef10_impl.h
index 6f5d0f9aae..4183325c0f 100644
--- a/dpdk/drivers/net/sfc/base/ef10_impl.h
+++ b/dpdk/drivers/net/sfc/base/ef10_impl.h
@@ -1030,6 +1030,8 @@ ef10_rx_fini(
#if EFSYS_OPT_FILTER
+enum efx_filter_replacement_policy_e;
+
typedef struct ef10_filter_handle_s {
uint32_t efh_lo;
uint32_t efh_hi;
@@ -1099,7 +1101,7 @@ ef10_filter_restore(
ef10_filter_add(
__in efx_nic_t *enp,
__inout efx_filter_spec_t *spec,
- __in boolean_t may_replace);
+ __in enum efx_filter_replacement_policy_e policy);
__checkReturn efx_rc_t
ef10_filter_delete(
diff --git a/dpdk/drivers/net/sfc/base/efx.h b/dpdk/drivers/net/sfc/base/efx.h
index 444f6d1db3..9babf8d40b 100644
--- a/dpdk/drivers/net/sfc/base/efx.h
+++ b/dpdk/drivers/net/sfc/base/efx.h
@@ -2867,17 +2867,15 @@ typedef uint8_t efx_filter_flags_t;
typedef uint32_t efx_filter_match_flags_t;
+/* Filter priority from lowest to highest */
typedef enum efx_filter_priority_s {
- EFX_FILTER_PRI_HINT = 0, /* Performance hint */
- EFX_FILTER_PRI_AUTO, /* Automatic filter based on device
+ EFX_FILTER_PRI_AUTO = 0, /* Automatic filter based on device
* address list or hardware
* requirements. This may only be used
* by the filter implementation for
* each NIC type. */
EFX_FILTER_PRI_MANUAL, /* Manually configured filter */
- EFX_FILTER_PRI_REQUIRED, /* Required for correct behaviour of the
- * client (e.g. SR-IOV, HyperV VMQ etc.)
- */
+ EFX_FILTER_NPRI,
} efx_filter_priority_t;
/*
@@ -2892,6 +2890,11 @@ typedef struct efx_filter_spec_s {
uint16_t efs_dmaq_id;
uint32_t efs_rss_context;
uint32_t efs_mark;
+ /*
+ * Saved lower-priority filter. If it is set, it is restored on
+ * filter delete operation.
+ */
+ struct efx_filter_spec_s *efs_overridden_spec;
/* Fields below here are hashed for software filter lookup */
uint16_t efs_outer_vid;
uint16_t efs_inner_vid;
diff --git a/dpdk/drivers/net/sfc/base/efx_filter.c b/dpdk/drivers/net/sfc/base/efx_filter.c
index a7523b38b6..f70717cbc2 100644
--- a/dpdk/drivers/net/sfc/base/efx_filter.c
+++ b/dpdk/drivers/net/sfc/base/efx_filter.c
@@ -28,7 +28,7 @@ static __checkReturn efx_rc_t
siena_filter_add(
__in efx_nic_t *enp,
__inout efx_filter_spec_t *spec,
- __in boolean_t may_replace);
+ __in efx_filter_replacement_policy_t policy);
static __checkReturn efx_rc_t
siena_filter_delete(
@@ -93,8 +93,16 @@ efx_filter_insert(
goto fail2;
}
- return (efop->efo_add(enp, spec, B_FALSE));
+ if (spec->efs_priority == EFX_FILTER_PRI_AUTO) {
+ rc = EINVAL;
+ goto fail3;
+ }
+ return (efop->efo_add(enp, spec,
+ EFX_FILTER_REPLACEMENT_HIGHER_PRIORITY));
+
+fail3:
+ EFSYS_PROBE(fail3);
fail2:
EFSYS_PROBE(fail2);
fail1:
@@ -314,7 +322,7 @@ efx_filter_spec_init_tx(
EFSYS_ASSERT3P(etp, !=, NULL);
memset(spec, 0, sizeof (*spec));
- spec->efs_priority = EFX_FILTER_PRI_REQUIRED;
+ spec->efs_priority = EFX_FILTER_PRI_MANUAL;
spec->efs_flags = EFX_FILTER_FLAG_TX;
spec->efs_dmaq_id = (uint16_t)etp->et_index;
}
@@ -1437,7 +1445,7 @@ static __checkReturn efx_rc_t
siena_filter_add(
__in efx_nic_t *enp,
__inout efx_filter_spec_t *spec,
- __in boolean_t may_replace)
+ __in efx_filter_replacement_policy_t policy)
{
efx_rc_t rc;
siena_filter_spec_t sf_spec;
@@ -1478,9 +1486,17 @@ siena_filter_add(
saved_sf_spec = &sftp->sft_spec[filter_idx];
if (siena_filter_test_used(sftp, filter_idx)) {
- if (may_replace == B_FALSE) {
+ /* All Siena filter are considered the same priority */
+ switch (policy) {
+ case EFX_FILTER_REPLACEMENT_NEVER:
+ case EFX_FILTER_REPLACEMENT_HIGHER_PRIORITY:
rc = EEXIST;
goto fail4;
+ case EFX_FILTER_REPLACEMENT_HIGHER_OR_EQUAL_PRIORITY:
+ break;
+ default:
+ EFSYS_ASSERT(0);
+ break;
}
}
siena_filter_set_used(sftp, filter_idx);
diff --git a/dpdk/drivers/net/sfc/base/efx_impl.h b/dpdk/drivers/net/sfc/base/efx_impl.h
index bad23f8198..a61b9460f0 100644
--- a/dpdk/drivers/net/sfc/base/efx_impl.h
+++ b/dpdk/drivers/net/sfc/base/efx_impl.h
@@ -240,12 +240,31 @@ typedef struct efx_phy_ops_s {
} efx_phy_ops_t;
#if EFSYS_OPT_FILTER
+
+/*
+ * Policy for replacing existing filter when inserting a new one.
+ * Note that all policies allow for storing the new lower priority
+ * filters as overridden by existing higher priority ones. It is needed
+ * to restore the lower priority filters on higher priority ones removal.
+ */
+typedef enum efx_filter_replacement_policy_e {
+ /* Cannot replace existing filter */
+ EFX_FILTER_REPLACEMENT_NEVER,
+ /* Higher priority filters can replace lower priotiry ones */
+ EFX_FILTER_REPLACEMENT_HIGHER_PRIORITY,
+ /*
+ * Higher priority filters can replace lower priority ones and
+ * equal priority filters can replace each other.
+ */
+ EFX_FILTER_REPLACEMENT_HIGHER_OR_EQUAL_PRIORITY,
+} efx_filter_replacement_policy_t;
+
typedef struct efx_filter_ops_s {
efx_rc_t (*efo_init)(efx_nic_t *);
void (*efo_fini)(efx_nic_t *);
efx_rc_t (*efo_restore)(efx_nic_t *);
efx_rc_t (*efo_add)(efx_nic_t *, efx_filter_spec_t *,
- boolean_t may_replace);
+ efx_filter_replacement_policy_t policy);
efx_rc_t (*efo_delete)(efx_nic_t *, efx_filter_spec_t *);
efx_rc_t (*efo_supported_filters)(efx_nic_t *, uint32_t *,
size_t, size_t *);
diff --git a/dpdk/drivers/net/sfc/sfc.c b/dpdk/drivers/net/sfc/sfc.c
index d056d12164..48d95845d6 100644
--- a/dpdk/drivers/net/sfc/sfc.c
+++ b/dpdk/drivers/net/sfc/sfc.c
@@ -240,8 +240,8 @@ sfc_estimate_resource_limits(struct sfc_adapter *sa)
return 0;
fail_get_vi_pool:
-fail_nic_init:
efx_nic_fini(sa->nic);
+fail_nic_init:
return rc;
}
diff --git a/dpdk/drivers/net/sfc/sfc_rx.c b/dpdk/drivers/net/sfc/sfc_rx.c
index 960ab62c19..2d506c3860 100644
--- a/dpdk/drivers/net/sfc/sfc_rx.c
+++ b/dpdk/drivers/net/sfc/sfc_rx.c
@@ -646,6 +646,7 @@ sfc_rx_default_rxq_set_filter(struct sfc_adapter *sa, struct sfc_rxq *rxq)
sfc_warn(sa, "promiscuous mode will be disabled");
port->promisc = B_FALSE;
+ sa->eth_dev->data->promiscuous = 0;
rc = sfc_set_rx_mode(sa);
if (rc != 0)
return rc;
@@ -659,6 +660,7 @@ sfc_rx_default_rxq_set_filter(struct sfc_adapter *sa, struct sfc_rxq *rxq)
sfc_warn(sa, "all-multicast mode will be disabled");
port->allmulti = B_FALSE;
+ sa->eth_dev->data->all_multicast = 0;
rc = sfc_set_rx_mode(sa);
if (rc != 0)
return rc;
@@ -748,10 +750,12 @@ sfc_rx_qstart(struct sfc_adapter *sa, unsigned int sw_index)
return 0;
fail_mac_filter_default_rxq_set:
+ sfc_rx_qflush(sa, sw_index);
sa->dp_rx->qstop(rxq->dp, &rxq->evq->read_ptr);
+ rxq->state = SFC_RXQ_INITIALIZED;
fail_dp_qstart:
- sfc_rx_qflush(sa, sw_index);
+ efx_rx_qdestroy(rxq->common);
fail_rx_qcreate:
fail_bad_contig_block_size:
diff --git a/dpdk/drivers/net/softnic/rte_eth_softnic_thread.c b/dpdk/drivers/net/softnic/rte_eth_softnic_thread.c
index 4572adfa6a..6a888d20ec 100644
--- a/dpdk/drivers/net/softnic/rte_eth_softnic_thread.c
+++ b/dpdk/drivers/net/softnic/rte_eth_softnic_thread.c
@@ -267,8 +267,6 @@ softnic_thread_pipeline_enable(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = thread_msg_send_recv(softnic, thread_id, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -355,8 +353,6 @@ softnic_thread_pipeline_disable(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = thread_msg_send_recv(softnic, thread_id, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -751,8 +747,6 @@ softnic_pipeline_port_in_stats_read(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -800,8 +794,6 @@ softnic_pipeline_port_in_enable(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -847,8 +839,6 @@ softnic_pipeline_port_in_disable(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -902,8 +892,6 @@ softnic_pipeline_port_out_stats_read(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -959,8 +947,6 @@ softnic_pipeline_table_stats_read(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1239,8 +1225,6 @@ softnic_pipeline_table_rule_add(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1323,8 +1307,6 @@ softnic_pipeline_table_rule_add_default(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1481,8 +1463,6 @@ softnic_pipeline_table_rule_add_bulk(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1546,8 +1526,6 @@ softnic_pipeline_table_rule_delete(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1596,8 +1574,6 @@ softnic_pipeline_table_rule_delete_default(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1656,8 +1632,6 @@ softnic_pipeline_table_rule_stats_read(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1737,10 +1711,6 @@ softnic_pipeline_table_mtr_profile_add(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL) {
- free(mp);
- return -1;
- }
/* Read response */
status = rsp->status;
@@ -1796,8 +1766,6 @@ softnic_pipeline_table_mtr_profile_delete(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1859,8 +1827,6 @@ softnic_pipeline_table_rule_mtr_read(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1924,8 +1890,6 @@ softnic_pipeline_table_dscp_table_update(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1989,8 +1953,6 @@ softnic_pipeline_table_rule_ttl_read(struct pmd_internals *softnic,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
diff --git a/dpdk/drivers/net/tap/rte_eth_tap.c b/dpdk/drivers/net/tap/rte_eth_tap.c
index 3a8aa44a73..62fb542865 100644
--- a/dpdk/drivers/net/tap/rte_eth_tap.c
+++ b/dpdk/drivers/net/tap/rte_eth_tap.c
@@ -18,8 +18,8 @@
#include <rte_string_fns.h>
#include <rte_ethdev.h>
#include <rte_errno.h>
+#include <rte_cycles.h>
-#include <assert.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/socket.h>
@@ -341,6 +341,23 @@ tap_rx_offload_get_queue_capa(void)
DEV_RX_OFFLOAD_TCP_CKSUM;
}
+static void
+tap_rxq_pool_free(struct rte_mbuf *pool)
+{
+ struct rte_mbuf *mbuf = pool;
+ uint16_t nb_segs = 1;
+
+ if (mbuf == NULL)
+ return;
+
+ while (mbuf->next) {
+ mbuf = mbuf->next;
+ nb_segs++;
+ }
+ pool->nb_segs = nb_segs;
+ rte_pktmbuf_free(pool);
+}
+
/* Callback to handle the rx burst of packets to the correct interface and
* file descriptor(s) in a multi-queue setup.
*/
@@ -391,7 +408,7 @@ pmd_rx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
goto end;
seg->next = NULL;
- rte_pktmbuf_free(mbuf);
+ tap_rxq_pool_free(mbuf);
goto end;
}
@@ -523,7 +540,7 @@ tap_tx_l3_cksum(char *packet, uint64_t ol_flags, unsigned int l2_len,
}
}
-static inline void
+static inline int
tap_write_mbufs(struct tx_queue *txq, uint16_t num_mbufs,
struct rte_mbuf **pmbufs,
uint16_t *num_packets, unsigned long *num_tx_bytes)
@@ -590,7 +607,7 @@ tap_write_mbufs(struct tx_queue *txq, uint16_t num_mbufs,
seg_len = rte_pktmbuf_data_len(mbuf);
l234_hlen = mbuf->l2_len + mbuf->l3_len + mbuf->l4_len;
if (seg_len < l234_hlen)
- break;
+ return -1;
/* To change checksums, work on a * copy of l2, l3
* headers + l4 pseudo header
@@ -636,10 +653,12 @@ tap_write_mbufs(struct tx_queue *txq, uint16_t num_mbufs,
/* copy the tx frame data */
n = writev(process_private->txq_fds[txq->queue_id], iovecs, j);
if (n <= 0)
- break;
+ return -1;
+
(*num_packets)++;
(*num_tx_bytes) += rte_pktmbuf_pkt_len(mbuf);
}
+ return 0;
}
/* Callback to handle sending packets from the tap interface
@@ -665,6 +684,7 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
uint16_t num_mbufs = 0;
uint16_t tso_segsz = 0;
int ret;
+ int num_tso_mbufs;
uint16_t hdrs_len;
int j;
uint64_t tso;
@@ -673,8 +693,6 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
if (tso) {
struct rte_gso_ctx *gso_ctx = &txq->gso_ctx;
- assert(gso_ctx != NULL);
-
/* TCP segmentation implies TCP checksum offload */
mbuf_in->ol_flags |= PKT_TX_TCP_CKSUM;
@@ -688,35 +706,43 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
break;
}
gso_ctx->gso_size = tso_segsz;
- ret = rte_gso_segment(mbuf_in, /* packet to segment */
+ /* 'mbuf_in' packet to segment */
+ num_tso_mbufs = rte_gso_segment(mbuf_in,
gso_ctx, /* gso control block */
(struct rte_mbuf **)&gso_mbufs, /* out mbufs */
RTE_DIM(gso_mbufs)); /* max tso mbufs */
/* ret contains the number of new created mbufs */
- if (ret < 0)
+ if (num_tso_mbufs < 0)
break;
mbuf = gso_mbufs;
- num_mbufs = ret;
+ num_mbufs = num_tso_mbufs;
} else {
/* stats.errs will be incremented */
if (rte_pktmbuf_pkt_len(mbuf_in) > max_size)
break;
/* ret 0 indicates no new mbufs were created */
- ret = 0;
+ num_tso_mbufs = 0;
mbuf = &mbuf_in;
num_mbufs = 1;
}
- tap_write_mbufs(txq, num_mbufs, mbuf,
+ ret = tap_write_mbufs(txq, num_mbufs, mbuf,
&num_packets, &num_tx_bytes);
+ if (ret == -1) {
+ txq->stats.errs++;
+ /* free tso mbufs */
+ for (j = 0; j < num_tso_mbufs; j++)
+ rte_pktmbuf_free(mbuf[j]);
+ break;
+ }
num_tx++;
/* free original mbuf */
rte_pktmbuf_free(mbuf_in);
/* free tso mbufs */
- for (j = 0; j < ret; j++)
+ for (j = 0; j < num_tso_mbufs; j++)
rte_pktmbuf_free(mbuf[j]);
}
@@ -724,7 +750,7 @@ pmd_tx_burst(void *queue, struct rte_mbuf **bufs, uint16_t nb_pkts)
txq->stats.errs += nb_pkts - num_tx;
txq->stats.obytes += num_tx_bytes;
- return num_packets;
+ return num_tx;
}
static const char *
@@ -780,7 +806,7 @@ tap_ioctl(struct pmd_internals *pmd, unsigned long request,
case SIOCSIFMTU:
break;
default:
- RTE_LOG(WARNING, PMD, "%s: ioctl() called with wrong arg\n",
+ TAP_LOG(WARNING, "%s: ioctl() called with wrong arg",
pmd->name);
return -EINVAL;
}
@@ -1010,15 +1036,25 @@ tap_dev_close(struct rte_eth_dev *dev)
int i;
struct pmd_internals *internals = dev->data->dev_private;
struct pmd_process_private *process_private = dev->process_private;
+ struct rx_queue *rxq;
tap_link_set_down(dev);
- tap_flow_flush(dev, NULL);
- tap_flow_implicit_flush(internals, NULL);
+ if (internals->nlsk_fd != -1) {
+ tap_flow_flush(dev, NULL);
+ tap_flow_implicit_flush(internals, NULL);
+ tap_nl_final(internals->nlsk_fd);
+ internals->nlsk_fd = -1;
+ }
for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
if (process_private->rxq_fds[i] != -1) {
+ rxq = &internals->rxq[i];
close(process_private->rxq_fds[i]);
process_private->rxq_fds[i] = -1;
+ tap_rxq_pool_free(rxq->pool);
+ rte_free(rxq->iovecs);
+ rxq->pool = NULL;
+ rxq->iovecs = NULL;
}
if (process_private->txq_fds[i] != -1) {
close(process_private->txq_fds[i]);
@@ -1051,10 +1087,10 @@ tap_rx_queue_release(void *queue)
if (!rxq)
return;
process_private = rte_eth_devices[rxq->in_port].process_private;
- if (process_private->rxq_fds[rxq->queue_id] > 0) {
+ if (process_private->rxq_fds[rxq->queue_id] != -1) {
close(process_private->rxq_fds[rxq->queue_id]);
process_private->rxq_fds[rxq->queue_id] = -1;
- rte_pktmbuf_free(rxq->pool);
+ tap_rxq_pool_free(rxq->pool);
rte_free(rxq->iovecs);
rxq->pool = NULL;
rxq->iovecs = NULL;
@@ -1071,7 +1107,7 @@ tap_tx_queue_release(void *queue)
return;
process_private = rte_eth_devices[txq->out_port].process_private;
- if (process_private->txq_fds[txq->queue_id] > 0) {
+ if (process_private->txq_fds[txq->queue_id] != -1) {
close(process_private->txq_fds[txq->queue_id]);
process_private->txq_fds[txq->queue_id] = -1;
}
@@ -1232,7 +1268,9 @@ tap_gso_ctx_setup(struct rte_gso_ctx *gso_ctx, struct rte_eth_dev *dev)
SOCKET_ID_ANY);
if (!mp) {
struct pmd_internals *pmd = dev->data->dev_private;
- RTE_LOG(DEBUG, PMD, "%s: failed to create mbuf pool for device %s\n",
+
+ TAP_LOG(ERR,
+ "%s: failed to create mbuf pool for device %s\n",
pmd->name, dev->device->name);
return -1;
}
@@ -1396,7 +1434,7 @@ tap_rx_queue_setup(struct rte_eth_dev *dev,
return 0;
error:
- rte_pktmbuf_free(rxq->pool);
+ tap_rxq_pool_free(rxq->pool);
rxq->pool = NULL;
rte_free(rxq->iovecs);
rxq->iovecs = NULL;
@@ -1494,13 +1532,12 @@ static int
tap_lsc_intr_handle_set(struct rte_eth_dev *dev, int set)
{
struct pmd_internals *pmd = dev->data->dev_private;
+ int ret;
/* In any case, disable interrupt if the conf is no longer there. */
if (!dev->data->dev_conf.intr_conf.lsc) {
if (pmd->intr_handle.fd != -1) {
- tap_nl_final(pmd->intr_handle.fd);
- rte_intr_callback_unregister(&pmd->intr_handle,
- tap_dev_intr_handler, dev);
+ goto clean;
}
return 0;
}
@@ -1511,9 +1548,26 @@ tap_lsc_intr_handle_set(struct rte_eth_dev *dev, int set)
return rte_intr_callback_register(
&pmd->intr_handle, tap_dev_intr_handler, dev);
}
+
+clean:
+ do {
+ ret = rte_intr_callback_unregister(&pmd->intr_handle,
+ tap_dev_intr_handler, dev);
+ if (ret >= 0) {
+ break;
+ } else if (ret == -EAGAIN) {
+ rte_delay_ms(100);
+ } else {
+ TAP_LOG(ERR, "intr callback unregister failed: %d",
+ ret);
+ break;
+ }
+ } while (true);
+
tap_nl_final(pmd->intr_handle.fd);
- return rte_intr_callback_unregister(&pmd->intr_handle,
- tap_dev_intr_handler, dev);
+ pmd->intr_handle.fd = -1;
+
+ return 0;
}
static int
@@ -1714,6 +1768,8 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name,
pmd->dev = dev;
snprintf(pmd->name, sizeof(pmd->name), "%s", tap_name);
pmd->type = type;
+ pmd->ka_fd = -1;
+ pmd->nlsk_fd = -1;
pmd->ioctl_sock = socket(AF_INET, SOCK_DGRAM, 0);
if (pmd->ioctl_sock == -1) {
@@ -1744,7 +1800,6 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name,
dev->intr_handle = &pmd->intr_handle;
/* Presetup the fds to -1 as being not valid */
- pmd->ka_fd = -1;
for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
process_private->rxq_fds[i] = -1;
process_private->txq_fds[i] = -1;
@@ -1885,7 +1940,11 @@ eth_dev_tap_create(struct rte_vdev_device *vdev, char *tap_name,
tap_flow_implicit_flush(pmd, NULL);
error_exit:
- if (pmd->ioctl_sock > 0)
+ if (pmd->nlsk_fd != -1)
+ close(pmd->nlsk_fd);
+ if (pmd->ka_fd != -1)
+ close(pmd->ka_fd);
+ if (pmd->ioctl_sock != -1)
close(pmd->ioctl_sock);
/* mac_addrs must not be freed alone because part of dev_private */
dev->data->mac_addrs = NULL;
@@ -2291,8 +2350,6 @@ rte_pmd_tap_remove(struct rte_vdev_device *dev)
{
struct rte_eth_dev *eth_dev = NULL;
struct pmd_internals *internals;
- struct pmd_process_private *process_private;
- int i;
/* find the ethdev entry */
eth_dev = rte_eth_dev_allocated(rte_vdev_device_name(dev));
@@ -2305,29 +2362,13 @@ rte_pmd_tap_remove(struct rte_vdev_device *dev)
if (rte_eal_process_type() != RTE_PROC_PRIMARY)
return rte_eth_dev_release_port(eth_dev);
- internals = eth_dev->data->dev_private;
- process_private = eth_dev->process_private;
+ tap_dev_close(eth_dev);
+ internals = eth_dev->data->dev_private;
TAP_LOG(DEBUG, "Closing %s Ethernet device on numa %u",
(internals->type == ETH_TUNTAP_TYPE_TAP) ? "TAP" : "TUN",
rte_socket_id());
- if (internals->nlsk_fd) {
- tap_flow_flush(eth_dev, NULL);
- tap_flow_implicit_flush(internals, NULL);
- tap_nl_final(internals->nlsk_fd);
- }
- for (i = 0; i < RTE_PMD_TAP_MAX_QUEUES; i++) {
- if (process_private->rxq_fds[i] != -1) {
- close(process_private->rxq_fds[i]);
- process_private->rxq_fds[i] = -1;
- }
- if (process_private->txq_fds[i] != -1) {
- close(process_private->txq_fds[i]);
- process_private->txq_fds[i] = -1;
- }
- }
-
close(internals->ioctl_sock);
rte_free(eth_dev->process_private);
if (tap_devices_count == 1)
@@ -2335,10 +2376,6 @@ rte_pmd_tap_remove(struct rte_vdev_device *dev)
tap_devices_count--;
rte_eth_dev_release_port(eth_dev);
- if (internals->ka_fd != -1) {
- close(internals->ka_fd);
- internals->ka_fd = -1;
- }
return 0;
}
diff --git a/dpdk/drivers/net/tap/tap_flow.c b/dpdk/drivers/net/tap/tap_flow.c
index d155618fc8..0c5043b63f 100644
--- a/dpdk/drivers/net/tap/tap_flow.c
+++ b/dpdk/drivers/net/tap/tap_flow.c
@@ -1378,7 +1378,7 @@ tap_flow_create(struct rte_eth_dev *dev,
NULL, "priority value too big");
goto fail;
}
- flow = rte_malloc(__func__, sizeof(struct rte_flow), 0);
+ flow = rte_zmalloc(__func__, sizeof(struct rte_flow), 0);
if (!flow) {
rte_flow_error_set(error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE,
NULL, "cannot allocate memory for rte_flow");
@@ -1414,7 +1414,7 @@ tap_flow_create(struct rte_eth_dev *dev,
* to the local pmd->if_index.
*/
if (pmd->remote_if_index) {
- remote_flow = rte_malloc(__func__, sizeof(struct rte_flow), 0);
+ remote_flow = rte_zmalloc(__func__, sizeof(struct rte_flow), 0);
if (!remote_flow) {
rte_flow_error_set(
error, ENOMEM, RTE_FLOW_ERROR_TYPE_HANDLE, NULL,
@@ -1691,7 +1691,7 @@ int tap_flow_implicit_create(struct pmd_internals *pmd,
}
};
- remote_flow = rte_malloc(__func__, sizeof(struct rte_flow), 0);
+ remote_flow = rte_zmalloc(__func__, sizeof(struct rte_flow), 0);
if (!remote_flow) {
TAP_LOG(ERR, "Cannot allocate memory for rte_flow");
goto fail;
@@ -1894,7 +1894,7 @@ static int rss_enable(struct pmd_internals *pmd,
return -ENOTSUP;
}
- rss_flow = rte_malloc(__func__, sizeof(struct rte_flow), 0);
+ rss_flow = rte_zmalloc(__func__, sizeof(struct rte_flow), 0);
if (!rss_flow) {
TAP_LOG(ERR,
"Cannot allocate memory for rte_flow");
diff --git a/dpdk/drivers/net/tap/tap_intr.c b/dpdk/drivers/net/tap/tap_intr.c
index 7af0010e37..5cf4f173a0 100644
--- a/dpdk/drivers/net/tap/tap_intr.c
+++ b/dpdk/drivers/net/tap/tap_intr.c
@@ -7,7 +7,6 @@
* Interrupts handling for tap driver.
*/
-#include <assert.h>
#include <errno.h>
#include <fcntl.h>
#include <signal.h>
@@ -72,7 +71,7 @@ tap_rx_intr_vec_install(struct rte_eth_dev *dev)
struct rx_queue *rxq = pmd->dev->data->rx_queues[i];
/* Skip queues that cannot request interrupts. */
- if (!rxq || process_private->rxq_fds[i] <= 0) {
+ if (!rxq || process_private->rxq_fds[i] == -1) {
/* Use invalid intr_vec[] index to disable entry. */
intr_handle->intr_vec[i] =
RTE_INTR_VEC_RXTX_OFFSET +
diff --git a/dpdk/drivers/net/thunderx/nicvf_ethdev.c b/dpdk/drivers/net/thunderx/nicvf_ethdev.c
index ae5a33e3a1..d627a3bb70 100644
--- a/dpdk/drivers/net/thunderx/nicvf_ethdev.c
+++ b/dpdk/drivers/net/thunderx/nicvf_ethdev.c
@@ -488,9 +488,10 @@ nicvf_dev_reta_query(struct rte_eth_dev *dev,
int ret, i, j;
if (reta_size != NIC_MAX_RSS_IDR_TBL_SIZE) {
- RTE_LOG(ERR, PMD, "The size of hash lookup table configured "
- "(%d) doesn't match the number hardware can supported "
- "(%d)", reta_size, NIC_MAX_RSS_IDR_TBL_SIZE);
+ PMD_DRV_LOG(ERR,
+ "The size of hash lookup table configured "
+ "(%u) doesn't match the number hardware can supported "
+ "(%u)", reta_size, NIC_MAX_RSS_IDR_TBL_SIZE);
return -EINVAL;
}
@@ -518,9 +519,9 @@ nicvf_dev_reta_update(struct rte_eth_dev *dev,
int ret, i, j;
if (reta_size != NIC_MAX_RSS_IDR_TBL_SIZE) {
- RTE_LOG(ERR, PMD, "The size of hash lookup table configured "
- "(%d) doesn't match the number hardware can supported "
- "(%d)", reta_size, NIC_MAX_RSS_IDR_TBL_SIZE);
+ PMD_DRV_LOG(ERR, "The size of hash lookup table configured "
+ "(%u) doesn't match the number hardware can supported "
+ "(%u)", reta_size, NIC_MAX_RSS_IDR_TBL_SIZE);
return -EINVAL;
}
@@ -561,8 +562,8 @@ nicvf_dev_rss_hash_update(struct rte_eth_dev *dev,
if (rss_conf->rss_key &&
rss_conf->rss_key_len != RSS_HASH_KEY_BYTE_SIZE) {
- RTE_LOG(ERR, PMD, "Hash key size mismatch %d",
- rss_conf->rss_key_len);
+ PMD_DRV_LOG(ERR, "Hash key size mismatch %u",
+ rss_conf->rss_key_len);
return -EINVAL;
}
diff --git a/dpdk/drivers/net/vhost/rte_eth_vhost.c b/dpdk/drivers/net/vhost/rte_eth_vhost.c
index 52b9e0c102..93ca8ebe4b 100644
--- a/dpdk/drivers/net/vhost/rte_eth_vhost.c
+++ b/dpdk/drivers/net/vhost/rte_eth_vhost.c
@@ -985,16 +985,14 @@ eth_dev_close(struct rte_eth_dev *dev)
eth_dev_stop(dev);
- rte_vhost_driver_unregister(internal->iface_name);
-
list = find_internal_resource(internal->iface_name);
- if (!list)
- return;
-
- pthread_mutex_lock(&internal_list_lock);
- TAILQ_REMOVE(&internal_list, list, next);
- pthread_mutex_unlock(&internal_list_lock);
- rte_free(list);
+ if (list) {
+ rte_vhost_driver_unregister(internal->iface_name);
+ pthread_mutex_lock(&internal_list_lock);
+ TAILQ_REMOVE(&internal_list, list, next);
+ pthread_mutex_unlock(&internal_list_lock);
+ rte_free(list);
+ }
if (dev->data->rx_queues)
for (i = 0; i < dev->data->nb_rx_queues; i++)
diff --git a/dpdk/drivers/net/virtio/virtio_ethdev.c b/dpdk/drivers/net/virtio/virtio_ethdev.c
index 2d4c6c7fa9..be24677093 100644
--- a/dpdk/drivers/net/virtio/virtio_ethdev.c
+++ b/dpdk/drivers/net/virtio/virtio_ethdev.c
@@ -349,7 +349,7 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
}
if (!rte_is_power_of_2(vq_size)) {
- PMD_INIT_LOG(ERR, "virtqueue size is not powerof 2");
+ PMD_INIT_LOG(ERR, "virtqueue size is not power of 2");
return -EINVAL;
}
@@ -464,8 +464,8 @@ virtio_init_queue(struct rte_eth_dev *dev, uint16_t vtpci_queue_idx)
hw->cvq = cvq;
}
- /* For virtio_user case (that is when hw->dev is NULL), we use
- * virtual address. And we need properly set _offset_, please see
+ /* For virtio_user case (that is when hw->virtio_user_dev is not NULL),
+ * we use virtual address. And we need properly set _offset_, please see
* VIRTIO_MBUF_DATA_DMA_ADDR in virtqueue.h for more information.
*/
if (!hw->virtio_user_dev)
diff --git a/dpdk/drivers/net/virtio/virtio_rxtx.c b/dpdk/drivers/net/virtio/virtio_rxtx.c
index db2d1f1c1e..8ce5c33940 100644
--- a/dpdk/drivers/net/virtio/virtio_rxtx.c
+++ b/dpdk/drivers/net/virtio/virtio_rxtx.c
@@ -708,7 +708,7 @@ virtio_dev_tx_queue_setup(struct rte_eth_dev *dev,
RTE_MIN(vq->vq_nentries / 4, DEFAULT_TX_FREE_THRESH);
if (tx_free_thresh >= (vq->vq_nentries - 3)) {
- RTE_LOG(ERR, PMD, "tx_free_thresh must be less than the "
+ PMD_DRV_LOG(ERR, "tx_free_thresh must be less than the "
"number of TX entries minus 3 (%u)."
" (tx_free_thresh=%u port=%u queue=%u)\n",
vq->vq_nentries - 3,
@@ -751,7 +751,7 @@ virtio_discard_rxbuf(struct virtqueue *vq, struct rte_mbuf *m)
error = virtqueue_enqueue_recv_refill(vq, m);
if (unlikely(error)) {
- RTE_LOG(ERR, PMD, "cannot requeue discarded mbuf");
+ PMD_DRV_LOG(ERR, "cannot requeue discarded mbuf");
rte_pktmbuf_free(m);
}
}
@@ -763,7 +763,7 @@ virtio_discard_rxbuf_inorder(struct virtqueue *vq, struct rte_mbuf *m)
error = virtqueue_enqueue_refill_inorder(vq, &m, 1);
if (unlikely(error)) {
- RTE_LOG(ERR, PMD, "cannot requeue discarded mbuf");
+ PMD_DRV_LOG(ERR, "cannot requeue discarded mbuf");
rte_pktmbuf_free(m);
}
}
diff --git a/dpdk/drivers/net/virtio/virtio_user_ethdev.c b/dpdk/drivers/net/virtio/virtio_user_ethdev.c
index 63b647dc52..7c275c7397 100644
--- a/dpdk/drivers/net/virtio/virtio_user_ethdev.c
+++ b/dpdk/drivers/net/virtio/virtio_user_ethdev.c
@@ -388,12 +388,17 @@ static int
get_integer_arg(const char *key __rte_unused,
const char *value, void *extra_args)
{
+ uint64_t integer = 0;
if (!value || !extra_args)
return -EINVAL;
-
- *(uint64_t *)extra_args = strtoull(value, NULL, 0);
-
- return 0;
+ errno = 0;
+ integer = strtoull(value, NULL, 0);
+ /* extra_args keeps default value, it should be replaced
+ * only in case of successful parsing of the 'value' arg
+ */
+ if (errno == 0)
+ *(uint64_t *)extra_args = integer;
+ return -errno;
}
static struct rte_eth_dev *
@@ -471,7 +476,7 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
const char *name = rte_vdev_device_name(dev);
eth_dev = rte_eth_dev_attach_secondary(name);
if (!eth_dev) {
- RTE_LOG(ERR, PMD, "Failed to probe %s\n", name);
+ PMD_INIT_LOG(ERR, "Failed to probe %s", name);
return -1;
}
@@ -614,7 +619,7 @@ virtio_user_pmd_probe(struct rte_vdev_device *dev)
goto end;
}
- /* previously called by rte_pci_probe() for physical dev */
+ /* previously called by pci probing for physical dev */
if (eth_virtio_dev_init(eth_dev) < 0) {
PMD_INIT_LOG(ERR, "eth_virtio_dev_init fails");
virtio_user_eth_dev_free(eth_dev);
diff --git a/dpdk/drivers/net/vmxnet3/vmxnet3_rxtx.c b/dpdk/drivers/net/vmxnet3/vmxnet3_rxtx.c
index 6efa3ac217..f15fb6368e 100644
--- a/dpdk/drivers/net/vmxnet3/vmxnet3_rxtx.c
+++ b/dpdk/drivers/net/vmxnet3/vmxnet3_rxtx.c
@@ -947,13 +947,17 @@ vmxnet3_recv_pkts(void *rx_queue, struct rte_mbuf **rx_pkts, uint16_t nb_pkts)
RTE_ASSERT(rxd->btype == VMXNET3_RXD_BTYPE_BODY);
- if (rxm->data_len) {
+ if (likely(start && rxm->data_len > 0)) {
start->pkt_len += rxm->data_len;
start->nb_segs++;
rxq->last_seg->next = rxm;
rxq->last_seg = rxm;
} else {
+ PMD_RX_LOG(ERR, "Error received empty or out of order frame.");
+ rxq->stats.drop_total++;
+ rxq->stats.drop_err++;
+
rte_pktmbuf_free_seg(rxm);
}
}
diff --git a/dpdk/examples/eventdev_pipeline/main.c b/dpdk/examples/eventdev_pipeline/main.c
index 92e08bc0c8..85d8a624bc 100644
--- a/dpdk/examples/eventdev_pipeline/main.c
+++ b/dpdk/examples/eventdev_pipeline/main.c
@@ -10,6 +10,8 @@
#include "pipeline_common.h"
+struct fastpath_data *fdata;
+
struct config_data cdata = {
.num_packets = (1L << 25), /* do ~32M packets */
.num_fids = 512,
@@ -417,11 +419,6 @@ signal_handler(int signum)
rte_eal_mp_wait_lcore();
- RTE_ETH_FOREACH_DEV(portid) {
- rte_eth_dev_close(portid);
- }
-
- rte_event_dev_close(0);
}
if (signum == SIGTSTP)
rte_event_dev_dump(0, stdout);
@@ -439,6 +436,7 @@ int
main(int argc, char **argv)
{
struct worker_data *worker_data;
+ uint16_t portid;
uint16_t num_ports;
int lcore_id;
int err;
@@ -576,5 +574,13 @@ main(int argc, char **argv)
}
+ RTE_ETH_FOREACH_DEV(portid) {
+ rte_eth_dev_close(portid);
+ }
+
+ rte_event_dev_close(0);
+
+ rte_eal_cleanup();
+
return 0;
}
diff --git a/dpdk/examples/eventdev_pipeline/pipeline_common.h b/dpdk/examples/eventdev_pipeline/pipeline_common.h
index a6cc912fbb..016a3f702b 100644
--- a/dpdk/examples/eventdev_pipeline/pipeline_common.h
+++ b/dpdk/examples/eventdev_pipeline/pipeline_common.h
@@ -93,8 +93,8 @@ struct port_link {
uint8_t priority;
};
-struct fastpath_data *fdata;
-struct config_data cdata;
+extern struct fastpath_data *fdata;
+extern struct config_data cdata;
static __rte_always_inline void
exchange_mac(struct rte_mbuf *m)
diff --git a/dpdk/examples/ip_fragmentation/main.c b/dpdk/examples/ip_fragmentation/main.c
index 68d40c19ac..0631a1a2d4 100644
--- a/dpdk/examples/ip_fragmentation/main.c
+++ b/dpdk/examples/ip_fragmentation/main.c
@@ -591,7 +591,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up .Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/ip_pipeline/thread.c b/dpdk/examples/ip_pipeline/thread.c
index 272fbbeed1..adb83167cd 100644
--- a/dpdk/examples/ip_pipeline/thread.c
+++ b/dpdk/examples/ip_pipeline/thread.c
@@ -325,8 +325,6 @@ thread_pipeline_enable(uint32_t thread_id,
/* Send request and wait for response */
rsp = thread_msg_send_recv(thread_id, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -412,8 +410,6 @@ thread_pipeline_disable(uint32_t thread_id,
/* Send request and wait for response */
rsp = thread_msg_send_recv(thread_id, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -815,8 +811,6 @@ pipeline_port_in_stats_read(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -863,8 +857,6 @@ pipeline_port_in_enable(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -909,8 +901,6 @@ pipeline_port_in_disable(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -963,8 +953,6 @@ pipeline_port_out_stats_read(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1019,8 +1007,6 @@ pipeline_table_stats_read(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1436,10 +1422,6 @@ pipeline_table_rule_add(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL) {
- free(rule);
- return -1;
- }
/* Read response */
status = rsp->status;
@@ -1538,10 +1520,6 @@ pipeline_table_rule_add_default(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL) {
- free(rule);
- return -1;
- }
/* Read response */
status = rsp->status;
@@ -1655,10 +1633,6 @@ pipeline_table_rule_add_bulk(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL) {
- table_rule_list_free(list);
- return -ENOMEM;
- }
/* Read response */
status = rsp->status;
@@ -1733,8 +1707,6 @@ pipeline_table_rule_delete(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1790,8 +1762,6 @@ pipeline_table_rule_delete_default(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1857,8 +1827,6 @@ pipeline_table_rule_stats_read(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1915,8 +1883,6 @@ pipeline_table_mtr_profile_add(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -1967,8 +1933,6 @@ pipeline_table_mtr_profile_delete(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -2037,8 +2001,6 @@ pipeline_table_rule_mtr_read(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -2096,8 +2058,6 @@ pipeline_table_dscp_table_update(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -2164,8 +2124,6 @@ pipeline_table_rule_ttl_read(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
@@ -2229,8 +2187,6 @@ pipeline_table_rule_time_read(const char *pipeline_name,
/* Send request and wait for response */
rsp = pipeline_msg_send_recv(p, req);
- if (rsp == NULL)
- return -1;
/* Read response */
status = rsp->status;
diff --git a/dpdk/examples/ip_reassembly/main.c b/dpdk/examples/ip_reassembly/main.c
index 17b55d4c76..d29efc5354 100644
--- a/dpdk/examples/ip_reassembly/main.c
+++ b/dpdk/examples/ip_reassembly/main.c
@@ -724,7 +724,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/ipsec-secgw/ipsec-secgw.c b/dpdk/examples/ipsec-secgw/ipsec-secgw.c
index c55606e078..be77a839d3 100644
--- a/dpdk/examples/ipsec-secgw/ipsec-secgw.c
+++ b/dpdk/examples/ipsec-secgw/ipsec-secgw.c
@@ -1325,7 +1325,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up - speed %u Mbps -%s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/ipv4_multicast/main.c b/dpdk/examples/ipv4_multicast/main.c
index 428ca4694e..e7cb4ba566 100644
--- a/dpdk/examples/ipv4_multicast/main.c
+++ b/dpdk/examples/ipv4_multicast/main.c
@@ -598,7 +598,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/kni/main.c b/dpdk/examples/kni/main.c
index 5dff7d3b52..54bd69491b 100644
--- a/dpdk/examples/kni/main.c
+++ b/dpdk/examples/kni/main.c
@@ -660,7 +660,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up - speed %uMbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
@@ -738,15 +738,16 @@ monitor_all_ports_link_status(void *arg)
return NULL;
}
-/* Callback for request of changing MTU */
static int
-kni_change_mtu(uint16_t port_id, unsigned int new_mtu)
+kni_change_mtu_(uint16_t port_id, unsigned int new_mtu)
{
int ret;
uint16_t nb_rxd = NB_RXD;
+ uint16_t nb_txd = NB_TXD;
struct rte_eth_conf conf;
struct rte_eth_dev_info dev_info;
struct rte_eth_rxconf rxq_conf;
+ struct rte_eth_txconf txq_conf;
if (!rte_eth_dev_is_valid_port(port_id)) {
RTE_LOG(ERR, APP, "Invalid port id %d\n", port_id);
@@ -774,7 +775,7 @@ kni_change_mtu(uint16_t port_id, unsigned int new_mtu)
return ret;
}
- ret = rte_eth_dev_adjust_nb_rx_tx_desc(port_id, &nb_rxd, NULL);
+ ret = rte_eth_dev_adjust_nb_rx_tx_desc(port_id, &nb_rxd, &nb_txd);
if (ret < 0)
rte_exit(EXIT_FAILURE, "Could not adjust number of descriptors "
"for port%u (%d)\n", (unsigned int)port_id,
@@ -791,6 +792,16 @@ kni_change_mtu(uint16_t port_id, unsigned int new_mtu)
return ret;
}
+ txq_conf = dev_info.default_txconf;
+ txq_conf.offloads = conf.txmode.offloads;
+ ret = rte_eth_tx_queue_setup(port_id, 0, nb_txd,
+ rte_eth_dev_socket_id(port_id), &txq_conf);
+ if (ret < 0) {
+ RTE_LOG(ERR, APP, "Fail to setup Tx queue of port %d\n",
+ port_id);
+ return ret;
+ }
+
/* Restart specific port */
ret = rte_eth_dev_start(port_id);
if (ret < 0) {
@@ -801,6 +812,19 @@ kni_change_mtu(uint16_t port_id, unsigned int new_mtu)
return 0;
}
+/* Callback for request of changing MTU */
+static int
+kni_change_mtu(uint16_t port_id, unsigned int new_mtu)
+{
+ int ret;
+
+ rte_atomic32_inc(&kni_pause);
+ ret = kni_change_mtu_(port_id, new_mtu);
+ rte_atomic32_dec(&kni_pause);
+
+ return ret;
+}
+
/* Callback for request of configuring network interface up/down */
static int
kni_config_network_interface(uint16_t port_id, uint8_t if_up)
diff --git a/dpdk/examples/l2fwd-crypto/main.c b/dpdk/examples/l2fwd-crypto/main.c
index f12fd266e6..2d79327875 100644
--- a/dpdk/examples/l2fwd-crypto/main.c
+++ b/dpdk/examples/l2fwd-crypto/main.c
@@ -1745,7 +1745,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/l2fwd-jobstats/main.c b/dpdk/examples/l2fwd-jobstats/main.c
index a4d28e1782..8443f685d3 100644
--- a/dpdk/examples/l2fwd-jobstats/main.c
+++ b/dpdk/examples/l2fwd-jobstats/main.c
@@ -702,7 +702,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/l2fwd-keepalive/main.c b/dpdk/examples/l2fwd-keepalive/main.c
index 0bf2b53364..e74eb1f53e 100644
--- a/dpdk/examples/l2fwd-keepalive/main.c
+++ b/dpdk/examples/l2fwd-keepalive/main.c
@@ -44,7 +44,7 @@
#define RTE_LOGTYPE_L2FWD RTE_LOGTYPE_USER1
-#define NB_MBUF 8192
+#define NB_MBUF_PER_PORT 3000
#define MAX_PKT_BURST 32
#define BURST_TX_DRAIN_US 100 /* TX drain every ~100us */
@@ -467,7 +467,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
@@ -528,6 +528,7 @@ main(int argc, char **argv)
uint16_t portid, last_port;
unsigned lcore_id, rx_lcore_id;
unsigned nb_ports_in_mask = 0;
+ unsigned int total_nb_mbufs;
struct sigaction signal_handler;
struct rte_keepalive_shm *ka_shm;
@@ -553,16 +554,19 @@ main(int argc, char **argv)
if (ret < 0)
rte_exit(EXIT_FAILURE, "Invalid L2FWD arguments\n");
- /* create the mbuf pool */
- l2fwd_pktmbuf_pool = rte_pktmbuf_pool_create("mbuf_pool", NB_MBUF, 32,
- 0, RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id());
- if (l2fwd_pktmbuf_pool == NULL)
- rte_exit(EXIT_FAILURE, "Cannot init mbuf pool\n");
-
nb_ports = rte_eth_dev_count_avail();
if (nb_ports == 0)
rte_exit(EXIT_FAILURE, "No Ethernet ports - bye\n");
+ /* create the mbuf pool */
+ total_nb_mbufs = NB_MBUF_PER_PORT * nb_ports;
+
+ l2fwd_pktmbuf_pool = rte_pktmbuf_pool_create("mbuf_pool",
+ total_nb_mbufs, 32, 0, RTE_MBUF_DEFAULT_BUF_SIZE,
+ rte_socket_id());
+ if (l2fwd_pktmbuf_pool == NULL)
+ rte_exit(EXIT_FAILURE, "Cannot init mbuf pool\n");
+
/* reset l2fwd_dst_ports */
for (portid = 0; portid < RTE_MAX_ETHPORTS; portid++)
l2fwd_dst_ports[portid] = 0;
diff --git a/dpdk/examples/l2fwd/main.c b/dpdk/examples/l2fwd/main.c
index 6c23215a54..6ddf94b005 100644
--- a/dpdk/examples/l2fwd/main.c
+++ b/dpdk/examples/l2fwd/main.c
@@ -470,7 +470,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/l3fwd-acl/main.c b/dpdk/examples/l3fwd-acl/main.c
index 8ed0c07ec1..f2fe20e48f 100644
--- a/dpdk/examples/l3fwd-acl/main.c
+++ b/dpdk/examples/l3fwd-acl/main.c
@@ -1827,7 +1827,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/l3fwd-power/main.c b/dpdk/examples/l3fwd-power/main.c
index 77009ce809..c2a9d36cb6 100644
--- a/dpdk/examples/l3fwd-power/main.c
+++ b/dpdk/examples/l3fwd-power/main.c
@@ -1781,7 +1781,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Mbps - %s\n", (uint8_t)portid,
(unsigned)link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n",
(uint8_t)portid);
diff --git a/dpdk/examples/l3fwd/main.c b/dpdk/examples/l3fwd/main.c
index 71a67f422b..3ca84c80d9 100644
--- a/dpdk/examples/l3fwd/main.c
+++ b/dpdk/examples/l3fwd/main.c
@@ -720,7 +720,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps -%s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/link_status_interrupt/main.c b/dpdk/examples/link_status_interrupt/main.c
index f3346d23b4..17e77427a9 100644
--- a/dpdk/examples/link_status_interrupt/main.c
+++ b/dpdk/examples/link_status_interrupt/main.c
@@ -482,7 +482,7 @@ check_all_ports_link_status(uint16_t port_num, uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/multi_process/client_server_mp/mp_server/init.c b/dpdk/examples/multi_process/client_server_mp/mp_server/init.c
index 1b0569937b..bf209522f8 100644
--- a/dpdk/examples/multi_process/client_server_mp/mp_server/init.c
+++ b/dpdk/examples/multi_process/client_server_mp/mp_server/init.c
@@ -199,7 +199,7 @@ check_all_ports_link_status(uint16_t port_num, uint32_t port_mask)
"Mbps - %s\n", ports->id[portid],
(unsigned)link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n",
(uint8_t)ports->id[portid]);
diff --git a/dpdk/examples/multi_process/symmetric_mp/main.c b/dpdk/examples/multi_process/symmetric_mp/main.c
index 62771e036c..762c3cdfc7 100644
--- a/dpdk/examples/multi_process/symmetric_mp/main.c
+++ b/dpdk/examples/multi_process/symmetric_mp/main.c
@@ -373,7 +373,7 @@ check_all_ports_link_status(uint16_t port_num, uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/performance-thread/l3fwd-thread/main.c b/dpdk/examples/performance-thread/l3fwd-thread/main.c
index 79523d23d3..8ec819dcbe 100644
--- a/dpdk/examples/performance-thread/l3fwd-thread/main.c
+++ b/dpdk/examples/performance-thread/l3fwd-thread/main.c
@@ -3438,7 +3438,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n", portid);
continue;
diff --git a/dpdk/examples/qos_sched/init.c b/dpdk/examples/qos_sched/init.c
index 37c2b95fd6..8f53bafbcb 100644
--- a/dpdk/examples/qos_sched/init.c
+++ b/dpdk/examples/qos_sched/init.c
@@ -153,7 +153,7 @@ app_init_port(uint16_t portid, struct rte_mempool *mp)
printf(" Link Up - speed %u Mbps - %s\n",
(uint32_t) link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
} else {
printf(" Link Down\n");
}
diff --git a/dpdk/examples/server_node_efd/server/init.c b/dpdk/examples/server_node_efd/server/init.c
index af5a18e285..ff5b08351e 100644
--- a/dpdk/examples/server_node_efd/server/init.c
+++ b/dpdk/examples/server_node_efd/server/init.c
@@ -259,7 +259,7 @@ check_all_ports_link_status(uint16_t port_num, uint32_t port_mask)
info->id[portid],
link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n",
info->id[portid]);
diff --git a/dpdk/examples/vm_power_manager/channel_manager.c b/dpdk/examples/vm_power_manager/channel_manager.c
index 4fac099dfd..c53ad4bf1b 100644
--- a/dpdk/examples/vm_power_manager/channel_manager.c
+++ b/dpdk/examples/vm_power_manager/channel_manager.c
@@ -4,7 +4,6 @@
#include <stdio.h>
#include <stdlib.h>
-#include <sys/un.h>
#include <fcntl.h>
#include <unistd.h>
#include <inttypes.h>
@@ -37,6 +36,8 @@
for (i = 0; mask_u64b; mask_u64b &= ~(1ULL << i++)) \
if ((mask_u64b >> i) & 1) \
+struct libvirt_vm_info lvm_info[MAX_CLIENTS];
+
/* Global pointer to libvirt connection */
static virConnectPtr global_vir_conn_ptr;
diff --git a/dpdk/examples/vm_power_manager/channel_manager.h b/dpdk/examples/vm_power_manager/channel_manager.h
index d948b304c4..3c48d6ae66 100644
--- a/dpdk/examples/vm_power_manager/channel_manager.h
+++ b/dpdk/examples/vm_power_manager/channel_manager.h
@@ -10,7 +10,7 @@ extern "C" {
#endif
#include <linux/limits.h>
-#include <sys/un.h>
+#include <linux/un.h>
#include <rte_atomic.h>
/* Maximum number of CPUs */
@@ -32,10 +32,6 @@ extern "C" {
/* File socket directory */
#define CHANNEL_MGR_SOCKET_PATH "/tmp/powermonitor/"
-#ifndef UNIX_PATH_MAX
-struct sockaddr_un _sockaddr_un;
-#define UNIX_PATH_MAX sizeof(_sockaddr_un.sun_path)
-#endif
#define MAX_CLIENTS 64
#define MAX_VCPUS 20
@@ -47,7 +43,7 @@ struct libvirt_vm_info {
uint8_t num_cpus;
};
-struct libvirt_vm_info lvm_info[MAX_CLIENTS];
+extern struct libvirt_vm_info lvm_info[MAX_CLIENTS];
/* Communication Channel Status */
enum channel_status { CHANNEL_MGR_CHANNEL_DISCONNECTED = 0,
CHANNEL_MGR_CHANNEL_CONNECTED,
diff --git a/dpdk/examples/vm_power_manager/channel_monitor.c b/dpdk/examples/vm_power_manager/channel_monitor.c
index 1d6d7ec6d5..7881c51885 100644
--- a/dpdk/examples/vm_power_manager/channel_monitor.c
+++ b/dpdk/examples/vm_power_manager/channel_monitor.c
@@ -30,6 +30,7 @@
#ifdef RTE_LIBRTE_I40E_PMD
#include <rte_pmd_i40e.h>
#endif
+#include <rte_string_fns.h>
#include <libvirt/libvirt.h>
#include "channel_monitor.h"
diff --git a/dpdk/examples/vm_power_manager/main.c b/dpdk/examples/vm_power_manager/main.c
index 5fa13fe621..30f9ceb73e 100644
--- a/dpdk/examples/vm_power_manager/main.c
+++ b/dpdk/examples/vm_power_manager/main.c
@@ -250,7 +250,7 @@ check_all_ports_link_status(uint32_t port_mask)
"Mbps - %s\n", (uint16_t)portid,
(unsigned int)link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
else
printf("Port %d Link Down\n",
(uint16_t)portid);
diff --git a/dpdk/examples/vm_power_manager/power_manager.c b/dpdk/examples/vm_power_manager/power_manager.c
index a7e98cf40b..ecdf9a5583 100644
--- a/dpdk/examples/vm_power_manager/power_manager.c
+++ b/dpdk/examples/vm_power_manager/power_manager.c
@@ -6,7 +6,6 @@
#include <stdlib.h>
#include <stdint.h>
#include <inttypes.h>
-#include <sys/un.h>
#include <fcntl.h>
#include <unistd.h>
#include <dirent.h>
diff --git a/dpdk/examples/vmdq/main.c b/dpdk/examples/vmdq/main.c
index 627a5da485..2c0e8a596c 100644
--- a/dpdk/examples/vmdq/main.c
+++ b/dpdk/examples/vmdq/main.c
@@ -59,6 +59,7 @@ static uint32_t enabled_port_mask;
/* number of pools (if user does not specify any, 8 by default */
static uint32_t num_queues = 8;
static uint32_t num_pools = 8;
+static uint8_t rss_enable;
/* empty vmdq configuration structure. Filled in programatically */
static const struct rte_eth_conf vmdq_conf_default = {
@@ -143,6 +144,13 @@ get_eth_conf(struct rte_eth_conf *eth_conf, uint32_t num_pools)
(void)(rte_memcpy(eth_conf, &vmdq_conf_default, sizeof(*eth_conf)));
(void)(rte_memcpy(ð_conf->rx_adv_conf.vmdq_rx_conf, &conf,
sizeof(eth_conf->rx_adv_conf.vmdq_rx_conf)));
+ if (rss_enable) {
+ eth_conf->rxmode.mq_mode = ETH_MQ_RX_VMDQ_RSS;
+ eth_conf->rx_adv_conf.rss_conf.rss_hf = ETH_RSS_IP |
+ ETH_RSS_UDP |
+ ETH_RSS_TCP |
+ ETH_RSS_SCTP;
+ }
return 0;
}
@@ -164,6 +172,7 @@ port_init(uint16_t port, struct rte_mempool *mbuf_pool)
uint16_t q;
uint16_t queues_per_pool;
uint32_t max_nb_pools;
+ uint64_t rss_hf_tmp;
/*
* The max pool number from dev_info will be used to validate the pool
@@ -203,6 +212,17 @@ port_init(uint16_t port, struct rte_mempool *mbuf_pool)
if (!rte_eth_dev_is_valid_port(port))
return -1;
+ rss_hf_tmp = port_conf.rx_adv_conf.rss_conf.rss_hf;
+ port_conf.rx_adv_conf.rss_conf.rss_hf &=
+ dev_info.flow_type_rss_offloads;
+ if (port_conf.rx_adv_conf.rss_conf.rss_hf != rss_hf_tmp) {
+ printf("Port %u modified RSS hash function based on hardware support,"
+ "requested:%#"PRIx64" configured:%#"PRIx64"\n",
+ port,
+ rss_hf_tmp,
+ port_conf.rx_adv_conf.rss_conf.rss_hf);
+ }
+
/*
* Though in this example, we only receive packets from the first queue
* of each pool and send packets through first rte_lcore_count() tx
@@ -346,7 +366,8 @@ static void
vmdq_usage(const char *prgname)
{
printf("%s [EAL options] -- -p PORTMASK]\n"
- " --nb-pools NP: number of pools\n",
+ " --nb-pools NP: number of pools\n"
+ " --enable-rss: enable RSS (disabled by default)\n",
prgname);
}
@@ -360,6 +381,7 @@ vmdq_parse_args(int argc, char **argv)
const char *prgname = argv[0];
static struct option long_option[] = {
{"nb-pools", required_argument, NULL, 0},
+ {"enable-rss", 0, NULL, 0},
{NULL, 0, 0, 0}
};
@@ -377,11 +399,18 @@ vmdq_parse_args(int argc, char **argv)
}
break;
case 0:
- if (vmdq_parse_num_pools(optarg) == -1) {
- printf("invalid number of pools\n");
- vmdq_usage(prgname);
- return -1;
+ if (!strcmp(long_option[option_index].name,
+ "nb-pools")) {
+ if (vmdq_parse_num_pools(optarg) == -1) {
+ printf("invalid number of pools\n");
+ vmdq_usage(prgname);
+ return -1;
+ }
}
+
+ if (!strcmp(long_option[option_index].name,
+ "enable-rss"))
+ rss_enable = 1;
break;
default:
@@ -424,10 +453,11 @@ update_mac_address(struct rte_mbuf *m, unsigned dst_port)
static void
sighup_handler(int signum)
{
- unsigned q;
- for (q = 0; q < num_queues; q++) {
- if (q % (num_queues/num_pools) == 0)
- printf("\nPool %u: ", q/(num_queues/num_pools));
+ unsigned int q = vmdq_queue_base;
+ for (; q < num_queues; q++) {
+ if ((q - vmdq_queue_base) % (num_vmdq_queues / num_pools) == 0)
+ printf("\nPool %u: ", (q - vmdq_queue_base) /
+ (num_vmdq_queues / num_pools));
printf("%lu ", rxPackets[q]);
}
printf("\nFinished handling signal %d\n", signum);
diff --git a/dpdk/kernel/freebsd/contigmem/contigmem.c b/dpdk/kernel/freebsd/contigmem/contigmem.c
index 64e0a7fecd..abb76f241e 100644
--- a/dpdk/kernel/freebsd/contigmem/contigmem.c
+++ b/dpdk/kernel/freebsd/contigmem/contigmem.c
@@ -165,9 +165,11 @@ contigmem_load()
error:
for (i = 0; i < contigmem_num_buffers; i++) {
- if (contigmem_buffers[i].addr != NULL)
+ if (contigmem_buffers[i].addr != NULL) {
contigfree(contigmem_buffers[i].addr,
contigmem_buffer_size, M_CONTIGMEM);
+ contigmem_buffers[i].addr = NULL;
+ }
if (mtx_initialized(&contigmem_buffers[i].mtx))
mtx_destroy(&contigmem_buffers[i].mtx);
}
diff --git a/dpdk/kernel/linux/kni/ethtool/igb/e1000_phy.c b/dpdk/kernel/linux/kni/ethtool/igb/e1000_phy.c
index 5257b9141e..1510211e3f 100644
--- a/dpdk/kernel/linux/kni/ethtool/igb/e1000_phy.c
+++ b/dpdk/kernel/linux/kni/ethtool/igb/e1000_phy.c
@@ -1586,7 +1586,7 @@ static s32 e1000_copper_link_autoneg(struct e1000_hw *hw)
s32 e1000_setup_copper_link_generic(struct e1000_hw *hw)
{
s32 ret_val;
- bool link;
+ bool link = true;
DEBUGFUNC("e1000_setup_copper_link_generic");
@@ -1641,7 +1641,7 @@ s32 e1000_phy_force_speed_duplex_igp(struct e1000_hw *hw)
struct e1000_phy_info *phy = &hw->phy;
s32 ret_val;
u16 phy_data;
- bool link;
+ bool link = true;
DEBUGFUNC("e1000_phy_force_speed_duplex_igp");
@@ -1707,7 +1707,7 @@ s32 e1000_phy_force_speed_duplex_m88(struct e1000_hw *hw)
struct e1000_phy_info *phy = &hw->phy;
s32 ret_val;
u16 phy_data;
- bool link;
+ bool link = true;
DEBUGFUNC("e1000_phy_force_speed_duplex_m88");
@@ -1844,7 +1844,7 @@ s32 e1000_phy_force_speed_duplex_ife(struct e1000_hw *hw)
struct e1000_phy_info *phy = &hw->phy;
s32 ret_val;
u16 data;
- bool link;
+ bool link = true;
DEBUGFUNC("e1000_phy_force_speed_duplex_ife");
@@ -2256,12 +2256,16 @@ s32 e1000_phy_has_link_generic(struct e1000_hw *hw, u32 iterations,
* it across the board.
*/
ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
- if (ret_val)
+ if (ret_val) {
/* If the first read fails, another entity may have
* ownership of the resources, wait and try again to
* see if they have relinquished the resources yet.
*/
- usec_delay(usec_interval);
+ if (usec_interval >= 1000)
+ msec_delay_irq(usec_interval/1000);
+ else
+ usec_delay(usec_interval);
+ }
ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status);
if (ret_val)
break;
@@ -2516,7 +2520,7 @@ s32 e1000_get_phy_info_m88(struct e1000_hw *hw)
struct e1000_phy_info *phy = &hw->phy;
s32 ret_val;
u16 phy_data;
- bool link;
+ bool link = true;
DEBUGFUNC("e1000_get_phy_info_m88");
@@ -2591,7 +2595,7 @@ s32 e1000_get_phy_info_igp(struct e1000_hw *hw)
struct e1000_phy_info *phy = &hw->phy;
s32 ret_val;
u16 data;
- bool link;
+ bool link = true;
DEBUGFUNC("e1000_get_phy_info_igp");
@@ -2653,7 +2657,7 @@ s32 e1000_get_phy_info_ife(struct e1000_hw *hw)
struct e1000_phy_info *phy = &hw->phy;
s32 ret_val;
u16 data;
- bool link;
+ bool link = true;
DEBUGFUNC("e1000_get_phy_info_ife");
@@ -3042,7 +3046,7 @@ s32 e1000_phy_force_speed_duplex_82577(struct e1000_hw *hw)
struct e1000_phy_info *phy = &hw->phy;
s32 ret_val;
u16 phy_data;
- bool link;
+ bool link = true;
DEBUGFUNC("e1000_phy_force_speed_duplex_82577");
@@ -3091,7 +3095,7 @@ s32 e1000_get_phy_info_82577(struct e1000_hw *hw)
struct e1000_phy_info *phy = &hw->phy;
s32 ret_val;
u16 data;
- bool link;
+ bool link = true;
DEBUGFUNC("e1000_get_phy_info_82577");
diff --git a/dpdk/kernel/linux/kni/ethtool/igb/igb_main.c b/dpdk/kernel/linux/kni/ethtool/igb/igb_main.c
index cb1b536775..5a07d007a2 100644
--- a/dpdk/kernel/linux/kni/ethtool/igb/igb_main.c
+++ b/dpdk/kernel/linux/kni/ethtool/igb/igb_main.c
@@ -36,6 +36,7 @@
#endif /* CONFIG_PM_RUNTIME */
#include <linux/if_bridge.h>
+#include "compat.h"
#include "igb.h"
#include "igb_vmdq.h"
@@ -154,7 +155,11 @@ static int igb_poll(struct napi_struct *, int);
static bool igb_clean_tx_irq(struct igb_q_vector *);
static bool igb_clean_rx_irq(struct igb_q_vector *, int);
static int igb_ioctl(struct net_device *, struct ifreq *, int cmd);
+#ifdef HAVE_TX_TIMEOUT_TXQUEUE
+static void igb_tx_timeout(struct net_device *, unsigned int);
+#else
static void igb_tx_timeout(struct net_device *);
+#endif /* HAVE_TX_TIMEOUT_TXQUEUE */
static void igb_reset_task(struct work_struct *);
#ifdef HAVE_VLAN_RX_REGISTER
static void igb_vlan_mode(struct net_device *, struct vlan_group *);
@@ -5623,7 +5628,11 @@ static netdev_tx_t igb_xmit_frame(struct sk_buff *skb,
* igb_tx_timeout - Respond to a Tx Hang
* @netdev: network interface device structure
**/
+#ifdef HAVE_TX_TIMEOUT_TXQUEUE
+static void igb_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+#else
static void igb_tx_timeout(struct net_device *netdev)
+#endif
{
struct igb_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
diff --git a/dpdk/kernel/linux/kni/ethtool/igb/kcompat.h b/dpdk/kernel/linux/kni/ethtool/igb/kcompat.h
index 964317508d..611a5b7c49 100644
--- a/dpdk/kernel/linux/kni/ethtool/igb/kcompat.h
+++ b/dpdk/kernel/linux/kni/ethtool/igb/kcompat.h
@@ -3947,14 +3947,18 @@ skb_set_hash(struct sk_buff *skb, __u32 hash, __always_unused int type)
#define HAVE_PCI_ENABLE_MSIX
#endif
-#if ( LINUX_VERSION_CODE >= KERNEL_VERSION(5,0,0) )
+#if ((LINUX_VERSION_CODE >= KERNEL_VERSION(5, 0, 0)) \
+ || (defined(RHEL_RELEASE_CODE) \
+ && (RHEL_RELEASE_CODE >= RHEL_RELEASE_VERSION(8, 1))))
#define dev_open(x) dev_open(x, NULL)
#define HAVE_NDO_BRIDGE_SETLINK_EXTACK
-#endif /* >= 5.0.0 */
+#endif /* >= 5.0.0 or >= RHEL/CentOS 8.1 */
-#if ( LINUX_VERSION_CODE >= KERNEL_VERSION(5,1,0) )
+#if ((LINUX_VERSION_CODE >= KERNEL_VERSION(5, 1, 0)) \
+ || (defined(RHEL_RELEASE_CODE) \
+ && (RHEL_RELEASE_CODE >= RHEL_RELEASE_VERSION(8, 1))))
#define HAVE_NDO_FDB_ADD_EXTACK
-#endif /* >= 5.1.0 */
+#endif /* >= 5.1.0 or >= RHEL/CentOS 8.1 */
#if defined(timer_setup) && defined(from_timer)
#define HAVE_TIMER_SETUP
diff --git a/dpdk/kernel/linux/kni/ethtool/ixgbe/kcompat.h b/dpdk/kernel/linux/kni/ethtool/ixgbe/kcompat.h
index e1671e91a9..73e2c3fb96 100644
--- a/dpdk/kernel/linux/kni/ethtool/ixgbe/kcompat.h
+++ b/dpdk/kernel/linux/kni/ethtool/ixgbe/kcompat.h
@@ -3131,9 +3131,11 @@ static inline int __kc_pci_vfs_assigned(struct pci_dev *dev)
#define SET_ETHTOOL_OPS(netdev, ops) ((netdev)->ethtool_ops = (ops))
#endif /* >= 3.16.0 */
-#if ( LINUX_VERSION_CODE >= KERNEL_VERSION(5,0,0) )
+#if ((LINUX_VERSION_CODE >= KERNEL_VERSION(5, 0, 0)) \
+ || (defined(RHEL_RELEASE_CODE) \
+ && (RHEL_RELEASE_CODE >= RHEL_RELEASE_VERSION(8, 1))))
#define dev_open(x) dev_open(x, NULL)
-#endif /* >= 5.0.0 */
+#endif /* >= 5.0.0 or >= RHEL/CentOS 8.1 */
/*
* vlan_tx_tag_* macros renamed to skb_vlan_tag_* (Linux commit: df8a39defad4)
diff --git a/dpdk/lib/librte_bbdev/rte_bbdev.h b/dpdk/lib/librte_bbdev/rte_bbdev.h
index 4a2873b2fe..f53ee101da 100644
--- a/dpdk/lib/librte_bbdev/rte_bbdev.h
+++ b/dpdk/lib/librte_bbdev/rte_bbdev.h
@@ -420,13 +420,13 @@ TAILQ_HEAD(rte_bbdev_cb_list, rte_bbdev_callback);
* these fields, but should only write to the *_ops fields.
*/
struct __rte_cache_aligned rte_bbdev {
- /**< Enqueue encode function */
+ /** Enqueue encode function */
rte_bbdev_enqueue_enc_ops_t enqueue_enc_ops;
- /**< Enqueue decode function */
+ /** Enqueue decode function */
rte_bbdev_enqueue_dec_ops_t enqueue_dec_ops;
- /**< Dequeue encode function */
+ /** Dequeue encode function */
rte_bbdev_dequeue_enc_ops_t dequeue_enc_ops;
- /**< Dequeue decode function */
+ /** Dequeue decode function */
rte_bbdev_dequeue_dec_ops_t dequeue_dec_ops;
const struct rte_bbdev_ops *dev_ops; /**< Functions exported by PMD */
struct rte_bbdev_data *data; /**< Pointer to device data */
diff --git a/dpdk/lib/librte_bbdev/rte_bbdev_op.h b/dpdk/lib/librte_bbdev/rte_bbdev_op.h
index 83f62c2dc2..14cb87cd96 100644
--- a/dpdk/lib/librte_bbdev/rte_bbdev_op.h
+++ b/dpdk/lib/librte_bbdev/rte_bbdev_op.h
@@ -277,11 +277,12 @@ struct rte_bbdev_op_turbo_dec {
*/
uint8_t num_maps;
- uint8_t code_block_mode; /**< [0 - TB : 1 - CB] */
+ /** [0 - TB : 1 - CB] */
+ uint8_t code_block_mode;
union {
- /**< Struct which stores Code Block specific parameters */
+ /** Struct which stores Code Block specific parameters */
struct rte_bbdev_op_dec_cb_params cb_params;
- /**< Struct which stores Transport Block specific parameters */
+ /** Struct which stores Transport Block specific parameters */
struct rte_bbdev_op_dec_tb_params tb_params;
};
};
@@ -338,7 +339,7 @@ struct rte_bbdev_op_enc_tb_params {
* the Turbo operation when r >= C-, [K:3*Kpi]
*/
uint16_t ncb_pos;
- /**< The index of the first CB in the inbound mbuf data, default is 0 */
+ /** The index of the first CB in the inbound mbuf data, default is 0 */
uint8_t r;
};
@@ -419,10 +420,13 @@ enum {
/**< Structure specifying a single encode operation */
struct rte_bbdev_enc_op {
- int status; /**< Status of operation that was performed */
- struct rte_mempool *mempool; /**< Mempool which op instance is in */
- void *opaque_data; /**< Opaque pointer for user data */
- /**< Contains encoder specific parameters */
+ /** Status of operation that was performed */
+ int status;
+ /** Mempool which op instance is in */
+ struct rte_mempool *mempool;
+ /** Opaque pointer for user data */
+ void *opaque_data;
+ /** Contains encoder specific parameters */
struct rte_bbdev_op_turbo_enc turbo_enc;
};
@@ -444,7 +448,7 @@ struct rte_bbdev_op_cap {
} cap; /**< Operation-type specific capabilities */
};
-/**< @internal Private data structure stored with operation pool. */
+/** @internal Private data structure stored with operation pool. */
struct rte_bbdev_op_pool_private {
enum rte_bbdev_op_type type; /**< Type of operations in a pool */
};
diff --git a/dpdk/lib/librte_bbdev/rte_bbdev_pmd.h b/dpdk/lib/librte_bbdev/rte_bbdev_pmd.h
index db9a04cdf9..f6091a5e99 100644
--- a/dpdk/lib/librte_bbdev/rte_bbdev_pmd.h
+++ b/dpdk/lib/librte_bbdev/rte_bbdev_pmd.h
@@ -143,18 +143,18 @@ typedef int (*rte_bbdev_queue_intr_disable_t)(struct rte_bbdev *dev,
* fields are for non-vital operations
*/
struct rte_bbdev_ops {
- /**< Allocate and configure device memory. Optional. */
+ /** Allocate and configure device memory. Optional. */
rte_bbdev_setup_queues_t setup_queues;
- /**< Configure interrupts. Optional. */
+ /** Configure interrupts. Optional. */
rte_bbdev_intr_enable_t intr_enable;
- /**< Start device. Optional. */
+ /** Start device. Optional. */
rte_bbdev_start_t start;
- /**< Stop device. Optional. */
+ /** Stop device. Optional. */
rte_bbdev_stop_t stop;
- /**< Close device. Optional. */
+ /** Close device. Optional. */
rte_bbdev_close_t close;
- /**< Get device info. Required. */
+ /** Get device info. Required. */
rte_bbdev_info_get_t info_get;
/** Get device statistics. Optional. */
rte_bbdev_stats_get_t stats_get;
@@ -167,7 +167,7 @@ struct rte_bbdev_ops {
rte_bbdev_queue_release_t queue_release;
/** Start a queue. Optional. */
rte_bbdev_queue_start_t queue_start;
- /**< Stop a queue pair. Optional. */
+ /** Stop a queue pair. Optional. */
rte_bbdev_queue_stop_t queue_stop;
/** Enable queue interrupt. Optional */
diff --git a/dpdk/lib/librte_cryptodev/rte_crypto_sym.h b/dpdk/lib/librte_cryptodev/rte_crypto_sym.h
index eb5afc5ef0..70038db776 100644
--- a/dpdk/lib/librte_cryptodev/rte_crypto_sym.h
+++ b/dpdk/lib/librte_cryptodev/rte_crypto_sym.h
@@ -219,9 +219,12 @@ enum rte_crypto_auth_algorithm {
/**< HMAC using MD5 algorithm */
RTE_CRYPTO_AUTH_SHA1,
- /**< 128 bit SHA algorithm. */
+ /**< 160 bit SHA algorithm. */
RTE_CRYPTO_AUTH_SHA1_HMAC,
- /**< HMAC using 128 bit SHA algorithm. */
+ /**< HMAC using 160 bit SHA algorithm.
+ * HMAC-SHA-1-96 can be generated by setting
+ * digest_length to 12 bytes in auth/aead xforms.
+ */
RTE_CRYPTO_AUTH_SHA224,
/**< 224 bit SHA algorithm. */
RTE_CRYPTO_AUTH_SHA224_HMAC,
diff --git a/dpdk/lib/librte_eal/bsdapp/eal/eal.c b/dpdk/lib/librte_eal/bsdapp/eal/eal.c
index 30b4cf7bf0..0e3452210b 100644
--- a/dpdk/lib/librte_eal/bsdapp/eal/eal.c
+++ b/dpdk/lib/librte_eal/bsdapp/eal/eal.c
@@ -691,13 +691,19 @@ rte_eal_init(int argc, char **argv)
/* if no EAL option "--iova-mode=<pa|va>", use bus IOVA scheme */
if (internal_config.iova_mode == RTE_IOVA_DC) {
/* autodetect the IOVA mapping mode (default is RTE_IOVA_PA) */
- rte_eal_get_configuration()->iova_mode =
- rte_bus_get_iommu_class();
+ enum rte_iova_mode iova_mode = rte_bus_get_iommu_class();
+
+ if (iova_mode == RTE_IOVA_DC)
+ iova_mode = RTE_IOVA_PA;
+ rte_eal_get_configuration()->iova_mode = iova_mode;
} else {
rte_eal_get_configuration()->iova_mode =
internal_config.iova_mode;
}
+ RTE_LOG(INFO, EAL, "Selected IOVA mode '%s'\n",
+ rte_eal_iova_mode() == RTE_IOVA_PA ? "PA" : "VA");
+
if (internal_config.no_hugetlbfs == 0) {
/* rte_config isn't initialized yet */
ret = internal_config.process_type == RTE_PROC_PRIMARY ?
diff --git a/dpdk/lib/librte_eal/bsdapp/eal/eal_memory.c b/dpdk/lib/librte_eal/bsdapp/eal/eal_memory.c
index 4b092e1f21..418c4bb0aa 100644
--- a/dpdk/lib/librte_eal/bsdapp/eal/eal_memory.c
+++ b/dpdk/lib/librte_eal/bsdapp/eal/eal_memory.c
@@ -435,7 +435,7 @@ memseg_primary_init(void)
*
* we need (N*2)-1 segments because we cannot guarantee that
* each segment will be IOVA-contiguous with the previous one,
- * so we will allocate more and put spaces inbetween segments
+ * so we will allocate more and put spaces between segments
* that are non-contiguous.
*/
avail_segs = (hpi->num_pages[0] * 2) - 1;
diff --git a/dpdk/lib/librte_eal/common/eal_common_bus.c b/dpdk/lib/librte_eal/common/eal_common_bus.c
index c8f1901f0b..04590485b1 100644
--- a/dpdk/lib/librte_eal/common/eal_common_bus.c
+++ b/dpdk/lib/librte_eal/common/eal_common_bus.c
@@ -228,19 +228,39 @@ rte_bus_find_by_device_name(const char *str)
enum rte_iova_mode
rte_bus_get_iommu_class(void)
{
- int mode = RTE_IOVA_DC;
+ enum rte_iova_mode mode = RTE_IOVA_DC;
+ bool buses_want_va = false;
+ bool buses_want_pa = false;
struct rte_bus *bus;
TAILQ_FOREACH(bus, &rte_bus_list, next) {
+ enum rte_iova_mode bus_iova_mode;
- if (bus->get_iommu_class)
- mode |= bus->get_iommu_class();
- }
+ if (bus->get_iommu_class == NULL)
+ continue;
- if (mode != RTE_IOVA_VA) {
- /* Use default IOVA mode */
+ bus_iova_mode = bus->get_iommu_class();
+ RTE_LOG(DEBUG, EAL, "Bus %s wants IOVA as '%s'\n",
+ bus->name,
+ bus_iova_mode == RTE_IOVA_DC ? "DC" :
+ (bus_iova_mode == RTE_IOVA_PA ? "PA" : "VA"));
+ if (bus_iova_mode == RTE_IOVA_PA)
+ buses_want_pa = true;
+ else if (bus_iova_mode == RTE_IOVA_VA)
+ buses_want_va = true;
+ }
+ if (buses_want_va && !buses_want_pa) {
+ mode = RTE_IOVA_VA;
+ } else if (buses_want_pa && !buses_want_va) {
mode = RTE_IOVA_PA;
+ } else {
+ mode = RTE_IOVA_DC;
+ if (buses_want_va) {
+ RTE_LOG(WARNING, EAL, "Some buses want 'VA' but forcing 'DC' because other buses want 'PA'.\n");
+ RTE_LOG(WARNING, EAL, "Depending on the final decision by the EAL, not all buses may be able to initialize.\n");
+ }
}
+
return mode;
}
diff --git a/dpdk/lib/librte_eal/common/eal_common_log.c b/dpdk/lib/librte_eal/common/eal_common_log.c
index 2c1200310d..9453fa3e9a 100644
--- a/dpdk/lib/librte_eal/common/eal_common_log.c
+++ b/dpdk/lib/librte_eal/common/eal_common_log.c
@@ -284,7 +284,7 @@ rte_log_register_type_and_pick_level(const char *name, uint32_t level_def)
continue;
if (opt_ll->pattern) {
- if (fnmatch(opt_ll->pattern, name, 0))
+ if (fnmatch(opt_ll->pattern, name, 0) == 0)
level = opt_ll->level;
} else {
if (regexec(&opt_ll->re_match, name, 0, NULL, 0) == 0)
diff --git a/dpdk/lib/librte_eal/common/eal_common_memory.c b/dpdk/lib/librte_eal/common/eal_common_memory.c
index 9a14698aae..030f1b261c 100644
--- a/dpdk/lib/librte_eal/common/eal_common_memory.c
+++ b/dpdk/lib/librte_eal/common/eal_common_memory.c
@@ -112,7 +112,7 @@ eal_get_virtual_area(void *requested_addr, size_t *size,
return NULL;
}
- mapped_addr = mmap(requested_addr, (size_t)map_sz, PROT_READ,
+ mapped_addr = mmap(requested_addr, (size_t)map_sz, PROT_NONE,
mmap_flags, -1, 0);
if (mapped_addr == MAP_FAILED && allow_shrink)
*size -= page_sz;
diff --git a/dpdk/lib/librte_eal/common/eal_common_options.c b/dpdk/lib/librte_eal/common/eal_common_options.c
index f742d4d384..f38888edf3 100644
--- a/dpdk/lib/librte_eal/common/eal_common_options.c
+++ b/dpdk/lib/librte_eal/common/eal_common_options.c
@@ -1036,7 +1036,7 @@ eal_parse_log_level(const char *arg)
if (regex) {
if (rte_log_set_level_regexp(regex, priority) < 0) {
fprintf(stderr, "cannot set log level %s,%d\n",
- pattern, priority);
+ regex, priority);
goto fail;
}
if (rte_log_save_regexp(regex, priority) < 0)
diff --git a/dpdk/lib/librte_eal/common/include/arch/arm/rte_cycles_32.h b/dpdk/lib/librte_eal/common/include/arch/arm/rte_cycles_32.h
index 859b09748c..f79718ce8c 100644
--- a/dpdk/lib/librte_eal/common/include/arch/arm/rte_cycles_32.h
+++ b/dpdk/lib/librte_eal/common/include/arch/arm/rte_cycles_32.h
@@ -57,7 +57,7 @@ __rte_rdtsc_syscall(void)
* asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(29));
* asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r"(0x8000000f));
*
- * which is possible only from the priviledged mode (kernel space).
+ * which is possible only from the privileged mode (kernel space).
*/
static inline uint64_t
__rte_rdtsc_pmccntr(void)
diff --git a/dpdk/lib/librte_eal/common/include/arch/arm/rte_cycles_64.h b/dpdk/lib/librte_eal/common/include/arch/arm/rte_cycles_64.h
index 68e7c73384..da557b6a10 100644
--- a/dpdk/lib/librte_eal/common/include/arch/arm/rte_cycles_64.h
+++ b/dpdk/lib/librte_eal/common/include/arch/arm/rte_cycles_64.h
@@ -62,7 +62,7 @@ rte_rdtsc(void)
static inline uint64_t
rte_rdtsc_precise(void)
{
- rte_mb();
+ asm volatile("isb" : : : "memory");
return rte_rdtsc();
}
diff --git a/dpdk/lib/librte_eal/common/include/arch/ppc_64/rte_memcpy.h b/dpdk/lib/librte_eal/common/include/arch/ppc_64/rte_memcpy.h
index 75f74897b3..b194564b55 100644
--- a/dpdk/lib/librte_eal/common/include/arch/ppc_64/rte_memcpy.h
+++ b/dpdk/lib/librte_eal/common/include/arch/ppc_64/rte_memcpy.h
@@ -37,6 +37,7 @@
#include <string.h>
/*To include altivec.h, GCC version must >= 4.8 */
#include <altivec.h>
+#include "rte_common.h"
#ifdef __cplusplus
extern "C" {
@@ -44,6 +45,11 @@ extern "C" {
#include "generic/rte_memcpy.h"
+#if (GCC_VERSION >= 90000 && GCC_VERSION < 90400)
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Warray-bounds"
+#endif
+
static inline void
rte_mov16(uint8_t *dst, const uint8_t *src)
{
@@ -219,6 +225,10 @@ rte_memcpy_func(void *dst, const void *src, size_t n)
return ret;
}
+#if (GCC_VERSION >= 90000 && GCC_VERSION < 90400)
+#pragma GCC diagnostic pop
+#endif
+
#ifdef __cplusplus
}
#endif
diff --git a/dpdk/lib/librte_eal/common/include/arch/x86/rte_atomic.h b/dpdk/lib/librte_eal/common/include/arch/x86/rte_atomic.h
index 148398f50a..b9dcd30aba 100644
--- a/dpdk/lib/librte_eal/common/include/arch/x86/rte_atomic.h
+++ b/dpdk/lib/librte_eal/common/include/arch/x86/rte_atomic.h
@@ -55,7 +55,7 @@ extern "C" {
*
* As pointed by Java guys, that makes possible to use lock-prefixed
* instructions to get the same effect as mfence and on most modern HW
- * that gives a better perfomance then using mfence:
+ * that gives a better performance then using mfence:
* https://shipilev.net/blog/2014/on-the-fence-with-dependencies/
* Basic idea is to use lock prefixed add with some dummy memory location
* as the destination. From their experiments 128B(2 cache lines) below
diff --git a/dpdk/lib/librte_eal/common/include/arch/x86/rte_memcpy.h b/dpdk/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
index ba44c4a328..9c67232df9 100644
--- a/dpdk/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
+++ b/dpdk/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
@@ -22,6 +22,11 @@
extern "C" {
#endif
+#if defined(RTE_TOOLCHAIN_GCC) && (GCC_VERSION >= 100000)
+#pragma GCC diagnostic push
+#pragma GCC diagnostic ignored "-Wstringop-overflow"
+#endif
+
/**
* Copy bytes from one location to another. The locations must not overlap.
*
@@ -869,6 +874,10 @@ rte_memcpy(void *dst, const void *src, size_t n)
return rte_memcpy_generic(dst, src, n);
}
+#if defined(RTE_TOOLCHAIN_GCC) && (GCC_VERSION >= 100000)
+#pragma GCC diagnostic pop
+#endif
+
#ifdef __cplusplus
}
#endif
diff --git a/dpdk/lib/librte_eal/common/include/generic/rte_byteorder.h b/dpdk/lib/librte_eal/common/include/generic/rte_byteorder.h
index 7d9a1463c4..ac167936de 100644
--- a/dpdk/lib/librte_eal/common/include/generic/rte_byteorder.h
+++ b/dpdk/lib/librte_eal/common/include/generic/rte_byteorder.h
@@ -93,9 +93,9 @@
#define RTE_BE16(v) (rte_be16_t)(RTE_STATIC_BSWAP16(v))
#define RTE_BE32(v) (rte_be32_t)(RTE_STATIC_BSWAP32(v))
#define RTE_BE64(v) (rte_be64_t)(RTE_STATIC_BSWAP64(v))
-#define RTE_LE16(v) (rte_be16_t)(v)
-#define RTE_LE32(v) (rte_be32_t)(v)
-#define RTE_LE64(v) (rte_be64_t)(v)
+#define RTE_LE16(v) (rte_le16_t)(v)
+#define RTE_LE32(v) (rte_le32_t)(v)
+#define RTE_LE64(v) (rte_le64_t)(v)
#else
#error Unsupported endianness.
#endif
diff --git a/dpdk/lib/librte_eal/common/include/rte_bus.h b/dpdk/lib/librte_eal/common/include/rte_bus.h
index 6be4b5cabe..b87e23b19e 100644
--- a/dpdk/lib/librte_eal/common/include/rte_bus.h
+++ b/dpdk/lib/librte_eal/common/include/rte_bus.h
@@ -348,7 +348,7 @@ struct rte_bus *rte_bus_find_by_name(const char *busname);
/**
* Get the common iommu class of devices bound on to buses available in the
- * system. The default mode is PA.
+ * system. RTE_IOVA_DC means that no preferrence has been expressed.
*
* @return
* enum rte_iova_mode value.
diff --git a/dpdk/lib/librte_eal/common/include/rte_common.h b/dpdk/lib/librte_eal/common/include/rte_common.h
index 48bf28ca5d..5006ba8cad 100644
--- a/dpdk/lib/librte_eal/common/include/rte_common.h
+++ b/dpdk/lib/librte_eal/common/include/rte_common.h
@@ -283,7 +283,7 @@ rte_is_aligned(void *ptr, unsigned align)
* The combined value.
*/
static inline uint32_t
-rte_combine32ms1b(register uint32_t x)
+rte_combine32ms1b(uint32_t x)
{
x |= x >> 1;
x |= x >> 2;
@@ -305,7 +305,7 @@ rte_combine32ms1b(register uint32_t x)
* The combined value.
*/
static inline uint64_t
-rte_combine64ms1b(register uint64_t v)
+rte_combine64ms1b(uint64_t v)
{
v |= v >> 1;
v |= v >> 2;
diff --git a/dpdk/lib/librte_eal/common/include/rte_service.h b/dpdk/lib/librte_eal/common/include/rte_service.h
index 11f673503b..21002209bc 100644
--- a/dpdk/lib/librte_eal/common/include/rte_service.h
+++ b/dpdk/lib/librte_eal/common/include/rte_service.h
@@ -104,12 +104,16 @@ int32_t rte_service_probe_capability(uint32_t id, uint32_t capability);
* Each core can be added or removed from running a specific service. This
* function enables or disables *lcore* to run *service_id*.
*
- * If multiple cores are enabled on a service, an atomic is used to ensure that
- * only one cores runs the service at a time. The exception to this is when
+ * If multiple cores are enabled on a service, a lock is used to ensure that
+ * only one core runs the service at a time. The exception to this is when
* a service indicates that it is multi-thread safe by setting the capability
* called RTE_SERVICE_CAP_MT_SAFE. With the multi-thread safe capability set,
* the service function can be run on multiple threads at the same time.
*
+ * If the service is known to be mapped to a single lcore, setting the
+ * capability of the service to RTE_SERVICE_CAP_MT_SAFE can achieve
+ * better performance by avoiding the use of lock.
+ *
* @param service_id the service to apply the lcore to
* @param lcore The lcore that will be mapped to service
* @param enable Zero to unmap or disable the core, non-zero to enable
diff --git a/dpdk/lib/librte_eal/common/include/rte_service_component.h b/dpdk/lib/librte_eal/common/include/rte_service_component.h
index c12adbc256..259e3182d8 100644
--- a/dpdk/lib/librte_eal/common/include/rte_service_component.h
+++ b/dpdk/lib/librte_eal/common/include/rte_service_component.h
@@ -43,7 +43,7 @@ struct rte_service_spec {
/**
* Register a new service.
*
- * A service represents a component that the requires CPU time periodically to
+ * A service represents a component that requires CPU time periodically to
* achieve its purpose.
*
* For example the eventdev SW PMD requires CPU cycles to perform its
@@ -56,6 +56,10 @@ struct rte_service_spec {
* *rte_service_component_runstate_set*, which indicates that the service
* component is ready to be executed.
*
+ * If the service is known to be mapped to a single lcore, setting the
+ * capability of the service to RTE_SERVICE_CAP_MT_SAFE can achieve
+ * better performance.
+ *
* @param spec The specification of the service to register
* @param[out] service_id A pointer to a uint32_t, which will be filled in
* during registration of the service. It is set to the integers
diff --git a/dpdk/lib/librte_eal/common/include/rte_version.h b/dpdk/lib/librte_eal/common/include/rte_version.h
index a1cce4802e..514cfe67b6 100644
--- a/dpdk/lib/librte_eal/common/include/rte_version.h
+++ b/dpdk/lib/librte_eal/common/include/rte_version.h
@@ -37,7 +37,7 @@ extern "C" {
/**
* Patch level number i.e. the z in yy.mm.z
*/
-#define RTE_VER_MINOR 7
+#define RTE_VER_MINOR 9
/**
* Extra string to be appended to version number
diff --git a/dpdk/lib/librte_eal/common/malloc_elem.c b/dpdk/lib/librte_eal/common/malloc_elem.c
index 24e1eb55f3..69ff063883 100644
--- a/dpdk/lib/librte_eal/common/malloc_elem.c
+++ b/dpdk/lib/librte_eal/common/malloc_elem.c
@@ -157,7 +157,7 @@ malloc_elem_insert(struct malloc_elem *elem)
next_elem = NULL;
heap->last = elem;
} else {
- /* the new memory is somewhere inbetween start and end */
+ /* the new memory is somewhere between start and end */
uint64_t dist_from_start, dist_from_end;
dist_from_end = RTE_PTR_DIFF(heap->last, elem);
diff --git a/dpdk/lib/librte_eal/common/malloc_heap.c b/dpdk/lib/librte_eal/common/malloc_heap.c
index b8f26f2b37..de3b73e8c5 100644
--- a/dpdk/lib/librte_eal/common/malloc_heap.c
+++ b/dpdk/lib/librte_eal/common/malloc_heap.c
@@ -238,6 +238,9 @@ heap_alloc(struct malloc_heap *heap, const char *type __rte_unused, size_t size,
size = RTE_CACHE_LINE_ROUNDUP(size);
align = RTE_CACHE_LINE_ROUNDUP(align);
+ /* roundup might cause an overflow */
+ if (size == 0)
+ return NULL;
elem = find_suitable_element(heap, size, flags, align, bound, contig);
if (elem != NULL) {
elem = malloc_elem_alloc(elem, size, align, bound, contig);
diff --git a/dpdk/lib/librte_eal/common/rte_service.c b/dpdk/lib/librte_eal/common/rte_service.c
index 53dd6a7bbf..607f9a0407 100644
--- a/dpdk/lib/librte_eal/common/rte_service.c
+++ b/dpdk/lib/librte_eal/common/rte_service.c
@@ -49,6 +49,10 @@ struct rte_service_spec_impl {
uint8_t internal_flags;
/* per service statistics */
+ /* Indicates how many cores the service is mapped to run on.
+ * It does not indicate the number of cores the service is running
+ * on currently.
+ */
rte_atomic32_t num_mapped_cores;
uint64_t calls;
uint64_t cycles_spent;
@@ -121,6 +125,9 @@ rte_service_finalize(void)
if (!rte_service_library_initialized)
return;
+ rte_service_lcore_reset_all();
+ rte_eal_mp_wait_lcore();
+
rte_free(rte_services);
rte_free(lcore_states);
@@ -332,8 +339,8 @@ rte_service_runstate_get(uint32_t id)
}
static inline void
-rte_service_runner_do_callback(struct rte_service_spec_impl *s,
- struct core_state *cs, uint32_t service_idx)
+service_runner_do_callback(struct rte_service_spec_impl *s,
+ struct core_state *cs, uint32_t service_idx)
{
void *userdata = s->spec.callback_userdata;
@@ -352,7 +359,7 @@ rte_service_runner_do_callback(struct rte_service_spec_impl *s,
/* Expects the service 's' is valid. */
static int32_t
service_run(uint32_t i, struct core_state *cs, uint64_t service_mask,
- struct rte_service_spec_impl *s)
+ struct rte_service_spec_impl *s, uint32_t serialize_mt_unsafe)
{
if (!s)
return -EINVAL;
@@ -366,19 +373,14 @@ service_run(uint32_t i, struct core_state *cs, uint64_t service_mask,
cs->service_active_on_lcore[i] = 1;
- /* check do we need cmpset, if MT safe or <= 1 core
- * mapped, atomic ops are not required.
- */
- const int use_atomics = (service_mt_safe(s) == 0) &&
- (rte_atomic32_read(&s->num_mapped_cores) > 1);
- if (use_atomics) {
+ if ((service_mt_safe(s) == 0) && (serialize_mt_unsafe == 1)) {
if (!rte_atomic32_cmpset((uint32_t *)&s->execute_lock, 0, 1))
return -EBUSY;
- rte_service_runner_do_callback(s, cs, i);
+ service_runner_do_callback(s, cs, i);
rte_atomic32_clear(&s->execute_lock);
} else
- rte_service_runner_do_callback(s, cs, i);
+ service_runner_do_callback(s, cs, i);
return 0;
}
@@ -409,44 +411,34 @@ rte_service_run_iter_on_app_lcore(uint32_t id, uint32_t serialize_mt_unsafe)
SERVICE_VALID_GET_OR_ERR_RET(id, s, -EINVAL);
- /* Atomically add this core to the mapped cores first, then examine if
- * we can run the service. This avoids a race condition between
- * checking the value, and atomically adding to the mapped count.
+ /* Increment num_mapped_cores to reflect that this core is
+ * now mapped capable of running the service.
*/
- if (serialize_mt_unsafe)
- rte_atomic32_inc(&s->num_mapped_cores);
+ rte_atomic32_inc(&s->num_mapped_cores);
- if (service_mt_safe(s) == 0 &&
- rte_atomic32_read(&s->num_mapped_cores) > 1) {
- if (serialize_mt_unsafe)
- rte_atomic32_dec(&s->num_mapped_cores);
- return -EBUSY;
- }
-
- int ret = service_run(id, cs, UINT64_MAX, s);
+ int ret = service_run(id, cs, UINT64_MAX, s, serialize_mt_unsafe);
- if (serialize_mt_unsafe)
- rte_atomic32_dec(&s->num_mapped_cores);
+ rte_atomic32_dec(&s->num_mapped_cores);
return ret;
}
static int32_t
-rte_service_runner_func(void *arg)
+service_runner_func(void *arg)
{
RTE_SET_USED(arg);
uint32_t i;
const int lcore = rte_lcore_id();
struct core_state *cs = &lcore_states[lcore];
- while (lcore_states[lcore].runstate == RUNSTATE_RUNNING) {
+ while (cs->runstate == RUNSTATE_RUNNING) {
const uint64_t service_mask = cs->service_mask;
for (i = 0; i < RTE_SERVICE_NUM_MAX; i++) {
if (!service_valid(i))
continue;
/* return value ignored as no change to code flow */
- service_run(i, cs, service_mask, service_get(i));
+ service_run(i, cs, service_mask, service_get(i), 1);
}
cs->loops++;
@@ -700,9 +692,9 @@ rte_service_lcore_start(uint32_t lcore)
/* set core to run state first, and then launch otherwise it will
* return immediately as runstate keeps it in the service poll loop
*/
- lcore_states[lcore].runstate = RUNSTATE_RUNNING;
+ cs->runstate = RUNSTATE_RUNNING;
- int ret = rte_eal_remote_launch(rte_service_runner_func, 0, lcore);
+ int ret = rte_eal_remote_launch(service_runner_func, 0, lcore);
/* returns -EBUSY if the core is already launched, 0 on success */
return ret;
}
@@ -781,13 +773,9 @@ rte_service_lcore_attr_get(uint32_t lcore, uint32_t attr_id,
}
static void
-rte_service_dump_one(FILE *f, struct rte_service_spec_impl *s,
- uint64_t all_cycles, uint32_t reset)
+service_dump_one(FILE *f, struct rte_service_spec_impl *s, uint32_t reset)
{
/* avoid divide by zero */
- if (all_cycles == 0)
- all_cycles = 1;
-
int calls = 1;
if (s->calls != 0)
calls = s->calls;
@@ -814,7 +802,7 @@ rte_service_attr_reset_all(uint32_t id)
SERVICE_VALID_GET_OR_ERR_RET(id, s, -EINVAL);
int reset = 1;
- rte_service_dump_one(NULL, s, 0, reset);
+ service_dump_one(NULL, s, reset);
return 0;
}
@@ -858,21 +846,13 @@ rte_service_dump(FILE *f, uint32_t id)
uint32_t i;
int print_one = (id != UINT32_MAX);
- uint64_t total_cycles = 0;
-
- for (i = 0; i < RTE_SERVICE_NUM_MAX; i++) {
- if (!service_valid(i))
- continue;
- total_cycles += rte_services[i].cycles_spent;
- }
-
/* print only the specified service */
if (print_one) {
struct rte_service_spec_impl *s;
SERVICE_VALID_GET_OR_ERR_RET(id, s, -EINVAL);
fprintf(f, "Service %s Summary\n", s->spec.name);
uint32_t reset = 0;
- rte_service_dump_one(f, s, total_cycles, reset);
+ service_dump_one(f, s, reset);
return 0;
}
@@ -882,7 +862,7 @@ rte_service_dump(FILE *f, uint32_t id)
if (!service_valid(i))
continue;
uint32_t reset = 0;
- rte_service_dump_one(f, &rte_services[i], total_cycles, reset);
+ service_dump_one(f, &rte_services[i], reset);
}
fprintf(f, "Service Cores Summary\n");
diff --git a/dpdk/lib/librte_eal/linuxapp/eal/eal.c b/dpdk/lib/librte_eal/linuxapp/eal/eal.c
index f453337f71..987efb9b24 100644
--- a/dpdk/lib/librte_eal/linuxapp/eal/eal.c
+++ b/dpdk/lib/librte_eal/linuxapp/eal/eal.c
@@ -944,6 +944,7 @@ rte_eal_init(int argc, char **argv)
static char logid[PATH_MAX];
char cpuset[RTE_CPU_AFFINITY_STR_LEN];
char thread_name[RTE_MAX_THREAD_NAME_LEN];
+ bool phys_addrs;
/* checks if the machine is adequate */
if (!rte_cpu_is_supported()) {
@@ -1031,25 +1032,46 @@ rte_eal_init(int argc, char **argv)
return -1;
}
+ phys_addrs = rte_eal_using_phys_addrs() != 0;
+
/* if no EAL option "--iova-mode=<pa|va>", use bus IOVA scheme */
if (internal_config.iova_mode == RTE_IOVA_DC) {
- /* autodetect the IOVA mapping mode (default is RTE_IOVA_PA) */
- rte_eal_get_configuration()->iova_mode =
- rte_bus_get_iommu_class();
+ /* autodetect the IOVA mapping mode */
+ enum rte_iova_mode iova_mode = rte_bus_get_iommu_class();
+ if (iova_mode == RTE_IOVA_DC) {
+ iova_mode = phys_addrs ? RTE_IOVA_PA : RTE_IOVA_VA;
+ RTE_LOG(DEBUG, EAL,
+ "Buses did not request a specific IOVA mode, using '%s' based on physical addresses availability.\n",
+ phys_addrs ? "PA" : "VA");
+ }
+#ifdef RTE_LIBRTE_KNI
/* Workaround for KNI which requires physical address to work */
- if (rte_eal_get_configuration()->iova_mode == RTE_IOVA_VA &&
+ if (iova_mode == RTE_IOVA_VA &&
rte_eal_check_module("rte_kni") == 1) {
- rte_eal_get_configuration()->iova_mode = RTE_IOVA_PA;
- RTE_LOG(WARNING, EAL,
- "Some devices want IOVA as VA but PA will be used because.. "
- "KNI module inserted\n");
+ if (phys_addrs) {
+ iova_mode = RTE_IOVA_PA;
+ RTE_LOG(WARNING, EAL, "Forcing IOVA as 'PA' because KNI module is loaded\n");
+ } else {
+ RTE_LOG(DEBUG, EAL, "KNI can not work since physical addresses are unavailable\n");
+ }
}
+#endif
+ rte_eal_get_configuration()->iova_mode = iova_mode;
} else {
rte_eal_get_configuration()->iova_mode =
internal_config.iova_mode;
}
+ if (rte_eal_iova_mode() == RTE_IOVA_PA && !phys_addrs) {
+ rte_eal_init_alert("Cannot use IOVA as 'PA' since physical addresses are not available");
+ rte_errno = EINVAL;
+ return -1;
+ }
+
+ RTE_LOG(INFO, EAL, "Selected IOVA mode '%s'\n",
+ rte_eal_iova_mode() == RTE_IOVA_PA ? "PA" : "VA");
+
if (internal_config.no_hugetlbfs == 0) {
/* rte_config isn't initialized yet */
ret = internal_config.process_type == RTE_PROC_PRIMARY ?
diff --git a/dpdk/lib/librte_eal/linuxapp/eal/eal_memalloc.c b/dpdk/lib/librte_eal/linuxapp/eal/eal_memalloc.c
index bff7dcd58e..518314d89c 100644
--- a/dpdk/lib/librte_eal/linuxapp/eal/eal_memalloc.c
+++ b/dpdk/lib/librte_eal/linuxapp/eal/eal_memalloc.c
@@ -806,7 +806,7 @@ free_seg(struct rte_memseg *ms, struct hugepage_info *hi,
/* erase page data */
memset(ms->addr, 0, ms->len);
- if (mmap(ms->addr, ms->len, PROT_READ,
+ if (mmap(ms->addr, ms->len, PROT_NONE,
MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0) ==
MAP_FAILED) {
RTE_LOG(DEBUG, EAL, "couldn't unmap page\n");
diff --git a/dpdk/lib/librte_eal/linuxapp/eal/eal_memory.c b/dpdk/lib/librte_eal/linuxapp/eal/eal_memory.c
index ac0424582e..4b82432dee 100644
--- a/dpdk/lib/librte_eal/linuxapp/eal/eal_memory.c
+++ b/dpdk/lib/librte_eal/linuxapp/eal/eal_memory.c
@@ -61,34 +61,10 @@
* zone as well as a physical contiguous zone.
*/
-static bool phys_addrs_available = true;
+static int phys_addrs_available = -1;
#define RANDOMIZE_VA_SPACE_FILE "/proc/sys/kernel/randomize_va_space"
-static void
-test_phys_addrs_available(void)
-{
- uint64_t tmp = 0;
- phys_addr_t physaddr;
-
- if (!rte_eal_has_hugepages()) {
- RTE_LOG(ERR, EAL,
- "Started without hugepages support, physical addresses not available\n");
- phys_addrs_available = false;
- return;
- }
-
- physaddr = rte_mem_virt2phy(&tmp);
- if (physaddr == RTE_BAD_PHYS_ADDR) {
- if (rte_eal_iova_mode() == RTE_IOVA_PA)
- RTE_LOG(ERR, EAL,
- "Cannot obtain physical addresses: %s. "
- "Only vfio will function.\n",
- strerror(errno));
- phys_addrs_available = false;
- }
-}
-
/*
* Get physical address of any mapped virtual address in the current process.
*/
@@ -101,8 +77,7 @@ rte_mem_virt2phy(const void *virtaddr)
int page_size;
off_t offset;
- /* Cannot parse /proc/self/pagemap, no need to log errors everywhere */
- if (!phys_addrs_available)
+ if (phys_addrs_available == 0)
return RTE_BAD_IOVA;
/* standard page size */
@@ -1332,8 +1307,6 @@ eal_legacy_hugepage_init(void)
int nr_hugefiles, nr_hugepages = 0;
void *addr;
- test_phys_addrs_available();
-
memset(used_hp, 0, sizeof(used_hp));
/* get pointer to global configuration */
@@ -1466,7 +1439,7 @@ eal_legacy_hugepage_init(void)
continue;
}
- if (phys_addrs_available &&
+ if (rte_eal_using_phys_addrs() &&
rte_eal_iova_mode() != RTE_IOVA_VA) {
/* find physical addresses for each hugepage */
if (find_physaddrs(&tmp_hp[hp_offset], hpi) < 0) {
@@ -1685,8 +1658,6 @@ eal_hugepage_init(void)
uint64_t memory[RTE_MAX_NUMA_NODES];
int hp_sz_idx, socket_id;
- test_phys_addrs_available();
-
memset(used_hp, 0, sizeof(used_hp));
for (hp_sz_idx = 0;
@@ -1812,8 +1783,6 @@ eal_legacy_hugepage_attach(void)
"into secondary processes\n");
}
- test_phys_addrs_available();
-
fd_hugepage = open(eal_hugepage_data_path(), O_RDONLY);
if (fd_hugepage < 0) {
RTE_LOG(ERR, EAL, "Could not open %s\n",
@@ -1950,6 +1919,15 @@ rte_eal_hugepage_attach(void)
int
rte_eal_using_phys_addrs(void)
{
+ if (phys_addrs_available == -1) {
+ uint64_t tmp = 0;
+
+ if (rte_eal_has_hugepages() != 0 &&
+ rte_mem_virt2phy(&tmp) != RTE_BAD_PHYS_ADDR)
+ phys_addrs_available = 1;
+ else
+ phys_addrs_available = 0;
+ }
return phys_addrs_available;
}
diff --git a/dpdk/lib/librte_eal/linuxapp/eal/eal_vfio.c b/dpdk/lib/librte_eal/linuxapp/eal/eal_vfio.c
index 48d2abafaa..b4619c2117 100644
--- a/dpdk/lib/librte_eal/linuxapp/eal/eal_vfio.c
+++ b/dpdk/lib/librte_eal/linuxapp/eal/eal_vfio.c
@@ -378,7 +378,7 @@ vfio_get_group_fd(struct vfio_config *vfio_cfg,
}
vfio_group_fd = vfio_open_group_fd(iommu_group_num);
- if (vfio_group_fd < 0) {
+ if (vfio_group_fd <= 0) {
RTE_LOG(ERR, EAL, "Failed to open group %d\n", iommu_group_num);
return -1;
}
@@ -1025,6 +1025,7 @@ vfio_get_default_container_fd(void)
struct rte_mp_reply mp_reply = {0};
struct timespec ts = {.tv_sec = 5, .tv_nsec = 0};
struct vfio_mp_param *p = (struct vfio_mp_param *)mp_req.param;
+ int container_fd;
if (default_vfio_cfg->vfio_enabled)
return default_vfio_cfg->vfio_container_fd;
@@ -1047,8 +1048,9 @@ vfio_get_default_container_fd(void)
mp_rep = &mp_reply.msgs[0];
p = (struct vfio_mp_param *)mp_rep->param;
if (p->result == SOCKET_OK && mp_rep->num_fds == 1) {
+ container_fd = mp_rep->fds[0];
free(mp_reply.msgs);
- return mp_rep->fds[0];
+ return container_fd;
}
}
diff --git a/dpdk/lib/librte_ethdev/ethdev_profile.h b/dpdk/lib/librte_ethdev/ethdev_profile.h
index 65031e6f3f..e5ee4df824 100644
--- a/dpdk/lib/librte_ethdev/ethdev_profile.h
+++ b/dpdk/lib/librte_ethdev/ethdev_profile.h
@@ -24,4 +24,13 @@
int
__rte_eth_dev_profile_init(uint16_t port_id, struct rte_eth_dev *dev);
+#ifdef RTE_ETHDEV_PROFILE_WITH_VTUNE
+
+uint16_t
+profile_hook_rx_burst_cb(uint16_t port_id, uint16_t queue_id,
+ struct rte_mbuf *pkts[], uint16_t nb_pkts,
+ uint16_t max_pkts, void *user_param);
+
+#endif /* RTE_ETHDEV_PROFILE_WITH_VTUNE */
+
#endif
diff --git a/dpdk/lib/librte_ethdev/rte_ethdev.c b/dpdk/lib/librte_ethdev/rte_ethdev.c
index 13866150ef..2929d10c22 100644
--- a/dpdk/lib/librte_ethdev/rte_ethdev.c
+++ b/dpdk/lib/librte_ethdev/rte_ethdev.c
@@ -2705,7 +2705,7 @@ rte_eth_dev_set_vlan_offload(uint16_t port_id, int offload_mask)
/* save original values in case of failure */
orig_offloads = dev->data->dev_conf.rxmode.offloads;
- /*check which option changed by application*/
+ /* check which option changed by application */
cur = !!(offload_mask & ETH_VLAN_STRIP_OFFLOAD);
org = !!(dev->data->dev_conf.rxmode.offloads &
DEV_RX_OFFLOAD_VLAN_STRIP);
@@ -3861,7 +3861,7 @@ rte_eth_add_first_rx_callback(uint16_t port_id, uint16_t queue_id,
cb->param = user_param;
rte_spinlock_lock(&rte_eth_rx_cb_lock);
- /* Add the callbacks at fisrt position*/
+ /* Add the callbacks at first position */
cb->next = rte_eth_devices[port_id].post_rx_burst_cbs[queue_id];
rte_smp_wmb();
rte_eth_devices[port_id].post_rx_burst_cbs[queue_id] = cb;
diff --git a/dpdk/lib/librte_eventdev/rte_eventdev.c b/dpdk/lib/librte_eventdev/rte_eventdev.c
index 6396a96490..a2db0fd5fb 100644
--- a/dpdk/lib/librte_eventdev/rte_eventdev.c
+++ b/dpdk/lib/librte_eventdev/rte_eventdev.c
@@ -13,6 +13,7 @@
#include <sys/types.h>
#include <sys/queue.h>
+#include <rte_string_fns.h>
#include <rte_byteorder.h>
#include <rte_log.h>
#include <rte_debug.h>
@@ -1362,15 +1363,17 @@ rte_event_pmd_allocate(const char *name, int socket_id)
eventdev->data = eventdev_data;
- snprintf(eventdev->data->name, RTE_EVENTDEV_NAME_MAX_LEN,
- "%s", name);
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
- eventdev->data->dev_id = dev_id;
- eventdev->data->socket_id = socket_id;
- eventdev->data->dev_started = 0;
+ strlcpy(eventdev->data->name, name,
+ RTE_EVENTDEV_NAME_MAX_LEN);
- eventdev->attached = RTE_EVENTDEV_ATTACHED;
+ eventdev->data->dev_id = dev_id;
+ eventdev->data->socket_id = socket_id;
+ eventdev->data->dev_started = 0;
+ }
+ eventdev->attached = RTE_EVENTDEV_ATTACHED;
eventdev_globals.nb_devs++;
}
diff --git a/dpdk/lib/librte_eventdev/rte_eventdev_pmd_pci.h b/dpdk/lib/librte_eventdev/rte_eventdev_pmd_pci.h
index 8fb61386fd..443cd38c23 100644
--- a/dpdk/lib/librte_eventdev/rte_eventdev_pmd_pci.h
+++ b/dpdk/lib/librte_eventdev/rte_eventdev_pmd_pci.h
@@ -112,9 +112,11 @@ rte_event_pmd_pci_remove(struct rte_pci_device *pci_dev,
if (eventdev == NULL)
return -ENODEV;
- ret = rte_event_dev_close(eventdev->data->dev_id);
- if (ret < 0)
- return ret;
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+ ret = rte_event_dev_close(eventdev->data->dev_id);
+ if (ret < 0)
+ return ret;
+ }
/* Invoke PMD device un-init function */
if (devuninit)
diff --git a/dpdk/lib/librte_kvargs/rte_kvargs.c b/dpdk/lib/librte_kvargs/rte_kvargs.c
index f7030c63b7..b6f8a6db87 100644
--- a/dpdk/lib/librte_kvargs/rte_kvargs.c
+++ b/dpdk/lib/librte_kvargs/rte_kvargs.c
@@ -50,6 +50,8 @@ rte_kvargs_tokenize(struct rte_kvargs *kvlist, const char *params)
/* Find the end of the list. */
while (str[strlen(str) - 1] != ']') {
/* Restore the comma erased by strtok_r(). */
+ if (ctx1 == NULL || ctx1[0] == '\0')
+ return -1; /* no closing bracket */
str[strlen(str)] = ',';
/* Parse until next comma. */
str = strtok_r(NULL, RTE_KVARGS_PAIRS_DELIM, &ctx1);
diff --git a/dpdk/lib/librte_kvargs/rte_kvargs.h b/dpdk/lib/librte_kvargs/rte_kvargs.h
index 1946195de4..eff598e08b 100644
--- a/dpdk/lib/librte_kvargs/rte_kvargs.h
+++ b/dpdk/lib/librte_kvargs/rte_kvargs.h
@@ -171,7 +171,7 @@ unsigned rte_kvargs_count(const struct rte_kvargs *kvlist,
* 0 if the strings match.
* !0 otherwise or on error.
*
- * Unless strcmp, comparison ordering is not kept.
+ * Unlike strcmp, comparison ordering is not kept.
* In order for rte_kvargs_process to stop processing on match error,
* a negative value is returned even if strcmp had returned a positive one.
*/
diff --git a/dpdk/lib/librte_lpm/rte_lpm6.c b/dpdk/lib/librte_lpm/rte_lpm6.c
index 6212003f4c..5b0db3b549 100644
--- a/dpdk/lib/librte_lpm/rte_lpm6.c
+++ b/dpdk/lib/librte_lpm/rte_lpm6.c
@@ -725,7 +725,8 @@ add_step(struct rte_lpm6 *lpm, struct rte_lpm6_tbl_entry *tbl,
tbl8_group_start = tbl8_gindex *
RTE_LPM6_TBL8_GROUP_NUM_ENTRIES;
memset(&lpm->tbl8[tbl8_group_start], 0,
- RTE_LPM6_TBL8_GROUP_NUM_ENTRIES);
+ RTE_LPM6_TBL8_GROUP_NUM_ENTRIES *
+ sizeof(struct rte_lpm6_tbl_entry));
/* init the new table's header:
* save the reference to the owner table
@@ -824,7 +825,7 @@ VERSION_SYMBOL(rte_lpm6_add, _v20, 2.0);
*
* Returns:
* 0 on success
- * -ENOSPC not enought tbl8 left
+ * -ENOSPC not enough tbl8 left
*/
static int
simulate_add(struct rte_lpm6 *lpm, const uint8_t *masked_ip, uint8_t depth)
@@ -854,7 +855,7 @@ simulate_add(struct rte_lpm6 *lpm, const uint8_t *masked_ip, uint8_t depth)
}
if (tbl8_available(lpm) < total_need_tbl_nb)
- /* not enought tbl8 to add a rule */
+ /* not enough tbl8 to add a rule */
return -ENOSPC;
return 0;
@@ -1314,7 +1315,7 @@ rule_find_range(struct rte_lpm6 *lpm, const uint8_t *ip, uint8_t depth,
/* minus top level */
depth -= 24;
- /* interate through levels (tbl8s)
+ /* iterate through levels (tbl8s)
* until we reach the last one
*/
while (depth > 8) {
diff --git a/dpdk/lib/librte_pci/rte_pci.c b/dpdk/lib/librte_pci/rte_pci.c
index f400178bb6..2c98c3efb5 100644
--- a/dpdk/lib/librte_pci/rte_pci.c
+++ b/dpdk/lib/librte_pci/rte_pci.c
@@ -20,6 +20,7 @@
#include <rte_eal.h>
#include <rte_string_fns.h>
#include <rte_common.h>
+#include <rte_debug.h>
#include "rte_pci.h"
@@ -34,6 +35,12 @@ get_u8_pciaddr_field(const char *in, void *_u8, char dlm)
if (*in == '\0')
return NULL;
+ /* PCI field starting with spaces is forbidden.
+ * Negative wrap-around is not reported as an error by strtoul.
+ */
+ if (*in == ' ' || *in == '-')
+ return NULL;
+
errno = 0;
val = strtoul(in, &end, 16);
if (errno != 0 || end[0] != dlm || val > UINT8_MAX) {
@@ -69,11 +76,17 @@ pci_dbdf_parse(const char *input, struct rte_pci_addr *dev_addr)
unsigned long val;
char *end;
+ /* PCI id starting with spaces is forbidden.
+ * Negative wrap-around is not reported as an error by strtoul.
+ */
+ if (*in == ' ' || *in == '-')
+ return -EINVAL;
+
errno = 0;
val = strtoul(in, &end, 16);
- if (errno != 0 || end[0] != ':' || val > UINT16_MAX)
+ if (errno != 0 || end[0] != ':' || val > UINT32_MAX)
return -EINVAL;
- dev_addr->domain = (uint16_t)val;
+ dev_addr->domain = (uint32_t)val;
in = end + 1;
in = get_u8_pciaddr_field(in, &dev_addr->bus, ':');
if (in == NULL)
diff --git a/dpdk/lib/librte_security/rte_security.c b/dpdk/lib/librte_security/rte_security.c
index a222b33cec..6ff7a9e69b 100644
--- a/dpdk/lib/librte_security/rte_security.c
+++ b/dpdk/lib/librte_security/rte_security.c
@@ -1,6 +1,7 @@
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright 2017 NXP.
* Copyright(c) 2017 Intel Corporation.
+ * Copyright (c) 2020 Samsung Electronics Co., Ltd All Rights Reserved
*/
#include <rte_malloc.h>
@@ -9,6 +10,19 @@
#include "rte_security.h"
#include "rte_security_driver.h"
+/* Macro to check for invalid pointers */
+#define RTE_PTR_OR_ERR_RET(ptr, retval) do { \
+ if ((ptr) == NULL) \
+ return retval; \
+} while (0)
+
+/* Macro to check for invalid pointers chains */
+#define RTE_PTR_CHAIN3_OR_ERR_RET(p1, p2, p3, retval, last_retval) do { \
+ RTE_PTR_OR_ERR_RET(p1, retval); \
+ RTE_PTR_OR_ERR_RET(p1->p2, retval); \
+ RTE_PTR_OR_ERR_RET(p1->p2->p3, last_retval); \
+} while (0)
+
struct rte_security_session *
rte_security_session_create(struct rte_security_ctx *instance,
struct rte_security_session_conf *conf,
@@ -16,10 +30,9 @@ rte_security_session_create(struct rte_security_ctx *instance,
{
struct rte_security_session *sess = NULL;
- if (conf == NULL)
- return NULL;
-
- RTE_FUNC_PTR_OR_ERR_RET(*instance->ops->session_create, NULL);
+ RTE_PTR_CHAIN3_OR_ERR_RET(instance, ops, session_create, NULL, NULL);
+ RTE_PTR_OR_ERR_RET(conf, NULL);
+ RTE_PTR_OR_ERR_RET(mp, NULL);
if (rte_mempool_get(mp, (void **)&sess))
return NULL;
@@ -38,14 +51,19 @@ rte_security_session_update(struct rte_security_ctx *instance,
struct rte_security_session *sess,
struct rte_security_session_conf *conf)
{
- RTE_FUNC_PTR_OR_ERR_RET(*instance->ops->session_update, -ENOTSUP);
+ RTE_PTR_CHAIN3_OR_ERR_RET(instance, ops, session_update, -EINVAL,
+ -ENOTSUP);
+ RTE_PTR_OR_ERR_RET(sess, -EINVAL);
+ RTE_PTR_OR_ERR_RET(conf, -EINVAL);
+
return instance->ops->session_update(instance->device, sess, conf);
}
unsigned int
rte_security_session_get_size(struct rte_security_ctx *instance)
{
- RTE_FUNC_PTR_OR_ERR_RET(*instance->ops->session_get_size, 0);
+ RTE_PTR_CHAIN3_OR_ERR_RET(instance, ops, session_get_size, 0, 0);
+
return instance->ops->session_get_size(instance->device);
}
@@ -54,7 +72,11 @@ rte_security_session_stats_get(struct rte_security_ctx *instance,
struct rte_security_session *sess,
struct rte_security_stats *stats)
{
- RTE_FUNC_PTR_OR_ERR_RET(*instance->ops->session_stats_get, -ENOTSUP);
+ RTE_PTR_CHAIN3_OR_ERR_RET(instance, ops, session_stats_get, -EINVAL,
+ -ENOTSUP);
+ /* Parameter sess can be NULL in case of getting global statistics. */
+ RTE_PTR_OR_ERR_RET(stats, -EINVAL);
+
return instance->ops->session_stats_get(instance->device, sess, stats);
}
@@ -64,16 +86,20 @@ rte_security_session_destroy(struct rte_security_ctx *instance,
{
int ret;
- RTE_FUNC_PTR_OR_ERR_RET(*instance->ops->session_destroy, -ENOTSUP);
+ RTE_PTR_CHAIN3_OR_ERR_RET(instance, ops, session_destroy, -EINVAL,
+ -ENOTSUP);
+ RTE_PTR_OR_ERR_RET(sess, -EINVAL);
+
+ ret = instance->ops->session_destroy(instance->device, sess);
+ if (ret != 0)
+ return ret;
+
+ rte_mempool_put(rte_mempool_from_obj(sess), (void *)sess);
if (instance->sess_cnt)
instance->sess_cnt--;
- ret = instance->ops->session_destroy(instance->device, sess);
- if (!ret)
- rte_mempool_put(rte_mempool_from_obj(sess), (void *)sess);
-
- return ret;
+ return 0;
}
int
@@ -81,6 +107,11 @@ rte_security_set_pkt_metadata(struct rte_security_ctx *instance,
struct rte_security_session *sess,
struct rte_mbuf *m, void *params)
{
+#ifdef RTE_DEBUG
+ RTE_PTR_OR_ERR_RET(sess, -EINVAL);
+ RTE_PTR_OR_ERR_RET(instance, -EINVAL);
+ RTE_PTR_OR_ERR_RET(instance->ops, -EINVAL);
+#endif
RTE_FUNC_PTR_OR_ERR_RET(*instance->ops->set_pkt_metadata, -ENOTSUP);
return instance->ops->set_pkt_metadata(instance->device,
sess, m, params);
@@ -91,6 +122,10 @@ rte_security_get_userdata(struct rte_security_ctx *instance, uint64_t md)
{
void *userdata = NULL;
+#ifdef RTE_DEBUG
+ RTE_PTR_OR_ERR_RET(instance, NULL);
+ RTE_PTR_OR_ERR_RET(instance->ops, NULL);
+#endif
RTE_FUNC_PTR_OR_ERR_RET(*instance->ops->get_userdata, NULL);
if (instance->ops->get_userdata(instance->device, md, &userdata))
return NULL;
@@ -101,7 +136,8 @@ rte_security_get_userdata(struct rte_security_ctx *instance, uint64_t md)
const struct rte_security_capability *
rte_security_capabilities_get(struct rte_security_ctx *instance)
{
- RTE_FUNC_PTR_OR_ERR_RET(*instance->ops->capabilities_get, NULL);
+ RTE_PTR_CHAIN3_OR_ERR_RET(instance, ops, capabilities_get, NULL, NULL);
+
return instance->ops->capabilities_get(instance->device);
}
@@ -113,7 +149,9 @@ rte_security_capability_get(struct rte_security_ctx *instance,
const struct rte_security_capability *capability;
uint16_t i = 0;
- RTE_FUNC_PTR_OR_ERR_RET(*instance->ops->capabilities_get, NULL);
+ RTE_PTR_CHAIN3_OR_ERR_RET(instance, ops, capabilities_get, NULL, NULL);
+ RTE_PTR_OR_ERR_RET(idx, NULL);
+
capabilities = instance->ops->capabilities_get(instance->device);
if (capabilities == NULL)
@@ -121,7 +159,7 @@ rte_security_capability_get(struct rte_security_ctx *instance,
while ((capability = &capabilities[i++])->action
!= RTE_SECURITY_ACTION_TYPE_NONE) {
- if (capability->action == idx->action &&
+ if (capability->action == idx->action &&
capability->protocol == idx->protocol) {
if (idx->protocol == RTE_SECURITY_PROTOCOL_IPSEC) {
if (capability->ipsec.proto ==
diff --git a/dpdk/lib/librte_security/rte_security.h b/dpdk/lib/librte_security/rte_security.h
index ad7898c72b..133ce9481c 100644
--- a/dpdk/lib/librte_security/rte_security.h
+++ b/dpdk/lib/librte_security/rte_security.h
@@ -342,7 +342,7 @@ rte_security_session_create(struct rte_security_ctx *instance,
* @param conf update configuration parameters
* @return
* - On success returns 0
- * - On failure return errno
+ * - On failure returns a negative errno value.
*/
int __rte_experimental
rte_security_session_update(struct rte_security_ctx *instance,
@@ -366,12 +366,14 @@ rte_security_session_get_size(struct rte_security_ctx *instance);
* return it to its original mempool.
*
* @param instance security instance
- * @param sess security session to freed
+ * @param sess security session to be freed
*
* @return
* - 0 if successful.
- * - -EINVAL if session is NULL.
+ * - -EINVAL if session or context instance is NULL.
* - -EBUSY if not all device private data has been freed.
+ * - -ENOTSUP if destroying private data is not supported.
+ * - other negative values in case of freeing private data errors.
*/
int
rte_security_session_destroy(struct rte_security_ctx *instance,
diff --git a/dpdk/lib/librte_vhost/iotlb.c b/dpdk/lib/librte_vhost/iotlb.c
index c6354fef7e..3dfde94e80 100644
--- a/dpdk/lib/librte_vhost/iotlb.c
+++ b/dpdk/lib/librte_vhost/iotlb.c
@@ -336,8 +336,9 @@ vhost_user_iotlb_init(struct virtio_net *dev, int vq_index)
TAILQ_INIT(&vq->iotlb_list);
TAILQ_INIT(&vq->iotlb_pending_list);
- snprintf(pool_name, sizeof(pool_name), "iotlb_cache_%d_%d",
- dev->vid, vq_index);
+ snprintf(pool_name, sizeof(pool_name), "iotlb_%u_%d_%d",
+ getpid(), dev->vid, vq_index);
+ RTE_LOG(DEBUG, VHOST_CONFIG, "IOTLB cache name: %s\n", pool_name);
/* If already created, free it and recreate */
vq->iotlb_pool = rte_mempool_lookup(pool_name);
diff --git a/dpdk/lib/librte_vhost/rte_vhost.h b/dpdk/lib/librte_vhost/rte_vhost.h
index ce1f12e1d5..d9307987a8 100644
--- a/dpdk/lib/librte_vhost/rte_vhost.h
+++ b/dpdk/lib/librte_vhost/rte_vhost.h
@@ -64,6 +64,10 @@ extern "C" {
#define VHOST_USER_PROTOCOL_F_PAGEFAULT 8
#endif
+#ifndef VHOST_USER_PROTOCOL_F_CONFIG
+#define VHOST_USER_PROTOCOL_F_CONFIG 9
+#endif
+
#ifndef VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD
#define VHOST_USER_PROTOCOL_F_SLAVE_SEND_FD 10
#endif
@@ -77,6 +81,7 @@ extern "C" {
#define VHOST_USER_F_PROTOCOL_FEATURES 30
#endif
+
/**
* Information relating to memory regions including offsets to
* addresses in QEMUs memory file.
@@ -132,7 +137,15 @@ struct vhost_device_ops {
int (*new_connection)(int vid);
void (*destroy_connection)(int vid);
- void *reserved[2]; /**< Reserved for future extension */
+ /**
+ * This callback gets called each time a guest gets notified
+ * about waiting packets. This is the interrupt handling trough
+ * the eventfd_write(callfd), which can be used for counting these
+ * "slow" syscalls.
+ */
+ void (*guest_notified)(int vid);
+
+ void *reserved[1]; /**< Reserved for future extension */
};
/**
diff --git a/dpdk/lib/librte_vhost/socket.c b/dpdk/lib/librte_vhost/socket.c
index 75f6703f56..6f7142be23 100644
--- a/dpdk/lib/librte_vhost/socket.c
+++ b/dpdk/lib/librte_vhost/socket.c
@@ -890,6 +890,10 @@ rte_vhost_driver_register(const char *path, uint64_t flags)
* not compatible with postcopy.
*/
if (vsocket->dequeue_zero_copy) {
+ if ((flags & RTE_VHOST_USER_CLIENT) != 0)
+ RTE_LOG(WARNING, VHOST_CONFIG,
+ "zero copy may be incompatible with vhost client mode\n");
+
vsocket->supported_features &= ~(1ULL << VIRTIO_F_IN_ORDER);
vsocket->features &= ~(1ULL << VIRTIO_F_IN_ORDER);
diff --git a/dpdk/lib/librte_vhost/vhost.h b/dpdk/lib/librte_vhost/vhost.h
index 535591927f..158b97375c 100644
--- a/dpdk/lib/librte_vhost/vhost.h
+++ b/dpdk/lib/librte_vhost/vhost.h
@@ -512,7 +512,6 @@ vhost_log_write_iova(struct virtio_net *dev, struct vhost_virtqueue *vq,
#define PRINT_PACKET(device, addr, size, header) do {} while (0)
#endif
-extern uint64_t VHOST_FEATURES;
#define MAX_VHOST_DEVICE 1024
extern struct virtio_net *vhost_devices[MAX_VHOST_DEVICE];
@@ -655,13 +654,19 @@ vhost_vring_call_split(struct virtio_net *dev, struct vhost_virtqueue *vq)
if ((vhost_need_event(vhost_used_event(vq), new, old) &&
(vq->callfd >= 0)) ||
- unlikely(!signalled_used_valid))
+ unlikely(!signalled_used_valid)) {
eventfd_write(vq->callfd, (eventfd_t) 1);
+ if (dev->notify_ops->guest_notified)
+ dev->notify_ops->guest_notified(dev->vid);
+ }
} else {
/* Kick the guest if necessary. */
if (!(vq->avail->flags & VRING_AVAIL_F_NO_INTERRUPT)
- && (vq->callfd >= 0))
+ && (vq->callfd >= 0)) {
eventfd_write(vq->callfd, (eventfd_t)1);
+ if (dev->notify_ops->guest_notified)
+ dev->notify_ops->guest_notified(dev->vid);
+ }
}
}
@@ -712,8 +717,11 @@ vhost_vring_call_packed(struct virtio_net *dev, struct vhost_virtqueue *vq)
if (vhost_need_event(off, new, old))
kick = true;
kick:
- if (kick)
+ if (kick) {
eventfd_write(vq->callfd, (eventfd_t)1);
+ if (dev->notify_ops->guest_notified)
+ dev->notify_ops->guest_notified(dev->vid);
+ }
}
static __rte_always_inline void
diff --git a/dpdk/lib/librte_vhost/vhost_crypto.c b/dpdk/lib/librte_vhost/vhost_crypto.c
index cf01c7ebe3..dfbac66f05 100644
--- a/dpdk/lib/librte_vhost/vhost_crypto.c
+++ b/dpdk/lib/librte_vhost/vhost_crypto.c
@@ -40,7 +40,8 @@
(1 << VIRTIO_RING_F_EVENT_IDX) | \
(1 << VIRTIO_CRYPTO_SERVICE_CIPHER) | \
(1 << VIRTIO_CRYPTO_SERVICE_MAC) | \
- (1 << VIRTIO_NET_F_CTRL_VQ))
+ (1 << VIRTIO_NET_F_CTRL_VQ) | \
+ (1 << VHOST_USER_PROTOCOL_F_CONFIG))
#define IOVA_TO_VVA(t, r, a, l, p) \
((t)(uintptr_t)vhost_iova_to_vva(r->dev, r->vq, a, l, p))
@@ -236,6 +237,11 @@ transform_cipher_param(struct rte_crypto_sym_xform *xform,
if (unlikely(ret < 0))
return ret;
+ if (param->cipher_key_len > VHOST_USER_CRYPTO_MAX_CIPHER_KEY_LENGTH) {
+ VC_LOG_DBG("Invalid cipher key length\n");
+ return -VIRTIO_CRYPTO_BADMSG;
+ }
+
xform->type = RTE_CRYPTO_SYM_XFORM_CIPHER;
xform->cipher.key.length = param->cipher_key_len;
if (xform->cipher.key.length > 0)
@@ -286,6 +292,12 @@ transform_chain_param(struct rte_crypto_sym_xform *xforms,
&xform_cipher->cipher.algo);
if (unlikely(ret < 0))
return ret;
+
+ if (param->cipher_key_len > VHOST_USER_CRYPTO_MAX_CIPHER_KEY_LENGTH) {
+ VC_LOG_DBG("Invalid cipher key length\n");
+ return -VIRTIO_CRYPTO_BADMSG;
+ }
+
xform_cipher->type = RTE_CRYPTO_SYM_XFORM_CIPHER;
xform_cipher->cipher.key.length = param->cipher_key_len;
xform_cipher->cipher.key.data = param->cipher_key_buf;
@@ -300,6 +312,12 @@ transform_chain_param(struct rte_crypto_sym_xform *xforms,
ret = auth_algo_transform(param->hash_algo, &xform_auth->auth.algo);
if (unlikely(ret < 0))
return ret;
+
+ if (param->auth_key_len > VHOST_USER_CRYPTO_MAX_HMAC_KEY_LENGTH) {
+ VC_LOG_DBG("Invalid auth key length\n");
+ return -VIRTIO_CRYPTO_BADMSG;
+ }
+
xform_auth->auth.digest_length = param->digest_len;
xform_auth->auth.key.length = param->auth_key_len;
xform_auth->auth.key.data = param->auth_key_buf;
diff --git a/dpdk/lib/librte_vhost/vhost_user.c b/dpdk/lib/librte_vhost/vhost_user.c
index 2f4bbb342d..4ed75104b9 100644
--- a/dpdk/lib/librte_vhost/vhost_user.c
+++ b/dpdk/lib/librte_vhost/vhost_user.c
@@ -1595,10 +1595,10 @@ vhost_user_set_log_base(struct virtio_net **pdev, struct VhostUserMsg *msg,
size = msg->payload.log.mmap_size;
off = msg->payload.log.mmap_offset;
- /* Don't allow mmap_offset to point outside the mmap region */
- if (off > size) {
+ /* Check for mmap size and offset overflow. */
+ if (off >= -size) {
RTE_LOG(ERR, VHOST_CONFIG,
- "log offset %#"PRIx64" exceeds log size %#"PRIx64"\n",
+ "log offset %#"PRIx64" and log size %#"PRIx64" overflow\n",
off, size);
return VH_RESULT_ERR;
}
@@ -2062,7 +2062,7 @@ static int
vhost_user_check_and_alloc_queue_pair(struct virtio_net *dev,
struct VhostUserMsg *msg)
{
- uint16_t vring_idx;
+ uint32_t vring_idx;
switch (msg->request.master) {
case VHOST_USER_SET_VRING_KICK:
@@ -2329,11 +2329,19 @@ static int process_slave_message_reply(struct virtio_net *dev,
if ((msg->flags & VHOST_USER_NEED_REPLY) == 0)
return 0;
- if (read_vhost_message(dev->slave_req_fd, &msg_reply) < 0) {
+ ret = read_vhost_message(dev->slave_req_fd, &msg_reply);
+ if (ret <= 0) {
+ if (ret < 0)
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "vhost read slave message reply failed\n");
+ else
+ RTE_LOG(INFO, VHOST_CONFIG,
+ "vhost peer closed\n");
ret = -1;
goto out;
}
+ ret = 0;
if (msg_reply.request.slave != msg->request.slave) {
RTE_LOG(ERR, VHOST_CONFIG,
"Received unexpected msg type (%u), expected %u\n",
diff --git a/dpdk/meson.build b/dpdk/meson.build
index 45b5a37f35..82c676c010 100644
--- a/dpdk/meson.build
+++ b/dpdk/meson.build
@@ -2,7 +2,7 @@
# Copyright(c) 2017 Intel Corporation
project('DPDK', 'C',
- version: '18.11.7',
+ version: '18.11.9',
license: 'BSD',
default_options: ['buildtype=release', 'default_library=static'],
meson_version: '>= 0.41'
diff --git a/dpdk/mk/toolchain/gcc/rte.vars.mk b/dpdk/mk/toolchain/gcc/rte.vars.mk
index b852fcfd7e..50f5e6f58d 100644
--- a/dpdk/mk/toolchain/gcc/rte.vars.mk
+++ b/dpdk/mk/toolchain/gcc/rte.vars.mk
@@ -71,6 +71,11 @@ ifeq ($(shell test $(GCC_VERSION) -lt 47 && echo 1), 1)
WERROR_FLAGS += -Wno-uninitialized
endif
+ifeq ($(shell test $(GCC_VERSION) -ge 100 && echo 1), 1)
+# FIXME: Bugzilla 396
+WERROR_FLAGS += -Wno-zero-length-bounds
+endif
+
HOST_WERROR_FLAGS := $(WERROR_FLAGS)
ifeq ($(shell test $(HOST_GCC_VERSION) -gt 70 && echo 1), 1)
diff --git a/dpdk/pkg/dpdk.spec b/dpdk/pkg/dpdk.spec
index d497857178..fee77eabe9 100644
--- a/dpdk/pkg/dpdk.spec
+++ b/dpdk/pkg/dpdk.spec
@@ -2,7 +2,7 @@
# Copyright 2014 6WIND S.A.
Name: dpdk
-Version: 18.11.7
+Version: 18.11.9
Release: 1
Packager: packaging@6wind.com
URL: http://dpdk.org
diff --git a/dpdk/test/test-acl/main.c b/dpdk/test/test-acl/main.c
index 648525af56..420a2c9b99 100644
--- a/dpdk/test/test-acl/main.c
+++ b/dpdk/test/test-acl/main.c
@@ -11,7 +11,7 @@
#include <rte_lcore.h>
#include <rte_ip.h>
-#define PRINT_USAGE_START "%s [EAL options]\n"
+#define PRINT_USAGE_START "%s [EAL options] --\n"
#define RTE_LOGTYPE_TESTACL RTE_LOGTYPE_USER1
diff --git a/dpdk/test/test-pipeline/config.c b/dpdk/test/test-pipeline/config.c
index 28ac9fcc0e..33f3f1c827 100644
--- a/dpdk/test/test-pipeline/config.c
+++ b/dpdk/test/test-pipeline/config.c
@@ -42,8 +42,6 @@
#include "main.h"
-struct app_params app;
-
static const char usage[] = "\n";
void
diff --git a/dpdk/test/test/test.h b/dpdk/test/test/test.h
index 7c24432303..705a311068 100644
--- a/dpdk/test/test/test.h
+++ b/dpdk/test/test/test.h
@@ -22,8 +22,6 @@
# define TEST_TRACE_FAILURE(_file, _line, _func)
#endif
-#define RTE_TEST_TRACE_FAILURE TEST_TRACE_FAILURE
-
#include <rte_test.h>
#define TEST_ASSERT RTE_TEST_ASSERT
diff --git a/dpdk/test/test/test_acl.c b/dpdk/test/test/test_acl.c
index b1f75d1bc7..4fedcf446f 100644
--- a/dpdk/test/test/test_acl.c
+++ b/dpdk/test/test/test_acl.c
@@ -1394,16 +1394,18 @@ test_invalid_parameters(void)
} else
rte_acl_free(acx);
- /* invalid NUMA node */
- memcpy(¶m, &acl_param, sizeof(param));
- param.socket_id = RTE_MAX_NUMA_NODES + 1;
-
- acx = rte_acl_create(¶m);
- if (acx != NULL) {
- printf("Line %i: ACL context creation with invalid NUMA "
- "should have failed!\n", __LINE__);
- rte_acl_free(acx);
- return -1;
+ if (rte_eal_has_hugepages()) {
+ /* invalid NUMA node */
+ memcpy(¶m, &acl_param, sizeof(param));
+ param.socket_id = RTE_MAX_NUMA_NODES + 1;
+
+ acx = rte_acl_create(¶m);
+ if (acx != NULL) {
+ printf("Line %i: ACL context creation with invalid "
+ "NUMA should have failed!\n", __LINE__);
+ rte_acl_free(acx);
+ return -1;
+ }
}
/* NULL name */
diff --git a/dpdk/test/test/test_cryptodev_blockcipher.c b/dpdk/test/test/test_cryptodev_blockcipher.c
index 4f1298ea21..660d5a7682 100644
--- a/dpdk/test/test/test_cryptodev_blockcipher.c
+++ b/dpdk/test/test/test_cryptodev_blockcipher.c
@@ -85,7 +85,7 @@ test_blockcipher_one_case(const struct blockcipher_test_case *t,
uint64_t feat_flags = dev_info.feature_flags;
uint64_t oop_flag = RTE_CRYPTODEV_FF_OOP_SGL_IN_LB_OUT;
- if (t->feature_mask && BLOCKCIPHER_TEST_FEATURE_OOP) {
+ if (t->feature_mask & BLOCKCIPHER_TEST_FEATURE_OOP) {
if (!(feat_flags & oop_flag)) {
printf("Device doesn't support out-of-place "
"scatter-gather in input mbuf. "
diff --git a/dpdk/test/test/test_flow_classify.c b/dpdk/test/test/test_flow_classify.c
index 90066713ed..b4ae229079 100644
--- a/dpdk/test/test/test_flow_classify.c
+++ b/dpdk/test/test/test_flow_classify.c
@@ -23,7 +23,7 @@
#define FLOW_CLASSIFY_MAX_RULE_NUM 100
#define MAX_PKT_BURST 32
-#define NB_SOCKETS 1
+#define NB_SOCKETS 4
#define MEMPOOL_CACHE_SIZE 256
#define MBUF_SIZE 512
#define NB_MBUF 512
diff --git a/dpdk/test/test/test_hash.c b/dpdk/test/test/test_hash.c
index fe607fadf2..ea711b1f10 100644
--- a/dpdk/test/test/test_hash.c
+++ b/dpdk/test/test/test_hash.c
@@ -1046,8 +1046,11 @@ fbk_hash_unit_test(void)
handle = rte_fbk_hash_create(&invalid_params_7);
RETURN_IF_ERROR_FBK(handle != NULL, "fbk hash creation should have failed");
- handle = rte_fbk_hash_create(&invalid_params_8);
- RETURN_IF_ERROR_FBK(handle != NULL, "fbk hash creation should have failed");
+ if (rte_eal_has_hugepages()) {
+ handle = rte_fbk_hash_create(&invalid_params_8);
+ RETURN_IF_ERROR_FBK(handle != NULL,
+ "fbk hash creation should have failed");
+ }
handle = rte_fbk_hash_create(&invalid_params_same_name_1);
RETURN_IF_ERROR_FBK(handle == NULL, "fbk hash creation should have succeeded");
diff --git a/dpdk/test/test/test_kvargs.c b/dpdk/test/test/test_kvargs.c
index a42056f361..2a2dae43a0 100644
--- a/dpdk/test/test/test_kvargs.c
+++ b/dpdk/test/test/test_kvargs.c
@@ -142,7 +142,7 @@ static int test_valid_kvargs(void)
valid_keys = valid_keys_list;
kvlist = rte_kvargs_parse(args, valid_keys);
if (kvlist == NULL) {
- printf("rte_kvargs_parse() error");
+ printf("rte_kvargs_parse() error\n");
goto fail;
}
if (strcmp(kvlist->pairs[0].value, "[0,1]") != 0) {
@@ -157,6 +157,40 @@ static int test_valid_kvargs(void)
}
rte_kvargs_free(kvlist);
+ /* test using empty string (it is valid) */
+ args = "";
+ kvlist = rte_kvargs_parse(args, NULL);
+ if (kvlist == NULL) {
+ printf("rte_kvargs_parse() error\n");
+ goto fail;
+ }
+ if (rte_kvargs_count(kvlist, NULL) != 0) {
+ printf("invalid count value\n");
+ goto fail;
+ }
+ rte_kvargs_free(kvlist);
+
+ /* test using empty elements (it is valid) */
+ args = "foo=1,,check=value2,,";
+ kvlist = rte_kvargs_parse(args, NULL);
+ if (kvlist == NULL) {
+ printf("rte_kvargs_parse() error\n");
+ goto fail;
+ }
+ if (rte_kvargs_count(kvlist, NULL) != 2) {
+ printf("invalid count value\n");
+ goto fail;
+ }
+ if (rte_kvargs_count(kvlist, "foo") != 1) {
+ printf("invalid count value for 'foo'\n");
+ goto fail;
+ }
+ if (rte_kvargs_count(kvlist, "check") != 1) {
+ printf("invalid count value for 'check'\n");
+ goto fail;
+ }
+ rte_kvargs_free(kvlist);
+
return 0;
fail:
@@ -179,11 +213,11 @@ static int test_invalid_kvargs(void)
const char *args_list[] = {
"wrong-key=x", /* key not in valid_keys_list */
"foo=1,foo=", /* empty value */
- "foo=1,,foo=2", /* empty key/value */
"foo=1,foo", /* no value */
"foo=1,=2", /* no key */
"foo=[1,2", /* no closing bracket in value */
",=", /* also test with a smiley */
+ "foo=[", /* no value in list and no closing bracket */
NULL };
const char **args;
const char *valid_keys_list[] = { "foo", "check", NULL };
@@ -197,8 +231,8 @@ static int test_invalid_kvargs(void)
rte_kvargs_free(kvlist);
goto fail;
}
- return 0;
}
+ return 0;
fail:
printf("while processing <%s>", *args);
diff --git a/dpdk/test/test/test_malloc.c b/dpdk/test/test/test_malloc.c
index 5e52724194..20788011ad 100644
--- a/dpdk/test/test/test_malloc.c
+++ b/dpdk/test/test/test_malloc.c
@@ -697,6 +697,18 @@ test_malloc_bad_params(void)
if (bad_ptr != NULL)
goto err_return;
+ /* rte_malloc expected to return null with size will cause overflow */
+ align = RTE_CACHE_LINE_SIZE;
+ size = (size_t)-8;
+
+ bad_ptr = rte_malloc(type, size, align);
+ if (bad_ptr != NULL)
+ goto err_return;
+
+ bad_ptr = rte_realloc(NULL, size, align);
+ if (bad_ptr != NULL)
+ goto err_return;
+
return 0;
err_return:
diff --git a/dpdk/test/test/test_pmd_perf.c b/dpdk/test/test/test_pmd_perf.c
index ed8524a176..d68f9599c7 100644
--- a/dpdk/test/test/test_pmd_perf.c
+++ b/dpdk/test/test/test_pmd_perf.c
@@ -142,7 +142,7 @@ check_all_ports_link_status(uint16_t port_num, uint32_t port_mask)
"Port%d Link Up. Speed %u Mbps - %s\n",
portid, link.link_speed,
(link.link_duplex == ETH_LINK_FULL_DUPLEX) ?
- ("full-duplex") : ("half-duplex\n"));
+ ("full-duplex") : ("half-duplex"));
if (link_mbps == 0)
link_mbps = link.link_speed;
} else
diff --git a/dpdk/test/test/test_table_pipeline.c b/dpdk/test/test/test_table_pipeline.c
index 441338ac01..bc412c3081 100644
--- a/dpdk/test/test/test_table_pipeline.c
+++ b/dpdk/test/test/test_table_pipeline.c
@@ -190,11 +190,13 @@ check_pipeline_invalid_params(void)
goto fail;
}
- p = rte_pipeline_create(&pipeline_params_3);
- if (p != NULL) {
- RTE_LOG(INFO, PIPELINE, "%s: Configure pipeline with invalid "
- "socket\n", __func__);
- goto fail;
+ if (rte_eal_has_hugepages()) {
+ p = rte_pipeline_create(&pipeline_params_3);
+ if (p != NULL) {
+ RTE_LOG(INFO, PIPELINE, "%s: Configure pipeline with "
+ "invalid socket\n", __func__);
+ goto fail;
+ }
}
/* Check pipeline consistency */
diff --git a/dpdk/usertools/dpdk-pmdinfo.py b/dpdk/usertools/dpdk-pmdinfo.py
index 9d5c6369a0..12f20735e0 100755
--- a/dpdk/usertools/dpdk-pmdinfo.py
+++ b/dpdk/usertools/dpdk-pmdinfo.py
@@ -561,7 +561,10 @@ def main(stream=None):
pcifile_default = "./pci.ids" # For unknown OS's assume local file
if platform.system() == 'Linux':
- pcifile_default = "/usr/share/hwdata/pci.ids"
+ # hwdata is the legacy location, misc is supported going forward
+ pcifile_default = "/usr/share/misc/pci.ids"
+ if not os.path.exists(pcifile_default):
+ pcifile_default = "/usr/share/hwdata/pci.ids"
elif platform.system() == 'FreeBSD':
pcifile_default = "/usr/local/share/pciids/pci.ids"
if not os.path.exists(pcifile_default):
diff --git a/include/linux/automake.mk b/include/linux/automake.mk
index b464fe0f5b..d757f7be3f 100644
--- a/include/linux/automake.mk
+++ b/include/linux/automake.mk
@@ -1,4 +1,5 @@
noinst_HEADERS += \
+ include/linux/netlink.h \
include/linux/pkt_cls.h \
include/linux/tc_act/tc_pedit.h \
include/linux/tc_act/tc_tunnel_key.h \
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
new file mode 100644
index 0000000000..cd558fb4c1
--- /dev/null
+++ b/include/linux/netlink.h
@@ -0,0 +1,30 @@
+#ifndef __UAPI_LINUX_NETLINK_WRAPPER_H
+#define __UAPI_LINUX_NETLINK_WRAPPER_H 1
+
+#if !defined(__KERNEL__) && !defined(HAVE_NLA_BITFIELD32)
+
+#include <linux/types.h>
+
+/* Generic 32 bitflags attribute content sent to the kernel.
+ *
+ * The value is a bitmap that defines the values being set
+ * The selector is a bitmask that defines which value is legit
+ *
+ * Examples:
+ * value = 0x0, and selector = 0x1
+ * implies we are selecting bit 1 and we want to set its value to 0.
+ *
+ * value = 0x2, and selector = 0x2
+ * implies we are selecting bit 2 and we want to set its value to 1.
+ *
+ */
+struct nla_bitfield32 {
+ __u32 value;
+ __u32 selector;
+};
+
+#endif /* !__KERNEL__ && !HAVE_NLA_BITFIELD32 */
+
+#include_next <linux/netlink.h>
+
+#endif /* __UAPI_LINUX_NETLINK_WRAPPER_H */
diff --git a/include/linux/pkt_cls.h b/include/linux/pkt_cls.h
index 1384d71f95..c8066ace88 100644
--- a/include/linux/pkt_cls.h
+++ b/include/linux/pkt_cls.h
@@ -1,7 +1,7 @@
#ifndef __LINUX_PKT_CLS_WRAPPER_H
#define __LINUX_PKT_CLS_WRAPPER_H 1
-#if defined(__KERNEL__) || defined(HAVE_TCA_FLOWER_KEY_ENC_IP_TTL_MASK)
+#if defined(__KERNEL__) || defined(HAVE_TCA_ACT_FLAGS)
#include_next <linux/pkt_cls.h>
#else
@@ -17,9 +17,14 @@ enum {
TCA_ACT_STATS,
TCA_ACT_PAD,
TCA_ACT_COOKIE,
+ TCA_ACT_FLAGS,
__TCA_ACT_MAX
};
+#define TCA_ACT_FLAGS_NO_PERCPU_STATS 1 /* Don't use percpu allocator for
+ * actions stats.
+ */
+
#define TCA_ACT_MAX __TCA_ACT_MAX
#define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
#define TCA_ACT_MAX_PRIO 32
@@ -64,7 +69,9 @@ struct tcf_t {
__u64 install;
__u64 lastuse;
__u64 expires;
+#ifdef HAVE_STRUCT_TCF_T_FIRSTUSE
__u64 firstuse;
+#endif
};
#define tc_gen \
diff --git a/include/openvswitch/ofp-actions.h b/include/openvswitch/ofp-actions.h
index 14c5eab74b..436c4aadf5 100644
--- a/include/openvswitch/ofp-actions.h
+++ b/include/openvswitch/ofp-actions.h
@@ -123,6 +123,8 @@ struct vl_mff_map;
OFPACT(NAT, ofpact_nat, ofpact, "nat") \
OFPACT(OUTPUT_TRUNC, ofpact_output_trunc,ofpact, "output_trunc") \
OFPACT(CLONE, ofpact_nest, actions, "clone") \
+ OFPACT(CHECK_PKT_LARGER, ofpact_check_pkt_larger, ofpact, \
+ "check_pkt_larger") \
\
/* Debugging actions. \
* \
@@ -225,6 +227,13 @@ ofpact_last(const struct ofpact *a, const struct ofpact *ofpacts,
return ofpact_next(a) == ofpact_end(ofpacts, ofpact_len);
}
+static inline size_t
+ofpact_remaining_len(const struct ofpact *a, const struct ofpact *ofpacts,
+ size_t ofpact_len)
+{
+ return ofpact_len - ((uint8_t *)a - (uint8_t *)ofpacts);
+}
+
static inline const struct ofpact *
ofpact_find_type_flattened(const struct ofpact *a, enum ofpact_type type,
const struct ofpact * const end)
@@ -620,6 +629,16 @@ struct ofpact_meter {
);
};
+/* OFPACT_CHECK_PKT_LARGER.
+ *
+ * Used for NXAST_CHECK_PKT_LARGER. */
+struct ofpact_check_pkt_larger {
+ OFPACT_PADDED_MEMBERS(
+ struct ofpact ofpact;
+ struct mf_subfield dst;
+ uint16_t pkt_len;
+ );
+};
/* OFPACT_WRITE_ACTIONS, OFPACT_CLONE.
*
* Used for OFPIT11_WRITE_ACTIONS, NXAST_CLONE. */
diff --git a/include/openvswitch/ofp-packet.h b/include/openvswitch/ofp-packet.h
index 67001cb3f5..77128d829b 100644
--- a/include/openvswitch/ofp-packet.h
+++ b/include/openvswitch/ofp-packet.h
@@ -140,6 +140,9 @@ struct ofputil_packet_in_private {
/* NXCPT_ACTION_SET. */
struct ofpact *action_set;
size_t action_set_len;
+
+ /* NXCPT_ODP_PORT. */
+ odp_port_t odp_port;
};
struct ofpbuf *ofputil_encode_packet_in_private(
diff --git a/include/sparse/automake.mk b/include/sparse/automake.mk
index 985ee6a2fc..445b627dd0 100644
--- a/include/sparse/automake.mk
+++ b/include/sparse/automake.mk
@@ -1,7 +1,6 @@
noinst_HEADERS += \
include/sparse/rte_byteorder.h \
include/sparse/rte_esp.h \
- include/sparse/rte_flow.h \
include/sparse/rte_icmp.h \
include/sparse/rte_ip.h \
include/sparse/rte_sctp.h \
diff --git a/include/sparse/rte_flow.h b/include/sparse/rte_flow.h
deleted file mode 100644
index a36ab45e7c..0000000000
--- a/include/sparse/rte_flow.h
+++ /dev/null
@@ -1,1483 +0,0 @@
-/*-
- * BSD LICENSE
- *
- * Copyright 2016 6WIND S.A.
- * Copyright 2016 Mellanox.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of 6WIND S.A. nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef __CHECKER__
-#error "Use this header only with sparse. It is not a correct implementation."
-#endif
-
-#ifndef RTE_FLOW_H_
-#define RTE_FLOW_H_
-
-/**
- * @file
- * RTE generic flow API
- *
- * This interface provides the ability to program packet matching and
- * associated actions in hardware through flow rules.
- */
-
-#include <rte_arp.h>
-#include <rte_ether.h>
-#include <rte_icmp.h>
-#include <rte_ip.h>
-#include <rte_sctp.h>
-#include <rte_tcp.h>
-#include <rte_udp.h>
-#include <rte_byteorder.h>
-#include <rte_esp.h>
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-/**
- * Flow rule attributes.
- *
- * Priorities are set on two levels: per group and per rule within groups.
- *
- * Lower values denote higher priority, the highest priority for both levels
- * is 0, so that a rule with priority 0 in group 8 is always matched after a
- * rule with priority 8 in group 0.
- *
- * Although optional, applications are encouraged to group similar rules as
- * much as possible to fully take advantage of hardware capabilities
- * (e.g. optimized matching) and work around limitations (e.g. a single
- * pattern type possibly allowed in a given group).
- *
- * Group and priority levels are arbitrary and up to the application, they
- * do not need to be contiguous nor start from 0, however the maximum number
- * varies between devices and may be affected by existing flow rules.
- *
- * If a packet is matched by several rules of a given group for a given
- * priority level, the outcome is undefined. It can take any path, may be
- * duplicated or even cause unrecoverable errors.
- *
- * Note that support for more than a single group and priority level is not
- * guaranteed.
- *
- * Flow rules can apply to inbound and/or outbound traffic (ingress/egress).
- *
- * Several pattern items and actions are valid and can be used in both
- * directions. Those valid for only one direction are described as such.
- *
- * At least one direction must be specified.
- *
- * Specifying both directions at once for a given rule is not recommended
- * but may be valid in a few cases (e.g. shared counter).
- */
-struct rte_flow_attr {
- uint32_t group; /**< Priority group. */
- uint32_t priority; /**< Priority level within group. */
- uint32_t ingress:1; /**< Rule applies to ingress traffic. */
- uint32_t egress:1; /**< Rule applies to egress traffic. */
- uint32_t reserved:30; /**< Reserved, must be zero. */
-};
-
-/**
- * Matching pattern item types.
- *
- * Pattern items fall in two categories:
- *
- * - Matching protocol headers and packet data (ANY, RAW, ETH, VLAN, IPV4,
- * IPV6, ICMP, UDP, TCP, SCTP, VXLAN and so on), usually associated with a
- * specification structure. These must be stacked in the same order as the
- * protocol layers to match, starting from the lowest.
- *
- * - Matching meta-data or affecting pattern processing (END, VOID, INVERT,
- * PF, VF, PORT and so on), often without a specification structure. Since
- * they do not match packet contents, these can be specified anywhere
- * within item lists without affecting others.
- *
- * See the description of individual types for more information. Those
- * marked with [META] fall into the second category.
- */
-enum rte_flow_item_type {
- /**
- * [META]
- *
- * End marker for item lists. Prevents further processing of items,
- * thereby ending the pattern.
- *
- * No associated specification structure.
- */
- RTE_FLOW_ITEM_TYPE_END,
-
- /**
- * [META]
- *
- * Used as a placeholder for convenience. It is ignored and simply
- * discarded by PMDs.
- *
- * No associated specification structure.
- */
- RTE_FLOW_ITEM_TYPE_VOID,
-
- /**
- * [META]
- *
- * Inverted matching, i.e. process packets that do not match the
- * pattern.
- *
- * No associated specification structure.
- */
- RTE_FLOW_ITEM_TYPE_INVERT,
-
- /**
- * Matches any protocol in place of the current layer, a single ANY
- * may also stand for several protocol layers.
- *
- * See struct rte_flow_item_any.
- */
- RTE_FLOW_ITEM_TYPE_ANY,
-
- /**
- * [META]
- *
- * Matches packets addressed to the physical function of the device.
- *
- * If the underlying device function differs from the one that would
- * normally receive the matched traffic, specifying this item
- * prevents it from reaching that device unless the flow rule
- * contains a PF action. Packets are not duplicated between device
- * instances by default.
- *
- * No associated specification structure.
- */
- RTE_FLOW_ITEM_TYPE_PF,
-
- /**
- * [META]
- *
- * Matches packets addressed to a virtual function ID of the device.
- *
- * If the underlying device function differs from the one that would
- * normally receive the matched traffic, specifying this item
- * prevents it from reaching that device unless the flow rule
- * contains a VF action. Packets are not duplicated between device
- * instances by default.
- *
- * See struct rte_flow_item_vf.
- */
- RTE_FLOW_ITEM_TYPE_VF,
-
- /**
- * [META]
- *
- * Matches packets coming from the specified physical port of the
- * underlying device.
- *
- * The first PORT item overrides the physical port normally
- * associated with the specified DPDK input port (port_id). This
- * item can be provided several times to match additional physical
- * ports.
- *
- * See struct rte_flow_item_port.
- */
- RTE_FLOW_ITEM_TYPE_PORT,
-
- /**
- * Matches a byte string of a given length at a given offset.
- *
- * See struct rte_flow_item_raw.
- */
- RTE_FLOW_ITEM_TYPE_RAW,
-
- /**
- * Matches an Ethernet header.
- *
- * See struct rte_flow_item_eth.
- */
- RTE_FLOW_ITEM_TYPE_ETH,
-
- /**
- * Matches an 802.1Q/ad VLAN tag.
- *
- * See struct rte_flow_item_vlan.
- */
- RTE_FLOW_ITEM_TYPE_VLAN,
-
- /**
- * Matches an IPv4 header.
- *
- * See struct rte_flow_item_ipv4.
- */
- RTE_FLOW_ITEM_TYPE_IPV4,
-
- /**
- * Matches an IPv6 header.
- *
- * See struct rte_flow_item_ipv6.
- */
- RTE_FLOW_ITEM_TYPE_IPV6,
-
- /**
- * Matches an ICMP header.
- *
- * See struct rte_flow_item_icmp.
- */
- RTE_FLOW_ITEM_TYPE_ICMP,
-
- /**
- * Matches a UDP header.
- *
- * See struct rte_flow_item_udp.
- */
- RTE_FLOW_ITEM_TYPE_UDP,
-
- /**
- * Matches a TCP header.
- *
- * See struct rte_flow_item_tcp.
- */
- RTE_FLOW_ITEM_TYPE_TCP,
-
- /**
- * Matches a SCTP header.
- *
- * See struct rte_flow_item_sctp.
- */
- RTE_FLOW_ITEM_TYPE_SCTP,
-
- /**
- * Matches a VXLAN header.
- *
- * See struct rte_flow_item_vxlan.
- */
- RTE_FLOW_ITEM_TYPE_VXLAN,
-
- /**
- * Matches a E_TAG header.
- *
- * See struct rte_flow_item_e_tag.
- */
- RTE_FLOW_ITEM_TYPE_E_TAG,
-
- /**
- * Matches a NVGRE header.
- *
- * See struct rte_flow_item_nvgre.
- */
- RTE_FLOW_ITEM_TYPE_NVGRE,
-
- /**
- * Matches a MPLS header.
- *
- * See struct rte_flow_item_mpls.
- */
- RTE_FLOW_ITEM_TYPE_MPLS,
-
- /**
- * Matches a GRE header.
- *
- * See struct rte_flow_item_gre.
- */
- RTE_FLOW_ITEM_TYPE_GRE,
-
- /**
- * [META]
- *
- * Fuzzy pattern match, expect faster than default.
- *
- * This is for device that support fuzzy matching option.
- * Usually a fuzzy matching is fast but the cost is accuracy.
- *
- * See struct rte_flow_item_fuzzy.
- */
- RTE_FLOW_ITEM_TYPE_FUZZY,
-
- /**
- * Matches a GTP header.
- *
- * Configure flow for GTP packets.
- *
- * See struct rte_flow_item_gtp.
- */
- RTE_FLOW_ITEM_TYPE_GTP,
-
- /**
- * Matches a GTP header.
- *
- * Configure flow for GTP-C packets.
- *
- * See struct rte_flow_item_gtp.
- */
- RTE_FLOW_ITEM_TYPE_GTPC,
-
- /**
- * Matches a GTP header.
- *
- * Configure flow for GTP-U packets.
- *
- * See struct rte_flow_item_gtp.
- */
- RTE_FLOW_ITEM_TYPE_GTPU,
-
- /**
- * Matches a ESP header.
- *
- * See struct rte_flow_item_esp.
- */
- RTE_FLOW_ITEM_TYPE_ESP,
-};
-
-/**
- * RTE_FLOW_ITEM_TYPE_ANY
- *
- * Matches any protocol in place of the current layer, a single ANY may also
- * stand for several protocol layers.
- *
- * This is usually specified as the first pattern item when looking for a
- * protocol anywhere in a packet.
- *
- * A zeroed mask stands for any number of layers.
- */
-struct rte_flow_item_any {
- uint32_t num; /**< Number of layers covered. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_ANY. */
-#ifndef __cplusplus
-static const struct rte_flow_item_any rte_flow_item_any_mask = {
- .num = 0x00000000,
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_VF
- *
- * Matches packets addressed to a virtual function ID of the device.
- *
- * If the underlying device function differs from the one that would
- * normally receive the matched traffic, specifying this item prevents it
- * from reaching that device unless the flow rule contains a VF
- * action. Packets are not duplicated between device instances by default.
- *
- * - Likely to return an error or never match any traffic if this causes a
- * VF device to match traffic addressed to a different VF.
- * - Can be specified multiple times to match traffic addressed to several
- * VF IDs.
- * - Can be combined with a PF item to match both PF and VF traffic.
- *
- * A zeroed mask can be used to match any VF ID.
- */
-struct rte_flow_item_vf {
- uint32_t id; /**< Destination VF ID. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_VF. */
-#ifndef __cplusplus
-static const struct rte_flow_item_vf rte_flow_item_vf_mask = {
- .id = 0x00000000,
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_PORT
- *
- * Matches packets coming from the specified physical port of the underlying
- * device.
- *
- * The first PORT item overrides the physical port normally associated with
- * the specified DPDK input port (port_id). This item can be provided
- * several times to match additional physical ports.
- *
- * Note that physical ports are not necessarily tied to DPDK input ports
- * (port_id) when those are not under DPDK control. Possible values are
- * specific to each device, they are not necessarily indexed from zero and
- * may not be contiguous.
- *
- * As a device property, the list of allowed values as well as the value
- * associated with a port_id should be retrieved by other means.
- *
- * A zeroed mask can be used to match any port index.
- */
-struct rte_flow_item_port {
- uint32_t index; /**< Physical port index. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_PORT. */
-#ifndef __cplusplus
-static const struct rte_flow_item_port rte_flow_item_port_mask = {
- .index = 0x00000000,
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_RAW
- *
- * Matches a byte string of a given length at a given offset.
- *
- * Offset is either absolute (using the start of the packet) or relative to
- * the end of the previous matched item in the stack, in which case negative
- * values are allowed.
- *
- * If search is enabled, offset is used as the starting point. The search
- * area can be delimited by setting limit to a nonzero value, which is the
- * maximum number of bytes after offset where the pattern may start.
- *
- * Matching a zero-length pattern is allowed, doing so resets the relative
- * offset for subsequent items.
- *
- * This type does not support ranges (struct rte_flow_item.last).
- */
-struct rte_flow_item_raw {
- uint32_t relative:1; /**< Look for pattern after the previous item. */
- uint32_t search:1; /**< Search pattern from offset (see also limit). */
- uint32_t reserved:30; /**< Reserved, must be set to zero. */
- int32_t offset; /**< Absolute or relative offset for pattern. */
- uint16_t limit; /**< Search area limit for start of pattern. */
- uint16_t length; /**< Pattern length. */
- uint8_t pattern[]; /**< Byte string to look for. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_RAW. */
-#ifndef __cplusplus
-static const struct rte_flow_item_raw rte_flow_item_raw_mask = {
- .relative = 1,
- .search = 1,
- .reserved = 0x3fffffff,
- .offset = 0xffffffff,
- .limit = 0xffff,
- .length = 0xffff,
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_ETH
- *
- * Matches an Ethernet header.
- */
-struct rte_flow_item_eth {
- struct ether_addr dst; /**< Destination MAC. */
- struct ether_addr src; /**< Source MAC. */
- rte_be16_t type; /**< EtherType. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_ETH. */
-#ifndef __cplusplus
-static const struct rte_flow_item_eth rte_flow_item_eth_mask = {
- .dst.addr_bytes = "\xff\xff\xff\xff\xff\xff",
- .src.addr_bytes = "\xff\xff\xff\xff\xff\xff",
- .type = RTE_BE16(0x0000),
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_VLAN
- *
- * Matches an 802.1Q/ad VLAN tag.
- *
- * This type normally follows either RTE_FLOW_ITEM_TYPE_ETH or
- * RTE_FLOW_ITEM_TYPE_VLAN.
- */
-struct rte_flow_item_vlan {
- rte_be16_t tpid; /**< Tag protocol identifier. */
- rte_be16_t tci; /**< Tag control information. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_VLAN. */
-#ifndef __cplusplus
-static const struct rte_flow_item_vlan rte_flow_item_vlan_mask = {
- .tpid = RTE_BE16(0x0000),
- .tci = RTE_BE16(0xffff),
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_IPV4
- *
- * Matches an IPv4 header.
- *
- * Note: IPv4 options are handled by dedicated pattern items.
- */
-struct rte_flow_item_ipv4 {
- struct ipv4_hdr hdr; /**< IPv4 header definition. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_IPV4. */
-#ifndef __cplusplus
-static const struct rte_flow_item_ipv4 rte_flow_item_ipv4_mask = {
- .hdr = {
- .src_addr = RTE_BE32(0xffffffff),
- .dst_addr = RTE_BE32(0xffffffff),
- },
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_IPV6.
- *
- * Matches an IPv6 header.
- *
- * Note: IPv6 options are handled by dedicated pattern items.
- */
-struct rte_flow_item_ipv6 {
- struct ipv6_hdr hdr; /**< IPv6 header definition. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_IPV6. */
-#ifndef __cplusplus
-static const struct rte_flow_item_ipv6 rte_flow_item_ipv6_mask = {
- .hdr = {
- .src_addr =
- "\xff\xff\xff\xff\xff\xff\xff\xff"
- "\xff\xff\xff\xff\xff\xff\xff\xff",
- .dst_addr =
- "\xff\xff\xff\xff\xff\xff\xff\xff"
- "\xff\xff\xff\xff\xff\xff\xff\xff",
- },
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_ICMP.
- *
- * Matches an ICMP header.
- */
-struct rte_flow_item_icmp {
- struct icmp_hdr hdr; /**< ICMP header definition. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_ICMP. */
-#ifndef __cplusplus
-static const struct rte_flow_item_icmp rte_flow_item_icmp_mask = {
- .hdr = {
- .icmp_type = 0xff,
- .icmp_code = 0xff,
- },
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_UDP.
- *
- * Matches a UDP header.
- */
-struct rte_flow_item_udp {
- struct udp_hdr hdr; /**< UDP header definition. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_UDP. */
-#ifndef __cplusplus
-static const struct rte_flow_item_udp rte_flow_item_udp_mask = {
- .hdr = {
- .src_port = RTE_BE16(0xffff),
- .dst_port = RTE_BE16(0xffff),
- },
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_TCP.
- *
- * Matches a TCP header.
- */
-struct rte_flow_item_tcp {
- struct tcp_hdr hdr; /**< TCP header definition. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_TCP. */
-#ifndef __cplusplus
-static const struct rte_flow_item_tcp rte_flow_item_tcp_mask = {
- .hdr = {
- .src_port = RTE_BE16(0xffff),
- .dst_port = RTE_BE16(0xffff),
- },
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_SCTP.
- *
- * Matches a SCTP header.
- */
-struct rte_flow_item_sctp {
- struct sctp_hdr hdr; /**< SCTP header definition. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_SCTP. */
-#ifndef __cplusplus
-static const struct rte_flow_item_sctp rte_flow_item_sctp_mask = {
- .hdr = {
- .src_port = RTE_BE16(0xffff),
- .dst_port = RTE_BE16(0xffff),
- },
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_VXLAN.
- *
- * Matches a VXLAN header (RFC 7348).
- */
-struct rte_flow_item_vxlan {
- uint8_t flags; /**< Normally 0x08 (I flag). */
- uint8_t rsvd0[3]; /**< Reserved, normally 0x000000. */
- uint8_t vni[3]; /**< VXLAN identifier. */
- uint8_t rsvd1; /**< Reserved, normally 0x00. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_VXLAN. */
-#ifndef __cplusplus
-static const struct rte_flow_item_vxlan rte_flow_item_vxlan_mask = {
- .vni = "\xff\xff\xff",
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_E_TAG.
- *
- * Matches a E-tag header.
- */
-struct rte_flow_item_e_tag {
- rte_be16_t tpid; /**< Tag protocol identifier (0x893F). */
- /**
- * E-Tag control information (E-TCI).
- * E-PCP (3b), E-DEI (1b), ingress E-CID base (12b).
- */
- rte_be16_t epcp_edei_in_ecid_b;
- /** Reserved (2b), GRP (2b), E-CID base (12b). */
- rte_be16_t rsvd_grp_ecid_b;
- uint8_t in_ecid_e; /**< Ingress E-CID ext. */
- uint8_t ecid_e; /**< E-CID ext. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_E_TAG. */
-#ifndef __cplusplus
-static const struct rte_flow_item_e_tag rte_flow_item_e_tag_mask = {
- .rsvd_grp_ecid_b = RTE_BE16(0x3fff),
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_NVGRE.
- *
- * Matches a NVGRE header.
- */
-struct rte_flow_item_nvgre {
- /**
- * Checksum (1b), undefined (1b), key bit (1b), sequence number (1b),
- * reserved 0 (9b), version (3b).
- *
- * c_k_s_rsvd0_ver must have value 0x2000 according to RFC 7637.
- */
- rte_be16_t c_k_s_rsvd0_ver;
- rte_be16_t protocol; /**< Protocol type (0x6558). */
- uint8_t tni[3]; /**< Virtual subnet ID. */
- uint8_t flow_id; /**< Flow ID. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_NVGRE. */
-#ifndef __cplusplus
-static const struct rte_flow_item_nvgre rte_flow_item_nvgre_mask = {
- .tni = "\xff\xff\xff",
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_MPLS.
- *
- * Matches a MPLS header.
- */
-struct rte_flow_item_mpls {
- /**
- * Label (20b), TC (3b), Bottom of Stack (1b).
- */
- uint8_t label_tc_s[3];
- uint8_t ttl; /** Time-to-Live. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_MPLS. */
-#ifndef __cplusplus
-static const struct rte_flow_item_mpls rte_flow_item_mpls_mask = {
- .label_tc_s = "\xff\xff\xf0",
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_GRE.
- *
- * Matches a GRE header.
- */
-struct rte_flow_item_gre {
- /**
- * Checksum (1b), reserved 0 (12b), version (3b).
- * Refer to RFC 2784.
- */
- rte_be16_t c_rsvd0_ver;
- rte_be16_t protocol; /**< Protocol type. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_GRE. */
-#ifndef __cplusplus
-static const struct rte_flow_item_gre rte_flow_item_gre_mask = {
- .protocol = RTE_BE16(0xffff),
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_FUZZY
- *
- * Fuzzy pattern match, expect faster than default.
- *
- * This is for device that support fuzzy match option.
- * Usually a fuzzy match is fast but the cost is accuracy.
- * i.e. Signature Match only match pattern's hash value, but it is
- * possible two different patterns have the same hash value.
- *
- * Matching accuracy level can be configure by threshold.
- * Driver can divide the range of threshold and map to different
- * accuracy levels that device support.
- *
- * Threshold 0 means perfect match (no fuzziness), while threshold
- * 0xffffffff means fuzziest match.
- */
-struct rte_flow_item_fuzzy {
- uint32_t thresh; /**< Accuracy threshold. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_FUZZY. */
-#ifndef __cplusplus
-static const struct rte_flow_item_fuzzy rte_flow_item_fuzzy_mask = {
- .thresh = 0xffffffff,
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_GTP.
- *
- * Matches a GTPv1 header.
- */
-struct rte_flow_item_gtp {
- /**
- * Version (3b), protocol type (1b), reserved (1b),
- * Extension header flag (1b),
- * Sequence number flag (1b),
- * N-PDU number flag (1b).
- */
- uint8_t v_pt_rsv_flags;
- uint8_t msg_type; /**< Message type. */
- rte_be16_t msg_len; /**< Message length. */
- rte_be32_t teid; /**< Tunnel endpoint identifier. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_GTP. */
-#ifndef __cplusplus
-static const struct rte_flow_item_gtp rte_flow_item_gtp_mask = {
- .teid = RTE_BE32(0xffffffff),
-};
-#endif
-
-/**
- * RTE_FLOW_ITEM_TYPE_ESP
- *
- * Matches an ESP header.
- */
-struct rte_flow_item_esp {
- struct esp_hdr hdr; /**< ESP header definition. */
-};
-
-/** Default mask for RTE_FLOW_ITEM_TYPE_ESP. */
-#ifndef __cplusplus
-static const struct rte_flow_item_esp rte_flow_item_esp_mask = {
- .hdr = {
- .spi = OVS_BE32_MAX,
- },
-};
-#endif
-
-/**
- * Matching pattern item definition.
- *
- * A pattern is formed by stacking items starting from the lowest protocol
- * layer to match. This stacking restriction does not apply to meta items
- * which can be placed anywhere in the stack without affecting the meaning
- * of the resulting pattern.
- *
- * Patterns are terminated by END items.
- *
- * The spec field should be a valid pointer to a structure of the related
- * item type. It may remain unspecified (NULL) in many cases to request
- * broad (nonspecific) matching. In such cases, last and mask must also be
- * set to NULL.
- *
- * Optionally, last can point to a structure of the same type to define an
- * inclusive range. This is mostly supported by integer and address fields,
- * may cause errors otherwise. Fields that do not support ranges must be set
- * to 0 or to the same value as the corresponding fields in spec.
- *
- * Only the fields defined to nonzero values in the default masks (see
- * rte_flow_item_{name}_mask constants) are considered relevant by
- * default. This can be overridden by providing a mask structure of the
- * same type with applicable bits set to one. It can also be used to
- * partially filter out specific fields (e.g. as an alternate mean to match
- * ranges of IP addresses).
- *
- * Mask is a simple bit-mask applied before interpreting the contents of
- * spec and last, which may yield unexpected results if not used
- * carefully. For example, if for an IPv4 address field, spec provides
- * 10.1.2.3, last provides 10.3.4.5 and mask provides 255.255.0.0, the
- * effective range becomes 10.1.0.0 to 10.3.255.255.
- */
-struct rte_flow_item {
- enum rte_flow_item_type type; /**< Item type. */
- const void *spec; /**< Pointer to item specification structure. */
- const void *last; /**< Defines an inclusive range (spec to last). */
- const void *mask; /**< Bit-mask applied to spec and last. */
-};
-
-/**
- * Action types.
- *
- * Each possible action is represented by a type. Some have associated
- * configuration structures. Several actions combined in a list can be
- * affected to a flow rule. That list is not ordered.
- *
- * They fall in three categories:
- *
- * - Terminating actions (such as QUEUE, DROP, RSS, PF, VF) that prevent
- * processing matched packets by subsequent flow rules, unless overridden
- * with PASSTHRU.
- *
- * - Non terminating actions (PASSTHRU, DUP) that leave matched packets up
- * for additional processing by subsequent flow rules.
- *
- * - Other non terminating meta actions that do not affect the fate of
- * packets (END, VOID, MARK, FLAG, COUNT).
- *
- * When several actions are combined in a flow rule, they should all have
- * different types (e.g. dropping a packet twice is not possible).
- *
- * Only the last action of a given type is taken into account. PMDs still
- * perform error checking on the entire list.
- *
- * Note that PASSTHRU is the only action able to override a terminating
- * rule.
- */
-enum rte_flow_action_type {
- /**
- * [META]
- *
- * End marker for action lists. Prevents further processing of
- * actions, thereby ending the list.
- *
- * No associated configuration structure.
- */
- RTE_FLOW_ACTION_TYPE_END,
-
- /**
- * [META]
- *
- * Used as a placeholder for convenience. It is ignored and simply
- * discarded by PMDs.
- *
- * No associated configuration structure.
- */
- RTE_FLOW_ACTION_TYPE_VOID,
-
- /**
- * Leaves packets up for additional processing by subsequent flow
- * rules. This is the default when a rule does not contain a
- * terminating action, but can be specified to force a rule to
- * become non-terminating.
- *
- * No associated configuration structure.
- */
- RTE_FLOW_ACTION_TYPE_PASSTHRU,
-
- /**
- * [META]
- *
- * Attaches an integer value to packets and sets PKT_RX_FDIR and
- * PKT_RX_FDIR_ID mbuf flags.
- *
- * See struct rte_flow_action_mark.
- */
- RTE_FLOW_ACTION_TYPE_MARK,
-
- /**
- * [META]
- *
- * Flags packets. Similar to MARK without a specific value; only
- * sets the PKT_RX_FDIR mbuf flag.
- *
- * No associated configuration structure.
- */
- RTE_FLOW_ACTION_TYPE_FLAG,
-
- /**
- * Assigns packets to a given queue index.
- *
- * See struct rte_flow_action_queue.
- */
- RTE_FLOW_ACTION_TYPE_QUEUE,
-
- /**
- * Drops packets.
- *
- * PASSTHRU overrides this action if both are specified.
- *
- * No associated configuration structure.
- */
- RTE_FLOW_ACTION_TYPE_DROP,
-
- /**
- * [META]
- *
- * Enables counters for this rule.
- *
- * These counters can be retrieved and reset through rte_flow_query(),
- * see struct rte_flow_query_count.
- *
- * No associated configuration structure.
- */
- RTE_FLOW_ACTION_TYPE_COUNT,
-
- /**
- * Duplicates packets to a given queue index.
- *
- * This is normally combined with QUEUE, however when used alone, it
- * is actually similar to QUEUE + PASSTHRU.
- *
- * See struct rte_flow_action_dup.
- */
- RTE_FLOW_ACTION_TYPE_DUP,
-
- /**
- * Similar to QUEUE, except RSS is additionally performed on packets
- * to spread them among several queues according to the provided
- * parameters.
- *
- * See struct rte_flow_action_rss.
- */
- RTE_FLOW_ACTION_TYPE_RSS,
-
- /**
- * Redirects packets to the physical function (PF) of the current
- * device.
- *
- * No associated configuration structure.
- */
- RTE_FLOW_ACTION_TYPE_PF,
-
- /**
- * Redirects packets to the virtual function (VF) of the current
- * device with the specified ID.
- *
- * See struct rte_flow_action_vf.
- */
- RTE_FLOW_ACTION_TYPE_VF,
-
- /**
- * Traffic metering and policing (MTR).
- *
- * See struct rte_flow_action_meter.
- * See file rte_mtr.h for MTR object configuration.
- */
- RTE_FLOW_ACTION_TYPE_METER,
-
- /**
- * Redirects packets to security engine of current device for security
- * processing as specified by security session.
- *
- * See struct rte_flow_action_security.
- */
- RTE_FLOW_ACTION_TYPE_SECURITY
-};
-
-/**
- * RTE_FLOW_ACTION_TYPE_MARK
- *
- * Attaches an integer value to packets and sets PKT_RX_FDIR and
- * PKT_RX_FDIR_ID mbuf flags.
- *
- * This value is arbitrary and application-defined. Maximum allowed value
- * depends on the underlying implementation. It is returned in the
- * hash.fdir.hi mbuf field.
- */
-struct rte_flow_action_mark {
- uint32_t id; /**< Integer value to return with packets. */
-};
-
-/**
- * RTE_FLOW_ACTION_TYPE_QUEUE
- *
- * Assign packets to a given queue index.
- *
- * Terminating by default.
- */
-struct rte_flow_action_queue {
- uint16_t index; /**< Queue index to use. */
-};
-
-/**
- * RTE_FLOW_ACTION_TYPE_COUNT (query)
- *
- * Query structure to retrieve and reset flow rule counters.
- */
-struct rte_flow_query_count {
- uint32_t reset:1; /**< Reset counters after query [in]. */
- uint32_t hits_set:1; /**< hits field is set [out]. */
- uint32_t bytes_set:1; /**< bytes field is set [out]. */
- uint32_t reserved:29; /**< Reserved, must be zero [in, out]. */
- uint64_t hits; /**< Number of hits for this rule [out]. */
- uint64_t bytes; /**< Number of bytes through this rule [out]. */
-};
-
-/**
- * RTE_FLOW_ACTION_TYPE_DUP
- *
- * Duplicates packets to a given queue index.
- *
- * This is normally combined with QUEUE, however when used alone, it is
- * actually similar to QUEUE + PASSTHRU.
- *
- * Non-terminating by default.
- */
-struct rte_flow_action_dup {
- uint16_t index; /**< Queue index to duplicate packets to. */
-};
-
-/**
- * RTE_FLOW_ACTION_TYPE_RSS
- *
- * Similar to QUEUE, except RSS is additionally performed on packets to
- * spread them among several queues according to the provided parameters.
- *
- * Note: RSS hash result is stored in the hash.rss mbuf field which overlaps
- * hash.fdir.lo. Since the MARK action sets the hash.fdir.hi field only,
- * both can be requested simultaneously.
- *
- * Terminating by default.
- */
-struct rte_flow_action_rss {
- const struct rte_eth_rss_conf *rss_conf; /**< RSS parameters. */
- uint16_t num; /**< Number of entries in queue[]. */
- uint16_t queue[]; /**< Queues indices to use. */
-};
-
-/**
- * RTE_FLOW_ACTION_TYPE_VF
- *
- * Redirects packets to a virtual function (VF) of the current device.
- *
- * Packets matched by a VF pattern item can be redirected to their original
- * VF ID instead of the specified one. This parameter may not be available
- * and is not guaranteed to work properly if the VF part is matched by a
- * prior flow rule or if packets are not addressed to a VF in the first
- * place.
- *
- * Terminating by default.
- */
-struct rte_flow_action_vf {
- uint32_t original:1; /**< Use original VF ID if possible. */
- uint32_t reserved:31; /**< Reserved, must be zero. */
- uint32_t id; /**< VF ID to redirect packets to. */
-};
-
-/**
- * RTE_FLOW_ACTION_TYPE_METER
- *
- * Traffic metering and policing (MTR).
- *
- * Packets matched by items of this type can be either dropped or passed to the
- * next item with their color set by the MTR object.
- *
- * Non-terminating by default.
- */
-struct rte_flow_action_meter {
- uint32_t mtr_id; /**< MTR object ID created with rte_mtr_create(). */
-};
-
-/**
- * RTE_FLOW_ACTION_TYPE_SECURITY
- *
- * Perform the security action on flows matched by the pattern items
- * according to the configuration of the security session.
- *
- * This action modifies the payload of matched flows. For INLINE_CRYPTO, the
- * security protocol headers and IV are fully provided by the application as
- * specified in the flow pattern. The payload of matching packets is
- * encrypted on egress, and decrypted and authenticated on ingress.
- * For INLINE_PROTOCOL, the security protocol is fully offloaded to HW,
- * providing full encapsulation and decapsulation of packets in security
- * protocols. The flow pattern specifies both the outer security header fields
- * and the inner packet fields. The security session specified in the action
- * must match the pattern parameters.
- *
- * The security session specified in the action must be created on the same
- * port as the flow action that is being specified.
- *
- * The ingress/egress flow attribute should match that specified in the
- * security session if the security session supports the definition of the
- * direction.
- *
- * Multiple flows can be configured to use the same security session.
- *
- * Non-terminating by default.
- */
-struct rte_flow_action_security {
- void *security_session; /**< Pointer to security session structure. */
-};
-
-/**
- * Definition of a single action.
- *
- * A list of actions is terminated by a END action.
- *
- * For simple actions without a configuration structure, conf remains NULL.
- */
-struct rte_flow_action {
- enum rte_flow_action_type type; /**< Action type. */
- const void *conf; /**< Pointer to action configuration structure. */
-};
-
-/**
- * Opaque type returned after successfully creating a flow.
- *
- * This handle can be used to manage and query the related flow (e.g. to
- * destroy it or retrieve counters).
- */
-struct rte_flow;
-
-/**
- * Verbose error types.
- *
- * Most of them provide the type of the object referenced by struct
- * rte_flow_error.cause.
- */
-enum rte_flow_error_type {
- RTE_FLOW_ERROR_TYPE_NONE, /**< No error. */
- RTE_FLOW_ERROR_TYPE_UNSPECIFIED, /**< Cause unspecified. */
- RTE_FLOW_ERROR_TYPE_HANDLE, /**< Flow rule (handle). */
- RTE_FLOW_ERROR_TYPE_ATTR_GROUP, /**< Group field. */
- RTE_FLOW_ERROR_TYPE_ATTR_PRIORITY, /**< Priority field. */
- RTE_FLOW_ERROR_TYPE_ATTR_INGRESS, /**< Ingress field. */
- RTE_FLOW_ERROR_TYPE_ATTR_EGRESS, /**< Egress field. */
- RTE_FLOW_ERROR_TYPE_ATTR, /**< Attributes structure. */
- RTE_FLOW_ERROR_TYPE_ITEM_NUM, /**< Pattern length. */
- RTE_FLOW_ERROR_TYPE_ITEM, /**< Specific pattern item. */
- RTE_FLOW_ERROR_TYPE_ACTION_NUM, /**< Number of actions. */
- RTE_FLOW_ERROR_TYPE_ACTION, /**< Specific action. */
-};
-
-/**
- * Verbose error structure definition.
- *
- * This object is normally allocated by applications and set by PMDs, the
- * message points to a constant string which does not need to be freed by
- * the application, however its pointer can be considered valid only as long
- * as its associated DPDK port remains configured. Closing the underlying
- * device or unloading the PMD invalidates it.
- *
- * Both cause and message may be NULL regardless of the error type.
- */
-struct rte_flow_error {
- enum rte_flow_error_type type; /**< Cause field and error types. */
- const void *cause; /**< Object responsible for the error. */
- const char *message; /**< Human-readable error message. */
-};
-
-/**
- * Check whether a flow rule can be created on a given port.
- *
- * The flow rule is validated for correctness and whether it could be accepted
- * by the device given sufficient resources. The rule is checked against the
- * current device mode and queue configuration. The flow rule may also
- * optionally be validated against existing flow rules and device resources.
- * This function has no effect on the target device.
- *
- * The returned value is guaranteed to remain valid only as long as no
- * successful calls to rte_flow_create() or rte_flow_destroy() are made in
- * the meantime and no device parameter affecting flow rules in any way are
- * modified, due to possible collisions or resource limitations (although in
- * such cases EINVAL should not be returned).
- *
- * @param port_id
- * Port identifier of Ethernet device.
- * @param[in] attr
- * Flow rule attributes.
- * @param[in] pattern
- * Pattern specification (list terminated by the END pattern item).
- * @param[in] actions
- * Associated actions (list terminated by the END action).
- * @param[out] error
- * Perform verbose error reporting if not NULL. PMDs initialize this
- * structure in case of error only.
- *
- * @return
- * 0 if flow rule is valid and can be created. A negative errno value
- * otherwise (rte_errno is also set), the following errors are defined:
- *
- * -ENOSYS: underlying device does not support this functionality.
- *
- * -EINVAL: unknown or invalid rule specification.
- *
- * -ENOTSUP: valid but unsupported rule specification (e.g. partial
- * bit-masks are unsupported).
- *
- * -EEXIST: collision with an existing rule. Only returned if device
- * supports flow rule collision checking and there was a flow rule
- * collision. Not receiving this return code is no guarantee that creating
- * the rule will not fail due to a collision.
- *
- * -ENOMEM: not enough memory to execute the function, or if the device
- * supports resource validation, resource limitation on the device.
- *
- * -EBUSY: action cannot be performed due to busy device resources, may
- * succeed if the affected queues or even the entire port are in a stopped
- * state (see rte_eth_dev_rx_queue_stop() and rte_eth_dev_stop()).
- */
-int
-rte_flow_validate(uint16_t port_id,
- const struct rte_flow_attr *attr,
- const struct rte_flow_item pattern[],
- const struct rte_flow_action actions[],
- struct rte_flow_error *error);
-
-/**
- * Create a flow rule on a given port.
- *
- * @param port_id
- * Port identifier of Ethernet device.
- * @param[in] attr
- * Flow rule attributes.
- * @param[in] pattern
- * Pattern specification (list terminated by the END pattern item).
- * @param[in] actions
- * Associated actions (list terminated by the END action).
- * @param[out] error
- * Perform verbose error reporting if not NULL. PMDs initialize this
- * structure in case of error only.
- *
- * @return
- * A valid handle in case of success, NULL otherwise and rte_errno is set
- * to the positive version of one of the error codes defined for
- * rte_flow_validate().
- */
-struct rte_flow *
-rte_flow_create(uint16_t port_id,
- const struct rte_flow_attr *attr,
- const struct rte_flow_item pattern[],
- const struct rte_flow_action actions[],
- struct rte_flow_error *error);
-
-/**
- * Destroy a flow rule on a given port.
- *
- * Failure to destroy a flow rule handle may occur when other flow rules
- * depend on it, and destroying it would result in an inconsistent state.
- *
- * This function is only guaranteed to succeed if handles are destroyed in
- * reverse order of their creation.
- *
- * @param port_id
- * Port identifier of Ethernet device.
- * @param flow
- * Flow rule handle to destroy.
- * @param[out] error
- * Perform verbose error reporting if not NULL. PMDs initialize this
- * structure in case of error only.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-rte_flow_destroy(uint16_t port_id,
- struct rte_flow *flow,
- struct rte_flow_error *error);
-
-/**
- * Destroy all flow rules associated with a port.
- *
- * In the unlikely event of failure, handles are still considered destroyed
- * and no longer valid but the port must be assumed to be in an inconsistent
- * state.
- *
- * @param port_id
- * Port identifier of Ethernet device.
- * @param[out] error
- * Perform verbose error reporting if not NULL. PMDs initialize this
- * structure in case of error only.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-rte_flow_flush(uint16_t port_id,
- struct rte_flow_error *error);
-
-/**
- * Query an existing flow rule.
- *
- * This function allows retrieving flow-specific data such as counters.
- * Data is gathered by special actions which must be present in the flow
- * rule definition.
- *
- * \see RTE_FLOW_ACTION_TYPE_COUNT
- *
- * @param port_id
- * Port identifier of Ethernet device.
- * @param flow
- * Flow rule handle to query.
- * @param action
- * Action type to query.
- * @param[in, out] data
- * Pointer to storage for the associated query data type.
- * @param[out] error
- * Perform verbose error reporting if not NULL. PMDs initialize this
- * structure in case of error only.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-rte_flow_query(uint16_t port_id,
- struct rte_flow *flow,
- enum rte_flow_action_type action,
- void *data,
- struct rte_flow_error *error);
-
-/**
- * Restrict ingress traffic to the defined flow rules.
- *
- * Isolated mode guarantees that all ingress traffic comes from defined flow
- * rules only (current and future).
- *
- * Besides making ingress more deterministic, it allows PMDs to safely reuse
- * resources otherwise assigned to handle the remaining traffic, such as
- * global RSS configuration settings, VLAN filters, MAC address entries,
- * legacy filter API rules and so on in order to expand the set of possible
- * flow rule types.
- *
- * Calling this function as soon as possible after device initialization,
- * ideally before the first call to rte_eth_dev_configure(), is recommended
- * to avoid possible failures due to conflicting settings.
- *
- * Once effective, leaving isolated mode may not be possible depending on
- * PMD implementation.
- *
- * Additionally, the following functionality has no effect on the underlying
- * port and may return errors such as ENOTSUP ("not supported"):
- *
- * - Toggling promiscuous mode.
- * - Toggling allmulticast mode.
- * - Configuring MAC addresses.
- * - Configuring multicast addresses.
- * - Configuring VLAN filters.
- * - Configuring Rx filters through the legacy API (e.g. FDIR).
- * - Configuring global RSS settings.
- *
- * @param port_id
- * Port identifier of Ethernet device.
- * @param set
- * Nonzero to enter isolated mode, attempt to leave it otherwise.
- * @param[out] error
- * Perform verbose error reporting if not NULL. PMDs initialize this
- * structure in case of error only.
- *
- * @return
- * 0 on success, a negative errno value otherwise and rte_errno is set.
- */
-int
-rte_flow_isolate(uint16_t port_id, int set, struct rte_flow_error *error);
-
-/**
- * Initialize flow error structure.
- *
- * @param[out] error
- * Pointer to flow error structure (may be NULL).
- * @param code
- * Related error code (rte_errno).
- * @param type
- * Cause field and error types.
- * @param cause
- * Object responsible for the error.
- * @param message
- * Human-readable error message.
- *
- * @return
- * Negative error code (errno value) and rte_errno is set.
- */
-int
-rte_flow_error_set(struct rte_flow_error *error,
- int code,
- enum rte_flow_error_type type,
- const void *cause,
- const char *message);
-
-/**
- * Generic flow representation.
- *
- * This form is sufficient to describe an rte_flow independently from any
- * PMD implementation and allows for replayability and identification.
- */
-struct rte_flow_desc {
- size_t size; /**< Allocated space including data[]. */
- struct rte_flow_attr attr; /**< Attributes. */
- struct rte_flow_item *items; /**< Items. */
- struct rte_flow_action *actions; /**< Actions. */
- uint8_t data[]; /**< Storage for items/actions. */
-};
-
-/**
- * Copy an rte_flow rule description.
- *
- * @param[in] fd
- * Flow rule description.
- * @param[in] len
- * Total size of allocated data for the flow description.
- * @param[in] attr
- * Flow rule attributes.
- * @param[in] items
- * Pattern specification (list terminated by the END pattern item).
- * @param[in] actions
- * Associated actions (list terminated by the END action).
- *
- * @return
- * If len is greater or equal to the size of the flow, the total size of the
- * flow description and its data.
- * If len is lower than the size of the flow, the number of bytes that would
- * have been written to desc had it been sufficient. Nothing is written.
- */
-size_t
-rte_flow_copy(struct rte_flow_desc *fd, size_t len,
- const struct rte_flow_attr *attr,
- const struct rte_flow_item *items,
- const struct rte_flow_action *actions);
-
-#ifdef __cplusplus
-}
-#endif
-
-#endif /* RTE_FLOW_H_ */
diff --git a/ipsec/ovs-monitor-ipsec.in b/ipsec/ovs-monitor-ipsec.in
index 4710be039a..534a5043fa 100755
--- a/ipsec/ovs-monitor-ipsec.in
+++ b/ipsec/ovs-monitor-ipsec.in
@@ -617,7 +617,10 @@ conn prevent_unencrypted_vxlan
continue
conn = m.group(1)
- m = re.match(r"(.*)(-in-\d+|-out-\d+|-\d+)", conn)
+ m = re.match(r"(.*)(-in-\d+|-out-\d+)", conn)
+ if not m:
+ # GRE connections have format <iface>-<ver>
+ m = re.match(r"(.*)(-\d+)", conn)
if not m:
continue
diff --git a/lib/automake.mk b/lib/automake.mk
index b1ff495ff1..49fbb1deaf 100644
--- a/lib/automake.mk
+++ b/lib/automake.mk
@@ -107,6 +107,8 @@ lib_libopenvswitch_la_SOURCES = \
lib/hmapx.h \
lib/id-pool.c \
lib/id-pool.h \
+ lib/if-notifier-manual.c \
+ lib/if-notifier.h \
lib/jhash.c \
lib/jhash.h \
lib/json.c \
@@ -385,7 +387,6 @@ lib_libopenvswitch_la_SOURCES += \
lib/dpif-netlink-rtnl.c \
lib/dpif-netlink-rtnl.h \
lib/if-notifier.c \
- lib/if-notifier.h \
lib/netdev-linux.c \
lib/netdev-linux.h \
lib/netdev-tc-offloads.c \
diff --git a/lib/classifier.c b/lib/classifier.c
index edb40c89c6..4272c45156 100644
--- a/lib/classifier.c
+++ b/lib/classifier.c
@@ -393,7 +393,9 @@ classifier_set_prefix_fields(struct classifier *cls,
bitmap_set1(fields.bm, trie_fields[i]);
new_fields[n_tries] = NULL;
- if (n_tries >= cls->n_tries || field != cls->tries[n_tries].field) {
+ const struct mf_field *cls_field
+ = ovsrcu_get(struct mf_field *, &cls->tries[n_tries].field);
+ if (n_tries >= cls->n_tries || field != cls_field) {
new_fields[n_tries] = field;
changed = true;
}
@@ -454,7 +456,7 @@ trie_init(struct classifier *cls, int trie_idx, const struct mf_field *field)
} else {
ovsrcu_set_hidden(&trie->root, NULL);
}
- trie->field = field;
+ ovsrcu_set_hidden(&trie->field, CONST_CAST(struct mf_field *, field));
/* Add existing rules to the new trie. */
CMAP_FOR_EACH (subtable, cmap_node, &cls->subtables_map) {
@@ -839,7 +841,6 @@ classifier_remove_assert(struct classifier *cls,
struct trie_ctx {
const struct cls_trie *trie;
bool lookup_done; /* Status of the lookup. */
- uint8_t be32ofs; /* U32 offset of the field in question. */
unsigned int maskbits; /* Prefix length needed to avoid false matches. */
union trie_prefix match_plens; /* Bitmask of prefix lengths with possible
* matches. */
@@ -849,7 +850,6 @@ static void
trie_ctx_init(struct trie_ctx *ctx, const struct cls_trie *trie)
{
ctx->trie = trie;
- ctx->be32ofs = trie->field->flow_be32ofs;
ctx->lookup_done = false;
}
@@ -1370,6 +1370,7 @@ cls_cursor_start(const struct classifier *cls, const struct cls_rule *target,
struct cls_cursor cursor;
struct cls_subtable *subtable;
+ memset(&cursor, 0x0, sizeof cursor);
cursor.cls = cls;
cursor.target = target && !cls_rule_is_catchall(target) ? target : NULL;
cursor.version = version;
@@ -1513,8 +1514,10 @@ insert_subtable(struct classifier *cls, const struct minimask *mask)
*CONST_CAST(uint8_t *, &subtable->n_indices) = index;
for (i = 0; i < cls->n_tries; i++) {
- subtable->trie_plen[i] = minimask_get_prefix_len(mask,
- cls->tries[i].field);
+ const struct mf_field *field
+ = ovsrcu_get(struct mf_field *, &cls->tries[i].field);
+ subtable->trie_plen[i]
+ = field ? minimask_get_prefix_len(mask, field) : 0;
}
/* Ports trie. */
@@ -1568,11 +1571,17 @@ check_tries(struct trie_ctx trie_ctx[CLS_MAX_TRIES], unsigned int n_tries,
* fields using the prefix tries. The trie checks are done only as
* needed to avoid folding in additional bits to the wildcards mask. */
for (j = 0; j < n_tries; j++) {
- /* Is the trie field relevant for this subtable, and
- is the trie field within the current range of fields? */
- if (field_plen[j] &&
- flowmap_is_set(&range_map, trie_ctx[j].be32ofs / 2)) {
+ /* Is the trie field relevant for this subtable? */
+ if (field_plen[j]) {
struct trie_ctx *ctx = &trie_ctx[j];
+ const struct mf_field *ctx_field
+ = ovsrcu_get(struct mf_field *, &ctx->trie->field);
+
+ /* Is the trie field within the current range of fields? */
+ if (!ctx_field
+ || !flowmap_is_set(&range_map, ctx_field->flow_be32ofs / 2)) {
+ continue;
+ }
/* On-demand trie lookup. */
if (!ctx->lookup_done) {
@@ -1594,14 +1603,16 @@ check_tries(struct trie_ctx trie_ctx[CLS_MAX_TRIES], unsigned int n_tries,
* than this subtable would otherwise. */
if (ctx->maskbits <= field_plen[j]) {
/* Unwildcard the bits and skip the rest. */
- mask_set_prefix_bits(wc, ctx->be32ofs, ctx->maskbits);
+ mask_set_prefix_bits(wc, ctx_field->flow_be32ofs,
+ ctx->maskbits);
/* Note: Prerequisite already unwildcarded, as the only
* prerequisite of the supported trie lookup fields is
* the ethertype, which is always unwildcarded. */
return true;
}
/* Can skip if the field is already unwildcarded. */
- if (mask_prefix_bits_set(wc, ctx->be32ofs, ctx->maskbits)) {
+ if (mask_prefix_bits_set(wc, ctx_field->flow_be32ofs,
+ ctx->maskbits)) {
return true;
}
}
@@ -1994,12 +2005,12 @@ static unsigned int
trie_lookup(const struct cls_trie *trie, const struct flow *flow,
union trie_prefix *plens)
{
- const struct mf_field *mf = trie->field;
+ const struct mf_field *mf = ovsrcu_get(struct mf_field *, &trie->field);
/* Check that current flow matches the prerequisites for the trie
* field. Some match fields are used for multiple purposes, so we
* must check that the trie is relevant for this flow. */
- if (mf_are_prereqs_ok(mf, flow, NULL)) {
+ if (mf && mf_are_prereqs_ok(mf, flow, NULL)) {
return trie_lookup_value(&trie->root,
&((ovs_be32 *)flow)[mf->flow_be32ofs],
&plens->be32, mf->n_bits);
@@ -2046,8 +2057,9 @@ minimask_get_prefix_len(const struct minimask *minimask,
* happened to be zeros.
*/
static const ovs_be32 *
-minimatch_get_prefix(const struct minimatch *match, const struct mf_field *mf)
+minimatch_get_prefix(const struct minimatch *match, rcu_field_ptr *field)
{
+ struct mf_field *mf = ovsrcu_get_protected(struct mf_field *, field);
size_t u64_ofs = mf->flow_be32ofs / 2;
return (OVS_FORCE const ovs_be32 *)miniflow_get__(match->flow, u64_ofs)
@@ -2061,7 +2073,7 @@ static void
trie_insert(struct cls_trie *trie, const struct cls_rule *rule, int mlen)
{
trie_insert_prefix(&trie->root,
- minimatch_get_prefix(&rule->match, trie->field), mlen);
+ minimatch_get_prefix(&rule->match, &trie->field), mlen);
}
static void
@@ -2116,7 +2128,7 @@ static void
trie_remove(struct cls_trie *trie, const struct cls_rule *rule, int mlen)
{
trie_remove_prefix(&trie->root,
- minimatch_get_prefix(&rule->match, trie->field), mlen);
+ minimatch_get_prefix(&rule->match, &trie->field), mlen);
}
/* 'mlen' must be the (non-zero) CIDR prefix length of the 'trie->field' mask
diff --git a/lib/classifier.h b/lib/classifier.h
index d1bd4aa12a..f646a8f742 100644
--- a/lib/classifier.h
+++ b/lib/classifier.h
@@ -314,13 +314,15 @@ extern "C" {
struct cls_subtable;
struct cls_match;
+struct mf_field;
+typedef OVSRCU_TYPE(struct mf_field *) rcu_field_ptr;
struct trie_node;
typedef OVSRCU_TYPE(struct trie_node *) rcu_trie_ptr;
/* Prefix trie for a 'field' */
struct cls_trie {
- const struct mf_field *field; /* Trie field, or NULL. */
- rcu_trie_ptr root; /* NULL if none. */
+ rcu_field_ptr field; /* Trie field, or NULL. */
+ rcu_trie_ptr root; /* NULL if none. */
};
enum {
diff --git a/lib/conntrack.c b/lib/conntrack.c
index ea9486b735..07ffc05e57 100644
--- a/lib/conntrack.c
+++ b/lib/conntrack.c
@@ -640,7 +640,7 @@ static void
reverse_nat_packet(struct dp_packet *pkt, const struct conn *conn)
{
char *tail = dp_packet_tail(pkt);
- char pad = dp_packet_l2_pad_size(pkt);
+ uint16_t pad = dp_packet_l2_pad_size(pkt);
struct conn_key inner_key;
const char *inner_l4 = NULL;
uint16_t orig_l3_ofs = pkt->l3_ofs;
@@ -650,6 +650,8 @@ reverse_nat_packet(struct dp_packet *pkt, const struct conn *conn)
struct ip_header *nh = dp_packet_l3(pkt);
struct icmp_header *icmp = dp_packet_l4(pkt);
struct ip_header *inner_l3 = (struct ip_header *) (icmp + 1);
+ /* This call is already verified to succeed during the code path from
+ * 'conn_key_extract()' which calls 'extract_l4_icmp()'. */
extract_l3_ipv4(&inner_key, inner_l3, tail - ((char *)inner_l3) - pad,
&inner_l4, false);
pkt->l3_ofs += (char *) inner_l3 - (char *) nh;
@@ -671,6 +673,8 @@ reverse_nat_packet(struct dp_packet *pkt, const struct conn *conn)
struct icmp6_error_header *icmp6 = dp_packet_l4(pkt);
struct ovs_16aligned_ip6_hdr *inner_l3_6 =
(struct ovs_16aligned_ip6_hdr *) (icmp6 + 1);
+ /* This call is already verified to succeed during the code path from
+ * 'conn_key_extract()' which calls 'extract_l4_icmp6()'. */
extract_l3_ipv6(&inner_key, inner_l3_6,
tail - ((char *)inner_l3_6) - pad,
&inner_l4);
@@ -1252,6 +1256,11 @@ process_one(struct conntrack *ct, struct dp_packet *pkt,
conn_key_lookup(&ct->buckets[bucket], ctx, now);
conn = ctx->conn;
+ /* Reset ct_state whenever entering a new zone. */
+ if (pkt->md.ct_state && pkt->md.ct_zone != zone) {
+ pkt->md.ct_state = 0;
+ }
+
/* Delete found entry if in wrong direction. 'force' implies commit. */
if (OVS_UNLIKELY(force && ctx->reply && conn)) {
struct conn lconn;
@@ -1284,7 +1293,8 @@ process_one(struct conntrack *ct, struct dp_packet *pkt,
/* It is a race condition where conn has timed out and removed
* between unlock of the rev_conn and lock of the forward conn;
* nothing to do. */
- pkt->md.ct_state |= CS_TRACKED | CS_INVALID;
+ pkt->md.ct_state |= CS_INVALID;
+ write_ct_md(pkt, zone, NULL, NULL, NULL);
ct_lock_unlock(&ct->buckets[bucket].lock);
return;
}
@@ -1715,9 +1725,10 @@ check_l4_icmp6(const struct conn_key *key, const void *data, size_t size,
}
static inline bool
-extract_l4_tcp(struct conn_key *key, const void *data, size_t size)
+extract_l4_tcp(struct conn_key *key, const void *data, size_t size,
+ size_t *chk_len)
{
- if (OVS_UNLIKELY(size < TCP_HEADER_LEN)) {
+ if (OVS_UNLIKELY(size < (chk_len ? *chk_len : TCP_HEADER_LEN))) {
return false;
}
@@ -1730,9 +1741,10 @@ extract_l4_tcp(struct conn_key *key, const void *data, size_t size)
}
static inline bool
-extract_l4_udp(struct conn_key *key, const void *data, size_t size)
+extract_l4_udp(struct conn_key *key, const void *data, size_t size,
+ size_t *chk_len)
{
- if (OVS_UNLIKELY(size < UDP_HEADER_LEN)) {
+ if (OVS_UNLIKELY(size < (chk_len ? *chk_len : UDP_HEADER_LEN))) {
return false;
}
@@ -1746,7 +1758,7 @@ extract_l4_udp(struct conn_key *key, const void *data, size_t size)
static inline bool extract_l4(struct conn_key *key, const void *data,
size_t size, bool *related, const void *l3,
- bool validate_checksum);
+ bool validate_checksum, size_t *chk_len);
static uint8_t
reverse_icmp_type(uint8_t type)
@@ -1778,9 +1790,9 @@ reverse_icmp_type(uint8_t type)
* possible */
static inline int
extract_l4_icmp(struct conn_key *key, const void *data, size_t size,
- bool *related)
+ bool *related, size_t *chk_len)
{
- if (OVS_UNLIKELY(size < ICMP_HEADER_LEN)) {
+ if (OVS_UNLIKELY(size < (chk_len ? *chk_len : ICMP_HEADER_LEN))) {
return false;
}
@@ -1831,8 +1843,9 @@ extract_l4_icmp(struct conn_key *key, const void *data, size_t size,
key->src = inner_key.src;
key->dst = inner_key.dst;
key->nw_proto = inner_key.nw_proto;
+ size_t check_len = ICMP_ERROR_DATA_L4_LEN;
- ok = extract_l4(key, l4, tail - l4, NULL, l3, false);
+ ok = extract_l4(key, l4, tail - l4, NULL, l3, false, &check_len);
if (ok) {
conn_key_reverse(key);
*related = true;
@@ -1919,7 +1932,7 @@ extract_l4_icmp6(struct conn_key *key, const void *data, size_t size,
key->dst = inner_key.dst;
key->nw_proto = inner_key.nw_proto;
- ok = extract_l4(key, l4, tail - l4, NULL, l3, false);
+ ok = extract_l4(key, l4, tail - l4, NULL, l3, false, NULL);
if (ok) {
conn_key_reverse(key);
*related = true;
@@ -1944,26 +1957,29 @@ extract_l4_icmp6(struct conn_key *key, const void *data, size_t size,
* an ICMP or ICMP6 header.
*
* If 'related' is NULL, it means that we're already parsing a header nested
- * in an ICMP error. In this case, we skip checksum and length validation. */
+ * in an ICMP error. In this case, we skip the checksum and some length
+ * validations. */
static inline bool
extract_l4(struct conn_key *key, const void *data, size_t size, bool *related,
- const void *l3, bool validate_checksum)
+ const void *l3, bool validate_checksum, size_t *chk_len)
{
if (key->nw_proto == IPPROTO_TCP) {
return (!related || check_l4_tcp(key, data, size, l3,
- validate_checksum)) && extract_l4_tcp(key, data, size);
+ validate_checksum))
+ && extract_l4_tcp(key, data, size, chk_len);
} else if (key->nw_proto == IPPROTO_UDP) {
return (!related || check_l4_udp(key, data, size, l3,
- validate_checksum)) && extract_l4_udp(key, data, size);
+ validate_checksum))
+ && extract_l4_udp(key, data, size, chk_len);
} else if (key->dl_type == htons(ETH_TYPE_IP)
&& key->nw_proto == IPPROTO_ICMP) {
return (!related || check_l4_icmp(data, size, validate_checksum))
- && extract_l4_icmp(key, data, size, related);
+ && extract_l4_icmp(key, data, size, related, chk_len);
} else if (key->dl_type == htons(ETH_TYPE_IPV6)
&& key->nw_proto == IPPROTO_ICMPV6) {
return (!related || check_l4_icmp6(key, data, size, l3,
- validate_checksum)) && extract_l4_icmp6(key, data, size,
- related);
+ validate_checksum))
+ && extract_l4_icmp6(key, data, size, related);
} else {
return false;
}
@@ -2042,7 +2058,8 @@ conn_key_extract(struct conntrack *ct, struct dp_packet *pkt, ovs_be16 dl_type,
bool hwol_good_l4_csum = dp_packet_l4_checksum_valid(pkt);
/* Validate the checksum only when hwol is not supported. */
if (extract_l4(&ctx->key, l4, dp_packet_l4_size(pkt),
- &ctx->icmp_related, l3, !hwol_good_l4_csum)) {
+ &ctx->icmp_related, l3, !hwol_good_l4_csum,
+ NULL)) {
ctx->hash = conn_key_hash(&ctx->key, ct->hash_basis);
return true;
}
diff --git a/lib/dp-packet.h b/lib/dp-packet.h
index c297a8f509..86a8f846ff 100644
--- a/lib/dp-packet.h
+++ b/lib/dp-packet.h
@@ -65,7 +65,7 @@ struct dp_packet {
/* All the following elements of this struct are copied in a single call
* of memcpy in dp_packet_clone_with_headroom. */
- uint8_t l2_pad_size; /* Detected l2 padding size.
+ uint16_t l2_pad_size; /* Detected l2 padding size.
* Padding is non-pullable. */
uint16_t l2_5_ofs; /* MPLS label stack offset, or UINT16_MAX */
uint16_t l3_ofs; /* Network-level header offset,
@@ -95,8 +95,8 @@ void *dp_packet_resize_l2(struct dp_packet *, int increment);
void *dp_packet_resize_l2_5(struct dp_packet *, int increment);
static inline void *dp_packet_eth(const struct dp_packet *);
static inline void dp_packet_reset_offsets(struct dp_packet *);
-static inline uint8_t dp_packet_l2_pad_size(const struct dp_packet *);
-static inline void dp_packet_set_l2_pad_size(struct dp_packet *, uint8_t);
+static inline uint16_t dp_packet_l2_pad_size(const struct dp_packet *);
+static inline void dp_packet_set_l2_pad_size(struct dp_packet *, uint16_t);
static inline void *dp_packet_l2_5(const struct dp_packet *);
static inline void dp_packet_set_l2_5(struct dp_packet *, void *);
static inline void *dp_packet_l3(const struct dp_packet *);
@@ -295,14 +295,14 @@ dp_packet_reset_offsets(struct dp_packet *b)
b->l4_ofs = UINT16_MAX;
}
-static inline uint8_t
+static inline uint16_t
dp_packet_l2_pad_size(const struct dp_packet *b)
{
return b->l2_pad_size;
}
static inline void
-dp_packet_set_l2_pad_size(struct dp_packet *b, uint8_t pad_size)
+dp_packet_set_l2_pad_size(struct dp_packet *b, uint16_t pad_size)
{
ovs_assert(pad_size <= dp_packet_size(b));
b->l2_pad_size = pad_size;
diff --git a/lib/dpctl.c b/lib/dpctl.c
index bea9f87e86..8e37a29b42 100644
--- a/lib/dpctl.c
+++ b/lib/dpctl.c
@@ -999,7 +999,7 @@ dpctl_dump_flows(int argc, const char *argv[], struct dpctl_params *dpctl_p)
memset(&dump_types, 0, sizeof dump_types);
error = populate_dump_types(types_list, &dump_types, dpctl_p);
if (error) {
- goto out_free;
+ goto out_dpifclose;
}
determine_dpif_flow_dump_types(&dump_types, &dpif_dump_types);
diff --git a/lib/dpif-netdev.c b/lib/dpif-netdev.c
index 5dae9e1e76..62f8b1bb6d 100644
--- a/lib/dpif-netdev.c
+++ b/lib/dpif-netdev.c
@@ -100,6 +100,17 @@ enum { MAX_METERS = 65536 }; /* Maximum number of meters. */
enum { MAX_BANDS = 8 }; /* Maximum number of bands / meter. */
enum { N_METER_LOCKS = 64 }; /* Maximum number of meters. */
+COVERAGE_DEFINE(datapath_drop_meter);
+COVERAGE_DEFINE(datapath_drop_upcall_error);
+COVERAGE_DEFINE(datapath_drop_lock_error);
+COVERAGE_DEFINE(datapath_drop_userspace_action_error);
+COVERAGE_DEFINE(datapath_drop_tunnel_push_error);
+COVERAGE_DEFINE(datapath_drop_tunnel_pop_error);
+COVERAGE_DEFINE(datapath_drop_recirc_error);
+COVERAGE_DEFINE(datapath_drop_invalid_port);
+COVERAGE_DEFINE(datapath_drop_invalid_tnl_port);
+COVERAGE_DEFINE(datapath_drop_rx_invalid_packet);
+
/* Protects against changes to 'dp_netdevs'. */
static struct ovs_mutex dp_netdev_mutex = OVS_MUTEX_INITIALIZER;
@@ -2094,7 +2105,11 @@ dp_netdev_pmd_find_dpcls(struct dp_netdev_pmd_thread *pmd,
}
#define MAX_FLOW_MARK (UINT32_MAX - 1)
-#define INVALID_FLOW_MARK (UINT32_MAX)
+#define INVALID_FLOW_MARK 0
+/* Zero flow mark is used to indicate the HW to remove the mark. A packet
+ * marked with zero mark is received in SW without a mark at all, so it
+ * cannot be used as a valid mark.
+ */
struct megaflow_to_mark_data {
const struct cmap_node node;
@@ -2120,7 +2135,7 @@ flow_mark_alloc(void)
if (!flow_mark.pool) {
/* Haven't initiated yet, do it here */
- flow_mark.pool = id_pool_create(0, MAX_FLOW_MARK);
+ flow_mark.pool = id_pool_create(1, MAX_FLOW_MARK);
}
if (id_pool_alloc_id(flow_mark.pool, &mark)) {
@@ -2225,6 +2240,12 @@ mark_to_flow_disassociate(struct dp_netdev_pmd_thread *pmd,
struct cmap_node *mark_node = CONST_CAST(struct cmap_node *,
&flow->mark_node);
+ /* INVALID_FLOW_MARK may mean that the flow has been disassociated or
+ * never associated. */
+ if (OVS_UNLIKELY(mark == INVALID_FLOW_MARK)) {
+ return EINVAL;
+ }
+
cmap_remove(&flow_mark.mark_to_flow, mark_node, hash_int(mark, 0));
flow->mark = INVALID_FLOW_MARK;
@@ -2374,6 +2395,7 @@ dp_netdev_flow_offload_put(struct dp_flow_offload_item *offload)
mark = flow_mark_alloc();
if (mark == INVALID_FLOW_MARK) {
VLOG_ERR("Failed to allocate flow mark!\n");
+ return -1;
}
}
info.flow_mark = mark;
@@ -2449,6 +2471,7 @@ dp_netdev_flow_offload_main(void *data OVS_UNUSED)
VLOG_DBG("%s to %s netdev flow\n",
ret == 0 ? "succeed" : "failed", op);
dp_netdev_free_flow_offload(offload);
+ ovsrcu_quiesce();
}
return NULL;
@@ -5552,6 +5575,14 @@ dp_netdev_run_meter(struct dp_netdev *dp, struct dp_packet_batch *packets_,
/* All packets will hit the meter at the same time. */
long_delta_t = now / 1000 - meter->used / 1000; /* msec */
+ if (long_delta_t < 0) {
+ /* This condition means that we have several threads fighting for a
+ meter lock, and the one who received the packets a bit later wins.
+ Assuming that all racing threads received packets at the same time
+ to avoid overflow. */
+ long_delta_t = 0;
+ }
+
/* Make sure delta_t will not be too large, so that bucket will not
* wrap around below. */
delta_t = (long_delta_t > (long long int)meter->max_delta_t)
@@ -5647,7 +5678,7 @@ dp_netdev_run_meter(struct dp_netdev *dp, struct dp_packet_batch *packets_,
band = &meter->bands[exceeded_band[j]];
band->packet_count += 1;
band->byte_count += dp_packet_size(packet);
-
+ COVERAGE_INC(datapath_drop_meter);
dp_packet_delete(packet);
} else {
/* Meter accepts packet. */
@@ -6200,7 +6231,6 @@ dpif_netdev_packet_get_rss_hash(struct dp_packet *packet,
recirc_depth = *recirc_depth_get_unsafe();
if (OVS_UNLIKELY(recirc_depth)) {
hash = hash_finish(hash, recirc_depth);
- dp_packet_set_rss_hash(packet, hash);
}
return hash;
}
@@ -6403,6 +6433,7 @@ dfc_processing(struct dp_netdev_pmd_thread *pmd,
if (OVS_UNLIKELY(dp_packet_size(packet) < ETH_HEADER_LEN)) {
dp_packet_delete(packet);
+ COVERAGE_INC(datapath_drop_rx_invalid_packet);
continue;
}
@@ -6522,6 +6553,7 @@ handle_packet_upcall(struct dp_netdev_pmd_thread *pmd,
put_actions);
if (OVS_UNLIKELY(error && error != ENOSPC)) {
dp_packet_delete(packet);
+ COVERAGE_INC(datapath_drop_upcall_error);
return error;
}
@@ -6652,6 +6684,7 @@ fast_path_processing(struct dp_netdev_pmd_thread *pmd,
DP_PACKET_BATCH_FOR_EACH (i, packet, packets_) {
if (OVS_UNLIKELY(!rules[i])) {
dp_packet_delete(packet);
+ COVERAGE_INC(datapath_drop_lock_error);
upcall_fail_cnt++;
}
}
@@ -6921,6 +6954,7 @@ dp_execute_userspace_action(struct dp_netdev_pmd_thread *pmd,
actions->data, actions->size);
} else if (should_steal) {
dp_packet_delete(packet);
+ COVERAGE_INC(datapath_drop_userspace_action_error);
}
}
@@ -6935,6 +6969,7 @@ dp_execute_cb(void *aux_, struct dp_packet_batch *packets_,
struct dp_netdev *dp = pmd->dp;
int type = nl_attr_type(a);
struct tx_port *p;
+ uint32_t packet_count, packets_dropped;
switch ((enum ovs_action_attr)type) {
case OVS_ACTION_ATTR_OUTPUT:
@@ -6976,6 +7011,9 @@ dp_execute_cb(void *aux_, struct dp_packet_batch *packets_,
dp_packet_batch_add(&p->output_pkts, packet);
}
return;
+ } else {
+ COVERAGE_ADD(datapath_drop_invalid_port,
+ dp_packet_batch_size(packets_));
}
break;
@@ -6988,7 +7026,11 @@ dp_execute_cb(void *aux_, struct dp_packet_batch *packets_,
break;
}
dp_packet_batch_apply_cutlen(packets_);
- push_tnl_action(pmd, a, packets_);
+ packet_count = dp_packet_batch_size(packets_);
+ if (push_tnl_action(pmd, a, packets_)) {
+ COVERAGE_ADD(datapath_drop_tunnel_push_error,
+ packet_count);
+ }
return;
case OVS_ACTION_ATTR_TUNNEL_POP:
@@ -7008,7 +7050,14 @@ dp_execute_cb(void *aux_, struct dp_packet_batch *packets_,
dp_packet_batch_apply_cutlen(packets_);
+ packet_count = dp_packet_batch_size(packets_);
netdev_pop_header(p->port->netdev, packets_);
+ packets_dropped =
+ packet_count - dp_packet_batch_size(packets_);
+ if (packets_dropped) {
+ COVERAGE_ADD(datapath_drop_tunnel_pop_error,
+ packets_dropped);
+ }
if (dp_packet_batch_is_empty(packets_)) {
return;
}
@@ -7023,6 +7072,11 @@ dp_execute_cb(void *aux_, struct dp_packet_batch *packets_,
(*depth)--;
return;
}
+ COVERAGE_ADD(datapath_drop_invalid_tnl_port,
+ dp_packet_batch_size(packets_));
+ } else {
+ COVERAGE_ADD(datapath_drop_recirc_error,
+ dp_packet_batch_size(packets_));
}
break;
@@ -7067,6 +7121,8 @@ dp_execute_cb(void *aux_, struct dp_packet_batch *packets_,
return;
}
+ COVERAGE_ADD(datapath_drop_lock_error,
+ dp_packet_batch_size(packets_));
break;
case OVS_ACTION_ATTR_RECIRC:
@@ -7090,6 +7146,8 @@ dp_execute_cb(void *aux_, struct dp_packet_batch *packets_,
return;
}
+ COVERAGE_ADD(datapath_drop_recirc_error,
+ dp_packet_batch_size(packets_));
VLOG_WARN("Packet dropped. Max recirculation depth exceeded.");
break;
@@ -7242,6 +7300,8 @@ dp_execute_cb(void *aux_, struct dp_packet_batch *packets_,
case OVS_ACTION_ATTR_PUSH_NSH:
case OVS_ACTION_ATTR_POP_NSH:
case OVS_ACTION_ATTR_CT_CLEAR:
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+ case OVS_ACTION_ATTR_DROP:
case __OVS_ACTION_ATTR_MAX:
OVS_NOT_REACHED();
}
diff --git a/lib/dpif-netlink-rtnl.c b/lib/dpif-netlink-rtnl.c
index 2e23a8c14f..582274c467 100644
--- a/lib/dpif-netlink-rtnl.c
+++ b/lib/dpif-netlink-rtnl.c
@@ -104,7 +104,13 @@ vport_type_to_kind(enum ovs_vport_type type,
case OVS_VPORT_TYPE_IP6ERSPAN:
return "ip6erspan";
case OVS_VPORT_TYPE_IP6GRE:
- return "ip6gre";
+ if (tnl_cfg->pt_mode == NETDEV_PT_LEGACY_L2) {
+ return "ip6gretap";
+ } else if (tnl_cfg->pt_mode == NETDEV_PT_LEGACY_L3) {
+ return NULL;
+ } else {
+ return NULL;
+ }
case OVS_VPORT_TYPE_NETDEV:
case OVS_VPORT_TYPE_INTERNAL:
case OVS_VPORT_TYPE_LISP:
diff --git a/lib/dpif-netlink.c b/lib/dpif-netlink.c
index 165b7a93fc..26d09f843f 100644
--- a/lib/dpif-netlink.c
+++ b/lib/dpif-netlink.c
@@ -456,6 +456,7 @@ vport_add_channel(struct dpif_netlink *dpif, odp_port_t port_no,
int error;
if (dpif->handlers == NULL) {
+ close_nl_sock(socksp);
return 0;
}
@@ -2037,6 +2038,7 @@ parse_flow_put(struct dpif_netlink *dpif, struct dpif_flow_put *put)
info.dpif_class = dpif_class;
info.tp_dst_port = dst_port;
info.tunnel_csum_on = csum_on;
+ info.tc_modify_flow_deleted = false;
err = netdev_flow_put(dev, &match,
CONST_CAST(struct nlattr *, put->actions),
put->actions_len,
@@ -2084,7 +2086,11 @@ parse_flow_put(struct dpif_netlink *dpif, struct dpif_flow_put *put)
out:
if (err && err != EEXIST && (put->flags & DPIF_FP_MODIFY)) {
/* Modified rule can't be offloaded, try and delete from HW */
- int del_err = netdev_flow_del(dev, put->ufid, put->stats);
+ int del_err = 0;
+
+ if (!info.tc_modify_flow_deleted) {
+ del_err = netdev_flow_del(dev, put->ufid, put->stats);
+ }
if (!del_err) {
/* Delete from hw success, so old flow was offloaded.
diff --git a/lib/dpif.c b/lib/dpif.c
index 457c9bfb92..c908a1054d 100644
--- a/lib/dpif.c
+++ b/lib/dpif.c
@@ -1269,6 +1269,8 @@ dpif_execute_helper_cb(void *aux_, struct dp_packet_batch *packets_,
case OVS_ACTION_ATTR_POP_NSH:
case OVS_ACTION_ATTR_CT_CLEAR:
case OVS_ACTION_ATTR_UNSPEC:
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+ case OVS_ACTION_ATTR_DROP:
case __OVS_ACTION_ATTR_MAX:
OVS_NOT_REACHED();
}
@@ -1874,6 +1876,12 @@ dpif_supports_tnl_push_pop(const struct dpif *dpif)
return dpif_is_netdev(dpif);
}
+bool
+dpif_supports_explicit_drop_action(const struct dpif *dpif)
+{
+ return dpif_is_netdev(dpif);
+}
+
/* Meters */
void
dpif_meter_get_features(const struct dpif *dpif,
diff --git a/lib/dpif.h b/lib/dpif.h
index 475d5a674e..c425042d91 100644
--- a/lib/dpif.h
+++ b/lib/dpif.h
@@ -888,6 +888,7 @@ int dpif_get_pmds_for_port(const struct dpif * dpif, odp_port_t port_no,
char *dpif_get_dp_version(const struct dpif *);
bool dpif_supports_tnl_push_pop(const struct dpif *);
+bool dpif_supports_explicit_drop_action(const struct dpif *);
/* Log functions. */
struct vlog_module;
diff --git a/lib/flow.c b/lib/flow.c
index 2cf8a020ae..4eeb09d426 100644
--- a/lib/flow.c
+++ b/lib/flow.c
@@ -646,7 +646,7 @@ ipv4_sanity_check(const struct ip_header *nh, size_t size,
tot_len = ntohs(nh->ip_tot_len);
if (OVS_UNLIKELY(tot_len > size || ip_len > tot_len ||
- size - tot_len > UINT8_MAX)) {
+ size - tot_len > UINT16_MAX)) {
return false;
}
@@ -684,8 +684,8 @@ ipv6_sanity_check(const struct ovs_16aligned_ip6_hdr *nh, size_t size)
if (OVS_UNLIKELY(plen + IPV6_HEADER_LEN > size)) {
return false;
}
- /* Jumbo Payload option not supported yet. */
- if (OVS_UNLIKELY(size - plen > UINT8_MAX)) {
+
+ if (OVS_UNLIKELY(size - (plen + IPV6_HEADER_LEN) > UINT16_MAX)) {
return false;
}
@@ -1013,15 +1013,14 @@ miniflow_extract(struct dp_packet *packet, struct miniflow *dst)
dst->map = mf.map;
}
-ovs_be16
-parse_dl_type(const struct eth_header *data_, size_t size)
+static ovs_be16
+parse_dl_type(const void **datap, size_t *sizep)
{
- const void *data = data_;
union flow_vlan_hdr vlans[FLOW_MAX_VLAN_HEADERS];
- parse_vlan(&data, &size, vlans);
+ parse_vlan(datap, sizep, vlans);
- return parse_ethertype(&data, &size);
+ return parse_ethertype(datap, sizep);
}
/* Parses and return the TCP flags in 'packet', converted to host byte order.
@@ -1044,11 +1043,11 @@ parse_tcp_flags(struct dp_packet *packet)
dp_packet_reset_offsets(packet);
- data_pull(&data, &size, ETH_ADDR_LEN * 2);
- dl_type = parse_ethertype(&data, &size);
+ dl_type = parse_dl_type(&data, &size);
if (OVS_UNLIKELY(eth_type_mpls(dl_type))) {
packet->l2_5_ofs = (char *)data - frame;
}
+ packet->l3_ofs = (char *)data - frame;
if (OVS_LIKELY(dl_type == htons(ETH_TYPE_IP))) {
const struct ip_header *nh = data;
int ip_len;
@@ -1058,7 +1057,6 @@ parse_tcp_flags(struct dp_packet *packet)
return 0;
}
dp_packet_set_l2_pad_size(packet, size - tot_len);
- packet->l3_ofs = (uint16_t)((char *)nh - frame);
nw_proto = nh->ip_proto;
nw_frag = ipv4_get_nw_frag(nh);
@@ -1071,7 +1069,6 @@ parse_tcp_flags(struct dp_packet *packet)
if (OVS_UNLIKELY(!ipv6_sanity_check(nh, size))) {
return 0;
}
- packet->l3_ofs = (uint16_t)((char *)nh - frame);
data_pull(&data, &size, sizeof *nh);
plen = ntohs(nh->ip6_plen); /* Never pull padding. */
diff --git a/lib/flow.h b/lib/flow.h
index 5ebdb1f1da..bee6f85e93 100644
--- a/lib/flow.h
+++ b/lib/flow.h
@@ -132,7 +132,6 @@ void packet_expand(struct dp_packet *, const struct flow *, size_t size);
bool parse_ipv6_ext_hdrs(const void **datap, size_t *sizep, uint8_t *nw_proto,
uint8_t *nw_frag);
-ovs_be16 parse_dl_type(const struct eth_header *data_, size_t size);
bool parse_nsh(const void **datap, size_t *sizep, struct ovs_key_nsh *key);
uint16_t parse_tcp_flags(struct dp_packet *packet);
diff --git a/lib/if-notifier-manual.c b/lib/if-notifier-manual.c
new file mode 100644
index 0000000000..54bbf76fb6
--- /dev/null
+++ b/lib/if-notifier-manual.c
@@ -0,0 +1,57 @@
+/*
+ * Copyright (c) 2019 Ilya Maximets <i.maximets@ovn.org>.
+ *
+ * Licensed under the Apache License, Version 2.0 (the "License");
+ * you may not use this file except in compliance with the License.
+ * You may obtain a copy of the License at:
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+#include <config.h>
+#include "openvswitch/compiler.h"
+#include "openvswitch/thread.h"
+#include "openvswitch/util.h"
+#include "if-notifier.h"
+
+/* Implementation of a manual interface notifier.
+ *
+ * Intended for catching interface events that could not be tracked by
+ * OS specific interface notifiers, e.g. iface updates in netdev-dpdk.
+ * For that purpose 'if_notifier_manual_report()' should be called directly
+ * by the code that aware of interface changes.
+ *
+ * Thread-safety
+ * =============
+ * This notifier is thread-safe in terms of calling its functions from
+ * different thread contexts, however if the callback passed to
+ * 'if_notifier_manual_set_cb' is used by some other code (i.e. by OS
+ * specific notifiers) it must be thread-safe itself.
+ */
+
+static struct ovs_mutex manual_notifier_mutex = OVS_MUTEX_INITIALIZER;
+static if_notify_func *notify OVS_GUARDED_BY(manual_notifier_mutex) = NULL;
+
+void
+if_notifier_manual_set_cb(if_notify_func *cb)
+{
+ ovs_mutex_lock(&manual_notifier_mutex);
+ notify = cb;
+ ovs_mutex_unlock(&manual_notifier_mutex);
+}
+
+void
+if_notifier_manual_report(void)
+{
+ ovs_mutex_lock(&manual_notifier_mutex);
+ if (notify) {
+ notify(NULL);
+ }
+ ovs_mutex_unlock(&manual_notifier_mutex);
+}
diff --git a/lib/if-notifier.h b/lib/if-notifier.h
index 259138f70c..dae852e9f0 100644
--- a/lib/if-notifier.h
+++ b/lib/if-notifier.h
@@ -27,4 +27,11 @@ void if_notifier_destroy(struct if_notifier *);
void if_notifier_run(void);
void if_notifier_wait(void);
+/* Below functions are reserved for if-notifier-manual , i.e. for manual
+ * notifications from the OVS code.
+ * Must not be implemented by OS specific notifiers. */
+
+void if_notifier_manual_set_cb(if_notify_func *);
+void if_notifier_manual_report(void);
+
#endif /* if-notifier.h */
diff --git a/lib/jsonrpc.c b/lib/jsonrpc.c
index 4c2c1ba84a..c366cf53eb 100644
--- a/lib/jsonrpc.c
+++ b/lib/jsonrpc.c
@@ -43,7 +43,7 @@ struct jsonrpc {
/* Input. */
struct byteq input;
- uint8_t input_buffer[512];
+ uint8_t input_buffer[4096];
struct json_parser *parser;
/* Output. */
diff --git a/lib/lldp/lldp.c b/lib/lldp/lldp.c
index 74f747fcdc..18afbab9a7 100644
--- a/lib/lldp/lldp.c
+++ b/lib/lldp/lldp.c
@@ -59,7 +59,7 @@ VLOG_DEFINE_THIS_MODULE(lldp);
} while (0)
#define PEEK_DISCARD_UINT8 PEEK_DISCARD(1)
#define PEEK_DISCARD_UINT16 PEEK_DISCARD(2)
-#define PEEK_DISCARD_UINT32 PEEK_DISCARD(3)
+#define PEEK_DISCARD_UINT32 PEEK_DISCARD(4)
#define PEEK_CMP(value, bytes) \
(length -= (bytes), \
pos += (bytes), \
@@ -341,6 +341,12 @@ lldp_send(struct lldpd *global OVS_UNUSED,
return dp_packet_size(p);
}
+#define CHECK_TLV_MAX_SIZE(x, name) \
+ do { if (tlv_size > (x)) { \
+ VLOG_WARN(name " TLV too large received on %s", \
+ hardware->h_ifname); \
+ goto malformed; \
+ } } while (0)
int
lldp_decode(struct lldpd *cfg OVS_UNUSED, char *frame, int s,
@@ -359,7 +365,7 @@ lldp_decode(struct lldpd *cfg OVS_UNUSED, char *frame, int s,
int length, af;
bool gotend = false;
bool ttl_received = false;
- int tlv_size, tlv_type, tlv_subtype;
+ int tlv_size, tlv_type, tlv_subtype, tlv_count = 0;
u_int8_t *pos, *tlv;
void *b;
struct lldpd_aa_isid_vlan_maps_tlv *isid_vlan_map = NULL;
@@ -411,6 +417,31 @@ lldp_decode(struct lldpd *cfg OVS_UNUSED, char *frame, int s,
hardware->h_ifname);
goto malformed;
}
+ /* Check order for mandatory TLVs */
+ tlv_count++;
+ switch (tlv_type) {
+ case LLDP_TLV_CHASSIS_ID:
+ if (tlv_count != 1) {
+ VLOG_WARN("first TLV should be a chassis ID on %s, not %d",
+ hardware->h_ifname, tlv_type);
+ goto malformed;
+ }
+ break;
+ case LLDP_TLV_PORT_ID:
+ if (tlv_count != 2) {
+ VLOG_WARN("second TLV should be a port ID on %s, not %d",
+ hardware->h_ifname, tlv_type);
+ goto malformed;
+ }
+ break;
+ case LLDP_TLV_TTL:
+ if (tlv_count != 3) {
+ VLOG_WARN("third TLV should be a TTL on %s, not %d",
+ hardware->h_ifname, tlv_type);
+ goto malformed;
+ }
+ break;
+ }
switch (tlv_type) {
case LLDP_TLV_END:
@@ -428,7 +459,8 @@ lldp_decode(struct lldpd *cfg OVS_UNUSED, char *frame, int s,
case LLDP_TLV_CHASSIS_ID:
case LLDP_TLV_PORT_ID:
- CHECK_TLV_SIZE(2, "Port Id");
+ CHECK_TLV_SIZE(2, "Port/Chassis Id");
+ CHECK_TLV_MAX_SIZE(256, "Port/Chassis Id");
tlv_subtype = PEEK_UINT8;
if (tlv_subtype == 0 || tlv_subtype > 7) {
VLOG_WARN("unknown subtype for tlv id received on %s",
@@ -438,10 +470,22 @@ lldp_decode(struct lldpd *cfg OVS_UNUSED, char *frame, int s,
b = xzalloc(tlv_size - 1);
PEEK_BYTES(b, tlv_size - 1);
if (tlv_type == LLDP_TLV_PORT_ID) {
+ if (port->p_id != NULL) {
+ VLOG_WARN("Port ID TLV received twice on %s",
+ hardware->h_ifname);
+ free(b);
+ goto malformed;
+ }
port->p_id_subtype = tlv_subtype;
port->p_id = b;
port->p_id_len = tlv_size - 1;
} else {
+ if (chassis->c_id != NULL) {
+ VLOG_WARN("Chassis ID TLV received twice on %s",
+ hardware->h_ifname);
+ free(b);
+ goto malformed;
+ }
chassis->c_id_subtype = tlv_subtype;
chassis->c_id = b;
chassis->c_id_len = tlv_size - 1;
@@ -449,6 +493,11 @@ lldp_decode(struct lldpd *cfg OVS_UNUSED, char *frame, int s,
break;
case LLDP_TLV_TTL:
+ if (ttl_received) {
+ VLOG_WARN("TTL TLV received twice on %s",
+ hardware->h_ifname);
+ goto malformed;
+ }
CHECK_TLV_SIZE(2, "TTL");
chassis->c_ttl = PEEK_UINT16;
ttl_received = true;
@@ -464,10 +513,13 @@ lldp_decode(struct lldpd *cfg OVS_UNUSED, char *frame, int s,
b = xzalloc(tlv_size + 1);
PEEK_BYTES(b, tlv_size);
if (tlv_type == LLDP_TLV_PORT_DESCR) {
+ free(port->p_descr);
port->p_descr = b;
} else if (tlv_type == LLDP_TLV_SYSTEM_NAME) {
+ free(chassis->c_name);
chassis->c_name = b;
} else {
+ free(chassis->c_descr);
chassis->c_descr = b;
}
break;
@@ -481,6 +533,11 @@ lldp_decode(struct lldpd *cfg OVS_UNUSED, char *frame, int s,
case LLDP_TLV_MGMT_ADDR:
CHECK_TLV_SIZE(1, "Management address");
addr_str_length = PEEK_UINT8;
+ if (addr_str_length > sizeof(addr_str_buffer)) {
+ VLOG_WARN("too large management address on %s",
+ hardware->h_ifname);
+ goto malformed;
+ }
CHECK_TLV_SIZE(1 + addr_str_length, "Management address");
PEEK_BYTES(addr_str_buffer, addr_str_length);
addr_length = addr_str_length - 1;
@@ -505,7 +562,7 @@ lldp_decode(struct lldpd *cfg OVS_UNUSED, char *frame, int s,
break;
case LLDP_TLV_ORG:
- CHECK_TLV_SIZE(4, "Organisational");
+ CHECK_TLV_SIZE(1 + sizeof orgid, "Organisational");
PEEK_BYTES(orgid, sizeof orgid);
tlv_subtype = PEEK_UINT8;
if (memcmp(dot1, orgid, sizeof orgid) == 0) {
@@ -625,6 +682,7 @@ lldp_decode(struct lldpd *cfg OVS_UNUSED, char *frame, int s,
VLOG_WARN("unknown tlv (%d) received on %s",
tlv_type,
hardware->h_ifname);
+ hardware->h_rx_unrecognized_cnt++;
goto malformed;
}
if (pos > tlv + tlv_size) {
diff --git a/lib/lldp/lldpd.c b/lib/lldp/lldpd.c
index 19e9305266..34738535db 100644
--- a/lib/lldp/lldpd.c
+++ b/lib/lldp/lldpd.c
@@ -244,6 +244,7 @@ lldpd_decode(struct lldpd *cfg, char *frame, int s,
if (s < sizeof(struct eth_header) + 4) {
/* Too short, just discard it */
+ hw->h_rx_discarded_cnt++;
return;
}
@@ -284,6 +285,7 @@ lldpd_decode(struct lldpd *cfg, char *frame, int s,
VLOG_DBG("function for %s protocol did not "
"decode this frame",
cfg->g_protocols[i].name);
+ hw->h_rx_discarded_cnt++;
return;
}
chassis->c_protocol = port->p_protocol = cfg->g_protocols[i].mode;
diff --git a/lib/meta-flow.c b/lib/meta-flow.c
index bc48d63049..a131adc918 100644
--- a/lib/meta-flow.c
+++ b/lib/meta-flow.c
@@ -2254,12 +2254,6 @@ mf_set(const struct mf_field *mf,
switch (mf->id) {
case MFF_CT_ZONE:
case MFF_CT_NW_PROTO:
- case MFF_CT_NW_SRC:
- case MFF_CT_NW_DST:
- case MFF_CT_IPV6_SRC:
- case MFF_CT_IPV6_DST:
- case MFF_CT_TP_SRC:
- case MFF_CT_TP_DST:
case MFF_RECIRC_ID:
case MFF_PACKET_TYPE:
case MFF_CONJ_ID:
@@ -2375,6 +2369,30 @@ mf_set(const struct mf_field *mf,
ntoh128(mask->be128));
break;
+ case MFF_CT_NW_SRC:
+ match_set_ct_nw_src_masked(match, value->be32, mask->be32);
+ break;
+
+ case MFF_CT_NW_DST:
+ match_set_ct_nw_dst_masked(match, value->be32, mask->be32);
+ break;
+
+ case MFF_CT_IPV6_SRC:
+ match_set_ct_ipv6_src_masked(match, &value->ipv6, &mask->ipv6);
+ break;
+
+ case MFF_CT_IPV6_DST:
+ match_set_ct_ipv6_dst_masked(match, &value->ipv6, &mask->ipv6);
+ break;
+
+ case MFF_CT_TP_SRC:
+ match_set_ct_tp_src_masked(match, value->be16, mask->be16);
+ break;
+
+ case MFF_CT_TP_DST:
+ match_set_ct_tp_dst_masked(match, value->be16, mask->be16);
+ break;
+
case MFF_ETH_DST:
match_set_dl_dst_masked(match, value->mac, mask->mac);
break;
diff --git a/lib/meta-flow.xml b/lib/meta-flow.xml
index 0b5c1d0087..e1b32d6ab4 100644
--- a/lib/meta-flow.xml
+++ b/lib/meta-flow.xml
@@ -3835,18 +3835,18 @@ r r c c c.
<ul>
<li>
- When <ref field="mpls_bos"/> is 1, there is another MPLS label
+ When <ref field="mpls_bos"/> is 0, there is another MPLS label
following this one, so the Ethertype passed to <code>pop_mpls</code>
should be an MPLS Ethertype. For example: <code>table=0,
- dl_type=0x8847, mpls_bos=1, actions=pop_mpls:0x8847,
+ dl_type=0x8847, mpls_bos=0, actions=pop_mpls:0x8847,
goto_table:1</code>
</li>
<li>
- When <ref field="mpls_bos"/> is 0, this MPLS label is the last one,
+ When <ref field="mpls_bos"/> is 1, this MPLS label is the last one,
so the Ethertype passed to <code>pop_mpls</code> should be a non-MPLS
Ethertype such as IPv4. For example: <code>table=1, dl_type=0x8847,
- mpls_bos=0, actions=pop_mpls:0x0800, goto_table:2</code>
+ mpls_bos=1, actions=pop_mpls:0x0800, goto_table:2</code>
</li>
</ul>
</field>
diff --git a/lib/netdev-dpdk.c b/lib/netdev-dpdk.c
index 20be56bc6c..a3283d3698 100644
--- a/lib/netdev-dpdk.c
+++ b/lib/netdev-dpdk.c
@@ -41,11 +41,13 @@
#include <rte_flow.h>
#include "cmap.h"
+#include "coverage.h"
#include "dirs.h"
#include "dp-packet.h"
#include "dpdk.h"
#include "dpif-netdev.h"
#include "fatal-signal.h"
+#include "if-notifier.h"
#include "netdev-provider.h"
#include "netdev-vport.h"
#include "odp-util.h"
@@ -71,6 +73,9 @@ enum {VIRTIO_RXQ, VIRTIO_TXQ, VIRTIO_QNUM};
VLOG_DEFINE_THIS_MODULE(netdev_dpdk);
static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(5, 20);
+COVERAGE_DEFINE(vhost_tx_contention);
+COVERAGE_DEFINE(vhost_notification);
+
#define DPDK_PORT_WATCHDOG_INTERVAL 5
#define OVS_CACHE_LINE_SIZE CACHE_LINE_SIZE
@@ -109,34 +114,6 @@ BUILD_ASSERT_DECL(MAX_NB_MBUF % ROUND_DOWN_POW2(MAX_NB_MBUF / MIN_NB_MBUF)
BUILD_ASSERT_DECL((MAX_NB_MBUF / ROUND_DOWN_POW2(MAX_NB_MBUF / MIN_NB_MBUF))
% MP_CACHE_SZ == 0);
-/*
- * DPDK XSTATS Counter names definition
- */
-#define XSTAT_RX_64_PACKETS "rx_size_64_packets"
-#define XSTAT_RX_65_TO_127_PACKETS "rx_size_65_to_127_packets"
-#define XSTAT_RX_128_TO_255_PACKETS "rx_size_128_to_255_packets"
-#define XSTAT_RX_256_TO_511_PACKETS "rx_size_256_to_511_packets"
-#define XSTAT_RX_512_TO_1023_PACKETS "rx_size_512_to_1023_packets"
-#define XSTAT_RX_1024_TO_1522_PACKETS "rx_size_1024_to_1522_packets"
-#define XSTAT_RX_1523_TO_MAX_PACKETS "rx_size_1523_to_max_packets"
-
-#define XSTAT_TX_64_PACKETS "tx_size_64_packets"
-#define XSTAT_TX_65_TO_127_PACKETS "tx_size_65_to_127_packets"
-#define XSTAT_TX_128_TO_255_PACKETS "tx_size_128_to_255_packets"
-#define XSTAT_TX_256_TO_511_PACKETS "tx_size_256_to_511_packets"
-#define XSTAT_TX_512_TO_1023_PACKETS "tx_size_512_to_1023_packets"
-#define XSTAT_TX_1024_TO_1522_PACKETS "tx_size_1024_to_1522_packets"
-#define XSTAT_TX_1523_TO_MAX_PACKETS "tx_size_1523_to_max_packets"
-
-#define XSTAT_RX_MULTICAST_PACKETS "rx_multicast_packets"
-#define XSTAT_TX_MULTICAST_PACKETS "tx_multicast_packets"
-#define XSTAT_RX_BROADCAST_PACKETS "rx_broadcast_packets"
-#define XSTAT_TX_BROADCAST_PACKETS "tx_broadcast_packets"
-#define XSTAT_RX_UNDERSIZED_ERRORS "rx_undersized_errors"
-#define XSTAT_RX_OVERSIZE_ERRORS "rx_oversize_errors"
-#define XSTAT_RX_FRAGMENTED_ERRORS "rx_fragmented_errors"
-#define XSTAT_RX_JABBER_ERRORS "rx_jabber_errors"
-
#define SOCKET0 0
/* Default size of Physical NIC RXQ */
@@ -157,12 +134,17 @@ BUILD_ASSERT_DECL((MAX_NB_MBUF / ROUND_DOWN_POW2(MAX_NB_MBUF / MIN_NB_MBUF))
typedef uint16_t dpdk_port_t;
#define DPDK_PORT_ID_FMT "%"PRIu16
-#define VHOST_ENQ_RETRY_NUM 8
+/* Minimum amount of vhost tx retries, effectively a disable. */
+#define VHOST_ENQ_RETRY_MIN 0
+/* Maximum amount of vhost tx retries. */
+#define VHOST_ENQ_RETRY_MAX 32
+/* Legacy default value for vhost tx retries. */
+#define VHOST_ENQ_RETRY_DEF 8
+
#define IF_NAME_SZ (PATH_MAX > IFNAMSIZ ? PATH_MAX : IFNAMSIZ)
static const struct rte_eth_conf port_conf = {
.rxmode = {
- .mq_mode = ETH_MQ_RX_RSS,
.split_hdr_size = 0,
.offloads = 0,
},
@@ -195,12 +177,28 @@ struct ufid_to_rte_flow_data {
static int new_device(int vid);
static void destroy_device(int vid);
static int vring_state_changed(int vid, uint16_t queue_id, int enable);
+static void vhost_guest_notified(int vid);
static const struct vhost_device_ops virtio_net_device_ops =
{
.new_device = new_device,
.destroy_device = destroy_device,
.vring_state_changed = vring_state_changed,
- .features_changed = NULL
+ .features_changed = NULL,
+ .guest_notified = vhost_guest_notified,
+};
+
+/* Custom software stats for dpdk ports */
+struct netdev_dpdk_sw_stats {
+ /* No. of retries when unable to transmit. */
+ uint64_t tx_retries;
+ /* Packet drops when unable to transmit; Probably Tx queue is full. */
+ uint64_t tx_failure_drops;
+ /* Packet length greater than device MTU. */
+ uint64_t tx_mtu_exceeded_drops;
+ /* Packet drops in egress policer processing. */
+ uint64_t tx_qos_drops;
+ /* Packet drops in ingress policer processing. */
+ uint64_t rx_qos_drops;
};
enum { DPDK_RING_SIZE = 256 };
@@ -391,6 +389,8 @@ struct netdev_dpdk {
bool attached;
/* If true, rte_eth_dev_start() was successfully called */
bool started;
+ bool reset_needed;
+ /* 1 pad byte here. */
struct eth_addr hwaddr;
int mtu;
int socket_id;
@@ -413,7 +413,9 @@ struct netdev_dpdk {
/* True if vHost device is 'up' and has been reconfigured at least once */
bool vhost_reconfigured;
- /* 3 pad bytes here. */
+
+ atomic_uint8_t vhost_tx_retries_max;
+ /* 2 pad bytes here. */
);
PADDED_MEMBERS(CACHE_LINE_SIZE,
@@ -437,9 +439,10 @@ struct netdev_dpdk {
PADDED_MEMBERS(CACHE_LINE_SIZE,
struct netdev_stats stats;
+ struct netdev_dpdk_sw_stats *sw_stats;
/* Protects stats */
rte_spinlock_t stats_lock;
- /* 44 pad bytes here. */
+ /* 36 pad bytes here. */
);
PADDED_MEMBERS(CACHE_LINE_SIZE,
@@ -493,6 +496,8 @@ struct netdev_rxq_dpdk {
static void netdev_dpdk_destruct(struct netdev *netdev);
static void netdev_dpdk_vhost_destruct(struct netdev *netdev);
+static int netdev_dpdk_get_sw_custom_stats(const struct netdev *,
+ struct netdev_custom_stats *);
static void netdev_dpdk_clear_xstats(struct netdev_dpdk *dev);
int netdev_dpdk_get_vid(const struct netdev_dpdk *dev);
@@ -915,6 +920,14 @@ dpdk_eth_dev_port_config(struct netdev_dpdk *dev, int n_rxq, int n_txq)
rte_eth_dev_info_get(dev->port_id, &info);
+ /* As of DPDK 18.11.6, it is not allowed to set a mq_mode for
+ * virtio PMD driver. */
+ if (!strcmp(info.driver_name, "net_virtio")) {
+ conf.rxmode.mq_mode = ETH_MQ_RX_NONE;
+ } else {
+ conf.rxmode.mq_mode = ETH_MQ_RX_RSS;
+ }
+
/* As of DPDK 17.11.1 a few PMDs require to explicitly enable
* scatter to support jumbo RX.
* Setting scatter for the device is done after checking for
@@ -1162,6 +1175,8 @@ common_construct(struct netdev *netdev, dpdk_port_t port_no,
ovsrcu_index_init(&dev->vid, -1);
dev->vhost_reconfigured = false;
dev->attached = false;
+ dev->started = false;
+ dev->reset_needed = false;
ovsrcu_init(&dev->qos_conf, NULL);
@@ -1194,6 +1209,9 @@ common_construct(struct netdev *netdev, dpdk_port_t port_no,
dev->rte_xstats_ids = NULL;
dev->rte_xstats_ids_size = 0;
+ dev->sw_stats = xzalloc(sizeof *dev->sw_stats);
+ dev->sw_stats->tx_retries = (dev->type == DPDK_DEV_VHOST) ? 0 : UINT64_MAX;
+
return 0;
}
@@ -1250,6 +1268,8 @@ vhost_common_construct(struct netdev *netdev)
return ENOMEM;
}
+ atomic_init(&dev->vhost_tx_retries_max, VHOST_ENQ_RETRY_DEF);
+
return common_construct(netdev, DPDK_ETH_PORT_ID_INVALID,
DPDK_DEV_VHOST, socket_id);
}
@@ -1366,6 +1386,7 @@ common_destruct(struct netdev_dpdk *dev)
ovs_list_remove(&dev->list_node);
free(ovsrcu_get_protected(struct ingress_policer *,
&dev->ingress_policer));
+ free(dev->sw_stats);
ovs_mutex_destroy(&dev->mutex);
}
@@ -1739,6 +1760,34 @@ netdev_dpdk_process_devargs(struct netdev_dpdk *dev,
return new_port_id;
}
+static int
+dpdk_eth_event_callback(dpdk_port_t port_id, enum rte_eth_event_type type,
+ void *param OVS_UNUSED, void *ret_param OVS_UNUSED)
+{
+ struct netdev_dpdk *dev;
+
+ switch ((int) type) {
+ case RTE_ETH_EVENT_INTR_RESET:
+ ovs_mutex_lock(&dpdk_mutex);
+ dev = netdev_dpdk_lookup_by_port_id(port_id);
+ if (dev) {
+ ovs_mutex_lock(&dev->mutex);
+ dev->reset_needed = true;
+ netdev_request_reconfigure(&dev->up);
+ VLOG_DBG_RL(&rl, "%s: Device reset requested.",
+ netdev_get_name(&dev->up));
+ ovs_mutex_unlock(&dev->mutex);
+ }
+ ovs_mutex_unlock(&dpdk_mutex);
+ break;
+
+ default:
+ /* Ignore all other types. */
+ break;
+ }
+ return 0;
+}
+
static void
dpdk_set_rxq_config(struct netdev_dpdk *dev, const struct smap *args)
OVS_REQUIRES(dev->mutex)
@@ -1775,6 +1824,7 @@ netdev_dpdk_set_config(struct netdev *netdev, const struct smap *args,
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
bool rx_fc_en, tx_fc_en, autoneg, lsc_interrupt_mode;
+ bool flow_control_requested = true;
enum rte_eth_fc_mode fc_mode;
static const enum rte_eth_fc_mode fc_mode_set[2][2] = {
{RTE_FC_NONE, RTE_FC_TX_PAUSE},
@@ -1797,7 +1847,7 @@ netdev_dpdk_set_config(struct netdev *netdev, const struct smap *args,
new_devargs = smap_get(args, "dpdk-devargs");
- if (dev->devargs && strcmp(new_devargs, dev->devargs)) {
+ if (dev->devargs && new_devargs && strcmp(new_devargs, dev->devargs)) {
/* The user requested a new device. If we return error, the caller
* will delete this netdev and try to recreate it. */
err = EAGAIN;
@@ -1862,15 +1912,34 @@ netdev_dpdk_set_config(struct netdev *netdev, const struct smap *args,
autoneg = smap_get_bool(args, "flow-ctrl-autoneg", false);
fc_mode = fc_mode_set[tx_fc_en][rx_fc_en];
+
+ if (!smap_get(args, "rx-flow-ctrl") && !smap_get(args, "tx-flow-ctrl")
+ && !smap_get(args, "flow-ctrl-autoneg")) {
+ /* FIXME: User didn't ask for flow control configuration.
+ * For now we'll not print a warning if flow control is not
+ * supported by the DPDK port. */
+ flow_control_requested = false;
+ }
+
+ /* Get the Flow control configuration. */
+ err = -rte_eth_dev_flow_ctrl_get(dev->port_id, &dev->fc_conf);
+ if (err) {
+ if (err == ENOTSUP) {
+ if (flow_control_requested) {
+ VLOG_WARN("%s: Flow control is not supported.",
+ netdev_get_name(netdev));
+ }
+ err = 0; /* Not fatal. */
+ } else {
+ VLOG_WARN("%s: Cannot get flow control parameters: %s",
+ netdev_get_name(netdev), rte_strerror(err));
+ }
+ goto out;
+ }
+
if (dev->fc_conf.mode != fc_mode || autoneg != dev->fc_conf.autoneg) {
dev->fc_conf.mode = fc_mode;
dev->fc_conf.autoneg = autoneg;
- /* Get the Flow control configuration for DPDK-ETH */
- err = rte_eth_dev_flow_ctrl_get(dev->port_id, &dev->fc_conf);
- if (err) {
- VLOG_WARN("Cannot get flow control parameters on port "
- DPDK_PORT_ID_FMT", err=%d", dev->port_id, err);
- }
dpdk_eth_flow_ctrl_setup(dev);
}
@@ -1901,6 +1970,7 @@ netdev_dpdk_vhost_client_set_config(struct netdev *netdev,
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
const char *path;
+ int max_tx_retries, cur_max_tx_retries;
ovs_mutex_lock(&dev->mutex);
if (!(dev->vhost_driver_flags & RTE_VHOST_USER_CLIENT)) {
@@ -1916,6 +1986,19 @@ netdev_dpdk_vhost_client_set_config(struct netdev *netdev,
netdev_request_reconfigure(netdev);
}
}
+
+ max_tx_retries = smap_get_int(args, "tx-retries-max",
+ VHOST_ENQ_RETRY_DEF);
+ if (max_tx_retries < VHOST_ENQ_RETRY_MIN
+ || max_tx_retries > VHOST_ENQ_RETRY_MAX) {
+ max_tx_retries = VHOST_ENQ_RETRY_DEF;
+ }
+ atomic_read_relaxed(&dev->vhost_tx_retries_max, &cur_max_tx_retries);
+ if (max_tx_retries != cur_max_tx_retries) {
+ atomic_store_relaxed(&dev->vhost_tx_retries_max, max_tx_retries);
+ VLOG_INFO("Max Tx retries for vhost device '%s' set to %d",
+ netdev_get_name(netdev), max_tx_retries);
+ }
ovs_mutex_unlock(&dev->mutex);
return 0;
@@ -2115,16 +2198,17 @@ netdev_dpdk_vhost_update_rx_size_counters(struct netdev_stats *stats,
}
static inline void
-netdev_dpdk_vhost_update_rx_counters(struct netdev_stats *stats,
+netdev_dpdk_vhost_update_rx_counters(struct netdev_dpdk *dev,
struct dp_packet **packets, int count,
- int dropped)
+ int qos_drops)
{
- int i;
- unsigned int packet_size;
+ struct netdev_stats *stats = &dev->stats;
struct dp_packet *packet;
+ unsigned int packet_size;
+ int i;
stats->rx_packets += count;
- stats->rx_dropped += dropped;
+ stats->rx_dropped += qos_drops;
for (i = 0; i < count; i++) {
packet = packets[i];
packet_size = dp_packet_size(packet);
@@ -2147,6 +2231,10 @@ netdev_dpdk_vhost_update_rx_counters(struct netdev_stats *stats,
stats->rx_bytes += packet_size;
}
+
+ if (OVS_UNLIKELY(qos_drops)) {
+ dev->sw_stats->rx_qos_drops += qos_drops;
+ }
}
/*
@@ -2159,7 +2247,7 @@ netdev_dpdk_vhost_rxq_recv(struct netdev_rxq *rxq,
struct netdev_dpdk *dev = netdev_dpdk_cast(rxq->netdev);
struct ingress_policer *policer = netdev_dpdk_get_ingress_policer(dev);
uint16_t nb_rx = 0;
- uint16_t dropped = 0;
+ uint16_t qos_drops = 0;
int qid = rxq->queue_id * VIRTIO_QNUM + VIRTIO_TXQ;
int vid = netdev_dpdk_get_vid(dev);
@@ -2186,16 +2274,16 @@ netdev_dpdk_vhost_rxq_recv(struct netdev_rxq *rxq,
}
if (policer) {
- dropped = nb_rx;
+ qos_drops = nb_rx;
nb_rx = ingress_policer_run(policer,
(struct rte_mbuf **) batch->packets,
nb_rx, true);
- dropped -= nb_rx;
+ qos_drops -= nb_rx;
}
rte_spinlock_lock(&dev->stats_lock);
- netdev_dpdk_vhost_update_rx_counters(&dev->stats, batch->packets,
- nb_rx, dropped);
+ netdev_dpdk_vhost_update_rx_counters(dev, batch->packets,
+ nb_rx, qos_drops);
rte_spinlock_unlock(&dev->stats_lock);
batch->count = nb_rx;
@@ -2237,6 +2325,7 @@ netdev_dpdk_rxq_recv(struct netdev_rxq *rxq, struct dp_packet_batch *batch,
if (OVS_UNLIKELY(dropped)) {
rte_spinlock_lock(&dev->stats_lock);
dev->stats.rx_dropped += dropped;
+ dev->sw_stats->rx_qos_drops += dropped;
rte_spinlock_unlock(&dev->stats_lock);
}
@@ -2296,13 +2385,17 @@ netdev_dpdk_filter_packet_len(struct netdev_dpdk *dev, struct rte_mbuf **pkts,
}
static inline void
-netdev_dpdk_vhost_update_tx_counters(struct netdev_stats *stats,
+netdev_dpdk_vhost_update_tx_counters(struct netdev_dpdk *dev,
struct dp_packet **packets,
int attempted,
- int dropped)
+ struct netdev_dpdk_sw_stats *sw_stats_add)
{
- int i;
+ int dropped = sw_stats_add->tx_mtu_exceeded_drops +
+ sw_stats_add->tx_qos_drops +
+ sw_stats_add->tx_failure_drops;
+ struct netdev_stats *stats = &dev->stats;
int sent = attempted - dropped;
+ int i;
stats->tx_packets += sent;
stats->tx_dropped += dropped;
@@ -2310,6 +2403,15 @@ netdev_dpdk_vhost_update_tx_counters(struct netdev_stats *stats,
for (i = 0; i < sent; i++) {
stats->tx_bytes += dp_packet_size(packets[i]);
}
+
+ if (OVS_UNLIKELY(dropped || sw_stats_add->tx_retries)) {
+ struct netdev_dpdk_sw_stats *sw_stats = dev->sw_stats;
+
+ sw_stats->tx_retries += sw_stats_add->tx_retries;
+ sw_stats->tx_failure_drops += sw_stats_add->tx_failure_drops;
+ sw_stats->tx_mtu_exceeded_drops += sw_stats_add->tx_mtu_exceeded_drops;
+ sw_stats->tx_qos_drops += sw_stats_add->tx_qos_drops;
+ }
}
static void
@@ -2318,9 +2420,11 @@ __netdev_dpdk_vhost_send(struct netdev *netdev, int qid,
{
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
struct rte_mbuf **cur_pkts = (struct rte_mbuf **) pkts;
- unsigned int total_pkts = cnt;
- unsigned int dropped = 0;
+ struct netdev_dpdk_sw_stats sw_stats_add;
+ unsigned int n_packets_to_free = cnt;
+ unsigned int total_packets = cnt;
int i, retries = 0;
+ int max_retries = VHOST_ENQ_RETRY_MIN;
int vid = netdev_dpdk_get_vid(dev);
qid = dev->tx_q[qid % netdev->n_txq].map;
@@ -2333,12 +2437,20 @@ __netdev_dpdk_vhost_send(struct netdev *netdev, int qid,
goto out;
}
- rte_spinlock_lock(&dev->tx_q[qid].tx_lock);
+ if (OVS_UNLIKELY(!rte_spinlock_trylock(&dev->tx_q[qid].tx_lock))) {
+ COVERAGE_INC(vhost_tx_contention);
+ rte_spinlock_lock(&dev->tx_q[qid].tx_lock);
+ }
cnt = netdev_dpdk_filter_packet_len(dev, cur_pkts, cnt);
+ sw_stats_add.tx_mtu_exceeded_drops = total_packets - cnt;
+
/* Check has QoS has been configured for the netdev */
+ sw_stats_add.tx_qos_drops = cnt;
cnt = netdev_dpdk_qos_run(dev, cur_pkts, cnt, true);
- dropped = total_pkts - cnt;
+ sw_stats_add.tx_qos_drops -= cnt;
+
+ n_packets_to_free = cnt;
do {
int vhost_qid = qid * VIRTIO_QNUM + VIRTIO_RXQ;
@@ -2350,21 +2462,31 @@ __netdev_dpdk_vhost_send(struct netdev *netdev, int qid,
cnt -= tx_pkts;
/* Prepare for possible retry.*/
cur_pkts = &cur_pkts[tx_pkts];
+ if (OVS_UNLIKELY(cnt && !retries)) {
+ /*
+ * Read max retries as there are packets not sent
+ * and no retries have already occurred.
+ */
+ atomic_read_relaxed(&dev->vhost_tx_retries_max, &max_retries);
+ }
} else {
/* No packets sent - do not retry.*/
break;
}
- } while (cnt && (retries++ < VHOST_ENQ_RETRY_NUM));
+ } while (cnt && (retries++ < max_retries));
rte_spinlock_unlock(&dev->tx_q[qid].tx_lock);
+ sw_stats_add.tx_failure_drops = cnt;
+ sw_stats_add.tx_retries = MIN(retries, max_retries);
+
rte_spinlock_lock(&dev->stats_lock);
- netdev_dpdk_vhost_update_tx_counters(&dev->stats, pkts, total_pkts,
- cnt + dropped);
+ netdev_dpdk_vhost_update_tx_counters(dev, pkts, total_packets,
+ &sw_stats_add);
rte_spinlock_unlock(&dev->stats_lock);
out:
- for (i = 0; i < total_pkts - dropped; i++) {
+ for (i = 0; i < n_packets_to_free; i++) {
dp_packet_delete(pkts[i]);
}
}
@@ -2383,14 +2505,18 @@ dpdk_do_tx_copy(struct netdev *netdev, int qid, struct dp_packet_batch *batch)
#endif
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
struct rte_mbuf *pkts[PKT_ARRAY_SIZE];
+ struct netdev_dpdk_sw_stats *sw_stats = dev->sw_stats;
uint32_t cnt = batch_cnt;
uint32_t dropped = 0;
+ uint32_t tx_failure = 0;
+ uint32_t mtu_drops = 0;
+ uint32_t qos_drops = 0;
if (dev->type != DPDK_DEV_VHOST) {
/* Check if QoS has been configured for this netdev. */
cnt = netdev_dpdk_qos_run(dev, (struct rte_mbuf **) batch->packets,
batch_cnt, false);
- dropped += batch_cnt - cnt;
+ qos_drops = batch_cnt - cnt;
}
uint32_t txcnt = 0;
@@ -2403,13 +2529,13 @@ dpdk_do_tx_copy(struct netdev *netdev, int qid, struct dp_packet_batch *batch)
VLOG_WARN_RL(&rl, "Too big size %u max_packet_len %d",
size, dev->max_packet_len);
- dropped++;
+ mtu_drops++;
continue;
}
pkts[txcnt] = rte_pktmbuf_alloc(dev->dpdk_mp->mp);
if (OVS_UNLIKELY(!pkts[txcnt])) {
- dropped += cnt - i;
+ dropped = cnt - i;
break;
}
@@ -2426,13 +2552,17 @@ dpdk_do_tx_copy(struct netdev *netdev, int qid, struct dp_packet_batch *batch)
__netdev_dpdk_vhost_send(netdev, qid, (struct dp_packet **) pkts,
txcnt);
} else {
- dropped += netdev_dpdk_eth_tx_burst(dev, qid, pkts, txcnt);
+ tx_failure = netdev_dpdk_eth_tx_burst(dev, qid, pkts, txcnt);
}
}
+ dropped += qos_drops + mtu_drops + tx_failure;
if (OVS_UNLIKELY(dropped)) {
rte_spinlock_lock(&dev->stats_lock);
dev->stats.tx_dropped += dropped;
+ sw_stats->tx_failure_drops += tx_failure;
+ sw_stats->tx_mtu_exceeded_drops += mtu_drops;
+ sw_stats->tx_qos_drops += qos_drops;
rte_spinlock_unlock(&dev->stats_lock);
}
}
@@ -2473,19 +2603,27 @@ netdev_dpdk_send__(struct netdev_dpdk *dev, int qid,
dpdk_do_tx_copy(netdev, qid, batch);
dp_packet_delete_batch(batch, true);
} else {
+ struct netdev_dpdk_sw_stats *sw_stats = dev->sw_stats;
int tx_cnt, dropped;
+ int tx_failure, mtu_drops, qos_drops;
int batch_cnt = dp_packet_batch_size(batch);
struct rte_mbuf **pkts = (struct rte_mbuf **) batch->packets;
tx_cnt = netdev_dpdk_filter_packet_len(dev, pkts, batch_cnt);
+ mtu_drops = batch_cnt - tx_cnt;
+ qos_drops = tx_cnt;
tx_cnt = netdev_dpdk_qos_run(dev, pkts, tx_cnt, true);
- dropped = batch_cnt - tx_cnt;
+ qos_drops -= tx_cnt;
- dropped += netdev_dpdk_eth_tx_burst(dev, qid, pkts, tx_cnt);
+ tx_failure = netdev_dpdk_eth_tx_burst(dev, qid, pkts, tx_cnt);
+ dropped = tx_failure + mtu_drops + qos_drops;
if (OVS_UNLIKELY(dropped)) {
rte_spinlock_lock(&dev->stats_lock);
dev->stats.tx_dropped += dropped;
+ sw_stats->tx_failure_drops += tx_failure;
+ sw_stats->tx_mtu_exceeded_drops += mtu_drops;
+ sw_stats->tx_qos_drops += qos_drops;
rte_spinlock_unlock(&dev->stats_lock);
}
}
@@ -2620,51 +2758,41 @@ netdev_dpdk_convert_xstats(struct netdev_stats *stats,
const struct rte_eth_xstat_name *names,
const unsigned int size)
{
+/* DPDK XSTATS Counter names definition. */
+#define DPDK_XSTATS \
+ DPDK_XSTAT(multicast, "rx_multicast_packets" ) \
+ DPDK_XSTAT(tx_multicast_packets, "tx_multicast_packets" ) \
+ DPDK_XSTAT(rx_broadcast_packets, "rx_broadcast_packets" ) \
+ DPDK_XSTAT(tx_broadcast_packets, "tx_broadcast_packets" ) \
+ DPDK_XSTAT(rx_undersized_errors, "rx_undersized_errors" ) \
+ DPDK_XSTAT(rx_oversize_errors, "rx_oversize_errors" ) \
+ DPDK_XSTAT(rx_fragmented_errors, "rx_fragmented_errors" ) \
+ DPDK_XSTAT(rx_jabber_errors, "rx_jabber_errors" ) \
+ DPDK_XSTAT(rx_1_to_64_packets, "rx_size_64_packets" ) \
+ DPDK_XSTAT(rx_65_to_127_packets, "rx_size_65_to_127_packets" ) \
+ DPDK_XSTAT(rx_128_to_255_packets, "rx_size_128_to_255_packets" ) \
+ DPDK_XSTAT(rx_256_to_511_packets, "rx_size_256_to_511_packets" ) \
+ DPDK_XSTAT(rx_512_to_1023_packets, "rx_size_512_to_1023_packets" ) \
+ DPDK_XSTAT(rx_1024_to_1522_packets, "rx_size_1024_to_1522_packets" ) \
+ DPDK_XSTAT(rx_1523_to_max_packets, "rx_size_1523_to_max_packets" ) \
+ DPDK_XSTAT(tx_1_to_64_packets, "tx_size_64_packets" ) \
+ DPDK_XSTAT(tx_65_to_127_packets, "tx_size_65_to_127_packets" ) \
+ DPDK_XSTAT(tx_128_to_255_packets, "tx_size_128_to_255_packets" ) \
+ DPDK_XSTAT(tx_256_to_511_packets, "tx_size_256_to_511_packets" ) \
+ DPDK_XSTAT(tx_512_to_1023_packets, "tx_size_512_to_1023_packets" ) \
+ DPDK_XSTAT(tx_1024_to_1522_packets, "tx_size_1024_to_1522_packets" ) \
+ DPDK_XSTAT(tx_1523_to_max_packets, "tx_size_1523_to_max_packets" )
+
for (unsigned int i = 0; i < size; i++) {
- if (strcmp(XSTAT_RX_64_PACKETS, names[i].name) == 0) {
- stats->rx_1_to_64_packets = xstats[i].value;
- } else if (strcmp(XSTAT_RX_65_TO_127_PACKETS, names[i].name) == 0) {
- stats->rx_65_to_127_packets = xstats[i].value;
- } else if (strcmp(XSTAT_RX_128_TO_255_PACKETS, names[i].name) == 0) {
- stats->rx_128_to_255_packets = xstats[i].value;
- } else if (strcmp(XSTAT_RX_256_TO_511_PACKETS, names[i].name) == 0) {
- stats->rx_256_to_511_packets = xstats[i].value;
- } else if (strcmp(XSTAT_RX_512_TO_1023_PACKETS, names[i].name) == 0) {
- stats->rx_512_to_1023_packets = xstats[i].value;
- } else if (strcmp(XSTAT_RX_1024_TO_1522_PACKETS, names[i].name) == 0) {
- stats->rx_1024_to_1522_packets = xstats[i].value;
- } else if (strcmp(XSTAT_RX_1523_TO_MAX_PACKETS, names[i].name) == 0) {
- stats->rx_1523_to_max_packets = xstats[i].value;
- } else if (strcmp(XSTAT_TX_64_PACKETS, names[i].name) == 0) {
- stats->tx_1_to_64_packets = xstats[i].value;
- } else if (strcmp(XSTAT_TX_65_TO_127_PACKETS, names[i].name) == 0) {
- stats->tx_65_to_127_packets = xstats[i].value;
- } else if (strcmp(XSTAT_TX_128_TO_255_PACKETS, names[i].name) == 0) {
- stats->tx_128_to_255_packets = xstats[i].value;
- } else if (strcmp(XSTAT_TX_256_TO_511_PACKETS, names[i].name) == 0) {
- stats->tx_256_to_511_packets = xstats[i].value;
- } else if (strcmp(XSTAT_TX_512_TO_1023_PACKETS, names[i].name) == 0) {
- stats->tx_512_to_1023_packets = xstats[i].value;
- } else if (strcmp(XSTAT_TX_1024_TO_1522_PACKETS, names[i].name) == 0) {
- stats->tx_1024_to_1522_packets = xstats[i].value;
- } else if (strcmp(XSTAT_TX_1523_TO_MAX_PACKETS, names[i].name) == 0) {
- stats->tx_1523_to_max_packets = xstats[i].value;
- } else if (strcmp(XSTAT_RX_MULTICAST_PACKETS, names[i].name) == 0) {
- stats->multicast = xstats[i].value;
- } else if (strcmp(XSTAT_TX_MULTICAST_PACKETS, names[i].name) == 0) {
- stats->tx_multicast_packets = xstats[i].value;
- } else if (strcmp(XSTAT_RX_BROADCAST_PACKETS, names[i].name) == 0) {
- stats->rx_broadcast_packets = xstats[i].value;
- } else if (strcmp(XSTAT_TX_BROADCAST_PACKETS, names[i].name) == 0) {
- stats->tx_broadcast_packets = xstats[i].value;
- } else if (strcmp(XSTAT_RX_UNDERSIZED_ERRORS, names[i].name) == 0) {
- stats->rx_undersized_errors = xstats[i].value;
- } else if (strcmp(XSTAT_RX_FRAGMENTED_ERRORS, names[i].name) == 0) {
- stats->rx_fragmented_errors = xstats[i].value;
- } else if (strcmp(XSTAT_RX_JABBER_ERRORS, names[i].name) == 0) {
- stats->rx_jabber_errors = xstats[i].value;
+#define DPDK_XSTAT(MEMBER, NAME) \
+ if (strcmp(NAME, names[i].name) == 0) { \
+ stats->MEMBER = xstats[i].value; \
+ continue; \
}
+ DPDK_XSTATS;
+#undef DPDK_XSTAT
}
+#undef DPDK_XSTATS
}
static int
@@ -2753,7 +2881,9 @@ netdev_dpdk_get_custom_stats(const struct netdev *netdev,
uint32_t i;
struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
- int rte_xstats_ret;
+ int rte_xstats_ret, sw_stats_size;
+
+ netdev_dpdk_get_sw_custom_stats(netdev, custom_stats);
ovs_mutex_lock(&dev->mutex);
@@ -2768,23 +2898,22 @@ netdev_dpdk_get_custom_stats(const struct netdev *netdev,
if (rte_xstats_ret > 0 &&
rte_xstats_ret <= dev->rte_xstats_ids_size) {
- custom_stats->size = rte_xstats_ret;
- custom_stats->counters =
- (struct netdev_custom_counter *) xcalloc(rte_xstats_ret,
- sizeof(struct netdev_custom_counter));
+ sw_stats_size = custom_stats->size;
+ custom_stats->size += rte_xstats_ret;
+ custom_stats->counters = xrealloc(custom_stats->counters,
+ custom_stats->size *
+ sizeof *custom_stats->counters);
for (i = 0; i < rte_xstats_ret; i++) {
- ovs_strlcpy(custom_stats->counters[i].name,
+ ovs_strlcpy(custom_stats->counters[sw_stats_size + i].name,
netdev_dpdk_get_xstat_name(dev,
dev->rte_xstats_ids[i]),
NETDEV_CUSTOM_STATS_NAME_SIZE);
- custom_stats->counters[i].value = values[i];
+ custom_stats->counters[sw_stats_size + i].value = values[i];
}
} else {
VLOG_WARN("Cannot get XSTATS values for port: "DPDK_PORT_ID_FMT,
dev->port_id);
- custom_stats->counters = NULL;
- custom_stats->size = 0;
/* Let's clear statistics cache, so it will be
* reconfigured */
netdev_dpdk_clear_xstats(dev);
@@ -2798,6 +2927,55 @@ netdev_dpdk_get_custom_stats(const struct netdev *netdev,
return 0;
}
+static int
+netdev_dpdk_get_sw_custom_stats(const struct netdev *netdev,
+ struct netdev_custom_stats *custom_stats)
+{
+ struct netdev_dpdk *dev = netdev_dpdk_cast(netdev);
+ int i, n;
+
+#define SW_CSTATS \
+ SW_CSTAT(tx_retries) \
+ SW_CSTAT(tx_failure_drops) \
+ SW_CSTAT(tx_mtu_exceeded_drops) \
+ SW_CSTAT(tx_qos_drops) \
+ SW_CSTAT(rx_qos_drops)
+
+#define SW_CSTAT(NAME) + 1
+ custom_stats->size = SW_CSTATS;
+#undef SW_CSTAT
+ custom_stats->counters = xcalloc(custom_stats->size,
+ sizeof *custom_stats->counters);
+
+ ovs_mutex_lock(&dev->mutex);
+
+ rte_spinlock_lock(&dev->stats_lock);
+ i = 0;
+#define SW_CSTAT(NAME) \
+ custom_stats->counters[i++].value = dev->sw_stats->NAME;
+ SW_CSTATS;
+#undef SW_CSTAT
+ rte_spinlock_unlock(&dev->stats_lock);
+
+ ovs_mutex_unlock(&dev->mutex);
+
+ i = 0;
+ n = 0;
+#define SW_CSTAT(NAME) \
+ if (custom_stats->counters[i].value != UINT64_MAX) { \
+ ovs_strlcpy(custom_stats->counters[n].name, \
+ "ovs_"#NAME, NETDEV_CUSTOM_STATS_NAME_SIZE); \
+ custom_stats->counters[n].value = custom_stats->counters[i].value; \
+ n++; \
+ } \
+ i++;
+ SW_CSTATS;
+#undef SW_CSTAT
+
+ custom_stats->size = n;
+ return 0;
+}
+
static int
netdev_dpdk_get_features(const struct netdev *netdev,
enum netdev_features *current,
@@ -3639,6 +3817,12 @@ vring_state_changed(int vid, uint16_t queue_id, int enable)
return 0;
}
+static
+void vhost_guest_notified(int vid OVS_UNUSED)
+{
+ COVERAGE_INC(vhost_notification);
+}
+
/*
* Retrieve the DPDK virtio device ID (vid) associated with a vhostuser
* or vhostuserclient netdev.
@@ -3672,6 +3856,8 @@ netdev_dpdk_class_init(void)
/* This function can be called for different classes. The initialization
* needs to be done only once */
if (ovsthread_once_start(&once)) {
+ int ret;
+
ovs_thread_create("dpdk_watchdog", dpdk_watchdog, NULL);
unixctl_command_register("netdev-dpdk/set-admin-state",
"[netdev] up|down", 1, 2,
@@ -3685,6 +3871,14 @@ netdev_dpdk_class_init(void)
"[netdev]", 0, 1,
netdev_dpdk_get_mempool_info, NULL);
+ ret = rte_eth_dev_callback_register(RTE_ETH_ALL,
+ RTE_ETH_EVENT_INTR_RESET,
+ dpdk_eth_event_callback, NULL);
+ if (ret != 0) {
+ VLOG_ERR("Ethernet device callback register error: %s",
+ rte_strerror(-ret));
+ }
+
ovsthread_once_done(&once);
}
@@ -4046,13 +4240,20 @@ netdev_dpdk_reconfigure(struct netdev *netdev)
&& dev->rxq_size == dev->requested_rxq_size
&& dev->txq_size == dev->requested_txq_size
&& dev->socket_id == dev->requested_socket_id
- && dev->started) {
+ && dev->started && !dev->reset_needed) {
/* Reconfiguration is unnecessary */
goto out;
}
- rte_eth_dev_stop(dev->port_id);
+ if (dev->reset_needed) {
+ rte_eth_dev_reset(dev->port_id);
+ if_notifier_manual_report();
+ dev->reset_needed = false;
+ } else {
+ rte_eth_dev_stop(dev->port_id);
+ }
+
dev->started = false;
err = netdev_dpdk_mempool_configure(dev);
@@ -4580,8 +4781,18 @@ netdev_dpdk_add_rte_flow_offload(struct netdev *netdev,
struct rte_flow_item_eth eth_mask;
memset(ð_spec, 0, sizeof(eth_spec));
memset(ð_mask, 0, sizeof(eth_mask));
- if (!eth_addr_is_zero(match->wc.masks.dl_src) ||
- !eth_addr_is_zero(match->wc.masks.dl_dst)) {
+ if (match->wc.masks.dl_type == OVS_BE16_MAX && is_ip_any(&match->flow)
+ && eth_addr_is_zero(match->wc.masks.dl_dst)
+ && eth_addr_is_zero(match->wc.masks.dl_src)) {
+ /*
+ * This is a temporary work around to fix ethernet pattern for partial
+ * hardware offload for X710 devices. This fix will be reverted once
+ * the issue is fixed within the i40e PMD driver.
+ */
+ add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_ETH, NULL, NULL);
+ } else if (match->wc.masks.dl_type ||
+ !eth_addr_is_zero(match->wc.masks.dl_src) ||
+ !eth_addr_is_zero(match->wc.masks.dl_dst)) {
rte_memcpy(ð_spec.dst, &match->flow.dl_dst, sizeof(eth_spec.dst));
rte_memcpy(ð_spec.src, &match->flow.dl_src, sizeof(eth_spec.src));
eth_spec.type = match->flow.dl_type;
@@ -4594,15 +4805,6 @@ netdev_dpdk_add_rte_flow_offload(struct netdev *netdev,
add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_ETH,
ð_spec, ð_mask);
- } else {
- /*
- * If user specifies a flow (like UDP flow) without L2 patterns,
- * OVS will at least set the dl_type. Normally, it's enough to
- * create an eth pattern just with it. Unluckily, some Intel's
- * NIC (such as XL710) doesn't support that. Below is a workaround,
- * which simply matches any L2 pkts.
- */
- add_flow_pattern(&patterns, RTE_FLOW_ITEM_TYPE_ETH, NULL, NULL);
}
/* VLAN */
@@ -5020,6 +5222,7 @@ static const struct netdev_class dpdk_vhost_class = {
.send = netdev_dpdk_vhost_send,
.get_carrier = netdev_dpdk_vhost_get_carrier,
.get_stats = netdev_dpdk_vhost_get_stats,
+ .get_custom_stats = netdev_dpdk_get_sw_custom_stats,
.get_status = netdev_dpdk_vhost_user_get_status,
.reconfigure = netdev_dpdk_vhost_reconfigure,
.rxq_recv = netdev_dpdk_vhost_rxq_recv
@@ -5034,6 +5237,7 @@ static const struct netdev_class dpdk_vhost_client_class = {
.send = netdev_dpdk_vhost_send,
.get_carrier = netdev_dpdk_vhost_get_carrier,
.get_stats = netdev_dpdk_vhost_get_stats,
+ .get_custom_stats = netdev_dpdk_get_sw_custom_stats,
.get_status = netdev_dpdk_vhost_user_get_status,
.reconfigure = netdev_dpdk_vhost_client_reconfigure,
.rxq_recv = netdev_dpdk_vhost_rxq_recv
diff --git a/lib/netdev-linux.c b/lib/netdev-linux.c
index 4ab645953b..1ff39e5da6 100644
--- a/lib/netdev-linux.c
+++ b/lib/netdev-linux.c
@@ -708,10 +708,6 @@ netdev_linux_update_lag(struct rtnetlink_change *change)
{
struct linux_lag_slave *lag;
- if (!rtnetlink_type_is_rtnlgrp_link(change->nlmsg_type)) {
- return;
- }
-
if (change->slave && netdev_linux_kind_is_lag(change->slave)) {
lag = shash_find_data(&lag_shash, change->ifname);
@@ -809,8 +805,11 @@ netdev_linux_run(const struct netdev_class *netdev_class OVS_UNUSED)
netdev_linux_update(netdev, nsid, &change);
ovs_mutex_unlock(&netdev->mutex);
}
- else if (!netdev_ && change.ifname) {
- /* Netdev is not present in OvS but its master could be. */
+
+ if (change.ifname &&
+ rtnetlink_type_is_rtnlgrp_link(change.nlmsg_type)) {
+
+ /* Need to try updating the LAG information. */
ovs_mutex_lock(&lag_mutex);
netdev_linux_update_lag(&change);
ovs_mutex_unlock(&lag_mutex);
@@ -5753,8 +5752,8 @@ netdev_linux_update_via_netlink(struct netdev_linux *netdev)
ofpbuf_init(&request, 0);
nl_msg_put_nlmsghdr(&request,
- sizeof(struct ifinfomsg) + NL_ATTR_SIZE(IFNAMSIZ),
- RTM_GETLINK, NLM_F_REQUEST);
+ sizeof(struct ifinfomsg) + NL_ATTR_SIZE(IFNAMSIZ) +
+ NL_A_U32_SIZE, RTM_GETLINK, NLM_F_REQUEST);
ofpbuf_put_zeros(&request, sizeof(struct ifinfomsg));
/* The correct identifiers for a Linux device are netnsid and ifindex,
diff --git a/lib/netdev-tc-offloads.c b/lib/netdev-tc-offloads.c
index d309810e45..b55108a260 100644
--- a/lib/netdev-tc-offloads.c
+++ b/lib/netdev-tc-offloads.c
@@ -574,7 +574,10 @@ parse_tc_flower_to_match(struct tc_flower *flower,
}
if (flower->tunnel) {
- match_set_tun_id(match, flower->key.tunnel.id);
+ if (flower->mask.tunnel.id) {
+ match_set_tun_id(match, flower->key.tunnel.id);
+ match->flow.tunnel.flags |= FLOW_TNL_F_KEY;
+ }
if (flower->key.tunnel.ipv4.ipv4_dst) {
match_set_tun_src(match, flower->key.tunnel.ipv4.ipv4_src);
match_set_tun_dst(match, flower->key.tunnel.ipv4.ipv4_dst);
@@ -628,7 +631,9 @@ parse_tc_flower_to_match(struct tc_flower *flower,
size_t tunnel_offset =
nl_msg_start_nested(buf, OVS_KEY_ATTR_TUNNEL);
- nl_msg_put_be64(buf, OVS_TUNNEL_KEY_ATTR_ID, action->encap.id);
+ if (action->encap.id_present) {
+ nl_msg_put_be64(buf, OVS_TUNNEL_KEY_ATTR_ID, action->encap.id);
+ }
if (action->encap.ipv4.ipv4_src) {
nl_msg_put_be32(buf, OVS_TUNNEL_KEY_ATTR_IPV4_SRC,
action->encap.ipv4.ipv4_src);
@@ -830,11 +835,13 @@ parse_put_flow_set_action(struct tc_flower *flower, struct tc_action *action,
tunnel_len = nl_attr_get_size(set);
action->type = TC_ACT_ENCAP;
+ action->encap.id_present = false;
flower->action_count++;
NL_ATTR_FOR_EACH_UNSAFE(tun_attr, tun_left, tunnel, tunnel_len) {
switch (nl_attr_type(tun_attr)) {
case OVS_TUNNEL_KEY_ATTR_ID: {
action->encap.id = nl_attr_get_be64(tun_attr);
+ action->encap.id_present = true;
}
break;
case OVS_TUNNEL_KEY_ATTR_IPV4_SRC: {
@@ -1099,6 +1106,7 @@ netdev_tc_flow_put(struct netdev *netdev, struct match *match,
flower.key.tunnel.tp_dst = tnl->tp_dst;
flower.mask.tunnel.tos = tnl_mask->ip_tos;
flower.mask.tunnel.ttl = tnl_mask->ip_ttl;
+ flower.mask.tunnel.id = (tnl->flags & FLOW_TNL_F_KEY) ? tnl_mask->tun_id : 0;
flower_match_to_tun_opt(&flower, tnl, tnl_mask);
flower.tunnel = true;
}
@@ -1113,6 +1121,10 @@ netdev_tc_flow_put(struct netdev *netdev, struct match *match,
}
mask->mpls_lse[0] = 0;
+ if (eth_type_vlan(key->vlans[0].tpid)) {
+ flower.key.encap_eth_type[0] = flower.key.eth_type;
+ flower.key.eth_type = key->vlans[0].tpid;
+ }
if (mask->vlans[0].tci) {
ovs_be16 vid_mask = mask->vlans[0].tci & htons(VLAN_VID_MASK);
ovs_be16 pcp_mask = mask->vlans[0].tci & htons(VLAN_PCP_MASK);
@@ -1133,8 +1145,6 @@ netdev_tc_flow_put(struct netdev *netdev, struct match *match,
VLOG_DBG_RL(&rl, "vlan_prio[0]: %d\n",
flower.key.vlan_prio[0]);
}
- flower.key.encap_eth_type[0] = flower.key.eth_type;
- flower.key.eth_type = key->vlans[0].tpid;
} else if (mask->vlans[0].tci == htons(0xffff) &&
ntohs(key->vlans[0].tci) == 0) {
/* exact && no vlan */
@@ -1144,6 +1154,10 @@ netdev_tc_flow_put(struct netdev *netdev, struct match *match,
}
}
+ if (eth_type_vlan(key->vlans[1].tpid)) {
+ flower.key.encap_eth_type[1] = flower.key.encap_eth_type[0];
+ flower.key.encap_eth_type[0] = key->vlans[1].tpid;
+ }
if (mask->vlans[1].tci) {
ovs_be16 vid_mask = mask->vlans[1].tci & htons(VLAN_VID_MASK);
ovs_be16 pcp_mask = mask->vlans[1].tci & htons(VLAN_PCP_MASK);
@@ -1163,8 +1177,6 @@ netdev_tc_flow_put(struct netdev *netdev, struct match *match,
flower.mask.vlan_prio[1] = vlan_tci_to_pcp(mask->vlans[1].tci);
VLOG_DBG_RL(&rl, "vlan_prio[1]: %d", flower.key.vlan_prio[1]);
}
- flower.key.encap_eth_type[1] = flower.key.encap_eth_type[0];
- flower.key.encap_eth_type[0] = key->vlans[1].tpid;
} else if (mask->vlans[1].tci == htons(0xffff) &&
ntohs(key->vlans[1].tci) == 0) {
/* exact && no vlan */
@@ -1256,14 +1268,19 @@ netdev_tc_flow_put(struct netdev *netdev, struct match *match,
}
}
+ /* ignore exact match on skb_mark of 0. */
+ if (mask->pkt_mark == UINT32_MAX && !key->pkt_mark) {
+ mask->pkt_mark = 0;
+ }
+
err = test_key_and_mask(match);
if (err) {
return err;
}
NL_ATTR_FOR_EACH(nla, left, actions, actions_len) {
- if (flower.action_count >= TCA_ACT_MAX_PRIO) {
- VLOG_DBG_RL(&rl, "Can only support %d actions", flower.action_count);
+ if (flower.action_count >= TCA_ACT_MAX_NUM) {
+ VLOG_DBG_RL(&rl, "Can only support %d actions", TCA_ACT_MAX_NUM);
return EOPNOTSUPP;
}
action = &flower.actions[flower.action_count];
@@ -1271,6 +1288,10 @@ netdev_tc_flow_put(struct netdev *netdev, struct match *match,
odp_port_t port = nl_attr_get_odp_port(nla);
struct netdev *outdev = netdev_ports_get(port, info->dpif_class);
+ if (!outdev) {
+ VLOG_DBG_RL(&rl, "Can't find netdev for output port %d", port);
+ return ENODEV;
+ }
action->ifindex_out = netdev_get_ifindex(outdev);
action->type = TC_ACT_OUTPUT;
flower.action_count++;
@@ -1317,8 +1338,12 @@ netdev_tc_flow_put(struct netdev *netdev, struct match *match,
block_id = get_block_id_from_netdev(netdev);
handle = get_ufid_tc_mapping(ufid, &prio, NULL);
if (handle && prio) {
+ bool flow_deleted;
+
VLOG_DBG_RL(&rl, "updating old handle: %d prio: %d", handle, prio);
- del_filter_and_ufid_mapping(ifindex, prio, handle, block_id, ufid);
+ flow_deleted = !del_filter_and_ufid_mapping(ifindex, prio, handle,
+ block_id, ufid);
+ info->tc_modify_flow_deleted = flow_deleted;
}
if (!prio) {
@@ -1524,11 +1549,16 @@ netdev_tc_init_flow_api(struct netdev *netdev)
return -ifindex;
}
+ block_id = get_block_id_from_netdev(netdev);
+ tc_del_filter(ifindex, 0, 0, block_id);
+
/* make sure there is no ingress qdisc */
tc_add_del_ingress_qdisc(ifindex, false, 0);
if (ovsthread_once_start(&block_once)) {
probe_tc_block_support(ifindex);
+ /* Need to re-fetch block id as it depends on feature availability. */
+ block_id = get_block_id_from_netdev(netdev);
ovsthread_once_done(&block_once);
}
@@ -1537,7 +1567,6 @@ netdev_tc_init_flow_api(struct netdev *netdev)
ovsthread_once_done(&multi_mask_once);
}
- block_id = get_block_id_from_netdev(netdev);
error = tc_add_del_ingress_qdisc(ifindex, true, block_id);
if (error && error != EEXIST) {
diff --git a/lib/netdev-vport.c b/lib/netdev-vport.c
index 808a43f99d..550fbe4722 100644
--- a/lib/netdev-vport.c
+++ b/lib/netdev-vport.c
@@ -189,22 +189,34 @@ netdev_vport_alloc(void)
int
netdev_vport_construct(struct netdev *netdev_)
{
+ const struct netdev_class *class = netdev_get_class(netdev_);
+ const char *dpif_port = netdev_vport_class_get_dpif_port(class);
struct netdev_vport *dev = netdev_vport_cast(netdev_);
+ const char *p, *name = netdev_get_name(netdev_);
const char *type = netdev_get_type(netdev_);
+ uint16_t port = 0;
ovs_mutex_init(&dev->mutex);
eth_addr_random(&dev->etheraddr);
- /* Add a default destination port for tunnel ports if none specified. */
+ if (name && dpif_port && (strlen(name) > strlen(dpif_port) + 1) &&
+ (!strncmp(name, dpif_port, strlen(dpif_port)))) {
+ p = name + strlen(dpif_port) + 1;
+ port = atoi(p);
+ }
+
+ /* If a destination port for tunnel ports is specified in the netdev
+ * name, use it instead of the default one. Otherwise, use the default
+ * destination port */
if (!strcmp(type, "geneve")) {
- dev->tnl_cfg.dst_port = htons(GENEVE_DST_PORT);
+ dev->tnl_cfg.dst_port = port ? htons(port) : htons(GENEVE_DST_PORT);
} else if (!strcmp(type, "vxlan")) {
- dev->tnl_cfg.dst_port = htons(VXLAN_DST_PORT);
+ dev->tnl_cfg.dst_port = port ? htons(port) : htons(VXLAN_DST_PORT);
update_vxlan_global_cfg(netdev_, NULL, &dev->tnl_cfg);
} else if (!strcmp(type, "lisp")) {
- dev->tnl_cfg.dst_port = htons(LISP_DST_PORT);
+ dev->tnl_cfg.dst_port = port ? htons(port) : htons(LISP_DST_PORT);
} else if (!strcmp(type, "stt")) {
- dev->tnl_cfg.dst_port = htons(STT_DST_PORT);
+ dev->tnl_cfg.dst_port = port ? htons(port) : htons(STT_DST_PORT);
}
dev->tnl_cfg.dont_fragment = true;
@@ -1210,7 +1222,8 @@ netdev_vport_tunnel_register(void)
.type = "ip6gre",
.build_header = netdev_gre_build_header,
.push_header = netdev_gre_push_header,
- .pop_header = netdev_gre_pop_header
+ .pop_header = netdev_gre_pop_header,
+ .get_ifindex = NETDEV_VPORT_GET_IFINDEX,
},
{{NULL, NULL, 0, 0}}
},
diff --git a/lib/netdev-windows.c b/lib/netdev-windows.c
index 4ad45ffa1b..3fad501e3e 100644
--- a/lib/netdev-windows.c
+++ b/lib/netdev-windows.c
@@ -156,6 +156,7 @@ netdev_windows_system_construct(struct netdev *netdev_)
struct netdev_windows_netdev_info info;
struct ofpbuf *buf;
int ret;
+ const char *type = NULL;
/* Query the attributes and runtime status of the netdev. */
ret = query_netdev(netdev_get_name(&netdev->up), &info, &buf);
@@ -167,6 +168,16 @@ netdev_windows_system_construct(struct netdev *netdev_)
}
ofpbuf_delete(buf);
+ /* Don't create netdev if ovs-type is "internal"
+ * but the type of netdev->up is "system". */
+ type = netdev_get_type(&netdev->up);
+ if (type && !strcmp(type, "system") &&
+ (info.ovs_type == OVS_VPORT_TYPE_INTERNAL)) {
+ VLOG_DBG("construct device %s, ovs_type: %u failed",
+ netdev_get_name(&netdev->up), info.ovs_type);
+ return 1;
+ }
+
netdev->change_seq = 1;
netdev->dev_type = info.ovs_type;
netdev->port_no = info.port_no;
diff --git a/lib/netdev.h b/lib/netdev.h
index d94817fb62..2d2d6f3a60 100644
--- a/lib/netdev.h
+++ b/lib/netdev.h
@@ -208,6 +208,9 @@ struct offload_info {
* it will be in the pkt meta data.
*/
uint32_t flow_mark;
+
+ bool tc_modify_flow_deleted; /* Indicate the tc modify flow put success
+ * to delete the original flow. */
};
struct dpif_class;
struct netdev_flow_dump;
diff --git a/lib/netlink.c b/lib/netlink.c
index de3ebcd0e7..26ab20bb4b 100644
--- a/lib/netlink.c
+++ b/lib/netlink.c
@@ -498,6 +498,7 @@ void
nl_msg_end_nested(struct ofpbuf *msg, size_t offset)
{
struct nlattr *attr = ofpbuf_at_assert(msg, offset, sizeof *attr);
+ ovs_assert(!nl_attr_oversized(msg->size - offset - NLA_HDRLEN));
attr->nla_len = msg->size - offset;
}
diff --git a/lib/nx-match.c b/lib/nx-match.c
index fd3eac0c0e..b6284b2432 100644
--- a/lib/nx-match.c
+++ b/lib/nx-match.c
@@ -1110,6 +1110,11 @@ nx_put_raw(struct ofpbuf *b, enum ofp_version oxm, const struct match *match,
mpls_lse_to_bos(flow->mpls_lse[0]));
}
+ if (match->wc.masks.mpls_lse[0] & htonl(MPLS_TTL_MASK)) {
+ nxm_put_8(&ctx, MFF_MPLS_TTL, oxm,
+ mpls_lse_to_ttl(flow->mpls_lse[0]));
+ }
+
if (match->wc.masks.mpls_lse[0] & htonl(MPLS_LABEL_MASK)) {
nxm_put_32(&ctx, MFF_MPLS_LABEL, oxm,
htonl(mpls_lse_to_label(flow->mpls_lse[0])));
diff --git a/lib/odp-execute.c b/lib/odp-execute.c
index 3b6890e952..1d33fcbb8d 100644
--- a/lib/odp-execute.c
+++ b/lib/odp-execute.c
@@ -25,6 +25,7 @@
#include <stdlib.h>
#include <string.h>
+#include "coverage.h"
#include "dp-packet.h"
#include "dpif.h"
#include "netlink.h"
@@ -36,6 +37,72 @@
#include "util.h"
#include "csum.h"
#include "conntrack.h"
+#include "openvswitch/vlog.h"
+
+VLOG_DEFINE_THIS_MODULE(odp_execute);
+COVERAGE_DEFINE(datapath_drop_sample_error);
+COVERAGE_DEFINE(datapath_drop_nsh_decap_error);
+COVERAGE_DEFINE(drop_action_of_pipeline);
+COVERAGE_DEFINE(drop_action_bridge_not_found);
+COVERAGE_DEFINE(drop_action_recursion_too_deep);
+COVERAGE_DEFINE(drop_action_too_many_resubmit);
+COVERAGE_DEFINE(drop_action_stack_too_deep);
+COVERAGE_DEFINE(drop_action_no_recirculation_context);
+COVERAGE_DEFINE(drop_action_recirculation_conflict);
+COVERAGE_DEFINE(drop_action_too_many_mpls_labels);
+COVERAGE_DEFINE(drop_action_invalid_tunnel_metadata);
+COVERAGE_DEFINE(drop_action_unsupported_packet_type);
+COVERAGE_DEFINE(drop_action_congestion);
+COVERAGE_DEFINE(drop_action_forwarding_disabled);
+
+static void
+dp_update_drop_action_counter(enum xlate_error drop_reason,
+ int delta)
+{
+ static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(1, 5);
+
+ switch (drop_reason) {
+ case XLATE_OK:
+ COVERAGE_ADD(drop_action_of_pipeline, delta);
+ break;
+ case XLATE_BRIDGE_NOT_FOUND:
+ COVERAGE_ADD(drop_action_bridge_not_found, delta);
+ break;
+ case XLATE_RECURSION_TOO_DEEP:
+ COVERAGE_ADD(drop_action_recursion_too_deep, delta);
+ break;
+ case XLATE_TOO_MANY_RESUBMITS:
+ COVERAGE_ADD(drop_action_too_many_resubmit, delta);
+ break;
+ case XLATE_STACK_TOO_DEEP:
+ COVERAGE_ADD(drop_action_stack_too_deep, delta);
+ break;
+ case XLATE_NO_RECIRCULATION_CONTEXT:
+ COVERAGE_ADD(drop_action_no_recirculation_context, delta);
+ break;
+ case XLATE_RECIRCULATION_CONFLICT:
+ COVERAGE_ADD(drop_action_recirculation_conflict, delta);
+ break;
+ case XLATE_TOO_MANY_MPLS_LABELS:
+ COVERAGE_ADD(drop_action_too_many_mpls_labels, delta);
+ break;
+ case XLATE_INVALID_TUNNEL_METADATA:
+ COVERAGE_ADD(drop_action_invalid_tunnel_metadata, delta);
+ break;
+ case XLATE_UNSUPPORTED_PACKET_TYPE:
+ COVERAGE_ADD(drop_action_unsupported_packet_type, delta);
+ break;
+ case XLATE_CONGESTION_DROP:
+ COVERAGE_ADD(drop_action_congestion, delta);
+ break;
+ case XLATE_FORWARDING_DISABLED:
+ COVERAGE_ADD(drop_action_forwarding_disabled, delta);
+ break;
+ case XLATE_MAX:
+ default:
+ VLOG_ERR_RL(&rl, "Invalid Drop reason type: %d", drop_reason);
+ }
+}
/* Masked copy of an ethernet address. 'src' is already properly masked. */
static void
@@ -589,6 +656,7 @@ odp_execute_sample(void *dp, struct dp_packet *packet, bool steal,
case OVS_SAMPLE_ATTR_PROBABILITY:
if (random_uint32() >= nl_attr_get_u32(a)) {
if (steal) {
+ COVERAGE_INC(datapath_drop_sample_error);
dp_packet_delete(packet);
}
return;
@@ -642,6 +710,49 @@ odp_execute_clone(void *dp, struct dp_packet_batch *batch, bool steal,
}
}
+static void
+odp_execute_check_pkt_len(void *dp, struct dp_packet *packet, bool steal,
+ const struct nlattr *action,
+ odp_execute_cb dp_execute_action)
+{
+ static const struct nl_policy ovs_cpl_policy[] = {
+ [OVS_CHECK_PKT_LEN_ATTR_PKT_LEN] = { .type = NL_A_U16 },
+ [OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER] = { .type = NL_A_NESTED },
+ [OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL]
+ = { .type = NL_A_NESTED },
+ };
+ struct nlattr *attrs[ARRAY_SIZE(ovs_cpl_policy)];
+
+ if (!nl_parse_nested(action, ovs_cpl_policy, attrs, ARRAY_SIZE(attrs))) {
+ OVS_NOT_REACHED();
+ }
+
+ const struct nlattr *a;
+ struct dp_packet_batch pb;
+
+ a = attrs[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN];
+ bool is_greater = dp_packet_size(packet) > nl_attr_get_u16(a);
+ if (is_greater) {
+ a = attrs[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER];
+ } else {
+ a = attrs[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL];
+ }
+
+ if (!steal) {
+ /* The 'subactions' may modify the packet, but the modification
+ * should not propagate beyond this action. Make a copy
+ * the packet in case we don't own the packet, so that the
+ * 'subactions' are only applid to check_pkt_len. 'odp_execute_actions'
+ * will free the clone. */
+ packet = dp_packet_clone(packet);
+ }
+ /* If nl_attr_get(a) is NULL, the packet will be freed by
+ * odp_execute_actions. */
+ dp_packet_batch_init_packet(&pb, packet);
+ odp_execute_actions(dp, &pb, true, nl_attr_get(a), nl_attr_get_size(a),
+ dp_execute_action);
+}
+
static bool
requires_datapath_assistance(const struct nlattr *a)
{
@@ -673,6 +784,8 @@ requires_datapath_assistance(const struct nlattr *a)
case OVS_ACTION_ATTR_PUSH_NSH:
case OVS_ACTION_ATTR_POP_NSH:
case OVS_ACTION_ATTR_CT_CLEAR:
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+ case OVS_ACTION_ATTR_DROP:
return false;
case OVS_ACTION_ATTR_UNSPEC:
@@ -889,6 +1002,7 @@ odp_execute_actions(void *dp, struct dp_packet_batch *batch, bool steal,
if (pop_nsh(packet)) {
dp_packet_batch_refill(batch, packet, i);
} else {
+ COVERAGE_INC(datapath_drop_nsh_decap_error);
dp_packet_delete(packet);
}
}
@@ -900,6 +1014,27 @@ odp_execute_actions(void *dp, struct dp_packet_batch *batch, bool steal,
}
break;
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+ DP_PACKET_BATCH_FOR_EACH (i, packet, batch) {
+ odp_execute_check_pkt_len(dp, packet, steal && last_action, a,
+ dp_execute_action);
+ }
+
+ if (last_action) {
+ /* We do not need to free the packets.
+ * odp_execute_check_pkt_len() has stolen them. */
+ return;
+ }
+ break;
+
+ case OVS_ACTION_ATTR_DROP:{
+ const enum xlate_error *drop_reason = nl_attr_get(a);
+
+ dp_update_drop_action_counter(*drop_reason,
+ dp_packet_batch_size(batch));
+ dp_packet_delete_batch(batch, steal);
+ return;
+ }
case OVS_ACTION_ATTR_OUTPUT:
case OVS_ACTION_ATTR_TUNNEL_PUSH:
case OVS_ACTION_ATTR_TUNNEL_POP:
diff --git a/lib/odp-util.c b/lib/odp-util.c
index d41c9369f2..5b04adf0ed 100644
--- a/lib/odp-util.c
+++ b/lib/odp-util.c
@@ -131,6 +131,8 @@ odp_action_len(uint16_t type)
case OVS_ACTION_ATTR_CLONE: return ATTR_LEN_VARIABLE;
case OVS_ACTION_ATTR_PUSH_NSH: return ATTR_LEN_VARIABLE;
case OVS_ACTION_ATTR_POP_NSH: return 0;
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN: return ATTR_LEN_VARIABLE;
+ case OVS_ACTION_ATTR_DROP: return sizeof(uint32_t);
case OVS_ACTION_ATTR_UNSPEC:
case __OVS_ACTION_ATTR_MAX:
@@ -378,7 +380,8 @@ format_odp_push_nsh_action(struct ds *ds,
break;
}
default:
- OVS_NOT_REACHED();
+ ds_put_cstr(ds, ",<error: unknown mdtype>");
+ break;
}
ds_put_format(ds, ")");
}
@@ -1042,6 +1045,42 @@ format_odp_set_nsh(struct ds *ds, const struct nlattr *attr)
ds_put_cstr(ds, "))");
}
+static void
+format_odp_check_pkt_len_action(struct ds *ds, const struct nlattr *attr,
+ const struct hmap *portno_names OVS_UNUSED)
+{
+ static const struct nl_policy ovs_cpl_policy[] = {
+ [OVS_CHECK_PKT_LEN_ATTR_PKT_LEN] = { .type = NL_A_U16 },
+ [OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER] = { .type = NL_A_NESTED },
+ [OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL]
+ = { .type = NL_A_NESTED },
+ };
+ struct nlattr *a[ARRAY_SIZE(ovs_cpl_policy)];
+ ds_put_cstr(ds, "check_pkt_len");
+ if (!nl_parse_nested(attr, ovs_cpl_policy, a, ARRAY_SIZE(a))) {
+ ds_put_cstr(ds, "(error)");
+ return;
+ }
+
+ if (!a[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER] ||
+ !a[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL]) {
+ ds_put_cstr(ds, "(error)");
+ return;
+ }
+
+ uint16_t pkt_len = nl_attr_get_u16(a[OVS_CHECK_PKT_LEN_ATTR_PKT_LEN]);
+ ds_put_format(ds, "(size=%u,gt(", pkt_len);
+ const struct nlattr *acts;
+ acts = a[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER];
+ format_odp_actions(ds, nl_attr_get(acts), nl_attr_get_size(acts),
+ portno_names);
+
+ ds_put_cstr(ds, "),le(");
+ acts = a[OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL];
+ format_odp_actions(ds, nl_attr_get(acts), nl_attr_get_size(acts),
+ portno_names);
+ ds_put_cstr(ds, "))");
+}
static void
format_odp_action(struct ds *ds, const struct nlattr *a,
@@ -1181,6 +1220,12 @@ format_odp_action(struct ds *ds, const struct nlattr *a,
case OVS_ACTION_ATTR_POP_NSH:
ds_put_cstr(ds, "pop_nsh()");
break;
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+ format_odp_check_pkt_len_action(ds, a, portno_names);
+ break;
+ case OVS_ACTION_ATTR_DROP:
+ ds_put_cstr(ds, "drop");
+ break;
case OVS_ACTION_ATTR_UNSPEC:
case __OVS_ACTION_ATTR_MAX:
default:
@@ -1380,14 +1425,20 @@ parse_odp_userspace_action(const char *s, struct ofpbuf *actions)
int n1 = -1;
if (ovs_scan(&s[n], ",tunnel_out_port=%"SCNi32")%n",
&tunnel_out_port, &n1)) {
- odp_put_userspace_action(pid, user_data, user_data_size,
- tunnel_out_port, include_actions, actions);
- res = n + n1;
+ res = odp_put_userspace_action(pid, user_data, user_data_size,
+ tunnel_out_port, include_actions,
+ actions, NULL);
+ if (!res) {
+ res = n + n1;
+ }
goto out;
} else if (s[n] == ')') {
- odp_put_userspace_action(pid, user_data, user_data_size,
- ODPP_NONE, include_actions, actions);
- res = n + 1;
+ res = odp_put_userspace_action(pid, user_data, user_data_size,
+ ODPP_NONE, include_actions,
+ actions, NULL);
+ if (!res) {
+ res = n + 1;
+ }
goto out;
}
}
@@ -2397,6 +2448,52 @@ parse_odp_action(const char *s, const struct simap *port_names,
}
}
+ {
+ uint16_t pkt_len;
+ int n = -1;
+ if (ovs_scan(s, "check_pkt_len(size=%"SCNi16",gt(%n", &pkt_len, &n)) {
+ size_t cpl_ofs, actions_ofs;
+ cpl_ofs = nl_msg_start_nested(actions,
+ OVS_ACTION_ATTR_CHECK_PKT_LEN);
+ nl_msg_put_u16(actions, OVS_CHECK_PKT_LEN_ATTR_PKT_LEN, pkt_len);
+ actions_ofs = nl_msg_start_nested(
+ actions, OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER);
+
+ int retval;
+ if (!strncasecmp(s + n, "drop", 4)) {
+ n += 4;
+ } else {
+ retval = parse_action_list(s + n, port_names, actions);
+ if (retval < 0) {
+ return retval;
+ }
+
+ n += retval;
+ }
+ nl_msg_end_nested(actions, actions_ofs);
+ retval = -1;
+ if (!ovs_scan(s + n, "),le(%n", &retval)) {
+ return -EINVAL;
+ }
+ n += retval;
+
+ actions_ofs = nl_msg_start_nested(
+ actions, OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL);
+ if (!strncasecmp(s + n, "drop", 4)) {
+ n += 4;
+ } else {
+ retval = parse_action_list(s + n, port_names, actions);
+ if (retval < 0) {
+ return retval;
+ }
+ n += retval;
+ }
+ nl_msg_end_nested(actions, actions_ofs);
+ nl_msg_end_nested(actions, cpl_ofs);
+ return s[n + 1] == ')' ? n + 2 : -EINVAL;
+ }
+ }
+
{
int retval;
@@ -2433,6 +2530,7 @@ odp_actions_from_string(const char *s, const struct simap *port_names,
size_t old_size;
if (!strcasecmp(s, "drop")) {
+ nl_msg_put_u32(actions, OVS_ACTION_ATTR_DROP, XLATE_OK);
return 0;
}
@@ -5185,13 +5283,16 @@ erspan_to_attr(struct ofpbuf *a, const void *data_)
do { \
len = 0;
-#define SCAN_END_NESTED() \
- SCAN_FINISH(); \
- nl_msg_end_nested(key, key_offset); \
- if (mask) { \
- nl_msg_end_nested(mask, mask_offset); \
- } \
- return s - start; \
+#define SCAN_END_NESTED() \
+ SCAN_FINISH(); \
+ if (nl_attr_oversized(key->size - key_offset - NLA_HDRLEN)) { \
+ return -E2BIG; \
+ } \
+ nl_msg_end_nested(key, key_offset); \
+ if (mask) { \
+ nl_msg_end_nested(mask, mask_offset); \
+ } \
+ return s - start; \
}
#define SCAN_FIELD_NESTED__(NAME, TYPE, SCAN_AS, ATTR, FUNC) \
@@ -5757,26 +5858,28 @@ odp_flow_key_from_flow__(const struct odp_flow_key_parms *parms,
if (flow->ct_nw_proto) {
if (parms->support.ct_orig_tuple
&& flow->dl_type == htons(ETH_TYPE_IP)) {
- struct ovs_key_ct_tuple_ipv4 ct = {
- data->ct_nw_src,
- data->ct_nw_dst,
- data->ct_tp_src,
- data->ct_tp_dst,
- data->ct_nw_proto,
- };
- nl_msg_put_unspec(buf, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, &ct,
- sizeof ct);
+ struct ovs_key_ct_tuple_ipv4 *ct;
+
+ /* 'struct ovs_key_ct_tuple_ipv4' has padding, clear it. */
+ ct = nl_msg_put_unspec_zero(buf, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4,
+ sizeof *ct);
+ ct->ipv4_src = data->ct_nw_src;
+ ct->ipv4_dst = data->ct_nw_dst;
+ ct->src_port = data->ct_tp_src;
+ ct->dst_port = data->ct_tp_dst;
+ ct->ipv4_proto = data->ct_nw_proto;
} else if (parms->support.ct_orig_tuple6
&& flow->dl_type == htons(ETH_TYPE_IPV6)) {
- struct ovs_key_ct_tuple_ipv6 ct = {
- data->ct_ipv6_src,
- data->ct_ipv6_dst,
- data->ct_tp_src,
- data->ct_tp_dst,
- data->ct_nw_proto,
- };
- nl_msg_put_unspec(buf, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, &ct,
- sizeof ct);
+ struct ovs_key_ct_tuple_ipv6 *ct;
+
+ /* 'struct ovs_key_ct_tuple_ipv6' has padding, clear it. */
+ ct = nl_msg_put_unspec_zero(buf, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6,
+ sizeof *ct);
+ ct->ipv6_src = data->ct_ipv6_src;
+ ct->ipv6_dst = data->ct_ipv6_dst;
+ ct->src_port = data->ct_tp_src;
+ ct->dst_port = data->ct_tp_dst;
+ ct->ipv6_proto = data->ct_nw_proto;
}
}
if (parms->support.recirc) {
@@ -5986,6 +6089,10 @@ odp_key_from_dp_packet(struct ofpbuf *buf, const struct dp_packet *packet)
nl_msg_put_u32(buf, OVS_KEY_ATTR_PRIORITY, md->skb_priority);
+ if (md->dp_hash) {
+ nl_msg_put_u32(buf, OVS_KEY_ATTR_DP_HASH, md->dp_hash);
+ }
+
if (flow_tnl_dst_is_set(&md->tunnel)) {
tun_key_to_attr(buf, &md->tunnel, &md->tunnel, NULL, NULL);
}
@@ -6957,15 +7064,18 @@ odp_key_fitness_to_string(enum odp_key_fitness fitness)
/* Appends an OVS_ACTION_ATTR_USERSPACE action to 'odp_actions' that specifies
* Netlink PID 'pid'. If 'userdata' is nonnull, adds a userdata attribute
- * whose contents are the 'userdata_size' bytes at 'userdata' and returns the
- * offset within 'odp_actions' of the start of the cookie. (If 'userdata' is
- * null, then the return value is not meaningful.) */
-size_t
+ * whose contents are the 'userdata_size' bytes at 'userdata' and sets
+ * 'odp_actions_ofs' if nonnull with the offset within 'odp_actions' of the
+ * start of the cookie. (If 'userdata' is null, then the 'odp_actions_ofs'
+ * value is not meaningful.)
+ *
+ * Returns negative error code on failure. */
+int
odp_put_userspace_action(uint32_t pid,
const void *userdata, size_t userdata_size,
odp_port_t tunnel_out_port,
bool include_actions,
- struct ofpbuf *odp_actions)
+ struct ofpbuf *odp_actions, size_t *odp_actions_ofs)
{
size_t userdata_ofs;
size_t offset;
@@ -6973,6 +7083,9 @@ odp_put_userspace_action(uint32_t pid,
offset = nl_msg_start_nested(odp_actions, OVS_ACTION_ATTR_USERSPACE);
nl_msg_put_u32(odp_actions, OVS_USERSPACE_ATTR_PID, pid);
if (userdata) {
+ if (nl_attr_oversized(userdata_size)) {
+ return -E2BIG;
+ }
userdata_ofs = odp_actions->size + NLA_HDRLEN;
/* The OVS kernel module before OVS 1.11 and the upstream Linux kernel
@@ -6998,9 +7111,16 @@ odp_put_userspace_action(uint32_t pid,
if (include_actions) {
nl_msg_put_flag(odp_actions, OVS_USERSPACE_ATTR_ACTIONS);
}
+ if (nl_attr_oversized(odp_actions->size - offset - NLA_HDRLEN)) {
+ return -E2BIG;
+ }
nl_msg_end_nested(odp_actions, offset);
- return userdata_ofs;
+ if (odp_actions_ofs) {
+ *odp_actions_ofs = userdata_ofs;
+ }
+
+ return 0;
}
void
diff --git a/lib/odp-util.h b/lib/odp-util.h
index aa8e6efe37..706fbeb8db 100644
--- a/lib/odp-util.h
+++ b/lib/odp-util.h
@@ -351,11 +351,12 @@ struct user_action_cookie {
};
BUILD_ASSERT_DECL(sizeof(struct user_action_cookie) == 48);
-size_t odp_put_userspace_action(uint32_t pid,
- const void *userdata, size_t userdata_size,
- odp_port_t tunnel_out_port,
- bool include_actions,
- struct ofpbuf *odp_actions);
+int odp_put_userspace_action(uint32_t pid,
+ const void *userdata, size_t userdata_size,
+ odp_port_t tunnel_out_port,
+ bool include_actions,
+ struct ofpbuf *odp_actions,
+ size_t *odp_actions_ofs);
void odp_put_tunnel_action(const struct flow_tnl *tunnel,
struct ofpbuf *odp_actions,
const char *tnl_type);
diff --git a/lib/ofp-actions.c b/lib/ofp-actions.c
index 68132c9455..20deed07bd 100644
--- a/lib/ofp-actions.c
+++ b/lib/ofp-actions.c
@@ -355,6 +355,9 @@ enum ofp_raw_action_type {
/* NX1.3+(48): void. */
NXAST_RAW_DEC_NSH_TTL,
+ /* NX1.0+(49): struct nx_action_check_pkt_larger, ... VLMFF */
+ NXAST_RAW_CHECK_PKT_LARGER,
+
/* ## ------------------ ## */
/* ## Debugging actions. ## */
/* ## ------------------ ## */
@@ -492,6 +495,7 @@ ofpact_next_flattened(const struct ofpact *ofpact)
case OFPACT_ENCAP:
case OFPACT_DECAP:
case OFPACT_DEC_NSH_TTL:
+ case OFPACT_CHECK_PKT_LARGER:
return ofpact_next(ofpact);
case OFPACT_CLONE:
@@ -4322,6 +4326,7 @@ decode_NXAST_RAW_ENCAP(const struct nx_action_encap *nae,
{
struct ofpact_encap *encap;
const struct ofp_ed_prop_header *ofp_prop;
+ const size_t encap_ofs = out->size;
size_t props_len;
uint16_t n_props = 0;
int err;
@@ -4349,6 +4354,7 @@ decode_NXAST_RAW_ENCAP(const struct nx_action_encap *nae,
}
n_props++;
}
+ encap = ofpbuf_at_assert(out, encap_ofs, sizeof *encap);
encap->n_props = n_props;
out->header = &encap->ofpact;
ofpact_finish_ENCAP(out, &encap);
@@ -7400,6 +7406,124 @@ check_WRITE_METADATA(const struct ofpact_metadata *a OVS_UNUSED,
return 0;
}
+/* Check packet length action. */
+
+struct nx_action_check_pkt_larger {
+ ovs_be16 type; /* OFPAT_VENDOR. */
+ ovs_be16 len; /* 24. */
+ ovs_be32 vendor; /* NX_VENDOR_ID. */
+ ovs_be16 subtype; /* NXAST_OUTPUT_REG. */
+ ovs_be16 pkt_len; /* Length of the packet to check. */
+ ovs_be16 offset; /* Result bit offset in destination. */
+ /* Followed by:
+ * - 'dst', as an OXM/NXM header (either 4 or 8 bytes).
+ * - Enough 0-bytes to pad the action out to 24 bytes. */
+ uint8_t pad[10];
+};
+
+OFP_ASSERT(sizeof(struct nx_action_check_pkt_larger) == 24);
+
+static enum ofperr
+decode_NXAST_RAW_CHECK_PKT_LARGER(
+ const struct nx_action_check_pkt_larger *ncpl,
+ enum ofp_version ofp_version OVS_UNUSED,
+ const struct vl_mff_map *vl_mff_map, uint64_t *tlv_bitmap,
+ struct ofpbuf *out)
+{
+ struct ofpact_check_pkt_larger *check_pkt_larger;
+ enum ofperr error;
+
+ check_pkt_larger = ofpact_put_CHECK_PKT_LARGER(out);
+ check_pkt_larger->pkt_len = ntohs(ncpl->pkt_len);
+ check_pkt_larger->dst.ofs = ntohs(ncpl->offset);
+ check_pkt_larger->dst.n_bits = 1;
+
+ struct ofpbuf b = ofpbuf_const_initializer(ncpl, ntohs(ncpl->len));
+ ofpbuf_pull(&b, OBJECT_OFFSETOF(ncpl, pad));
+
+ error = mf_vl_mff_nx_pull_header(&b, vl_mff_map,
+ &check_pkt_larger->dst.field,
+ NULL, tlv_bitmap);
+ if (error) {
+ return error;
+ }
+
+ if (!is_all_zeros(b.data, b.size)) {
+ return OFPERR_NXBRC_MUST_BE_ZERO;
+ }
+
+ return mf_check_dst(&check_pkt_larger->dst, NULL);
+}
+
+static void
+encode_CHECK_PKT_LARGER(const struct ofpact_check_pkt_larger *check_pkt_larger,
+ enum ofp_version ofp_version OVS_UNUSED,
+ struct ofpbuf *out)
+{
+ struct nx_action_check_pkt_larger *ncpl = put_NXAST_CHECK_PKT_LARGER(out);
+ ncpl->pkt_len = htons(check_pkt_larger->pkt_len);
+ ncpl->offset = htons(check_pkt_larger->dst.ofs);
+
+ if (check_pkt_larger->dst.field) {
+ size_t size = out->size;
+ out->size = size - sizeof ncpl->pad;
+ nx_put_mff_header(out, check_pkt_larger->dst.field, 0, false);
+ out->size = size;
+ }
+}
+
+static char * OVS_WARN_UNUSED_RESULT
+parse_CHECK_PKT_LARGER(char *arg, const struct ofpact_parse_params *pp)
+{
+ char *value;
+ char *delim;
+ char *key;
+ char *error = set_field_split_str(arg, &key, &value, &delim);
+ if (error) {
+ return error;
+ }
+
+ delim[0] = '\0';
+ if (value[strlen(value) - 1] == ')') {
+ value[strlen(value) - 1] = '\0';
+ }
+ struct mf_subfield dst;
+ error = mf_parse_subfield(&dst, key);
+ if (error) {
+ return error;
+ }
+
+ if (dst.n_bits != 1) {
+ return xstrdup("Only 1-bit destination field is allowed");
+ }
+
+ struct ofpact_check_pkt_larger *check_pkt_larger =
+ ofpact_put_CHECK_PKT_LARGER(pp->ofpacts);
+ error = str_to_u16(value, NULL, &check_pkt_larger->pkt_len);
+ if (error) {
+ return error;
+ }
+ check_pkt_larger->dst = dst;
+ return NULL;
+}
+
+static void
+format_CHECK_PKT_LARGER(const struct ofpact_check_pkt_larger *a,
+ const struct ofpact_format_params *fp)
+{
+ ds_put_format(fp->s, "%scheck_pkt_larger(%s%"PRIu32")->",
+ colors.param, colors.end, a->pkt_len);
+ mf_format_subfield(&a->dst, fp->s);
+}
+
+static enum ofperr
+check_CHECK_PKT_LARGER(const struct ofpact_check_pkt_larger *a OVS_UNUSED,
+ const struct ofpact_check_params *cp OVS_UNUSED)
+{
+ return 0;
+}
+
+
/* Goto-Table instruction. */
static void
@@ -7686,6 +7810,7 @@ action_set_classify(const struct ofpact *a)
case OFPACT_WRITE_METADATA:
case OFPACT_DEBUG_RECIRC:
case OFPACT_DEBUG_SLOW:
+ case OFPACT_CHECK_PKT_LARGER:
return ACTION_SLOT_INVALID;
default:
@@ -7885,6 +8010,7 @@ ovs_instruction_type_from_ofpact_type(enum ofpact_type type)
case OFPACT_ENCAP:
case OFPACT_DECAP:
case OFPACT_DEC_NSH_TTL:
+ case OFPACT_CHECK_PKT_LARGER:
default:
return OVSINST_OFPIT11_APPLY_ACTIONS;
}
@@ -8755,6 +8881,7 @@ ofpact_outputs_to_port(const struct ofpact *ofpact, ofp_port_t port)
case OFPACT_ENCAP:
case OFPACT_DECAP:
case OFPACT_DEC_NSH_TTL:
+ case OFPACT_CHECK_PKT_LARGER:
default:
return false;
}
@@ -8991,7 +9118,6 @@ ofpacts_parse__(char *str, const struct ofpact_parse_params *pp,
enum ofpact_type type;
char *error = NULL;
ofp_port_t port;
-
if (ofpact_type_from_name(key, &type)) {
error = ofpact_parse(type, value, pp);
inst = ovs_instruction_type_from_ofpact_type(type);
diff --git a/lib/ofp-ed-props.c b/lib/ofp-ed-props.c
index 28382e0123..02a9235d51 100644
--- a/lib/ofp-ed-props.c
+++ b/lib/ofp-ed-props.c
@@ -49,7 +49,7 @@ decode_ed_prop(const struct ofp_ed_prop_header **ofp_prop,
return OFPERR_NXBAC_BAD_ED_PROP;
}
struct ofpact_ed_prop_nsh_md_type *pnmt =
- ofpbuf_put_uninit(out, sizeof(*pnmt));
+ ofpbuf_put_zeros(out, sizeof *pnmt);
pnmt->header.prop_class = prop_class;
pnmt->header.type = prop_type;
pnmt->header.len = len;
@@ -108,6 +108,7 @@ encode_ed_prop(const struct ofpact_ed_prop **prop,
opnmt->header.len =
offsetof(struct ofp_ed_prop_nsh_md_type, pad);
opnmt->md_type = pnmt->md_type;
+ memset(opnmt->pad, 0, sizeof opnmt->pad);
prop_len = sizeof(*pnmt);
break;
}
diff --git a/lib/ofp-group.c b/lib/ofp-group.c
index 6857164f01..9c1b5b6cc3 100644
--- a/lib/ofp-group.c
+++ b/lib/ofp-group.c
@@ -64,7 +64,7 @@ ofputil_group_from_string(const char *s, uint32_t *group_idp)
void
ofputil_format_group(uint32_t group_id, struct ds *s)
{
- char name[MAX_GROUP_NAME_LEN];
+ char name[MAX_GROUP_NAME_LEN + 1];
ofputil_group_to_string(group_id, name, sizeof name);
ds_put_cstr(s, name);
diff --git a/lib/ofp-packet.c b/lib/ofp-packet.c
index aa3417c9b0..4638d8192c 100644
--- a/lib/ofp-packet.c
+++ b/lib/ofp-packet.c
@@ -420,6 +420,7 @@ enum nx_continuation_prop_type {
NXCPT_COOKIE,
NXCPT_ACTIONS,
NXCPT_ACTION_SET,
+ NXCPT_ODP_PORT,
};
/* Only NXT_PACKET_IN2 (not NXT_RESUME) should include NXCPT_USERDATA, so this
@@ -506,6 +507,10 @@ ofputil_put_packet_in_private(const struct ofputil_packet_in_private *pin,
ofpprop_end(msg, start);
}
+ if (pin->odp_port) {
+ ofpprop_put_u32(msg, NXCPT_ODP_PORT, odp_to_u32(pin->odp_port));
+ }
+
if (msg->size > inner_ofs) {
ofpprop_end(msg, continuation_ofs);
} else {
@@ -876,6 +881,13 @@ ofputil_decode_packet_in_private(const struct ofp_header *oh, bool loose,
error = parse_actions_property(&payload, oh->version, &action_set);
break;
+ case NXCPT_ODP_PORT: {
+ uint32_t value;
+ error = ofpprop_parse_u32(&payload, &value);
+ pin->odp_port = u32_to_odp(value);
+ break;
+ }
+
default:
error = OFPPROP_UNKNOWN(loose, "continuation", type);
break;
@@ -1011,6 +1023,11 @@ ofputil_packet_in_private_format(struct ds *s,
ds_put_char(s, '\n');
}
+ if (pin->odp_port) {
+ ds_put_format(s, " continuation.odp_port=%"PRIu32, pin->odp_port);
+ ds_put_char(s, '\n');
+ }
+
if (verbosity > 0) {
char *packet = ofp_packet_to_string(
public->packet, public->packet_len,
diff --git a/lib/ofp-parse.c b/lib/ofp-parse.c
index a8b5a877c5..a90b926efb 100644
--- a/lib/ofp-parse.c
+++ b/lib/ofp-parse.c
@@ -335,6 +335,16 @@ ofputil_parse_key_value(char **stringp, char **keyp, char **valuep)
char *value = *stringp;
size_t value_len = parse_value(value, value_delims);
char value_delim = value[value_len];
+
+ /* Handle the special case if the value is of the form "(x)->y".
+ * After parsing, 'valuep' will be pointing to - "x)->y".
+ * */
+ if (key_delim == '(' && value[value_len] == ')' &&
+ value[value_len + 1] == '-' && value[value_len + 2] == '>') {
+ value_delims = ", \t\r\n";
+ value_len += parse_value(&value[value_len], value_delims);
+ value_delim = value[value_len];
+ }
value[value_len] = '\0';
*stringp += value_len + (value_delim != '\0');
diff --git a/lib/ovs-actions.xml b/lib/ovs-actions.xml
index fec0b95fe7..758083e771 100644
--- a/lib/ovs-actions.xml
+++ b/lib/ovs-actions.xml
@@ -1453,6 +1453,43 @@ $ ovs-ofctl -O OpenFlow10 add-flow br0 actions=mod_nw_src:1.2.3.4
</p>
</conformance>
</action>
+
+ <action name="CHECK_PKT_LARGER">
+ <h2>The <code>check_pkt_larger</code> action</h2>
+ <syntax>
+ <code>check_pkt_larger(<var>pkt_len</var>)-><var>dst</var></code>
+ </syntax>
+
+ <p>
+ Checks if the packet is larger than the specified length in
+ <var>pkt_len</var>. If so, stores 1 in <var>dst</var>, which should be
+ a 1-bit field; if not, stores 0.
+ </p>
+
+ <p>
+ The packet length to check againt the argument <var>pkt_len</var>
+ includes the L2 header and L2 payload of the packet, but not the VLAN
+ tag (if present).
+ </p>
+
+ <p>
+ Examples:
+ </p>
+
+ <ul>
+ <li>
+ <code>check_pkt_larger(1500)->reg0[0]</code>
+ </li>
+
+ <li>
+ <code>check_pkt_larger(8000)->reg9[10]</code>
+ </li>
+ </ul>
+
+ <p>
+ This action was added in Open vSwitch 2.11.90.
+ </p>
+ </action>
</group>
<group title="Metadata Actions">
diff --git a/lib/ovs-rcu.c b/lib/ovs-rcu.c
index ebc8120f0f..cde1e925ba 100644
--- a/lib/ovs-rcu.c
+++ b/lib/ovs-rcu.c
@@ -30,6 +30,8 @@
VLOG_DEFINE_THIS_MODULE(ovs_rcu);
+#define MIN_CBS 16
+
struct ovsrcu_cb {
void (*function)(void *aux);
void *aux;
@@ -37,7 +39,8 @@ struct ovsrcu_cb {
struct ovsrcu_cbset {
struct ovs_list list_node;
- struct ovsrcu_cb cbs[16];
+ struct ovsrcu_cb *cbs;
+ size_t n_allocated;
int n_cbs;
};
@@ -310,16 +313,19 @@ ovsrcu_postpone__(void (*function)(void *aux), void *aux)
cbset = perthread->cbset;
if (!cbset) {
cbset = perthread->cbset = xmalloc(sizeof *perthread->cbset);
+ cbset->cbs = xmalloc(MIN_CBS * sizeof *cbset->cbs);
+ cbset->n_allocated = MIN_CBS;
cbset->n_cbs = 0;
}
+ if (cbset->n_cbs == cbset->n_allocated) {
+ cbset->cbs = x2nrealloc(cbset->cbs, &cbset->n_allocated,
+ sizeof *cbset->cbs);
+ }
+
cb = &cbset->cbs[cbset->n_cbs++];
cb->function = function;
cb->aux = aux;
-
- if (cbset->n_cbs >= ARRAY_SIZE(cbset->cbs)) {
- ovsrcu_flush_cbset(perthread);
- }
}
static bool
@@ -341,6 +347,7 @@ ovsrcu_call_postponed(void)
for (cb = cbset->cbs; cb < &cbset->cbs[cbset->n_cbs]; cb++) {
cb->function(cb->aux);
}
+ free(cbset->cbs);
free(cbset);
}
diff --git a/lib/ovs-router.c b/lib/ovs-router.c
index bfb2b7071b..09b81c6e5a 100644
--- a/lib/ovs-router.c
+++ b/lib/ovs-router.c
@@ -505,7 +505,7 @@ ovs_router_flush(void)
ovs_mutex_lock(&mutex);
classifier_defer(&cls);
CLS_FOR_EACH(rt, cr, &cls) {
- if (rt->priority == rt->plen) {
+ if (rt->priority == rt->plen || rt->local) {
rt_entry_delete__(&rt->cr);
}
}
diff --git a/lib/ovsdb-idl.c b/lib/ovsdb-idl.c
index 4c9862b88b..7e66d37e9d 100644
--- a/lib/ovsdb-idl.c
+++ b/lib/ovsdb-idl.c
@@ -577,7 +577,6 @@ ovsdb_idl_db_clear(struct ovsdb_idl_db *db)
struct ovsdb_idl_table *table = &db->tables[i];
struct ovsdb_idl_row *row, *next_row;
- table->cond_changed = false;
if (hmap_is_empty(&table->rows)) {
continue;
}
@@ -600,7 +599,6 @@ ovsdb_idl_db_clear(struct ovsdb_idl_db *db)
}
}
- db->cond_changed = false;
db->cond_seqno = 0;
ovsdb_idl_db_track_clear(db);
@@ -1771,6 +1769,11 @@ ovsdb_idl_db_track_clear(struct ovsdb_idl_db *db)
free(row->updated);
row->updated = NULL;
}
+
+ row->change_seqno[OVSDB_IDL_CHANGE_INSERT] =
+ row->change_seqno[OVSDB_IDL_CHANGE_MODIFY] =
+ row->change_seqno[OVSDB_IDL_CHANGE_DELETE] = 0;
+
ovs_list_remove(&row->track_node);
ovs_list_init(&row->track_node);
if (ovsdb_idl_row_is_orphan(row)) {
@@ -2351,22 +2354,25 @@ ovsdb_idl_process_update2(struct ovsdb_idl_table *table,
return true;
}
-/* Recursively add rows to tracked change lists for current row
- * and the rows that reference this row. */
+/* Recursively add rows to tracked change lists for all rows that reference
+ 'row'. */
static void
add_tracked_change_for_references(struct ovsdb_idl_row *row)
{
- if (ovs_list_is_empty(&row->track_node) &&
- ovsdb_idl_track_is_set(row->table)) {
- ovs_list_push_back(&row->table->track_list,
- &row->track_node);
- row->change_seqno[OVSDB_IDL_CHANGE_MODIFY]
- = row->table->change_seqno[OVSDB_IDL_CHANGE_MODIFY]
- = row->table->db->change_seqno + 1;
-
- const struct ovsdb_idl_arc *arc;
- LIST_FOR_EACH (arc, dst_node, &row->dst_arcs) {
- add_tracked_change_for_references(arc->src);
+ const struct ovsdb_idl_arc *arc;
+ LIST_FOR_EACH (arc, dst_node, &row->dst_arcs) {
+ struct ovsdb_idl_row *ref = arc->src;
+
+ if (ovs_list_is_empty(&ref->track_node) &&
+ ovsdb_idl_track_is_set(ref->table)) {
+ ovs_list_push_back(&ref->table->track_list,
+ &ref->track_node);
+
+ ref->change_seqno[OVSDB_IDL_CHANGE_MODIFY]
+ = ref->table->change_seqno[OVSDB_IDL_CHANGE_MODIFY]
+ = ref->table->db->change_seqno + 1;
+
+ add_tracked_change_for_references(ref);
}
}
}
@@ -2434,7 +2440,14 @@ ovsdb_idl_row_change__(struct ovsdb_idl_row *row, const struct json *row_json,
row->change_seqno[change]
= row->table->change_seqno[change]
= row->table->db->change_seqno + 1;
+
if (table->modes[column_idx] & OVSDB_IDL_TRACK) {
+ if (ovs_list_is_empty(&row->track_node) &&
+ ovsdb_idl_track_is_set(row->table)) {
+ ovs_list_push_back(&row->table->track_list,
+ &row->track_node);
+ }
+
add_tracked_change_for_references(row);
if (!row->updated) {
row->updated = bitmap_allocate(class->n_columns);
@@ -4496,6 +4509,7 @@ ovsdb_idl_txn_insert(struct ovsdb_idl_txn *txn,
hmap_insert(&row->table->rows, &row->hmap_node, uuid_hash(&row->uuid));
hmap_insert(&txn->txn_rows, &row->txn_node, uuid_hash(&row->uuid));
ovsdb_idl_add_to_indexes(row);
+
return row;
}
diff --git a/lib/packets.h b/lib/packets.h
index 8ae054a742..5e438db9dd 100644
--- a/lib/packets.h
+++ b/lib/packets.h
@@ -744,6 +744,9 @@ struct icmp_header {
};
BUILD_ASSERT_DECL(ICMP_HEADER_LEN == sizeof(struct icmp_header));
+/* ICMPV4 */
+#define ICMP_ERROR_DATA_L4_LEN 8
+
#define IGMP_HEADER_LEN 8
struct igmp_header {
uint8_t igmp_type;
diff --git a/lib/pvector.c b/lib/pvector.c
index aaeee92147..cc527fdc41 100644
--- a/lib/pvector.c
+++ b/lib/pvector.c
@@ -33,7 +33,7 @@ pvector_impl_alloc(size_t size)
struct pvector_impl *impl;
impl = xmalloc(sizeof *impl + size * sizeof impl->vector[0]);
- impl->size = 0;
+ atomic_init(&impl->size, 0);
impl->allocated = size;
return impl;
@@ -117,18 +117,22 @@ pvector_insert(struct pvector *pvec, void *ptr, int priority)
{
struct pvector_impl *temp = pvec->temp;
struct pvector_impl *old = pvector_impl_get(pvec);
+ size_t size;
ovs_assert(ptr != NULL);
+ /* There is no possible concurrent writer. Insertions must be protected
+ * by mutex or be always excuted from the same thread. */
+ atomic_read_relaxed(&old->size, &size);
+
/* Check if can add to the end without reallocation. */
- if (!temp && old->allocated > old->size &&
- (!old->size || priority <= old->vector[old->size - 1].priority)) {
- old->vector[old->size].ptr = ptr;
- old->vector[old->size].priority = priority;
+ if (!temp && old->allocated > size &&
+ (!size || priority <= old->vector[size - 1].priority)) {
+ old->vector[size].ptr = ptr;
+ old->vector[size].priority = priority;
/* Size increment must not be visible to the readers before the new
* entry is stored. */
- atomic_thread_fence(memory_order_release);
- ++old->size;
+ atomic_store_explicit(&old->size, size + 1, memory_order_release);
} else {
if (!temp) {
temp = pvector_impl_dup(old);
diff --git a/lib/pvector.h b/lib/pvector.h
index b175b213d1..3d491ee257 100644
--- a/lib/pvector.h
+++ b/lib/pvector.h
@@ -62,8 +62,8 @@ struct pvector_entry {
};
struct pvector_impl {
- size_t size; /* Number of entries in the vector. */
- size_t allocated; /* Number of allocated entries. */
+ atomic_size_t size; /* Number of entries in the vector. */
+ size_t allocated; /* Number of allocated entries. */
struct pvector_entry vector[];
};
@@ -174,12 +174,17 @@ pvector_cursor_init(const struct pvector *pvec,
{
const struct pvector_impl *impl;
struct pvector_cursor cursor;
+ size_t size;
impl = ovsrcu_get(struct pvector_impl *, &pvec->impl);
- ovs_prefetch_range(impl->vector, impl->size * sizeof impl->vector[0]);
+ /* Use memory_order_acquire to ensure entry access can not be
+ * reordered to happen before size read. */
+ atomic_read_explicit(&CONST_CAST(struct pvector_impl *, impl)->size,
+ &size, memory_order_acquire);
+ ovs_prefetch_range(impl->vector, size * sizeof impl->vector[0]);
- cursor.size = impl->size;
+ cursor.size = size;
cursor.vector = impl->vector;
cursor.entry_idx = -1;
diff --git a/lib/sha1.c b/lib/sha1.c
index 4f48ef2102..87360d9cd0 100644
--- a/lib/sha1.c
+++ b/lib/sha1.c
@@ -197,7 +197,7 @@ sha1_init(struct sha1_ctx *sha_info)
* inputLen: The length of the input buffer.
*/
void
-sha1_update(struct sha1_ctx *ctx, const void *buffer_, size_t count)
+sha1_update(struct sha1_ctx *ctx, const void *buffer_, uint32_t count)
{
const uint8_t *buffer = buffer_;
unsigned int i;
@@ -274,7 +274,7 @@ sha1_final(struct sha1_ctx *ctx, uint8_t digest[SHA1_DIGEST_SIZE])
/* Computes the hash of 'n' bytes in 'data' into 'digest'. */
void
-sha1_bytes(const void *data, size_t n, uint8_t digest[SHA1_DIGEST_SIZE])
+sha1_bytes(const void *data, uint32_t n, uint8_t digest[SHA1_DIGEST_SIZE])
{
struct sha1_ctx ctx;
diff --git a/lib/sha1.h b/lib/sha1.h
index eda265dfc5..a635ff7689 100644
--- a/lib/sha1.h
+++ b/lib/sha1.h
@@ -45,9 +45,9 @@ struct sha1_ctx {
};
void sha1_init(struct sha1_ctx *);
-void sha1_update(struct sha1_ctx *, const void *, size_t);
+void sha1_update(struct sha1_ctx *, const void *, uint32_t size);
void sha1_final(struct sha1_ctx *, uint8_t digest[SHA1_DIGEST_SIZE]);
-void sha1_bytes(const void *, size_t, uint8_t digest[SHA1_DIGEST_SIZE]);
+void sha1_bytes(const void *, uint32_t size, uint8_t digest[SHA1_DIGEST_SIZE]);
#define SHA1_FMT \
"%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x" \
diff --git a/lib/stream-ssl.c b/lib/stream-ssl.c
index 63b141d1ca..343dced587 100644
--- a/lib/stream-ssl.c
+++ b/lib/stream-ssl.c
@@ -425,6 +425,7 @@ do_ca_cert_bootstrap(struct stream *stream)
static char *
get_peer_common_name(const struct ssl_stream *sslv)
{
+ char *peer_name = NULL;
X509 *peer_cert = SSL_get_peer_certificate(sslv->ssl);
if (!peer_cert) {
return NULL;
@@ -433,18 +434,18 @@ get_peer_common_name(const struct ssl_stream *sslv)
int cn_index = X509_NAME_get_index_by_NID(X509_get_subject_name(peer_cert),
NID_commonName, -1);
if (cn_index < 0) {
- return NULL;
+ goto error;
}
X509_NAME_ENTRY *cn_entry = X509_NAME_get_entry(
X509_get_subject_name(peer_cert), cn_index);
if (!cn_entry) {
- return NULL;
+ goto error;
}
ASN1_STRING *cn_data = X509_NAME_ENTRY_get_data(cn_entry);
if (!cn_data) {
- return NULL;
+ goto error;
}
const char *cn;
@@ -454,7 +455,11 @@ get_peer_common_name(const struct ssl_stream *sslv)
#else
cn = (const char *)ASN1_STRING_get0_data(cn_data);
#endif
- return xstrdup(cn);
+ peer_name = xstrdup(cn);
+
+error:
+ X509_free(peer_cert);
+ return peer_name;
}
static int
diff --git a/lib/tc.c b/lib/tc.c
index b19f075f2b..ec3fef5ac2 100644
--- a/lib/tc.c
+++ b/lib/tc.c
@@ -380,7 +380,7 @@ nl_parse_flower_mpls(struct nlattr **attrs, struct tc_flower *flower)
if (attrs[TCA_FLOWER_KEY_MPLS_BOS]) {
bos = nl_attr_get_u8(attrs[TCA_FLOWER_KEY_MPLS_BOS]);
set_mpls_lse_bos(&flower->key.mpls_lse, bos);
- set_mpls_lse_ttl(&flower->mask.mpls_lse, 0xff);
+ set_mpls_lse_bos(&flower->mask.mpls_lse, 0xff);
}
if (attrs[TCA_FLOWER_KEY_MPLS_TC]) {
@@ -571,6 +571,7 @@ nl_parse_flower_tunnel(struct nlattr **attrs, struct tc_flower *flower)
ovs_be32 id = nl_attr_get_be32(attrs[TCA_FLOWER_KEY_ENC_KEY_ID]);
flower->key.tunnel.id = be32_to_be64(id);
+ flower->mask.tunnel.id = OVS_BE64_MAX;
}
if (attrs[TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK]) {
flower->key.tunnel.ipv4.ipv4_src =
@@ -1014,6 +1015,7 @@ nl_parse_act_tunnel_key(struct nlattr *options, struct tc_flower *flower)
action->encap.ipv6.ipv6_dst = nl_attr_get_in6_addr(ipv6_dst);
}
action->encap.id = id ? be32_to_be64(nl_attr_get_be32(id)) : 0;
+ action->encap.id_present = id ? true : false;
action->encap.tp_dst = dst_port ? nl_attr_get_be16(dst_port) : 0;
action->encap.tos = tos ? nl_attr_get_u8(tos) : 0;
action->encap.ttl = ttl ? nl_attr_get_u8(ttl) : 0;
@@ -1304,7 +1306,7 @@ static int
nl_parse_flower_actions(struct nlattr **attrs, struct tc_flower *flower)
{
const struct nlattr *actions = attrs[TCA_FLOWER_ACT];
- static struct nl_policy actions_orders_policy[TCA_ACT_MAX_PRIO + 1] = {};
+ static struct nl_policy actions_orders_policy[TCA_ACT_MAX_NUM + 1] = {};
struct nlattr *actions_orders[ARRAY_SIZE(actions_orders_policy)];
const int max_size = ARRAY_SIZE(actions_orders_policy);
@@ -1323,8 +1325,8 @@ nl_parse_flower_actions(struct nlattr **attrs, struct tc_flower *flower)
if (actions_orders[i]) {
int err;
- if (flower->action_count >= TCA_ACT_MAX_PRIO) {
- VLOG_DBG_RL(&error_rl, "Can only support %d actions", flower->action_count);
+ if (flower->action_count >= TCA_ACT_MAX_NUM) {
+ VLOG_DBG_RL(&error_rl, "Can only support %d actions", TCA_ACT_MAX_NUM);
return EOPNOTSUPP;
}
err = nl_parse_single_action(actions_orders[i], flower);
@@ -1631,9 +1633,9 @@ nl_msg_put_act_tunnel_geneve_option(struct ofpbuf *request,
}
static void
-nl_msg_put_act_tunnel_key_set(struct ofpbuf *request, ovs_be64 id,
- ovs_be32 ipv4_src, ovs_be32 ipv4_dst,
- struct in6_addr *ipv6_src,
+nl_msg_put_act_tunnel_key_set(struct ofpbuf *request, bool id_present,
+ ovs_be64 id, ovs_be32 ipv4_src,
+ ovs_be32 ipv4_dst, struct in6_addr *ipv6_src,
struct in6_addr *ipv6_dst,
ovs_be16 tp_dst, uint8_t tos, uint8_t ttl,
struct tun_metadata tun_metadata,
@@ -1650,7 +1652,9 @@ nl_msg_put_act_tunnel_key_set(struct ofpbuf *request, ovs_be64 id,
nl_msg_put_unspec(request, TCA_TUNNEL_KEY_PARMS, &tun, sizeof tun);
ovs_be32 id32 = be64_to_be32(id);
- nl_msg_put_be32(request, TCA_TUNNEL_KEY_ENC_KEY_ID, id32);
+ if (id_present) {
+ nl_msg_put_be32(request, TCA_TUNNEL_KEY_ENC_KEY_ID, id32);
+ }
if (ipv4_dst) {
nl_msg_put_be32(request, TCA_TUNNEL_KEY_ENC_IPV4_SRC, ipv4_src);
nl_msg_put_be32(request, TCA_TUNNEL_KEY_ENC_IPV4_DST, ipv4_dst);
@@ -1715,6 +1719,14 @@ nl_msg_put_act_cookie(struct ofpbuf *request, struct tc_cookie *ck) {
}
}
+static inline void
+nl_msg_put_act_flags(struct ofpbuf *request) {
+ struct nla_bitfield32 act_flags = { TCA_ACT_FLAGS_NO_PERCPU_STATS,
+ TCA_ACT_FLAGS_NO_PERCPU_STATS };
+
+ nl_msg_put_unspec(request, TCA_ACT_FLAGS, &act_flags, sizeof act_flags);
+}
+
/* Given flower, a key_to_pedit map entry, calculates the rest,
* where:
*
@@ -1883,6 +1895,7 @@ nl_msg_put_flower_acts(struct ofpbuf *request, struct tc_flower *flower)
if (flower->tunnel) {
act_offset = nl_msg_start_nested(request, act_index++);
nl_msg_put_act_tunnel_key_release(request);
+ nl_msg_put_act_flags(request);
nl_msg_end_nested(request, act_offset);
}
@@ -1900,13 +1913,15 @@ nl_msg_put_flower_acts(struct ofpbuf *request, struct tc_flower *flower)
if (flower->csum_update_flags) {
act_offset = nl_msg_start_nested(request, act_index++);
nl_msg_put_act_csum(request, flower->csum_update_flags);
+ nl_msg_put_act_flags(request);
nl_msg_end_nested(request, act_offset);
}
}
break;
case TC_ACT_ENCAP: {
act_offset = nl_msg_start_nested(request, act_index++);
- nl_msg_put_act_tunnel_key_set(request, action->encap.id,
+ nl_msg_put_act_tunnel_key_set(request, action->encap.id_present,
+ action->encap.id,
action->encap.ipv4.ipv4_src,
action->encap.ipv4.ipv4_dst,
&action->encap.ipv6.ipv6_src,
@@ -1916,12 +1931,14 @@ nl_msg_put_flower_acts(struct ofpbuf *request, struct tc_flower *flower)
action->encap.ttl,
action->encap.data,
action->encap.no_csum);
+ nl_msg_put_act_flags(request);
nl_msg_end_nested(request, act_offset);
}
break;
case TC_ACT_VLAN_POP: {
act_offset = nl_msg_start_nested(request, act_index++);
nl_msg_put_act_pop_vlan(request);
+ nl_msg_put_act_flags(request);
nl_msg_end_nested(request, act_offset);
}
break;
@@ -1931,6 +1948,7 @@ nl_msg_put_flower_acts(struct ofpbuf *request, struct tc_flower *flower)
action->vlan.vlan_push_tpid,
action->vlan.vlan_push_id,
action->vlan.vlan_push_prio);
+ nl_msg_put_act_flags(request);
nl_msg_end_nested(request, act_offset);
}
break;
@@ -1950,6 +1968,7 @@ nl_msg_put_flower_acts(struct ofpbuf *request, struct tc_flower *flower)
TCA_EGRESS_MIRROR);
}
nl_msg_put_act_cookie(request, &flower->act_cookie);
+ nl_msg_put_act_flags(request);
nl_msg_end_nested(request, act_offset);
}
break;
@@ -1960,6 +1979,7 @@ nl_msg_put_flower_acts(struct ofpbuf *request, struct tc_flower *flower)
act_offset = nl_msg_start_nested(request, act_index++);
nl_msg_put_act_drop(request);
nl_msg_put_act_cookie(request, &flower->act_cookie);
+ nl_msg_put_act_flags(request);
nl_msg_end_nested(request, act_offset);
}
nl_msg_end_nested(request, offset);
@@ -2026,6 +2046,7 @@ nl_msg_put_flower_tunnel(struct ofpbuf *request, struct tc_flower *flower)
uint8_t ttl = flower->key.tunnel.ttl;
uint8_t tos_mask = flower->mask.tunnel.tos;
uint8_t ttl_mask = flower->mask.tunnel.ttl;
+ ovs_be64 id_mask = flower->mask.tunnel.id;
if (ipv4_dst) {
nl_msg_put_be32(request, TCA_FLOWER_KEY_ENC_IPV4_SRC, ipv4_src);
@@ -2045,7 +2066,9 @@ nl_msg_put_flower_tunnel(struct ofpbuf *request, struct tc_flower *flower)
if (tp_dst) {
nl_msg_put_be16(request, TCA_FLOWER_KEY_ENC_UDP_DST_PORT, tp_dst);
}
- nl_msg_put_be32(request, TCA_FLOWER_KEY_ENC_KEY_ID, id);
+ if (id_mask) {
+ nl_msg_put_be32(request, TCA_FLOWER_KEY_ENC_KEY_ID, id);
+ }
nl_msg_put_flower_tunnel_opts(request, TCA_FLOWER_KEY_ENC_OPTS,
flower->key.tunnel.metadata);
nl_msg_put_flower_tunnel_opts(request, TCA_FLOWER_KEY_ENC_OPTS_MASK,
diff --git a/lib/tc.h b/lib/tc.h
index 7196a32d75..c6bcda8efb 100644
--- a/lib/tc.h
+++ b/lib/tc.h
@@ -147,6 +147,7 @@ struct tc_action {
} vlan;
struct {
+ bool id_present;
ovs_be64 id;
ovs_be16 tp_src;
ovs_be16 tp_dst;
@@ -174,6 +175,8 @@ enum tc_offloaded_state {
TC_OFFLOADED_STATE_NOT_IN_HW,
};
+#define TCA_ACT_MAX_NUM 16
+
struct tc_flower {
uint32_t handle;
uint32_t prio;
@@ -182,7 +185,7 @@ struct tc_flower {
struct tc_flower_key mask;
int action_count;
- struct tc_action actions[TCA_ACT_MAX_PRIO];
+ struct tc_action actions[TCA_ACT_MAX_NUM];
struct ovs_flow_stats stats;
uint64_t lastused;
diff --git a/ofproto/ofproto-dpif-ipfix.c b/ofproto/ofproto-dpif-ipfix.c
index 4029806788..3f7c50dbd6 100644
--- a/ofproto/ofproto-dpif-ipfix.c
+++ b/ofproto/ofproto-dpif-ipfix.c
@@ -3014,7 +3014,9 @@ dpif_ipfix_read_actions(const struct flow *flow,
case OVS_ACTION_ATTR_POP_ETH:
case OVS_ACTION_ATTR_PUSH_NSH:
case OVS_ACTION_ATTR_POP_NSH:
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
case OVS_ACTION_ATTR_UNSPEC:
+ case OVS_ACTION_ATTR_DROP:
case __OVS_ACTION_ATTR_MAX:
default:
break;
diff --git a/ofproto/ofproto-dpif-sflow.c b/ofproto/ofproto-dpif-sflow.c
index 7da31753c7..28b04682ea 100644
--- a/ofproto/ofproto-dpif-sflow.c
+++ b/ofproto/ofproto-dpif-sflow.c
@@ -1026,7 +1026,7 @@ sflow_read_set_action(const struct nlattr *attr,
sflow_actions->tunnel.ip_tos = key->ipv4_tos;
}
if (key->ipv4_ttl) {
- sflow_actions->tunnel.ip_tos = key->ipv4_ttl;
+ sflow_actions->tunnel.ip_ttl = key->ipv4_ttl;
}
}
break;
@@ -1222,6 +1222,8 @@ dpif_sflow_read_actions(const struct flow *flow,
case OVS_ACTION_ATTR_PUSH_NSH:
case OVS_ACTION_ATTR_POP_NSH:
case OVS_ACTION_ATTR_UNSPEC:
+ case OVS_ACTION_ATTR_CHECK_PKT_LEN:
+ case OVS_ACTION_ATTR_DROP:
case __OVS_ACTION_ATTR_MAX:
default:
break;
diff --git a/ofproto/ofproto-dpif-upcall.c b/ofproto/ofproto-dpif-upcall.c
index 4143bfa29f..8c440372fa 100644
--- a/ofproto/ofproto-dpif-upcall.c
+++ b/ofproto/ofproto-dpif-upcall.c
@@ -1088,7 +1088,7 @@ compose_slow_path(struct udpif *udpif, struct xlate_out *xout,
}
odp_put_userspace_action(pid, &cookie, sizeof cookie,
- ODPP_NONE, false, buf);
+ ODPP_NONE, false, buf, NULL);
if (meter_id != UINT32_MAX) {
nl_msg_end_nested(buf, ac_offset);
@@ -1526,6 +1526,7 @@ process_upcall(struct udpif *udpif, struct upcall *upcall,
: NULL),
am->pin.up.action_set_len = state->action_set_len,
am->pin.up.bridge = upcall->ofproto->uuid;
+ am->pin.up.odp_port = upcall->packet->md.in_port.odp_port;
}
/* We don't want to use the upcall 'flow', since it may be
@@ -1797,7 +1798,7 @@ ukey_create_from_dpif_flow(const struct udpif *udpif,
}
reval_seq = seq_read(udpif->reval_seq) - 1; /* Ensure revalidation. */
- ofpbuf_use_const(&actions, &flow->actions, flow->actions_len);
+ ofpbuf_use_const(&actions, flow->actions, flow->actions_len);
*ukey = ukey_create__(flow->key, flow->key_len,
flow->mask, flow->mask_len, flow->ufid_present,
&flow->ufid, flow->pmd_id, &actions,
diff --git a/ofproto/ofproto-dpif-xlate.c b/ofproto/ofproto-dpif-xlate.c
index 09ad76538f..d1981769fd 100644
--- a/ofproto/ofproto-dpif-xlate.c
+++ b/ofproto/ofproto-dpif-xlate.c
@@ -444,6 +444,12 @@ const char *xlate_strerror(enum xlate_error error)
return "Invalid tunnel metadata";
case XLATE_UNSUPPORTED_PACKET_TYPE:
return "Unsupported packet type";
+ case XLATE_CONGESTION_DROP:
+ return "Congestion Drop";
+ case XLATE_FORWARDING_DISABLED:
+ return "Forwarding is disabled";
+ case XLATE_MAX:
+ break;
}
return "Unknown error";
}
@@ -487,6 +493,7 @@ ctx_cancel_freeze(struct xlate_ctx *ctx)
ctx->recirc_update_dp_hash = false;
ofpbuf_clear(&ctx->frozen_actions);
ctx->frozen_actions.header = NULL;
+ ctx->pause = NULL;
}
}
@@ -3043,6 +3050,7 @@ xlate_normal(struct xlate_ctx *ctx)
xlate_report(ctx, OFT_DETAIL, "MLD query, flooding");
xlate_normal_flood(ctx, in_xbundle, &xvlan);
}
+ return;
} else {
if (is_ip_local_multicast(flow, wc)) {
/* RFC4541: section 2.1.2, item 2: Packets with a dst IP
@@ -3158,12 +3166,11 @@ compose_sample_action(struct xlate_ctx *ctx,
odp_port_t odp_port = ofp_port_to_odp_port(
ctx->xbridge, ctx->xin->flow.in_port.ofp_port);
uint32_t pid = dpif_port_get_pid(ctx->xbridge->dpif, odp_port);
- size_t cookie_offset = odp_put_userspace_action(pid, cookie,
- sizeof *cookie,
- tunnel_out_port,
- include_actions,
- ctx->odp_actions);
-
+ size_t cookie_offset;
+ int res = odp_put_userspace_action(pid, cookie, sizeof *cookie,
+ tunnel_out_port, include_actions,
+ ctx->odp_actions, &cookie_offset);
+ ovs_assert(res == 0);
if (is_sample) {
nl_msg_end_nested(ctx->odp_actions, actions_offset);
nl_msg_end_nested(ctx->odp_actions, sample_offset);
@@ -4296,6 +4303,7 @@ xlate_table_action(struct xlate_ctx *ctx, ofp_port_t in_port, uint8_t table_id,
!is_ip_any(&ctx->xin->flow)) {
xlate_report_error(ctx,
"resubmit(ct) with non-tracked or non-IP packet!");
+ ctx->table_id = old_table_id;
return;
}
tuple_swap(&ctx->xin->flow, ctx->wc);
@@ -4709,7 +4717,7 @@ put_controller_user_action(struct xlate_ctx *ctx,
ctx->xin->flow.in_port.ofp_port);
uint32_t pid = dpif_port_get_pid(ctx->xbridge->dpif, odp_port);
odp_put_userspace_action(pid, &cookie, sizeof cookie, ODPP_NONE,
- false, ctx->odp_actions);
+ false, ctx->odp_actions, NULL);
}
static void
@@ -5569,6 +5577,7 @@ reversible_actions(const struct ofpact *ofpacts, size_t ofpacts_len)
case OFPACT_UNROLL_XLATE:
case OFPACT_WRITE_ACTIONS:
case OFPACT_WRITE_METADATA:
+ case OFPACT_CHECK_PKT_LARGER:
break;
case OFPACT_CT:
@@ -5877,6 +5886,7 @@ freeze_unroll_actions(const struct ofpact *a, const struct ofpact *end,
case OFPACT_CT:
case OFPACT_CT_CLEAR:
case OFPACT_NAT:
+ case OFPACT_CHECK_PKT_LARGER:
/* These may not generate PACKET INs. */
break;
@@ -5924,6 +5934,12 @@ put_ct_label(const struct flow *flow, struct ofpbuf *odp_actions,
}
}
+static void
+put_drop_action(struct ofpbuf *odp_actions, enum xlate_error error)
+{
+ nl_msg_put_u32(odp_actions, OVS_ACTION_ATTR_DROP, error);
+}
+
static void
put_ct_helper(struct xlate_ctx *ctx,
struct ofpbuf *odp_actions, struct ofpact_conntrack *ofc)
@@ -6069,6 +6085,118 @@ compose_ct_clear_action(struct xlate_ctx *ctx)
}
}
+/* check_pkt_larger action checks the packet length and stores the
+ * result in the register bit. We translate this action to the
+ * datapath action - 'check_pkt_len' whose format
+ * is: 'check_pkt_len(pkt_len, ge(actions), le(actions))'.
+ *
+ * We first set the destination register bit to 1 and call
+ * 'do_xlate_actions' for the case - packet len greater than
+ * the specified packet length.
+ *
+ * We then set the destination register bit to 0 and call
+ * 'do_xlate_actions' for the case - packet length is lesser or
+ * equal to the specified packet length.
+ *
+ * It is possible for freezing to happen for both the cases.
+ */
+static void
+xlate_check_pkt_larger(struct xlate_ctx *ctx,
+ struct ofpact_check_pkt_larger *check_pkt_larger,
+ const struct ofpact *remaining_acts,
+ size_t remaining_acts_len)
+{
+ union mf_subvalue value;
+ memset(&value, 0, sizeof value);
+ if (!ctx->xbridge->support.check_pkt_len) {
+ uint8_t is_pkt_larger = 0;
+ if (ctx->xin->packet) {
+ is_pkt_larger =
+ dp_packet_size(ctx->xin->packet) > check_pkt_larger->pkt_len;
+ }
+ value.u8_val = is_pkt_larger;
+ mf_write_subfield_flow(&check_pkt_larger->dst, &value,
+ &ctx->xin->flow);
+ /* If datapath doesn't support check_pkt_len action, then set the
+ * SLOW_ACTION flag. If we don't set SLOW_ACTION, we
+ * will push a flow to the datapath based on the packet length
+ * in ctx->xin->packet. For subsequent patches which match the
+ * same flow, datapath will apply the actions without considering
+ * the packet length. This results in wrong actions being applied.
+ */
+ ctx->xout->slow |= SLOW_ACTION;
+ return;
+ }
+
+ struct ofpbuf old_stack = ctx->stack;
+ union mf_subvalue new_stack[1024 / sizeof(union mf_subvalue)];
+ ofpbuf_use_stub(&ctx->stack, new_stack, sizeof new_stack);
+ ofpbuf_put(&ctx->stack, old_stack.data, old_stack.size);
+
+ struct ofpbuf old_action_set = ctx->action_set;
+ uint64_t actset_stub[1024 / 8];
+ ofpbuf_use_stub(&ctx->action_set, actset_stub, sizeof actset_stub);
+ ofpbuf_put(&ctx->action_set, old_action_set.data, old_action_set.size);
+
+ struct flow old_flow = ctx->xin->flow;
+ xlate_commit_actions(ctx);
+ struct flow old_base = ctx->base_flow;
+ bool old_was_mpls = ctx->was_mpls;
+ bool old_conntracked = ctx->conntracked;
+
+ size_t offset = nl_msg_start_nested(ctx->odp_actions,
+ OVS_ACTION_ATTR_CHECK_PKT_LEN);
+ nl_msg_put_u16(ctx->odp_actions, OVS_CHECK_PKT_LEN_ATTR_PKT_LEN,
+ check_pkt_larger->pkt_len);
+ size_t offset_attr = nl_msg_start_nested(
+ ctx->odp_actions, OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER);
+ value.u8_val = 1;
+ mf_write_subfield_flow(&check_pkt_larger->dst, &value, &ctx->xin->flow);
+ do_xlate_actions(remaining_acts, remaining_acts_len, ctx, true, false);
+ if (!ctx->freezing) {
+ xlate_action_set(ctx);
+ }
+ if (ctx->freezing) {
+ finish_freezing(ctx);
+ }
+ nl_msg_end_nested(ctx->odp_actions, offset_attr);
+
+ ctx->base_flow = old_base;
+ ctx->was_mpls = old_was_mpls;
+ ctx->conntracked = old_conntracked;
+ ctx->xin->flow = old_flow;
+
+ /* If the flow translation for the IF_GREATER case requires freezing,
+ * then ctx->exit would be true. Reset to false so that we can
+ * do flow translation for 'IF_LESS_EQUAL' case. finish_freezing()
+ * would have taken care of Undoing the changes done for freeze. */
+ ctx->exit = false;
+
+ offset_attr = nl_msg_start_nested(
+ ctx->odp_actions, OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL);
+ value.u8_val = 0;
+ mf_write_subfield_flow(&check_pkt_larger->dst, &value, &ctx->xin->flow);
+ do_xlate_actions(remaining_acts, remaining_acts_len, ctx, true, false);
+ if (!ctx->freezing) {
+ xlate_action_set(ctx);
+ }
+ if (ctx->freezing) {
+ finish_freezing(ctx);
+ }
+ nl_msg_end_nested(ctx->odp_actions, offset_attr);
+ nl_msg_end_nested(ctx->odp_actions, offset);
+
+ ofpbuf_uninit(&ctx->action_set);
+ ctx->action_set = old_action_set;
+ ofpbuf_uninit(&ctx->stack);
+ ctx->stack = old_stack;
+ ctx->base_flow = old_base;
+ ctx->was_mpls = old_was_mpls;
+ ctx->conntracked = old_conntracked;
+ ctx->xin->flow = old_flow;
+ ctx->exit = true;
+}
+
static void
rewrite_flow_encap_ethernet(struct xlate_ctx *ctx,
struct flow *flow,
@@ -6391,6 +6519,7 @@ recirc_for_mpls(const struct ofpact *a, struct xlate_ctx *ctx)
case OFPACT_WRITE_ACTIONS:
case OFPACT_WRITE_METADATA:
case OFPACT_GOTO_TABLE:
+ case OFPACT_CHECK_PKT_LARGER:
default:
break;
}
@@ -6846,6 +6975,21 @@ do_xlate_actions(const struct ofpact *ofpacts, size_t ofpacts_len,
case OFPACT_DEBUG_SLOW:
ctx->xout->slow |= SLOW_ACTION;
break;
+
+ case OFPACT_CHECK_PKT_LARGER: {
+ if (last) {
+ /* If this is last action, then there is no need to
+ * translate the action. */
+ break;
+ }
+ const struct ofpact *remaining_acts = ofpact_next(a);
+ size_t remaining_acts_len = ofpact_remaining_len(remaining_acts,
+ ofpacts,
+ ofpacts_len);
+ xlate_check_pkt_larger(ctx, ofpact_get_CHECK_PKT_LARGER(a),
+ remaining_acts, remaining_acts_len);
+ break;
+ }
}
/* Check if need to store this and the remaining actions for later
@@ -7386,8 +7530,9 @@ xlate_actions(struct xlate_in *xin, struct xlate_out *xout)
compose_ipfix_action(&ctx, ODPP_NONE);
}
size_t sample_actions_len = ctx.odp_actions->size;
+ bool ecn_drop = !tnl_process_ecn(flow);
- if (tnl_process_ecn(flow)
+ if (!ecn_drop
&& (!in_port || may_receive(in_port, &ctx))) {
const struct ofpact *ofpacts;
size_t ofpacts_len;
@@ -7419,6 +7564,7 @@ xlate_actions(struct xlate_in *xin, struct xlate_out *xout)
ctx.odp_actions->size = sample_actions_len;
ctx_cancel_freeze(&ctx);
ofpbuf_clear(&ctx.action_set);
+ ctx.error = XLATE_FORWARDING_DISABLED;
}
if (!ctx.freezing) {
@@ -7427,6 +7573,8 @@ xlate_actions(struct xlate_in *xin, struct xlate_out *xout)
if (ctx.freezing) {
finish_freezing(&ctx);
}
+ } else if (ecn_drop) {
+ ctx.error = XLATE_CONGESTION_DROP;
}
/* Output only fully processed packets. */
@@ -7526,6 +7674,21 @@ exit:
ofpbuf_clear(xin->odp_actions);
}
}
+
+ /* Install drop action if datapath supports explicit drop action. */
+ if (xin->odp_actions && !xin->odp_actions->size &&
+ ovs_explicit_drop_action_supported(ctx.xbridge->ofproto)) {
+ put_drop_action(xin->odp_actions, ctx.error);
+ }
+
+ /* Since congestion drop and forwarding drop are not exactly
+ * translation error, we are resetting the translation error.
+ */
+ if (ctx.error == XLATE_CONGESTION_DROP ||
+ ctx.error == XLATE_FORWARDING_DISABLED) {
+ ctx.error = XLATE_OK;
+ }
+
return ctx.error;
}
diff --git a/ofproto/ofproto-dpif-xlate.h b/ofproto/ofproto-dpif-xlate.h
index 0a5a52887b..ded81ca0e9 100644
--- a/ofproto/ofproto-dpif-xlate.h
+++ b/ofproto/ofproto-dpif-xlate.h
@@ -205,19 +205,6 @@ int xlate_lookup(const struct dpif_backer *, const struct flow *,
struct dpif_sflow **, struct netflow **,
ofp_port_t *ofp_in_port);
-enum xlate_error {
- XLATE_OK = 0,
- XLATE_BRIDGE_NOT_FOUND,
- XLATE_RECURSION_TOO_DEEP,
- XLATE_TOO_MANY_RESUBMITS,
- XLATE_STACK_TOO_DEEP,
- XLATE_NO_RECIRCULATION_CONTEXT,
- XLATE_RECIRCULATION_CONFLICT,
- XLATE_TOO_MANY_MPLS_LABELS,
- XLATE_INVALID_TUNNEL_METADATA,
- XLATE_UNSUPPORTED_PACKET_TYPE,
-};
-
const char *xlate_strerror(enum xlate_error error);
enum xlate_error xlate_actions(struct xlate_in *, struct xlate_out *);
diff --git a/ofproto/ofproto-dpif.c b/ofproto/ofproto-dpif.c
index 050ff65773..eaaa25f615 100644
--- a/ofproto/ofproto-dpif.c
+++ b/ofproto/ofproto-dpif.c
@@ -827,6 +827,12 @@ ovs_native_tunneling_is_on(struct ofproto_dpif *ofproto)
&& atomic_count_get(&ofproto->backer->tnl_count);
}
+bool
+ovs_explicit_drop_action_supported(struct ofproto_dpif *ofproto)
+{
+ return ofproto->backer->rt_support.explicit_drop_action;
+}
+
/* Tests whether 'backer''s datapath supports recirculation. Only newer
* datapaths support OVS_KEY_ATTR_RECIRC_ID in keys. We need to disable some
* features on older datapaths that don't support this feature.
@@ -1290,6 +1296,48 @@ check_ct_clear(struct dpif_backer *backer)
return supported;
}
+
+/* Tests whether 'backer''s datapath supports the
+ * OVS_ACTION_ATTR_CHECK_PKT_LEN action. */
+static bool
+check_check_pkt_len(struct dpif_backer *backer)
+{
+ struct odputil_keybuf keybuf;
+ struct ofpbuf actions;
+ struct ofpbuf key;
+ struct flow flow;
+ bool supported;
+
+ struct odp_flow_key_parms odp_parms = {
+ .flow = &flow,
+ .probe = true,
+ };
+
+ memset(&flow, 0, sizeof flow);
+ ofpbuf_use_stack(&key, &keybuf, sizeof keybuf);
+ odp_flow_key_from_flow(&odp_parms, &key);
+ ofpbuf_init(&actions, 64);
+ size_t cpl_start;
+
+ cpl_start = nl_msg_start_nested(&actions, OVS_ACTION_ATTR_CHECK_PKT_LEN);
+ nl_msg_put_u16(&actions, OVS_CHECK_PKT_LEN_ATTR_PKT_LEN, 100);
+
+ /* Putting these actions without any data is good enough to check
+ * if check_pkt_len is supported or not. */
+ nl_msg_put_flag(&actions, OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_GREATER);
+ nl_msg_put_flag(&actions, OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL);
+
+ nl_msg_end_nested(&actions, cpl_start);
+
+ supported = dpif_probe_feature(backer->dpif, "check_pkt_len", &key,
+ &actions, NULL);
+ ofpbuf_uninit(&actions);
+ VLOG_INFO("%s: Datapath %s check_pkt_len action",
+ dpif_name(backer->dpif), supported ? "supports"
+ : "does not support");
+ return supported;
+}
+
/* Probe the highest dp_hash algorithm supported by the datapath. */
static size_t
check_max_dp_hash_alg(struct dpif_backer *backer)
@@ -1397,6 +1445,9 @@ check_support(struct dpif_backer *backer)
backer->rt_support.ct_eventmask = check_ct_eventmask(backer);
backer->rt_support.ct_clear = check_ct_clear(backer);
backer->rt_support.max_hash_alg = check_max_dp_hash_alg(backer);
+ backer->rt_support.check_pkt_len = check_check_pkt_len(backer);
+ backer->rt_support.explicit_drop_action =
+ dpif_supports_explicit_drop_action(backer->dpif);
/* Flow fields. */
backer->rt_support.odp.ct_state = check_ct_state(backer);
@@ -2228,24 +2279,24 @@ set_lldp(struct ofport *ofport_,
const struct smap *cfg)
{
struct ofport_dpif *ofport = ofport_dpif_cast(ofport_);
+ struct ofproto_dpif *ofproto = ofproto_dpif_cast(ofport->up.ofproto);
int error = 0;
if (cfg) {
if (!ofport->lldp) {
- struct ofproto_dpif *ofproto;
-
- ofproto = ofproto_dpif_cast(ofport->up.ofproto);
ofproto->backer->need_revalidate = REV_RECONFIGURE;
ofport->lldp = lldp_create(ofport->up.netdev, ofport_->mtu, cfg);
}
if (!lldp_configure(ofport->lldp, cfg)) {
+ lldp_unref(ofport->lldp);
+ ofport->lldp = NULL;
error = EINVAL;
}
- }
- if (error) {
+ } else if (ofport->lldp) {
lldp_unref(ofport->lldp);
ofport->lldp = NULL;
+ ofproto->backer->need_revalidate = REV_RECONFIGURE;
}
ofproto_dpif_monitor_port_update(ofport,
@@ -4655,12 +4706,13 @@ ofproto_dpif_xcache_execute(struct ofproto_dpif *ofproto,
}
static void
-packet_execute(struct ofproto *ofproto_, struct ofproto_packet_out *opo)
+packet_execute_prepare(struct ofproto *ofproto_,
+ struct ofproto_packet_out *opo)
OVS_REQUIRES(ofproto_mutex)
{
struct ofproto_dpif *ofproto = ofproto_dpif_cast(ofproto_);
struct dpif_flow_stats stats;
- struct dpif_execute execute;
+ struct dpif_execute *execute;
struct ofproto_dpif_packet_out *aux = opo->aux;
ovs_assert(aux);
@@ -4669,22 +4721,40 @@ packet_execute(struct ofproto *ofproto_, struct ofproto_packet_out *opo)
dpif_flow_stats_extract(opo->flow, opo->packet, time_msec(), &stats);
ofproto_dpif_xcache_execute(ofproto, &aux->xcache, &stats);
- execute.actions = aux->odp_actions.data;
- execute.actions_len = aux->odp_actions.size;
+ execute = xzalloc(sizeof *execute);
+ execute->actions = xmemdup(aux->odp_actions.data, aux->odp_actions.size);
+ execute->actions_len = aux->odp_actions.size;
pkt_metadata_from_flow(&opo->packet->md, opo->flow);
- execute.packet = opo->packet;
- execute.flow = opo->flow;
- execute.needs_help = aux->needs_help;
- execute.probe = false;
- execute.mtu = 0;
+ execute->packet = opo->packet;
+ execute->flow = opo->flow;
+ execute->needs_help = aux->needs_help;
+ execute->probe = false;
+ execute->mtu = 0;
/* Fix up in_port. */
ofproto_dpif_set_packet_odp_port(ofproto, opo->flow->in_port.ofp_port,
opo->packet);
- dpif_execute(ofproto->backer->dpif, &execute);
ofproto_dpif_packet_out_delete(aux);
+ opo->aux = execute;
+}
+
+static void
+packet_execute(struct ofproto *ofproto_, struct ofproto_packet_out *opo)
+ OVS_EXCLUDED(ofproto_mutex)
+{
+ struct ofproto_dpif *ofproto = ofproto_dpif_cast(ofproto_);
+ struct dpif_execute *execute = opo->aux;
+
+ if (!execute) {
+ return;
+ }
+
+ dpif_execute(ofproto->backer->dpif, execute);
+
+ free(CONST_CAST(struct nlattr *, execute->actions));
+ free(execute);
opo->aux = NULL;
}
@@ -5056,9 +5126,7 @@ nxt_resume(struct ofproto *ofproto_,
pkt_metadata_from_flow(&packet.md, &pin->base.flow_metadata.flow);
/* Fix up in_port. */
- ofproto_dpif_set_packet_odp_port(ofproto,
- pin->base.flow_metadata.flow.in_port.ofp_port,
- &packet);
+ packet.md.in_port.odp_port = pin->odp_port;
struct flow headers;
flow_extract(&packet, &headers);
@@ -5076,6 +5144,7 @@ nxt_resume(struct ofproto *ofproto_,
/* Clean up. */
ofpbuf_uninit(&odp_actions);
dp_packet_uninit(&packet);
+ xlate_cache_uninit(&xcache);
return error;
}
@@ -6060,6 +6129,7 @@ const struct ofproto_class ofproto_dpif_class = {
rule_get_stats,
packet_xlate,
packet_xlate_revert,
+ packet_execute_prepare,
packet_execute,
set_frag_handling,
nxt_resume,
diff --git a/ofproto/ofproto-dpif.h b/ofproto/ofproto-dpif.h
index 1a404c82fa..29373db02a 100644
--- a/ofproto/ofproto-dpif.h
+++ b/ofproto/ofproto-dpif.h
@@ -192,7 +192,14 @@ struct group_dpif *group_dpif_lookup(struct ofproto_dpif *,
DPIF_SUPPORT_FIELD(bool, ct_clear, "Conntrack clear") \
\
/* Highest supported dp_hash algorithm. */ \
- DPIF_SUPPORT_FIELD(size_t, max_hash_alg, "Max dp_hash algorithm")
+ DPIF_SUPPORT_FIELD(size_t, max_hash_alg, "Max dp_hash algorithm") \
+ \
+ /* True if the datapath supports OVS_ACTION_ATTR_CHECK_PKT_LEN. */ \
+ DPIF_SUPPORT_FIELD(bool, check_pkt_len, "Check pkt length action") \
+ \
+ /* True if the datapath supports explicit drop action. */ \
+ DPIF_SUPPORT_FIELD(bool, explicit_drop_action, "Explicit Drop action")
+
/* Stores the various features which the corresponding backer supports. */
struct dpif_backer_support {
@@ -361,4 +368,6 @@ int ofproto_dpif_delete_internal_flow(struct ofproto_dpif *, struct match *,
bool ovs_native_tunneling_is_on(struct ofproto_dpif *);
+bool ovs_explicit_drop_action_supported(struct ofproto_dpif *);
+
#endif /* ofproto-dpif.h */
diff --git a/ofproto/ofproto-provider.h b/ofproto/ofproto-provider.h
index 074edfc119..958e0ef1f9 100644
--- a/ofproto/ofproto-provider.h
+++ b/ofproto/ofproto-provider.h
@@ -1357,9 +1357,15 @@ struct ofproto_class {
* packet_xlate_revert() calls have to be made in reverse order. */
void (*packet_xlate_revert)(struct ofproto *, struct ofproto_packet_out *);
- /* Executes the datapath actions, translation side-effects, and stats as
- * produced by ->packet_xlate(). The caller retains ownership of 'opo'.
- */
+ /* Translates side-effects, and stats as produced by ->packet_xlate().
+ * Prepares to execute datapath actions. The caller retains ownership
+ * of 'opo'. */
+ void (*packet_execute_prepare)(struct ofproto *,
+ struct ofproto_packet_out *opo);
+
+ /* Executes the datapath actions. The caller retains ownership of 'opo'.
+ * Should be called after successful packet_execute_prepare().
+ * No-op if called after packet_xlate_revert(). */
void (*packet_execute)(struct ofproto *, struct ofproto_packet_out *opo);
/* Changes the OpenFlow IP fragment handling policy to 'frag_handling',
diff --git a/ofproto/ofproto.c b/ofproto/ofproto.c
index 994e89d9ff..1576de4be2 100644
--- a/ofproto/ofproto.c
+++ b/ofproto/ofproto.c
@@ -2507,6 +2507,9 @@ ofproto_port_unregister(struct ofproto *ofproto, ofp_port_t ofp_port)
{
struct ofport *port = ofproto_get_port(ofproto, ofp_port);
if (port) {
+ if (port->ofproto->ofproto_class->set_lldp) {
+ port->ofproto->ofproto_class->set_lldp(port, NULL);
+ }
if (port->ofproto->ofproto_class->set_stp_port) {
port->ofproto->ofproto_class->set_stp_port(port, NULL);
}
@@ -3572,10 +3575,21 @@ ofproto_packet_out_revert(struct ofproto *ofproto,
ofproto->ofproto_class->packet_xlate_revert(ofproto, opo);
}
+static void
+ofproto_packet_out_prepare(struct ofproto *ofproto,
+ struct ofproto_packet_out *opo)
+ OVS_REQUIRES(ofproto_mutex)
+{
+ ofproto->ofproto_class->packet_execute_prepare(ofproto, opo);
+}
+
+/* Execution of packet_out action in datapath could end up in upcall with
+ * subsequent flow translations and possible rule modifications.
+ * So, the caller should not hold 'ofproto_mutex'. */
static void
ofproto_packet_out_finish(struct ofproto *ofproto,
struct ofproto_packet_out *opo)
- OVS_REQUIRES(ofproto_mutex)
+ OVS_EXCLUDED(ofproto_mutex)
{
ofproto->ofproto_class->packet_execute(ofproto, opo);
}
@@ -3618,10 +3632,13 @@ handle_packet_out(struct ofconn *ofconn, const struct ofp_header *oh)
opo.version = p->tables_version;
error = ofproto_packet_out_start(p, &opo);
if (!error) {
- ofproto_packet_out_finish(p, &opo);
+ ofproto_packet_out_prepare(p, &opo);
}
ovs_mutex_unlock(&ofproto_mutex);
+ if (!error) {
+ ofproto_packet_out_finish(p, &opo);
+ }
ofproto_packet_out_uninit(&opo);
return error;
}
@@ -8114,7 +8131,7 @@ do_bundle_commit(struct ofconn *ofconn, uint32_t id, uint16_t flags)
} else if (be->type == OFPTYPE_GROUP_MOD) {
ofproto_group_mod_finish(ofproto, &be->ogm, &req);
} else if (be->type == OFPTYPE_PACKET_OUT) {
- ofproto_packet_out_finish(ofproto, &be->opo);
+ ofproto_packet_out_prepare(ofproto, &be->opo);
}
}
}
@@ -8124,6 +8141,13 @@ do_bundle_commit(struct ofconn *ofconn, uint32_t id, uint16_t flags)
ovs_mutex_unlock(&ofproto_mutex);
}
+ /* Executing remaining datapath actions. */
+ LIST_FOR_EACH (be, node, &bundle->msg_list) {
+ if (be->type == OFPTYPE_PACKET_OUT) {
+ ofproto_packet_out_finish(ofproto, &be->opo);
+ }
+ }
+
/* The bundle is discarded regardless the outcome. */
ofp_bundle_remove__(ofconn, bundle);
return error;
diff --git a/ovn/northd/ovn-northd.c b/ovn/northd/ovn-northd.c
index d1c64d3429..c548faf942 100644
--- a/ovn/northd/ovn-northd.c
+++ b/ovn/northd/ovn-northd.c
@@ -1039,7 +1039,14 @@ ipam_add_port_addresses(struct ovn_datapath *od, struct ovn_port *op)
for (size_t i = 0; i < lrp_networks.n_ipv4_addrs; i++) {
uint32_t ip = ntohl(lrp_networks.ipv4_addrs[i].addr);
- ipam_insert_ip(op->peer->od, ip);
+ /* If the router has the first IP address of the subnet, don't add
+ * it to IPAM. We already added this when we initialized IPAM for
+ * the datapath. This will just result in an erroneous message
+ * about a duplicate IP address.
+ */
+ if (ip != op->peer->od->ipam_info.start_ipv4) {
+ ipam_insert_ip(op->peer->od, ip);
+ }
}
destroy_lport_addresses(&lrp_networks);
diff --git a/ovn/utilities/ovn-ctl b/ovn/utilities/ovn-ctl
index f1297a2626..769c09752a 100755
--- a/ovn/utilities/ovn-ctl
+++ b/ovn/utilities/ovn-ctl
@@ -314,6 +314,15 @@ start_northd () {
if test X"$OVN_NORTHD_LOGFILE" != X; then
set "$@" --log-file=$OVN_NORTHD_LOGFILE
fi
+ if test X"$OVN_NORTHD_SSL_KEY" != X; then
+ set "$@" --private-key=$OVN_NORTHD_SSL_KEY
+ fi
+ if test X"$OVN_NORTHD_SSL_CERT" != X; then
+ set "$@" --certificate=$OVN_NORTHD_SSL_CERT
+ fi
+ if test X"$OVN_NORTHD_SSL_CA_CERT" != X; then
+ set "$@" --ca-cert=$OVN_NORTHD_SSL_CA_CERT
+ fi
[ "$OVN_USER" != "" ] && set "$@" --user "$OVN_USER"
@@ -475,6 +484,10 @@ set_defaults () {
OVN_CONTROLLER_SSL_CA_CERT=""
OVN_CONTROLLER_SSL_BOOTSTRAP_CA_CERT=""
+ OVN_NORTHD_SSL_KEY=""
+ OVN_NORTHD_SSL_CERT=""
+ OVN_NORTHD_SSL_CA_CERT=""
+
DB_SB_CREATE_INSECURE_REMOTE="no"
DB_NB_CREATE_INSECURE_REMOTE="no"
@@ -571,6 +584,9 @@ Options:
--ovn-sb-db-ssl-key=KEY OVN Southbound DB SSL private key file
--ovn-sb-db-ssl-cert=CERT OVN Southbound DB SSL certificate file
--ovn-sb-db-ssl-ca-cert=CERT OVN Southbound DB SSL CA certificate file
+ --ovn-northd-ssl-key=KEY OVN Northd SSL private key file
+ --ovn-northd-ssl-cert=CERT OVN Northd SSL certificate file
+ --ovn-northd-ssl-ca-cert=CERT OVN Northd SSL CA certificate file
--ovn-manage-ovsdb=yes|no Whether or not the OVN databases should be
automatically started and stopped along
with ovn-northd. The default is "yes". If
diff --git a/ovsdb/execution.c b/ovsdb/execution.c
index c55a0b7710..fdbb5c399f 100644
--- a/ovsdb/execution.c
+++ b/ovsdb/execution.c
@@ -696,7 +696,7 @@ ovsdb_execute_wait(struct ovsdb_execution *x, struct ovsdb_parser *parser,
long long int timeout_msec = 0;
size_t i;
- timeout = ovsdb_parser_member(parser, "timeout", OP_NUMBER | OP_OPTIONAL);
+ timeout = ovsdb_parser_member(parser, "timeout", OP_INTEGER | OP_OPTIONAL);
where = ovsdb_parser_member(parser, "where", OP_ARRAY);
columns_json = ovsdb_parser_member(parser, "columns",
OP_ARRAY | OP_OPTIONAL);
@@ -714,7 +714,7 @@ ovsdb_execute_wait(struct ovsdb_execution *x, struct ovsdb_parser *parser,
}
if (!error) {
if (timeout) {
- timeout_msec = MIN(LLONG_MAX, json_real(timeout));
+ timeout_msec = json_integer(timeout);
if (timeout_msec < 0) {
error = ovsdb_syntax_error(timeout, NULL,
"timeout must be nonnegative");
diff --git a/ovsdb/file.c b/ovsdb/file.c
index 8d16b097b7..0af077fcec 100644
--- a/ovsdb/file.c
+++ b/ovsdb/file.c
@@ -235,10 +235,14 @@ ovsdb_convert_table(struct ovsdb_txn *txn,
continue;
}
+ ovsdb_datum_destroy(&dst_row->fields[dst_column->index],
+ &dst_column->type);
+
struct ovsdb_error *error = ovsdb_datum_convert(
&dst_row->fields[dst_column->index], &dst_column->type,
&src_row->fields[src_column->index], &src_column->type);
if (error) {
+ ovsdb_datum_init_empty(&dst_row->fields[dst_column->index]);
ovsdb_row_destroy(dst_row);
return error;
}
diff --git a/ovsdb/jsonrpc-server.c b/ovsdb/jsonrpc-server.c
index 7c7a277f0d..fee3e2bcf6 100644
--- a/ovsdb/jsonrpc-server.c
+++ b/ovsdb/jsonrpc-server.c
@@ -80,6 +80,8 @@ static void ovsdb_jsonrpc_session_unlock_all(struct ovsdb_jsonrpc_session *);
static void ovsdb_jsonrpc_session_unlock__(struct ovsdb_lock_waiter *);
static void ovsdb_jsonrpc_session_send(struct ovsdb_jsonrpc_session *,
struct jsonrpc_msg *);
+static void ovsdb_jsonrpc_session_set_readonly_all(
+ struct ovsdb_jsonrpc_remote *remote, bool read_only);
/* Triggers. */
static void ovsdb_jsonrpc_trigger_create(struct ovsdb_jsonrpc_session *,
@@ -365,10 +367,13 @@ ovsdb_jsonrpc_server_set_read_only(struct ovsdb_jsonrpc_server *svr,
{
if (svr->read_only != read_only) {
svr->read_only = read_only;
- ovsdb_jsonrpc_server_reconnect(svr, false,
- xstrdup(read_only
- ? "making server read-only"
- : "making server read/write"));
+
+ struct shash_node *node;
+ SHASH_FOR_EACH (node, &svr->remotes) {
+ struct ovsdb_jsonrpc_remote *remote = node->data;
+
+ ovsdb_jsonrpc_session_set_readonly_all(remote, read_only);
+ }
}
}
@@ -670,6 +675,17 @@ ovsdb_jsonrpc_session_reconnect_all(struct ovsdb_jsonrpc_remote *remote,
}
}
+static void
+ovsdb_jsonrpc_session_set_readonly_all(struct ovsdb_jsonrpc_remote *remote,
+ bool read_only)
+{
+ struct ovsdb_jsonrpc_session *s;
+
+ LIST_FOR_EACH (s, node, &remote->sessions) {
+ s->read_only = read_only;
+ }
+}
+
/* Sets the options for all of the JSON-RPC sessions managed by 'remote' to
* 'options'.
*
diff --git a/ovsdb/mutation.c b/ovsdb/mutation.c
index cd20bdb7cb..56edc5f000 100644
--- a/ovsdb/mutation.c
+++ b/ovsdb/mutation.c
@@ -147,6 +147,8 @@ ovsdb_mutation_from_json(const struct ovsdb_table_schema *ts,
if (error && ovsdb_type_is_map(&m->type)
&& m->mutator == OVSDB_M_DELETE) {
ovsdb_error_destroy(error);
+ ovsdb_base_type_destroy(&m->type.value);
+ m->type.value.enum_ = NULL;
m->type.value.type = OVSDB_TYPE_VOID;
error = ovsdb_datum_from_json(&m->arg, &m->type, array->elems[2],
symtab);
diff --git a/ovsdb/ovsdb-client.c b/ovsdb/ovsdb-client.c
index 0215357fee..e823b9823e 100644
--- a/ovsdb/ovsdb-client.c
+++ b/ovsdb/ovsdb-client.c
@@ -1571,14 +1571,15 @@ static void
do_needs_conversion(struct jsonrpc *rpc, const char *database_ OVS_UNUSED,
int argc OVS_UNUSED, char *argv[])
{
+ const char *schema_file_name = argv[argc - 1];
struct ovsdb_schema *schema1;
- check_ovsdb_error(ovsdb_schema_from_file(argv[0], &schema1));
+ check_ovsdb_error(ovsdb_schema_from_file(schema_file_name, &schema1));
char *database = schema1->name;
open_rpc(1, NEED_DATABASE, argc, argv, &rpc, &database);
if (is_database_clustered(rpc, database)) {
- ovsdb_schema_persist_ephemeral_columns(schema1, argv[0]);
+ ovsdb_schema_persist_ephemeral_columns(schema1, schema_file_name);
}
struct ovsdb_schema *schema2 = fetch_schema(rpc, schema1->name);
diff --git a/ovsdb/ovsdb-idlc.in b/ovsdb/ovsdb-idlc.in
index 40fef39edf..96a48d8711 100755
--- a/ovsdb/ovsdb-idlc.in
+++ b/ovsdb/ovsdb-idlc.in
@@ -279,13 +279,21 @@ const struct %(s)s *%(s)s_table_track_get_first(const struct %(s)s_table *);
(ROW) = %(s)s_track_get_next(ROW))
-/* Returns true if 'row' was inserted since the last change tracking reset. */
+/* Returns true if 'row' was inserted since the last change tracking reset.
+ *
+ * Note: This can only be used to test rows of tracked changes. This cannot be
+ * used to test if an uncommitted row that has been added locally is new or it
+ * may given unexpected results. */
static inline bool %(s)s_is_new(const struct %(s)s *row)
{
- return %(s)s_row_get_seqno(row, OVSDB_IDL_CHANGE_MODIFY) == 0;
+ return %(s)s_row_get_seqno(row, OVSDB_IDL_CHANGE_INSERT) > 0;
}
-/* Returns true if 'row' was deleted since the last change tracking reset. */
+/* Returns true if 'row' was deleted since the last change tracking reset.
+ *
+ * Note: This can only be used to test rows of tracked changes. This cannot be
+ * used to test if an uncommitted row that has been added locally has been
+ * deleted or it may given unexpected results. */
static inline bool %(s)s_is_deleted(const struct %(s)s *row)
{
return %(s)s_row_get_seqno(row, OVSDB_IDL_CHANGE_DELETE) > 0;
@@ -333,6 +341,14 @@ struct %(s)s *%(s)s_cursor_data(struct ovsdb_idl_cursor *);
void %(s)s_init(struct %(s)s *);
void %(s)s_delete(const struct %(s)s *);
struct %(s)s *%(s)s_insert(struct ovsdb_idl_txn *);
+
+/* Returns true if the tracked column referenced by 'enum %(s)s_column_id' of
+ * the row referenced by 'struct %(s)s *' was updated since the last change
+ * tracking reset.
+ *
+ * Note: This can only be used to test rows of tracked changes. This cannot be
+ * used to test if an uncommitted row that has been added locally has been
+ * updated or it may given unexpected results. */
bool %(s)s_is_updated(const struct %(s)s *, enum %(s)s_column_id);
''' % {'s': structName, 'S': structName.upper()})
diff --git a/ovsdb/ovsdb-server.1.in b/ovsdb/ovsdb-server.1.in
index 9f78e87f65..11403b1009 100644
--- a/ovsdb/ovsdb-server.1.in
+++ b/ovsdb/ovsdb-server.1.in
@@ -288,6 +288,11 @@ Switches the server to an active role. The server stops synchronizing
its databases with an active server and closes all existing client
connections, which requires clients to reconnect.
.
+.IP "\fBovsdb\-server/set\-active\-ovsdb\-server\-probe\-interval \fIprobe interval"
+Sets the probe interval (in milli seconds) for the connection to
+active \fIserver\fR.
+.
+.
.IP "\fBovsdb\-server/set\-sync\-exclude\-tables \fIdb\fB:\fItable\fR[\fB,\fIdb\fB:\fItable\fR]..."
Sets the \fItable\fR within \fIdb\fR that will be excluded from synchronization.
This overrides the \fB\-\-sync\-exclude-tables\fR command-line option.
diff --git a/ovsdb/ovsdb-server.c b/ovsdb/ovsdb-server.c
index 65a47a41d3..d3ed043db0 100644
--- a/ovsdb/ovsdb-server.c
+++ b/ovsdb/ovsdb-server.c
@@ -86,6 +86,7 @@ static unixctl_cb_func ovsdb_server_set_active_ovsdb_server;
static unixctl_cb_func ovsdb_server_get_active_ovsdb_server;
static unixctl_cb_func ovsdb_server_connect_active_ovsdb_server;
static unixctl_cb_func ovsdb_server_disconnect_active_ovsdb_server;
+static unixctl_cb_func ovsdb_server_set_active_ovsdb_server_probe_interval;
static unixctl_cb_func ovsdb_server_set_sync_exclude_tables;
static unixctl_cb_func ovsdb_server_get_sync_exclude_tables;
static unixctl_cb_func ovsdb_server_get_sync_status;
@@ -97,6 +98,7 @@ struct server_config {
char **sync_from;
char **sync_exclude;
bool *is_backup;
+ int *replication_probe_interval;
struct ovsdb_jsonrpc_server *jsonrpc;
};
static unixctl_cb_func ovsdb_server_add_remote;
@@ -144,9 +146,10 @@ static void load_config(FILE *config_file, struct sset *remotes,
static void
ovsdb_replication_init(const char *sync_from, const char *exclude,
- struct shash *all_dbs, const struct uuid *server_uuid)
+ struct shash *all_dbs, const struct uuid *server_uuid,
+ int probe_interval)
{
- replication_init(sync_from, exclude, server_uuid);
+ replication_init(sync_from, exclude, server_uuid, probe_interval);
struct shash_node *node;
SHASH_FOR_EACH (node, all_dbs) {
struct db *db = node->data;
@@ -301,6 +304,7 @@ main(int argc, char *argv[])
struct server_config server_config;
struct shash all_dbs;
struct shash_node *node, *next;
+ int replication_probe_interval = REPLICATION_DEFAULT_PROBE_INTERVAL;
ovs_cmdl_proctitle_init(argc, argv);
set_program_name(argv[0]);
@@ -348,6 +352,7 @@ main(int argc, char *argv[])
server_config.sync_from = &sync_from;
server_config.sync_exclude = &sync_exclude;
server_config.is_backup = &is_backup;
+ server_config.replication_probe_interval = &replication_probe_interval;
perf_counters_init();
@@ -433,6 +438,9 @@ main(int argc, char *argv[])
unixctl_command_register("ovsdb-server/disconnect-active-ovsdb-server", "",
0, 0, ovsdb_server_disconnect_active_ovsdb_server,
&server_config);
+ unixctl_command_register(
+ "ovsdb-server/set-active-ovsdb-server-probe-interval", "", 1, 1,
+ ovsdb_server_set_active_ovsdb_server_probe_interval, &server_config);
unixctl_command_register("ovsdb-server/set-sync-exclude-tables", "",
0, 1, ovsdb_server_set_sync_exclude_tables,
&server_config);
@@ -451,7 +459,8 @@ main(int argc, char *argv[])
if (is_backup) {
const struct uuid *server_uuid;
server_uuid = ovsdb_jsonrpc_server_get_uuid(jsonrpc);
- ovsdb_replication_init(sync_from, sync_exclude, &all_dbs, server_uuid);
+ ovsdb_replication_init(sync_from, sync_exclude, &all_dbs, server_uuid,
+ replication_probe_interval);
}
main_loop(&server_config, jsonrpc, &all_dbs, unixctl, &remotes,
@@ -528,7 +537,7 @@ close_db(struct server_config *config, struct db *db, char *comment)
static struct ovsdb_error * OVS_WARN_UNUSED_RESULT
parse_txn(struct server_config *config, struct db *db,
- struct ovsdb_schema *schema, const struct json *txn_json,
+ const struct ovsdb_schema *schema, const struct json *txn_json,
const struct uuid *txnid)
{
if (schema) {
@@ -552,7 +561,7 @@ parse_txn(struct server_config *config, struct db *db,
? xasprintf("database %s schema changed", db->db->name)
: xasprintf("database %s connected to storage", db->db->name)));
- ovsdb_replace(db->db, ovsdb_create(schema, NULL));
+ ovsdb_replace(db->db, ovsdb_create(ovsdb_schema_clone(schema), NULL));
/* Force update to schema in _Server database. */
db->row_uuid = UUID_ZERO;
@@ -600,6 +609,7 @@ read_db(struct server_config *config, struct db *db)
} else {
error = parse_txn(config, db, schema, txn_json, &txnid);
json_destroy(txn_json);
+ ovsdb_schema_destroy(schema);
if (error) {
break;
}
@@ -624,8 +634,6 @@ add_db(struct server_config *config, struct db *db)
static struct ovsdb_error * OVS_WARN_UNUSED_RESULT
open_db(struct server_config *config, const char *filename)
{
- struct db *db;
-
/* If we know that the file is already open, return a good error message.
* Otherwise, if the file is open, we'll fail later on with a harder to
* interpret file locking error. */
@@ -640,9 +648,6 @@ open_db(struct server_config *config, const char *filename)
return error;
}
- db = xzalloc(sizeof *db);
- db->filename = xstrdup(filename);
-
struct ovsdb_schema *schema;
if (ovsdb_storage_is_clustered(storage)) {
schema = NULL;
@@ -655,6 +660,9 @@ open_db(struct server_config *config, const char *filename)
}
ovs_assert(schema && !txn_json);
}
+
+ struct db *db = xzalloc(sizeof *db);
+ db->filename = xstrdup(filename);
db->db = ovsdb_create(schema, storage);
ovsdb_jsonrpc_server_add_db(config->jsonrpc, db->db);
@@ -1307,7 +1315,8 @@ ovsdb_server_connect_active_ovsdb_server(struct unixctl_conn *conn,
const struct uuid *server_uuid;
server_uuid = ovsdb_jsonrpc_server_get_uuid(config->jsonrpc);
ovsdb_replication_init(*config->sync_from, *config->sync_exclude,
- config->all_dbs, server_uuid);
+ config->all_dbs, server_uuid,
+ *config->replication_probe_interval);
if (!*config->is_backup) {
*config->is_backup = true;
save_config(config);
@@ -1330,6 +1339,28 @@ ovsdb_server_disconnect_active_ovsdb_server(struct unixctl_conn *conn,
unixctl_command_reply(conn, NULL);
}
+static void
+ovsdb_server_set_active_ovsdb_server_probe_interval(struct unixctl_conn *conn,
+ int argc OVS_UNUSED,
+ const char *argv[],
+ void *config_)
+{
+ struct server_config *config = config_;
+
+ int probe_interval;
+ if (str_to_int(argv[1], 10, &probe_interval)) {
+ *config->replication_probe_interval = probe_interval;
+ save_config(config);
+ if (*config->is_backup) {
+ replication_set_probe_interval(probe_interval);
+ }
+ unixctl_command_reply(conn, NULL);
+ } else {
+ unixctl_command_reply(
+ conn, "Invalid probe interval, integer value expected");
+ }
+}
+
static void
ovsdb_server_set_sync_exclude_tables(struct unixctl_conn *conn,
int argc OVS_UNUSED,
@@ -1347,7 +1378,8 @@ ovsdb_server_set_sync_exclude_tables(struct unixctl_conn *conn,
const struct uuid *server_uuid;
server_uuid = ovsdb_jsonrpc_server_get_uuid(config->jsonrpc);
ovsdb_replication_init(*config->sync_from, *config->sync_exclude,
- config->all_dbs, server_uuid);
+ config->all_dbs, server_uuid,
+ *config->replication_probe_interval);
}
err = set_blacklist_tables(argv[1], false);
}
@@ -1558,7 +1590,8 @@ ovsdb_server_add_database(struct unixctl_conn *conn, int argc OVS_UNUSED,
const struct uuid *server_uuid;
server_uuid = ovsdb_jsonrpc_server_get_uuid(config->jsonrpc);
ovsdb_replication_init(*config->sync_from, *config->sync_exclude,
- config->all_dbs, server_uuid);
+ config->all_dbs, server_uuid,
+ *config->replication_probe_interval);
}
unixctl_command_reply(conn, NULL);
} else {
@@ -1580,7 +1613,8 @@ remove_db(struct server_config *config, struct shash_node *node, char *comment)
const struct uuid *server_uuid;
server_uuid = ovsdb_jsonrpc_server_get_uuid(config->jsonrpc);
ovsdb_replication_init(*config->sync_from, *config->sync_exclude,
- config->all_dbs, server_uuid);
+ config->all_dbs, server_uuid,
+ *config->replication_probe_interval);
}
}
diff --git a/ovsdb/ovsdb-tool.c b/ovsdb/ovsdb-tool.c
index 438f975902..49ba05c88a 100644
--- a/ovsdb/ovsdb-tool.c
+++ b/ovsdb/ovsdb-tool.c
@@ -559,7 +559,9 @@ do_db_has_magic(struct ovs_cmdl_context *ctx, const char *magic)
check_ovsdb_error(ovsdb_log_open(filename, OVSDB_MAGIC"|"RAFT_MAGIC,
OVSDB_LOG_READ_ONLY, -1, &log));
- if (strcmp(ovsdb_log_get_magic(log), magic)) {
+ int cmp = strcmp(ovsdb_log_get_magic(log), magic);
+ ovsdb_log_close(log);
+ if (cmp) {
exit(2);
}
}
@@ -715,6 +717,7 @@ print_db_changes(struct shash *tables, struct smap *names,
ds_init(&s);
ovsdb_datum_to_string(&datum, type, &s);
value_string = ds_steal_cstr(&s);
+ ovsdb_datum_destroy(&datum, type);
} else {
ovsdb_error_destroy(error);
}
diff --git a/ovsdb/raft.c b/ovsdb/raft.c
index 68b527c12a..7ba75f6a3f 100644
--- a/ovsdb/raft.c
+++ b/ovsdb/raft.c
@@ -3738,7 +3738,7 @@ raft_handle_install_snapshot_request__(
struct ovsdb_error *error = raft_save_snapshot(raft, new_log_start,
&new_snapshot);
if (error) {
- char *error_s = ovsdb_error_to_string(error);
+ char *error_s = ovsdb_error_to_string_free(error);
VLOG_WARN("could not save snapshot: %s", error_s);
free(error_s);
return false;
@@ -3960,9 +3960,7 @@ raft_handle_execute_command_request__(
cmd->sid = rq->common.sid;
enum raft_command_status status = cmd->status;
- if (status != RAFT_CMD_INCOMPLETE) {
- raft_command_unref(cmd);
- }
+ raft_command_unref(cmd);
return status;
}
diff --git a/ovsdb/replication.c b/ovsdb/replication.c
index 752b3c89c5..cbbce64dfb 100644
--- a/ovsdb/replication.c
+++ b/ovsdb/replication.c
@@ -43,7 +43,7 @@ static struct uuid server_uuid;
static struct jsonrpc_session *session;
static unsigned int session_seqno = UINT_MAX;
-static struct jsonrpc_msg *create_monitor_request(struct ovsdb *db);
+static struct jsonrpc_msg *create_monitor_request(struct ovsdb_schema *);
static void add_monitored_table(struct ovsdb_table_schema *table,
struct json *monitor_requests);
@@ -100,21 +100,32 @@ enum ovsdb_replication_state {
static enum ovsdb_replication_state state;
+struct replication_db {
+ struct ovsdb *db;
+ bool schema_version_higher;
+ /* Points to the schema received from the active server if
+ * the local db schema version is higher. NULL otherwise. */
+ struct ovsdb_schema *active_db_schema;
+};
+
+static bool is_replication_possible(struct ovsdb_schema *local_db_schema,
+ struct ovsdb_schema *active_db_schema);
+
/* All DBs known to ovsdb-server. The actual replication dbs are stored
* in 'replication dbs', which is a subset of all dbs and remote dbs whose
* schema matches. */
static struct shash local_dbs = SHASH_INITIALIZER(&local_dbs);
static struct shash *replication_dbs;
-static struct shash *replication_db_clone(struct shash *dbs);
+static struct shash *replication_dbs_create(void);
static void replication_dbs_destroy(void);
/* Find 'struct ovsdb' by name within 'replication_dbs' */
-static struct ovsdb* find_db(const char *db_name);
+static struct replication_db *find_db(const char *db_name);
void
replication_init(const char *sync_from_, const char *exclude_tables,
- const struct uuid *server)
+ const struct uuid *server, int probe_interval)
{
free(sync_from);
sync_from = xstrdup(sync_from_);
@@ -132,6 +143,8 @@ replication_init(const char *sync_from_, const char *exclude_tables,
session = jsonrpc_session_open(sync_from, true);
session_seqno = UINT_MAX;
+ jsonrpc_session_set_probe_interval(session, probe_interval);
+
/* Keep a copy of local server uuid. */
server_uuid = *server;
@@ -152,8 +165,8 @@ send_schema_requests(const struct json *result)
if (name->type == JSON_STRING) {
/* Send one schema request for each remote DB. */
const char *db_name = json_string(name);
- struct ovsdb *db = find_db(db_name);
- if (db) {
+ struct replication_db *rdb = find_db(db_name);
+ if (rdb) {
struct jsonrpc_msg *request =
jsonrpc_create_request(
"get_schema",
@@ -161,7 +174,7 @@ send_schema_requests(const struct json *result)
json_string_create(db_name)),
NULL);
- request_ids_add(request->id, db);
+ request_ids_add(request->id, rdb->db);
jsonrpc_session_send(session, request);
}
}
@@ -206,11 +219,11 @@ replication_run(void)
&& msg->params->array.n == 2
&& msg->params->array.elems[0]->type == JSON_STRING) {
char *db_name = msg->params->array.elems[0]->string;
- struct ovsdb *db = find_db(db_name);
- if (db) {
+ struct replication_db *rdb = find_db(db_name);
+ if (rdb) {
struct ovsdb_error *error;
error = process_notification(msg->params->array.elems[1],
- db);
+ rdb->db);
if (error) {
ovsdb_error_assert(error);
state = RPL_S_ERR;
@@ -218,6 +231,7 @@ replication_run(void)
}
}
} else if (msg->type == JSONRPC_REPLY) {
+ struct replication_db *rdb;
struct ovsdb *db;
if (!request_ids_lookup_and_free(msg->id, &db)) {
VLOG_WARN("received unexpected reply");
@@ -256,7 +270,7 @@ replication_run(void)
jsonrpc_session_send(session, request);
replication_dbs_destroy();
- replication_dbs = replication_db_clone(&local_dbs);
+ replication_dbs = replication_dbs_create();
state = RPL_S_DB_REQUESTED;
break;
}
@@ -284,17 +298,37 @@ replication_run(void)
state = RPL_S_ERR;
}
- if (db != find_db(schema->name)) {
+ rdb = find_db(schema->name);
+ if (!rdb) {
/* Unexpected schema. */
VLOG_WARN("unexpected schema %s", schema->name);
state = RPL_S_ERR;
- } else if (!ovsdb_schema_equal(schema, db->schema)) {
+ } else if (!ovsdb_schema_equal(schema, rdb->db->schema)) {
/* Schmea version mismatch. */
- VLOG_INFO("Schema version mismatch, %s not replicated",
+ VLOG_INFO("Schema version mismatch, checking if %s can "
+ "still be replicated or not.",
schema->name);
- shash_find_and_delete(replication_dbs, schema->name);
+ if (is_replication_possible(rdb->db->schema, schema)) {
+ VLOG_INFO("%s can be replicated.", schema->name);
+ rdb->schema_version_higher = true;
+ if (rdb->active_db_schema) {
+ ovsdb_schema_destroy(rdb->active_db_schema);
+ }
+ rdb->active_db_schema = schema;
+ } else {
+ VLOG_INFO("%s cannot be replicated.", schema->name);
+ struct replication_db *r =
+ shash_find_and_delete(replication_dbs,
+ schema->name);
+ if (r->active_db_schema) {
+ ovsdb_schema_destroy(r->active_db_schema);
+ }
+ free(r);
+ ovsdb_schema_destroy(schema);
+ }
+ } else {
+ ovsdb_schema_destroy(schema);
}
- ovsdb_schema_destroy(schema);
/* After receiving schemas, reset the local databases that
* will be monitored and send out monitor requests for them. */
@@ -306,11 +340,13 @@ replication_run(void)
state = RPL_S_ERR;
} else {
SHASH_FOR_EACH (node, replication_dbs) {
- db = node->data;
+ rdb = node->data;
struct jsonrpc_msg *request =
- create_monitor_request(db);
+ create_monitor_request(
+ rdb->schema_version_higher ?
+ rdb->active_db_schema : rdb->db->schema);
- request_ids_add(request->id, db);
+ request_ids_add(request->id, rdb->db);
jsonrpc_session_send(session, request);
VLOG_DBG("Send monitor requests");
state = RPL_S_MONITOR_REQUESTED;
@@ -509,7 +545,7 @@ replication_destroy(void)
shash_destroy(&local_dbs);
}
-static struct ovsdb *
+static struct replication_db *
find_db(const char *db_name)
{
return shash_find_data(replication_dbs, db_name);
@@ -541,11 +577,10 @@ reset_database(struct ovsdb *db)
* Caller is responsible for disposing 'request'.
*/
static struct jsonrpc_msg *
-create_monitor_request(struct ovsdb *db)
+create_monitor_request(struct ovsdb_schema *schema)
{
struct jsonrpc_msg *request;
struct json *monitor;
- struct ovsdb_schema *schema = db->schema;
const char *db_name = schema->name;
struct json *monitor_request = json_object_create();
@@ -779,14 +814,18 @@ request_ids_clear(void)
}
static struct shash *
-replication_db_clone(struct shash *dbs)
+replication_dbs_create(void)
{
struct shash *new = xmalloc(sizeof *new);
shash_init(new);
struct shash_node *node;
- SHASH_FOR_EACH (node, dbs) {
- shash_add(new, node->name, node->data);
+ SHASH_FOR_EACH (node, &local_dbs) {
+ struct replication_db *repl_db = xmalloc(sizeof *repl_db);
+ repl_db->db = node->data;
+ repl_db->schema_version_higher = false;
+ repl_db->active_db_schema = NULL;
+ shash_add(new, node->name, repl_db);
}
return new;
@@ -795,7 +834,24 @@ replication_db_clone(struct shash *dbs)
static void
replication_dbs_destroy(void)
{
- shash_destroy(replication_dbs);
+ if (!replication_dbs) {
+ return;
+ }
+
+ struct shash_node *node, *next;
+
+ SHASH_FOR_EACH_SAFE (node, next, replication_dbs) {
+ hmap_remove(&replication_dbs->map, &node->node);
+ struct replication_db *rdb = node->data;
+ if (rdb->active_db_schema) {
+ ovsdb_schema_destroy(rdb->active_db_schema);
+ }
+ free(rdb);
+ free(node->name);
+ free(node);
+ }
+
+ hmap_destroy(&replication_dbs->map);
free(replication_dbs);
replication_dbs = NULL;
}
@@ -877,6 +933,62 @@ replication_status(void)
return ds_steal_cstr(&ds);
}
+/* Checks if it's possible to replicate to the local db from the active db
+ * schema. Returns true, if 'local_db_schema' has all the tables and columns
+ * of 'active_db_schema', false otherwise.
+ */
+static bool
+is_replication_possible(struct ovsdb_schema *local_db_schema,
+ struct ovsdb_schema *active_db_schema)
+{
+ struct shash_node *node;
+ SHASH_FOR_EACH (node, &active_db_schema->tables) {
+ struct ovsdb_table_schema *ldb_table_schema =
+ shash_find_data(&local_db_schema->tables, node->name);
+ if (!ldb_table_schema) {
+ VLOG_INFO("Table %s not present in the local db schema",
+ node->name);
+ return false;
+ }
+
+ /* Local schema table should have all the columns
+ * of active schema table. */
+ struct ovsdb_table_schema *adb_table_schema = node->data;
+ struct shash_node *n;
+ SHASH_FOR_EACH (n, &adb_table_schema->columns) {
+ struct ovsdb_column *ldb_col =
+ shash_find_data(&ldb_table_schema->columns, n->name);
+ if (!ldb_col) {
+ VLOG_INFO("Column %s not present in the local "
+ "db schema table %s.", n->name, node->name);
+ return false;
+ }
+
+ struct json *ldb_col_json = ovsdb_column_to_json(ldb_col);
+ struct json *adb_col_json = ovsdb_column_to_json(n->data);
+ bool cols_equal = json_equal(ldb_col_json, adb_col_json);
+ json_destroy(ldb_col_json);
+ json_destroy(adb_col_json);
+
+ if (!cols_equal) {
+ VLOG_INFO("Column %s mismatch in local "
+ "db schema table %s.", n->name, node->name);
+ return false;
+ }
+ }
+ }
+
+ return true;
+}
+
+void
+replication_set_probe_interval(int probe_interval)
+{
+ if (session) {
+ jsonrpc_session_set_probe_interval(session, probe_interval);
+ }
+}
+
void
replication_usage(void)
{
diff --git a/ovsdb/replication.h b/ovsdb/replication.h
index 1f9c32fa74..c45f33e262 100644
--- a/ovsdb/replication.h
+++ b/ovsdb/replication.h
@@ -44,8 +44,10 @@ struct ovsdb;
* used mainly by uinxctl commands.
*/
+#define REPLICATION_DEFAULT_PROBE_INTERVAL 60000
+
void replication_init(const char *sync_from, const char *exclude_tables,
- const struct uuid *server);
+ const struct uuid *server, int probe_interval);
void replication_run(void);
void replication_wait(void);
void replication_destroy(void);
@@ -54,6 +56,7 @@ void replication_add_local_db(const char *databse, struct ovsdb *db);
bool replication_is_alive(void);
int replication_get_last_error(void);
char *replication_status(void);
+void replication_set_probe_interval(int);
char *set_blacklist_tables(const char *blacklist, bool dryrun)
OVS_WARN_UNUSED_RESULT;
diff --git a/python/ovs/db/idl.py b/python/ovs/db/idl.py
index 250e89756c..53ebb5cc0c 100644
--- a/python/ovs/db/idl.py
+++ b/python/ovs/db/idl.py
@@ -12,6 +12,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
+import collections
import functools
import uuid
@@ -39,6 +40,10 @@ OVSDB_UPDATE = 0
OVSDB_UPDATE2 = 1
+Notice = collections.namedtuple('Notice', ('event', 'row', 'updates'))
+Notice.__new__.__defaults__ = (None,) # default updates=None
+
+
class Idl(object):
"""Open vSwitch Database Interface Definition Language (OVSDB IDL).
@@ -479,6 +484,7 @@ class Idl(object):
raise error.Error("<table-updates> is not an object",
table_updates)
+ notices = []
for table_name, table_update in six.iteritems(table_updates):
table = self.tables.get(table_name)
if not table:
@@ -504,7 +510,9 @@ class Idl(object):
% (table_name, uuid_string))
if version == OVSDB_UPDATE2:
- if self.__process_update2(table, uuid, row_update):
+ changes = self.__process_update2(table, uuid, row_update)
+ if changes:
+ notices.append(changes)
self.change_seqno += 1
continue
@@ -517,17 +525,20 @@ class Idl(object):
raise error.Error('<row-update> missing "old" and '
'"new" members', row_update)
- if self.__process_update(table, uuid, old, new):
+ changes = self.__process_update(table, uuid, old, new)
+ if changes:
+ notices.append(changes)
self.change_seqno += 1
+ for notice in notices:
+ self.notify(*notice)
def __process_update2(self, table, uuid, row_update):
+ """Returns Notice if a column changed, False otherwise."""
row = table.rows.get(uuid)
- changed = False
if "delete" in row_update:
if row:
del table.rows[uuid]
- self.notify(ROW_DELETE, row)
- changed = True
+ return Notice(ROW_DELETE, row)
else:
# XXX rate-limit
vlog.warn("cannot delete missing row %s from table"
@@ -546,29 +557,27 @@ class Idl(object):
changed = self.__row_update(table, row, row_update)
table.rows[uuid] = row
if changed:
- self.notify(ROW_CREATE, row)
+ return Notice(ROW_CREATE, row)
elif "modify" in row_update:
if not row:
raise error.Error('Modify non-existing row')
old_row = self.__apply_diff(table, row, row_update['modify'])
- self.notify(ROW_UPDATE, row, Row(self, table, uuid, old_row))
- changed = True
+ return Notice(ROW_UPDATE, row, Row(self, table, uuid, old_row))
else:
raise error.Error('<row-update> unknown operation',
row_update)
- return changed
+ return False
def __process_update(self, table, uuid, old, new):
- """Returns True if a column changed, False otherwise."""
+ """Returns Notice if a column changed, False otherwise."""
row = table.rows.get(uuid)
changed = False
if not new:
# Delete row.
if row:
del table.rows[uuid]
- changed = True
- self.notify(ROW_DELETE, row)
+ return Notice(ROW_DELETE, row)
else:
# XXX rate-limit
vlog.warn("cannot delete missing row %s from table %s"
@@ -588,7 +597,7 @@ class Idl(object):
if op == ROW_CREATE:
table.rows[uuid] = row
if changed:
- self.notify(ROW_CREATE, row)
+ return Notice(ROW_CREATE, row)
else:
op = ROW_UPDATE
if not row:
@@ -602,8 +611,8 @@ class Idl(object):
if op == ROW_CREATE:
table.rows[uuid] = row
if changed:
- self.notify(op, row, Row.from_json(self, table, uuid, old))
- return changed
+ return Notice(op, row, Row.from_json(self, table, uuid, old))
+ return False
def __column_name(self, column):
if column.type.key.type == ovs.db.types.UuidType:
@@ -1374,10 +1383,9 @@ class Transaction(object):
for col, val in six.iteritems(row._mutations['_inserts']):
column = row._table.columns[col]
if column.type.is_map():
- opdat = ["map"]
datum = data.Datum.from_python(column.type, val,
_row_to_uuid)
- opdat.append(datum.as_list())
+ opdat = self._substitute_uuids(datum.to_json())
else:
opdat = ["set"]
inner_opdat = []
diff --git a/python/ovs/stream.py b/python/ovs/stream.py
index c15be4b3e5..73aa993da3 100644
--- a/python/ovs/stream.py
+++ b/python/ovs/stream.py
@@ -134,6 +134,10 @@ class Stream(object):
IPTOS_PREC_INTERNETCONTROL = 0xc0
DSCP_DEFAULT = IPTOS_PREC_INTERNETCONTROL >> 2
+ @staticmethod
+ def check_connection_completion(sock):
+ return ovs.socket_util.check_connection_completion(sock)
+
@staticmethod
def open(name, dscp=DSCP_DEFAULT):
"""Attempts to connect a stream to a remote peer. 'name' is a
@@ -191,7 +195,7 @@ class Stream(object):
if error:
return error, None
else:
- err = ovs.socket_util.check_connection_completion(sock)
+ err = cls.check_connection_completion(sock)
if err == errno.EAGAIN or err == errno.EINPROGRESS:
status = errno.EAGAIN
err = 0
@@ -263,7 +267,7 @@ class Stream(object):
def __scs_connecting(self):
if self.socket is not None:
- retval = ovs.socket_util.check_connection_completion(self.socket)
+ retval = self.check_connection_completion(self.socket)
assert retval != errno.EINPROGRESS
elif sys.platform == 'win32':
if self.retry_connect:
@@ -763,6 +767,13 @@ Stream.register_method("tcp", TCPStream)
class SSLStream(Stream):
+ @staticmethod
+ def check_connection_completion(sock):
+ try:
+ return Stream.check_connection_completion(sock)
+ except SSL.SysCallError as e:
+ return ovs.socket_util.get_exception_errno(e)
+
@staticmethod
def needs_probes():
return True
@@ -825,6 +836,14 @@ class SSLStream(Stream):
except SSL.SysCallError as e:
return -ovs.socket_util.get_exception_errno(e)
+ def close(self):
+ if self.socket:
+ try:
+ self.socket.shutdown()
+ except SSL.Error:
+ pass
+ return super(SSLStream, self).close()
+
if SSL:
# Register SSL only if the OpenSSL module is available
diff --git a/python/setup.py b/python/setup.py
index b52657df3a..2cff74eec8 100644
--- a/python/setup.py
+++ b/python/setup.py
@@ -82,7 +82,7 @@ setup_args = dict(
ext_modules=[setuptools.Extension("ovs._json", sources=["ovs/_json.c"],
libraries=['openvswitch'])],
cmdclass={'build_ext': try_build_ext},
- install_requires=['sortedcontainers'],
+ install_requires=['six', 'sortedcontainers'],
)
try:
diff --git a/rhel/openvswitch-fedora.spec.in b/rhel/openvswitch-fedora.spec.in
index 4ece47a54d..ba862e25e1 100644
--- a/rhel/openvswitch-fedora.spec.in
+++ b/rhel/openvswitch-fedora.spec.in
@@ -361,18 +361,19 @@ exit 0
%post
if [ $1 -eq 1 ]; then
- sed -i 's:^#OVS_USER_ID=:OVS_USER_ID=:' /etc/sysconfig/openvswitch
- sed -i 's:\(.*su\).*:\1 openvswitch openvswitch:' %{_sysconfdir}/logrotate.d/openvswitch
-
%if %{with dpdk}
- sed -i \
- 's@OVS_USER_ID="openvswitch:openvswitch"@OVS_USER_ID="openvswitch:hugetlbfs"@'\
- /etc/sysconfig/openvswitch
+ %define gname hugetlbfs
+%else
+ %define gname openvswitch
%endif
+ sed -i \
+ 's@^#OVS_USER_ID="openvswitch:openvswitch"@OVS_USER_ID="openvswitch:%{gname}"@'\
+ %{_sysconfdir}/sysconfig/openvswitch
+ sed -i 's:\(.*su\).*:\1 openvswitch %{gname}:' %{_sysconfdir}/logrotate.d/openvswitch
- # In the case of upgrade, this is not needed.
- chown -R openvswitch:openvswitch /etc/openvswitch
- chown -R openvswitch:openvswitch /var/log/openvswitch
+ # In the case of upgrade, this is not needed
+ chown -R openvswitch:openvswitch %{_sysconfdir}/openvswitch
+ chown -R openvswitch:%{gname} %{_localstatedir}/log/openvswitch
fi
%if 0%{?systemd_post:1}
@@ -380,7 +381,7 @@ fi
%else
# Package install, not upgrade
if [ $1 -eq 1 ]; then
- /bin/systemctl daemon-reload >dev/null || :
+ /bin/systemctl daemon-reload >/dev/null || :
fi
%endif
diff --git a/rhel/usr_lib_systemd_system_ovs-vswitchd.service.in b/rhel/usr_lib_systemd_system_ovs-vswitchd.service.in
index 82925133dc..ff43dae961 100644
--- a/rhel/usr_lib_systemd_system_ovs-vswitchd.service.in
+++ b/rhel/usr_lib_systemd_system_ovs-vswitchd.service.in
@@ -14,18 +14,19 @@ Restart=on-failure
Environment=XDG_RUNTIME_DIR=/var/run/openvswitch
EnvironmentFile=/etc/openvswitch/default.conf
EnvironmentFile=-/etc/sysconfig/openvswitch
-EnvironmentFile=-/run/openvswitch/useropts
+EnvironmentFile=-/run/openvswitch.useropts
+LimitSTACK=2M
@begin_dpdk@
ExecStartPre=-/bin/sh -c '/usr/bin/chown :$${OVS_USER_ID##*:} /dev/hugepages'
ExecStartPre=-/usr/bin/chmod 0775 /dev/hugepages
@end_dpdk@
ExecStart=/usr/share/openvswitch/scripts/ovs-ctl \
--no-ovsdb-server --no-monitor --system-id=random \
- ${OVSUSER} \
+ ${OVS_USER_OPT} \
start $OPTIONS
ExecStop=/usr/share/openvswitch/scripts/ovs-ctl --no-ovsdb-server stop
ExecReload=/usr/share/openvswitch/scripts/ovs-ctl --no-ovsdb-server \
--no-monitor --system-id=random \
- ${OVSUSER} \
+ ${OVS_USER_OPT} \
restart $OPTIONS
TimeoutSec=300
diff --git a/rhel/usr_lib_systemd_system_ovsdb-server.service b/rhel/usr_lib_systemd_system_ovsdb-server.service
index 41ac2dded1..4c170c09b4 100644
--- a/rhel/usr_lib_systemd_system_ovsdb-server.service
+++ b/rhel/usr_lib_systemd_system_ovsdb-server.service
@@ -11,16 +11,15 @@ PIDFile=/var/run/openvswitch/ovsdb-server.pid
Restart=on-failure
EnvironmentFile=/etc/openvswitch/default.conf
EnvironmentFile=-/etc/sysconfig/openvswitch
-ExecStartPre=/usr/bin/chown ${OVS_USER_ID} /var/run/openvswitch /var/log/openvswitch
-ExecStartPre=/bin/sh -c 'rm -f /run/openvswitch/useropts; if [ "$${OVS_USER_ID/:*/}" != "root" ]; then /usr/bin/echo "OVSUSER=--ovs-user=${OVS_USER_ID}" > /run/openvswitch/useropts; fi'
-EnvironmentFile=-/run/openvswitch/useropts
+ExecStartPre=-/usr/bin/chown ${OVS_USER_ID} /var/run/openvswitch /var/log/openvswitch
+ExecStartPre=/bin/sh -c 'rm -f /run/openvswitch.useropts; /usr/bin/echo "OVS_USER_ID=${OVS_USER_ID}" > /run/openvswitch.useropts'
+ExecStartPre=/bin/sh -c 'if [ "$${OVS_USER_ID/:*/}" != "root" ]; then /usr/bin/echo "OVS_USER_OPT=--ovs-user=${OVS_USER_ID}" >> /run/openvswitch.useropts; fi'
+EnvironmentFile=-/run/openvswitch.useropts
ExecStart=/usr/share/openvswitch/scripts/ovs-ctl \
--no-ovs-vswitchd --no-monitor --system-id=random \
- ${OVSUSER} \
+ ${OVS_USER_OPT} \
start $OPTIONS
ExecStop=/usr/share/openvswitch/scripts/ovs-ctl --no-ovs-vswitchd stop
ExecReload=/usr/share/openvswitch/scripts/ovs-ctl --no-ovs-vswitchd \
- ${OVSUSER} \
+ ${OVS_USER_OPT} \
--no-monitor restart $OPTIONS
-RuntimeDirectory=openvswitch
-RuntimeDirectoryMode=0755
diff --git a/rhel/usr_share_openvswitch_scripts_systemd_sysconfig.template b/rhel/usr_share_openvswitch_scripts_systemd_sysconfig.template
index 9364454020..c467d02db9 100644
--- a/rhel/usr_share_openvswitch_scripts_systemd_sysconfig.template
+++ b/rhel/usr_share_openvswitch_scripts_systemd_sysconfig.template
@@ -21,6 +21,10 @@
# --ovs-vswitchd-wrapper=valgrind
# --ovsdb-server-wrapper=valgrind
#
+# Specify additional options, for example to start with debug logs:
+# --ovs-vswitchd-options='-vconsole:dbg -vfile:dbg'
+# --ovsdb-server-options='-vconsole:dbg -vfile:dbg'
+#
OPTIONS=""
# Uncomment and set the OVS User/Group value
diff --git a/tests/automake.mk b/tests/automake.mk
index 92d56b29de..57831e8a6e 100644
--- a/tests/automake.mk
+++ b/tests/automake.mk
@@ -108,7 +108,8 @@ TESTSUITE_AT = \
tests/ovn-controller-vtep.at \
tests/mcast-snooping.at \
tests/packet-type-aware.at \
- tests/nsh.at
+ tests/nsh.at \
+ tests/drop-stats.at
EXTRA_DIST += $(FUZZ_REGRESSION_TESTS)
FUZZ_REGRESSION_TESTS = \
@@ -134,7 +135,8 @@ FUZZ_REGRESSION_TESTS = \
tests/fuzz-regression/ofp_print_fuzzer-5722747668791296 \
tests/fuzz-regression/ofp_print_fuzzer-6285128790704128 \
tests/fuzz-regression/ofp_print_fuzzer-6470117922701312 \
- tests/fuzz-regression/ofp_print_fuzzer-6502620041576448
+ tests/fuzz-regression/ofp_print_fuzzer-6502620041576448 \
+ tests/fuzz-regression/ofp_print_fuzzer-6540965472632832
$(srcdir)/tests/fuzz-regression-list.at: tests/automake.mk
$(AM_V_GEN)for name in $(FUZZ_REGRESSION_TESTS); do \
basename=`echo $$name | sed 's,^.*/,,'`; \
@@ -150,7 +152,8 @@ SYSTEM_USERSPACE_TESTSUITE_AT = \
tests/system-userspace-testsuite.at \
tests/system-ovn.at \
tests/system-userspace-macros.at \
- tests/system-userspace-packet-type-aware.at
+ tests/system-userspace-packet-type-aware.at \
+ tests/system-route.at
SYSTEM_TESTSUITE_AT = \
tests/system-common-macros.at \
diff --git a/tests/classifier.at b/tests/classifier.at
index 86f872db6b..a63d8c32d7 100644
--- a/tests/classifier.at
+++ b/tests/classifier.at
@@ -306,3 +306,39 @@ ovs-ofctl: Incorrect instruction ordering
])
OVS_VSWITCHD_STOP
AT_CLEANUP
+
+# Flow classifier a packet with excess of padding.
+AT_SETUP([flow classifier - packet with extra padding])
+OVS_VSWITCHD_START
+add_of_ports br0 1 2
+AT_DATA([flows.txt], [dnl
+priority=5,ip,ip_dst=1.1.1.1,actions=1
+priority=5,ip,ip_dst=1.1.1.2,actions=2
+priority=0,actions=drop
+])
+AT_CHECK([ovs-ofctl add-flows br0 flows.txt])
+packet=00020202020000010101010008004500001c00010000401176cc01010101010101020d6a00350008ee3a
+AT_CHECK([ovs-appctl ofproto/trace br0 in_port=1 $packet] , [0], [stdout])
+AT_CHECK([tail -2 stdout], [0],
+ [Megaflow: recirc_id=0,eth,ip,in_port=1,nw_dst=1.1.1.2,nw_frag=no
+Datapath actions: 2
+])
+# normal packet plus 255 bytes of padding (8bit padding).
+# 255 * 2 = 510
+padding=$(printf '%*s' 510 | tr ' ' '0')
+AT_CHECK([ovs-appctl ofproto/trace br0 in_port=1 ${packet}${padding}] , [0], [stdout])
+AT_CHECK([tail -2 stdout], [0],
+ [Megaflow: recirc_id=0,eth,ip,in_port=1,nw_dst=1.1.1.2,nw_frag=no
+Datapath actions: 2
+])
+# normal packet plus padding up to 65535 bytes of length (16bit limit).
+# 65535 - 43 = 65492
+# 65492 * 2 = 130984
+padding=$(printf '%*s' 130984 | tr ' ' '0')
+AT_CHECK([ovs-appctl ofproto/trace br0 in_port=1 ${packet}${padding}], [0], [stdout])
+AT_CHECK([tail -2 stdout], [0],
+ [Megaflow: recirc_id=0,eth,ip,in_port=1,nw_dst=1.1.1.2,nw_frag=no
+Datapath actions: 2
+])
+OVS_VSWITCHD_STOP
+AT_CLEANUP
diff --git a/tests/dpif-netdev.at b/tests/dpif-netdev.at
index 6915d43ba1..9295f5a0ec 100644
--- a/tests/dpif-netdev.at
+++ b/tests/dpif-netdev.at
@@ -337,6 +337,14 @@ meter:2 flow_count:1 packet_in_count:10 byte_in_count:600 duration:0.0s bands:
0: packet_count:5 byte_count:300
])
+ovs-appctl time/warp 5000
+
+AT_CHECK([
+ovs-appctl coverage/show | grep datapath_drop_meter | awk '{ print $6 } END { if (!NR) print "0" }'
+], [0], [dnl
+14
+])
+
AT_CHECK([cat ovs-vswitchd.log | filter_flow_install | strip_xout_keep_actions], [0], [dnl
recirc_id(0),in_port(1),packet_type(ns=0,id=0),eth_type(0x0800),ipv4(frag=no), actions:meter(0),7
recirc_id(0),in_port(2),packet_type(ns=0,id=0),eth_type(0x0800),ipv4(frag=no), actions:8
diff --git a/tests/drop-stats.at b/tests/drop-stats.at
new file mode 100644
index 0000000000..67d1a4aa23
--- /dev/null
+++ b/tests/drop-stats.at
@@ -0,0 +1,190 @@
+AT_BANNER([drop-stats])
+
+AT_SETUP([drop-stats - cli tests])
+
+OVS_VSWITCHD_START([dnl
+ set bridge br0 datapath_type=dummy \
+ protocols=OpenFlow10,OpenFlow13,OpenFlow14,OpenFlow15 -- \
+ add-port br0 p1 -- set Interface p1 type=dummy ofport_request=1])
+
+AT_DATA([flows.txt], [dnl
+table=0,in_port=1,actions=drop
+])
+
+AT_CHECK([
+ ovs-ofctl del-flows br0
+ ovs-ofctl -Oopenflow13 add-flows br0 flows.txt
+ ovs-ofctl -Oopenflow13 dump-flows br0 | ofctl_strip | sort | grep actions ], [0], [dnl
+ in_port=1 actions=drop
+])
+
+AT_CHECK([
+ ovs-appctl netdev-dummy/receive p1 'in_port(1),packet_type(ns=0,id=0),eth(src=3a:6d:d2:09:9c:ab,dst=1e:2c:e9:2a:66:9e),ipv4(src=192.168.10.10,dst=192.168.10.30,proto=1,tos=0,ttl=64,frag=no),icmp(type=8,code=0)'
+ ovs-appctl netdev-dummy/receive p1 'in_port(1),packet_type(ns=0,id=0),eth(src=3a:6d:d2:09:9c:ab,dst=1e:2c:e9:2a:66:9e),ipv4(src=192.168.10.10,dst=192.168.10.30,proto=1,tos=0,ttl=64,frag=no),icmp(type=8,code=0)'
+ ovs-appctl netdev-dummy/receive p1 'in_port(1),packet_type(ns=0,id=0),eth(src=3a:6d:d2:09:9c:ab,dst=1e:2c:e9:2a:66:9e),ipv4(src=192.168.10.10,dst=192.168.10.30,proto=1,tos=0,ttl=64,frag=no),icmp(type=8,code=0)'
+], [0], [ignore])
+
+AT_CHECK([ovs-appctl dpctl/dump-flows | sed 's/used:[[0-9]].[[0-9]]*s/used:0.0/' | sort], [0], [flow-dump from non-dpdk interfaces:
+recirc_id(0),in_port(1),packet_type(ns=0,id=0),eth_type(0x0800),ipv4(frag=no), packets:2, bytes:212, used:0.0, actions:drop
+])
+
+ovs-appctl time/warp 5000
+
+AT_CHECK([
+ovs-appctl coverage/show | grep drop_action_of_pipeline | awk '{ print $6 } END { if (!NR) print "0" }'
+], [0], [dnl
+3
+])
+
+
+OVS_VSWITCHD_STOP
+AT_CLEANUP
+
+AT_SETUP([drop-stats - pipeline and recurssion drops])
+
+OVS_VSWITCHD_START([dnl
+ set bridge br0 datapath_type=dummy \
+ protocols=OpenFlow10,OpenFlow13,OpenFlow14,OpenFlow15 -- \
+ add-port br0 p1 -- set Interface p1 type=dummy ofport_request=1 -- \
+ add-port br0 p2 -- set Interface p2 type=dummy ofport_request=2])
+
+AT_DATA([flows.txt], [dnl
+table=0,in_port=1,actions=drop
+])
+
+AT_CHECK([
+ ovs-ofctl del-flows br0
+ ovs-ofctl -Oopenflow13 add-flows br0 flows.txt
+ ovs-ofctl -Oopenflow13 dump-flows br0 | ofctl_strip | sort | grep actions ], [0], [dnl
+ in_port=1 actions=drop
+])
+
+AT_CHECK([
+ ovs-appctl netdev-dummy/receive p1 'in_port(1),packet_type(ns=0,id=0),eth(src=3a:6d:d2:09:9c:ab,dst=1e:2c:e9:2a:66:9e),ipv4(src=192.168.10.10,dst=192.168.10.30,proto=1,tos=0,ttl=64,frag=no),icmp(type=8,code=0)'
+], [0], [ignore])
+
+ovs-appctl time/warp 5000
+
+AT_CHECK([
+ovs-appctl coverage/show | grep drop_action_of_pipeline | awk '{ print $6 } END { if (!NR) print "0" }'
+], [0], [dnl
+1
+])
+
+
+AT_DATA([flows.txt], [dnl
+table=0, in_port=1, actions=goto_table:1
+table=1, in_port=1, actions=goto_table:2
+table=2, in_port=1, actions=resubmit(,1)
+])
+
+AT_CHECK([
+ ovs-ofctl del-flows br0
+ ovs-ofctl -Oopenflow13 add-flows br0 flows.txt
+ ovs-ofctl -Oopenflow13 dump-flows br0 | ofctl_strip | sort | grep actions ], [0], [ignore])
+
+AT_CHECK([
+ ovs-appctl netdev-dummy/receive p1 'in_port(1),packet_type(ns=0,id=0),eth(src=3a:6d:d2:09:9c:ab,dst=1e:2c:e9:2a:66:9e),ipv4(src=192.168.10.10,dst=192.168.10.30,proto=1,tos=0,ttl=64,frag=no),icmp(type=8,code=0)'
+], [0], [ignore])
+
+ovs-appctl time/warp 5000
+
+AT_CHECK([
+ovs-appctl coverage/show | grep drop_action_recursion_too_deep | awk '{ print $6 } END { if (!NR) print "0" }'
+], [0], [dnl
+1
+])
+
+
+OVS_VSWITCHD_STOP(["/|WARN|/d"])
+AT_CLEANUP
+
+AT_SETUP([drop-stats - too many resubmit])
+OVS_VSWITCHD_START
+add_of_ports br0 1
+(for i in `seq 1 64`; do
+ j=`expr $i + 1`
+ echo "in_port=$i, actions=resubmit:$j, resubmit:$j, local"
+ done
+ echo "in_port=65, actions=local") > flows.txt
+
+AT_CHECK([
+ ovs-ofctl del-flows br0
+ ovs-ofctl -Oopenflow13 add-flows br0 flows.txt ], [0], [ignore])
+
+ovs-appctl netdev-dummy/receive p1 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x1234)'
+
+ovs-appctl time/warp 5000
+
+AT_CHECK([
+ovs-appctl coverage/show | grep drop_action_too_many_resubmit | awk '{ print $6 } END { if (!NR) print "0" }'
+], [0], [dnl
+1
+])
+
+OVS_VSWITCHD_STOP(["/|WARN|/d"])
+AT_CLEANUP
+
+
+AT_SETUP([drop-stats - stack too deep])
+OVS_VSWITCHD_START
+add_of_ports br0 1
+(for i in `seq 1 12`; do
+ j=`expr $i + 1`
+ echo "in_port=$i, actions=resubmit:$j, resubmit:$j, local"
+ done
+ push="push:NXM_NX_REG0[[]]"
+ echo "in_port=13, actions=$push,$push,$push,$push,$push,$push,$push,$push") > flows
+
+AT_CHECK([ovs-ofctl add-flows br0 flows])
+
+ovs-appctl netdev-dummy/receive p1 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x1234)'
+
+ovs-appctl time/warp 5000
+
+AT_CHECK([
+ovs-appctl coverage/show | grep drop_action_stack_too_deep | awk '{ print $6 } END { if (!NR) print "0" }'
+], [0], [dnl
+1
+])
+
+
+OVS_VSWITCHD_STOP(["/resubmits yielded over 64 kB of stack/d"])
+AT_CLEANUP
+
+AT_SETUP([drop-stats - too many mpls labels])
+
+OVS_VSWITCHD_START([dnl
+ set bridge br0 datapath_type=dummy \
+ protocols=OpenFlow10,OpenFlow13,OpenFlow14,OpenFlow15 -- \
+ add-port br0 p1 -- set Interface p1 type=dummy ofport_request=1 -- \
+ add-port br0 p2 -- set Interface p2 type=dummy ofport_request=2])
+
+AT_DATA([flows.txt], [dnl
+table=0, in_port=1, actions=push_mpls:0x8847, resubmit:3
+table=0, in_port=3, actions=push_mpls:0x8847, set_field:10->mpls_label, set_field:15->mpls_label, resubmit:4
+table=0, in_port=4, actions=push_mpls:0x8847, set_field:11->mpls_label, resubmit:5
+table=0, in_port=5, actions=push_mpls:0x8847, set_field:12->mpls_label, resubmit:6
+table=0, in_port=6, actions=push_mpls:0x8847, set_field:13->mpls_label, output:2
+])
+
+AT_CHECK([
+ ovs-ofctl del-flows br0
+ ovs-ofctl -Oopenflow13 add-flows br0 flows.txt
+])
+
+AT_CHECK([
+ ovs-appctl netdev-dummy/receive p1 'in_port(1),packet_type(ns=0,id=0),eth(src=3a:6d:d2:09:9c:ab,dst=1e:2c:e9:2a:66:9e),ipv4(src=192.168.10.10,dst=192.168.10.30,proto=1,tos=0,ttl=64,frag=no),icmp(type=8,code=0)'
+], [0], [ignore])
+
+ovs-appctl time/warp 5000
+
+AT_CHECK([
+ovs-appctl coverage/show | grep drop_action_too_many_mpls_labels | awk '{ print $6 } END { if (!NR) print "0" }'
+], [0], [dnl
+1
+])
+
+
+OVS_VSWITCHD_STOP(["/|WARN|/d"])
+AT_CLEANUP
diff --git a/tests/fuzz-regression-list.at b/tests/fuzz-regression-list.at
index e3173fb88f..2347c690ef 100644
--- a/tests/fuzz-regression-list.at
+++ b/tests/fuzz-regression-list.at
@@ -21,3 +21,4 @@ TEST_FUZZ_REGRESSION([ofp_print_fuzzer-5722747668791296])
TEST_FUZZ_REGRESSION([ofp_print_fuzzer-6285128790704128])
TEST_FUZZ_REGRESSION([ofp_print_fuzzer-6470117922701312])
TEST_FUZZ_REGRESSION([ofp_print_fuzzer-6502620041576448])
+TEST_FUZZ_REGRESSION([ofp_print_fuzzer-6540965472632832])
diff --git a/tests/fuzz-regression/ofp_print_fuzzer-6540965472632832 b/tests/fuzz-regression/ofp_print_fuzzer-6540965472632832
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/tests/idltest.ovsschema b/tests/idltest.ovsschema
index bee79fc50f..e02b975bc5 100644
--- a/tests/idltest.ovsschema
+++ b/tests/idltest.ovsschema
@@ -171,6 +171,21 @@
},
"isRoot" : false
},
+ "simple5": {
+ "columns" : {
+ "name": {"type": "string"},
+ "irefmap": {
+ "type": {
+ "key": {"type": "integer"},
+ "value": {"type": "uuid",
+ "refTable": "simple3"},
+ "min": 0,
+ "max": "unlimited"
+ }
+ }
+ },
+ "isRoot": true
+ },
"singleton" : {
"columns" : {
"name" : {
diff --git a/tests/library.at b/tests/library.at
index a30d362e34..49d90f4303 100644
--- a/tests/library.at
+++ b/tests/library.at
@@ -53,7 +53,8 @@ AT_CHECK([ovstest test-packets])
AT_CLEANUP
AT_SETUP([SHA-1])
-AT_CHECK([ovstest test-sha1], [0], [.........
+AT_KEYWORDS([sha1])
+AT_CHECK([ovstest test-sha1], [0], [..........
])
AT_CLEANUP
diff --git a/tests/odp.at b/tests/odp.at
index 86a918e662..ac17b8525f 100644
--- a/tests/odp.at
+++ b/tests/odp.at
@@ -377,6 +377,10 @@ clone(1)
clone(clone(push_vlan(vid=12,pcp=0),2),1)
set(tunnel(tun_id=0x1,dst=1.1.1.1,ttl=64,erspan(ver=1,idx=0x7),flags(df|key)))
set(tunnel(tun_id=0x1,dst=1.1.1.1,ttl=64,erspan(ver=2,dir=1,hwid=0x1),flags(df|key)))
+check_pkt_len(size=200,gt(4),le(5))
+check_pkt_len(size=200,gt(drop),le(5))
+check_pkt_len(size=200,gt(ct(nat)),le(drop))
+check_pkt_len(size=200,gt(set(eth(src=00:01:02:03:04:05,dst=10:11:12:13:14:15))),le(set(eth(src=00:01:02:03:04:06,dst=10:11:12:13:14:16))))
])
AT_CHECK_UNQUOTED([ovstest test-odp parse-actions < actions.txt], [0],
[`cat actions.txt`
@@ -391,6 +395,43 @@ odp_actions_from_string: error
])
AT_CLEANUP
+AT_SETUP([OVS datapath actions parsing and formatting - userdata overflow])
+dnl Userdata should fit in a single netlink message, i.e. should be less than
+dnl UINT16_MAX - NLA_HDRLEN = 65535 - 4 = 65531 bytes. OVS should not accept
+dnl larger userdata. OTOH, userdata is part of a nested netlink message, that
+dnl should not be oversized too. 'pid' takes NLA_HDRLEN + 4 = 8 bytes.
+dnl Plus NLA_HDRLEN for the nested header. 'actions' flag takes NLA_HDRLEN = 4
+dnl and 'tunnel_out_port' takes NLA_HDRLEN + 4 = 8 bytes.
+dnl So, for the variant with 'actions' maximum length of userdata should be:
+dnl UINT16_MAX - NLA_HDRLEN - (NLA_HDRLEN + 4) - NLA_HDRLEN - NLA_HDRLEN
+dnl total max nested header pid actions userdata
+dnl Result: 65515 bytes for the actual userdata.
+dnl For the case with 'tunnel_out_port': 65511
+dnl Size of userdata will be rounded up to be multiple of 4, so highest
+dnl acceptable sizes are 65512 and 65508.
+
+dnl String with length 65512 * 2 = 131024 is valid, while 131026 is not.
+data_valid=$( printf '%*s' 131024 | tr ' ' "a")
+data_invalid=$(printf '%*s' 131026 | tr ' ' "a")
+
+echo "userspace(pid=1234567,userdata(${data_valid}),actions)" > actions.txt
+echo "userspace(pid=1234567,userdata(${data_invalid}),actions)" >> actions.txt
+
+dnl String with length 65508 * 2 = 131016 is valid, while 131018 is not.
+data_valid=$( printf '%*s' 131016 | tr ' ' "a")
+data_invalid=$(printf '%*s' 131018 | tr ' ' "a")
+
+echo "userspace(pid=1234567,userdata(${data_valid}),tunnel_out_port=10)" >> actions.txt
+echo "userspace(pid=1234567,userdata(${data_invalid}),tunnel_out_port=10)" >> actions.txt
+
+AT_CHECK_UNQUOTED([ovstest test-odp parse-actions < actions.txt], [0], [dnl
+`cat actions.txt | head -1`
+odp_actions_from_string: error
+`cat actions.txt | head -3 | tail -1`
+odp_actions_from_string: error
+])
+AT_CLEANUP
+
AT_SETUP([OVS datapath keys parsing and formatting - 33 nested encap ])
AT_DATA([odp-in.txt], [dnl
encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap(encap()))))))))))))))))))))))))))))))))
diff --git a/tests/ofp-actions.at b/tests/ofp-actions.at
index e320a92a8f..348117197c 100644
--- a/tests/ofp-actions.at
+++ b/tests/ofp-actions.at
@@ -310,6 +310,12 @@ ffff 0018 00002320 0025 0000 0005 5000 1122334455 000000
ffff 0048 00002320 0023 0001 00000000 0000 FF 000000 0000 dnl
ffff 0030 00002320 0024 00 00 0011 000c fe800000 00000000 020c 29ff fe88 a18b fe800000 00000000 020c 29ff fe88 0001
+# actions=check_pkt_larger(1500)->NXM_NX_REG0[0]
+ffff 0018 00002320 0031 05dc 000000010004000000000000
+
+# actions=check_pkt_larger(1000)->NXM_NX_XXREG1[4]
+ffff 0018 00002320 0031 03e8 00040001e010000000000000
+
])
sed '/^[[#&]]/d' < test-data > input.txt
sed -n 's/^# //p; /^$/p' < test-data > expout
@@ -746,6 +752,17 @@ dnl Check the ONF extension form of "copy_field".
# actions=move:NXM_OF_IN_PORT[]->NXM_OF_VLAN_TCI[]
ffff 0020 4f4e4600 0c80 0000 0010 0000 0000 0000 00000002 00000802 00000000
+dnl Check NSH encap (experimenter extension).
+# actions=encap(nsh(md_type=1))
+ffff 0018 00002320 002e 0000 0001894f 0004 01 05 01 000000
+
+dnl NSH encap with non-zero padding.
+# actions=encap(nsh(md_type=1))
+# 21: 12 -> 00
+# 22: 34 -> 00
+# 23: 56 -> 00
+ffff 0018 00002320 002e 0000 0001894f 0004 01 05 01 123456
+
])
sed '/^[[#&]]/d' < test-data > input.txt
sed -n 's/^# //p; /^$/p' < test-data > expout
diff --git a/tests/ofproto-dpif.at b/tests/ofproto-dpif.at
index ded2ef0132..b7cb3cf5f8 100644
--- a/tests/ofproto-dpif.at
+++ b/tests/ofproto-dpif.at
@@ -5434,6 +5434,47 @@ AT_CHECK([test 1 = `$PYTHON "$top_srcdir/utilities/ovs-pcap.in" p2-tx.pcap | wc
OVS_VSWITCHD_STOP
AT_CLEANUP
+AT_SETUP([ofproto-dpif - continuation with patch port])
+AT_KEYWORDS([continuations pause resume])
+OVS_VSWITCHD_START(
+ [add-port br0 p0 -- set Interface p0 type=dummy -- \
+ add-port br0 patch- -- \
+ set interface patch- type=patch options:peer=patch+ -- \
+ add-br br1 -- set bridge br1 datapath-type=dummy fail-mode=secure -- \
+ add-port br1 patch+ -- set interface patch+ type=patch options:peer=patch-
+])
+add_of_ports --pcap br1 1
+
+flow="in_port(1),eth(src=50:54:00:00:00:05,dst=50:54:00:00:00:07),eth_type(0x0800),ipv4(src=192.168.0.1,dst=192.168.0.2,proto=1,tos=0,ttl=128,frag=no),icmp(type=8,code=0)"
+
+AT_DATA([flows.txt], [dnl
+table=0, in_port=patch+ icmp action=controller(pause), resubmit(,1)
+table=1, in_port=patch+ icmp action=ct(table=2)
+table=2, in_port=patch+ icmp ct_state=+trk+new action=ct(commit, table=3)
+table=3, in_port=patch+ icmp action=p1
+])
+
+AT_CHECK([ovs-ofctl add-flow br0 action=normal])
+AT_CHECK([ovs-ofctl -O OpenFlow13 add-flows br1 flows.txt])
+
+AT_CAPTURE_FILE([ofctl_monitor.log])
+ovs-ofctl monitor br1 resume --detach --no-chdir --pidfile=ovs-ofctl.pid 2> ofctl_monitor.log
+
+# Run a packet through the switch.
+AT_CHECK([ovs-appctl netdev-dummy/receive p0 "$flow"], [0], [stdout])
+
+# Check flow stats
+AT_CHECK([ovs-ofctl dump-flows br1], [0], [stdout])
+AT_CHECK([strip_xids < stdout | sed -n 's/duration=[[0-9]]*\.[[0-9]]*s/duration=0.0s/p' | sed -n 's/idle_age=[[0-9]]*/idle_age=0/p' | grep 'table=3' | grep -v 'commit'], [0], [dnl
+ cookie=0x0, duration=0.0s, table=3, n_packets=1, n_bytes=106, idle_age=0, icmp,in_port=1 actions=output:2
+])
+
+# The packet should be received by port 1
+AT_CHECK([test 1 = `$PYTHON "$top_srcdir/utilities/ovs-pcap.in" p1-tx.pcap | wc -l`])
+
+OVS_VSWITCHD_STOP
+AT_CLEANUP
+
# Check that pause works after the packet is cloned.
AT_SETUP([ofproto-dpif - continuation after clone])
AT_KEYWORDS([continuations clone pause resume])
@@ -9384,7 +9425,7 @@ recirc_id(0),in_port(1),packet_type(ns=0,id=0),eth_type(0x8100),vlan(vid=99,pcp=
# are wildcarded.
AT_CHECK([grep '\(modify\)\|\(flow_add\)' ovs-vswitchd.log | strip_ufid ], [0], [dnl
dpif_netdev|DBG|flow_add: recirc_id(0),in_port(1),packet_type(ns=0,id=0),eth_type(0x1234), actions:100
-dpif|DBG|dummy@ovs-dummy: put[[modify]] skb_priority(0/0),skb_mark(0/0),ct_state(0/0),ct_zone(0/0),ct_mark(0/0),ct_label(0/0),recirc_id(0),dp_hash(0/0),in_port(1),packet_type(ns=0,id=0),eth(src=50:54:00:00:00:09/00:00:00:00:00:00,dst=50:54:00:00:00:0a/00:00:00:00:00:00),eth_type(0x1234)
+dpif|DBG|dummy@ovs-dummy: put[[modify]] skb_priority(0/0),skb_mark(0/0),ct_state(0/0),ct_zone(0/0),ct_mark(0/0),ct_label(0/0),recirc_id(0),dp_hash(0/0),in_port(1),packet_type(ns=0,id=0),eth(src=50:54:00:00:00:09/00:00:00:00:00:00,dst=50:54:00:00:00:0a/00:00:00:00:00:00),eth_type(0x1234), actions:drop
dpif|DBG|dummy@ovs-dummy: put[[modify]] skb_priority(0/0),skb_mark(0/0),ct_state(0/0),ct_zone(0/0),ct_mark(0/0),ct_label(0/0),recirc_id(0),dp_hash(0/0),in_port(1),packet_type(ns=0,id=0),eth(src=50:54:00:00:00:09/00:00:00:00:00:00,dst=50:54:00:00:00:0a/00:00:00:00:00:00),eth_type(0x1234), actions:100
dpif_netdev|DBG|flow_add: recirc_id(0),in_port(1),packet_type(ns=0,id=0),eth_type(0x8100),vlan(vid=99,pcp=7/0x0),encap(eth_type(0x1234)), actions:drop
])
@@ -10361,6 +10402,62 @@ udp,vlan_tci=0x0000,dl_src=50:54:00:00:00:0a,dl_dst=50:54:00:00:00:09,nw_src=10.
OVS_VSWITCHD_STOP
AT_CLEANUP
+AT_SETUP([ofproto-dpif - conntrack - match masked ct fields])
+OVS_VSWITCHD_START
+
+add_of_ports br0 1 2
+
+AT_CHECK([ovs-appctl vlog/set dpif_netdev:dbg vconn:info ofproto_dpif:info])
+
+dnl Allow new connections on p1->p2. Allow only established connections p2->p1
+AT_DATA([flows.txt], [dnl
+table=0,arp,action=normal
+table=0,ip,in_port=1,udp,nw_src=10.1.2.1/24,action=ct(commit)
+table=0,ip,in_port=1,udp6,ipv6_dst=2001:db8::1/64,action=ct(commit)
+table=0,ip,in_port=1,udp,tp_src=3/0x1,action=ct(commit)
+table=0,ip,in_port=2,actions=ct(table=1)
+table=0,ip6,in_port=2,actions=ct(table=1)
+table=1,priority=10,udp,ct_state=+trk+rpl,ct_nw_src=10.1.2.1/24,actions=controller
+table=1,priority=10,udp6,ct_state=+trk+rpl,ct_ipv6_dst=2001:db8::1/64,actions=controller
+table=1,priority=10,udp,ct_state=+trk+rpl,ct_tp_src=3/0x1,actions=controller
+table=1,priority=1,action=drop
+])
+
+AT_CHECK([ovs-ofctl add-flows br0 flows.txt])
+
+AT_CAPTURE_FILE([ofctl_monitor.log])
+AT_CHECK([ovs-ofctl monitor br0 65534 invalid_ttl -P nxt_packet_in --detach --no-chdir --pidfile 2> ofctl_monitor.log])
+
+dnl Match ct_nw_src=10.1.2.1/24
+AT_CHECK([ovs-appctl netdev-dummy/receive p1 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x0800),ipv4(src=10.1.2.100,dst=10.1.2.200,proto=17,tos=0,ttl=64,frag=no),udp(src=6,dst=6)'])
+AT_CHECK([ovs-appctl netdev-dummy/receive p2 'in_port(2),eth(src=50:54:00:00:00:0a,dst=50:54:00:00:00:09),eth_type(0x0800),ipv4(src=10.1.2.200,dst=10.1.2.100,proto=17,tos=0,ttl=64,frag=no),udp(src=6,dst=6)'])
+
+dnl Match ct_ipv6_dst=2001:db8::1/64
+AT_CHECK([ovs-appctl netdev-dummy/receive p1 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x86dd),ipv6(src=2001:db8::1,dst=2001:db8::2,label=0,proto=17,tclass=0x70,hlimit=128,frag=no),udp(src=1,dst=2)'])
+AT_CHECK([ovs-appctl netdev-dummy/receive p2 'in_port(2),eth(src=50:54:00:00:00:0a,dst=50:54:00:00:00:09),eth_type(0x86dd),ipv6(src=2001:db8::2,dst=2001:db8::1,label=0,proto=17,tclass=0x70,hlimit=128,frag=no),udp(src=2,dst=1)'])
+
+dnl Match ct_tp_src=3/0x1
+AT_CHECK([ovs-appctl netdev-dummy/receive p1 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x0800),ipv4(src=10.1.1.1,dst=10.1.1.2,proto=17,tos=0,ttl=64,frag=no),udp(src=1,dst=2)'])
+AT_CHECK([ovs-appctl netdev-dummy/receive p2 'in_port(2),eth(src=50:54:00:00:00:0a,dst=50:54:00:00:00:09),eth_type(0x0800),ipv4(src=10.1.1.2,dst=10.1.1.1,proto=17,tos=0,ttl=64,frag=no),udp(src=2,dst=1)'])
+
+OVS_WAIT_UNTIL([test `wc -l < ofctl_monitor.log` -ge 6])
+OVS_WAIT_UNTIL([ovs-appctl -t ovs-ofctl exit])
+
+dnl Check this output.
+AT_CHECK([cat ofctl_monitor.log], [0], [dnl
+NXT_PACKET_IN (xid=0x0): table_id=1 cookie=0x0 total_len=106 ct_state=est|rpl|trk,ct_nw_src=10.1.2.100,ct_nw_dst=10.1.2.200,ct_nw_proto=17,ct_tp_src=6,ct_tp_dst=6,ip,in_port=2 (via action) data_len=106 (unbuffered)
+udp,vlan_tci=0x0000,dl_src=50:54:00:00:00:0a,dl_dst=50:54:00:00:00:09,nw_src=10.1.2.200,nw_dst=10.1.2.100,nw_tos=0,nw_ecn=0,nw_ttl=64,tp_src=6,tp_dst=6 udp_csum:221
+dnl
+NXT_PACKET_IN (xid=0x0): table_id=1 cookie=0x0 total_len=126 ct_state=est|rpl|trk,ct_ipv6_src=2001:db8::1,ct_ipv6_dst=2001:db8::2,ct_nw_proto=17,ct_tp_src=1,ct_tp_dst=2,ipv6,in_port=2 (via action) data_len=126 (unbuffered)
+udp6,vlan_tci=0x0000,dl_src=50:54:00:00:00:0a,dl_dst=50:54:00:00:00:09,ipv6_src=2001:db8::2,ipv6_dst=2001:db8::1,ipv6_label=0x00000,nw_tos=112,nw_ecn=0,nw_ttl=128,tp_src=2,tp_dst=1 udp_csum:bfe2
+dnl
+NXT_PACKET_IN (xid=0x0): table_id=1 cookie=0x0 total_len=106 ct_state=est|rpl|trk,ct_nw_src=10.1.1.1,ct_nw_dst=10.1.1.2,ct_nw_proto=17,ct_tp_src=1,ct_tp_dst=2,ip,in_port=2 (via action) data_len=106 (unbuffered)
+udp,vlan_tci=0x0000,dl_src=50:54:00:00:00:0a,dl_dst=50:54:00:00:00:09,nw_src=10.1.1.2,nw_dst=10.1.1.1,nw_tos=0,nw_ecn=0,nw_ttl=64,tp_src=2,tp_dst=1 udp_csum:553
+])
+
+OVS_VSWITCHD_STOP
+AT_CLEANUP
+
AT_SETUP([ofproto-dpif - conntrack - ofproto/trace])
OVS_VSWITCHD_START
@@ -10503,3 +10600,166 @@ AT_CHECK([grep flow_del ovs-vswitchd.log], [1])
OVS_VSWITCHD_STOP
AT_CLEANUP
+
+AT_SETUP([ofproto-dpif - check_pkt_larger action])
+OVS_VSWITCHD_START
+add_of_ports br0 1 2 3 4
+
+AT_DATA([flows.txt], [dnl
+table=0,in_port=1 actions=check_pkt_larger(200)->NXM_NX_REG0[[0]],resubmit(,1)
+table=1,in_port=1,reg0=0x1/0x1 actions=output:2,resubmit(,2)
+table=1,in_port=1,actions=output:3,resubmit(,2)
+table=2,in_port=1,actions=mod_dl_dst:82:82:82:82:82:82,output:4
+])
+
+AT_CHECK([ovs-ofctl --protocols=OpenFlow10 add-flows br0 flows.txt])
+AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x0800),ipv4(src=10.10.10.2,dst=10.10.10.1,proto=1,tos=1,ttl=128,frag=no),icmp(type=8,code=0)'], [0], [stdout])
+AT_CHECK([tail -1 stdout], [0], [dnl
+Datapath actions: check_pkt_len(size=200,gt(2,set(eth(dst=82:82:82:82:82:82)),4),le(3,set(eth(dst=82:82:82:82:82:82)),4))
+])
+
+dnl Test flow xlate check_pkt_large clone action without using datapath check_pkt_len action.
+AT_CHECK([ovs-appctl dpif/set-dp-features br0 check_pkt_len false], [0], [ignore])
+
+AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x0800),ipv4(src=10.10.10.2,dst=10.10.10.1,proto=1,tos=1,ttl=128,frag=no),icmp(type=8,code=0)'], [0], [stdout])
+AT_CHECK([tail -3 stdout], [0], [dnl
+Datapath actions: 3,set(eth(dst=82:82:82:82:82:82)),4
+This flow is handled by the userspace slow path because it:
+ - Uses action(s) not supported by datapath.
+])
+
+dnl Enable datapath check_pkt_len action
+AT_CHECK([ovs-appctl dpif/set-dp-features br0 check_pkt_len true], [0], [ignore])
+
+ovs-ofctl del-flows br0
+
+AT_DATA([flows.txt], [dnl
+table=0,in_port=1 actions=check_pkt_larger(200)->NXM_NX_REG0[[0]],resubmit(,1)
+table=1,in_port=1,priority=200,reg0=0x1/0x1 actions=output:2
+])
+
+AT_CHECK([ovs-ofctl --protocols=OpenFlow10 add-flows br0 flows.txt])
+AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x0800),ipv4(src=10.10.10.2,dst=10.10.10.1,proto=1,tos=1,ttl=128,frag=no),icmp(type=8,code=0)'], [0], [stdout])
+AT_CHECK([tail -1 stdout], [0], [dnl
+Datapath actions: check_pkt_len(size=200,gt(2),le(drop))
+])
+
+ovs-ofctl del-flows br0
+AT_DATA([flows.txt], [dnl
+table=0,in_port=1 actions=check_pkt_larger(200)->NXM_NX_REG0[[0]]
+])
+
+AT_CHECK([ovs-ofctl --protocols=OpenFlow10 add-flows br0 flows.txt])
+AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x0800),ipv4(src=10.10.10.2,dst=10.10.10.1,proto=1,tos=1,ttl=128,frag=no),icmp(type=8,code=0)'], [0], [stdout])
+AT_CHECK([tail -1 stdout], [0], [dnl
+Datapath actions: check_pkt_len(size=200,gt(drop),le(drop))
+])
+
+ovs-ofctl del-flows br0
+AT_DATA([flows.txt], [dnl
+table=0,in_port=1 actions=check_pkt_larger(200)->NXM_NX_REG0[[0]],resubmit(,1)
+table=1,in_port=1,priority=200,reg0=0x1/0x1,ip actions=clone(set_field:192.168.3.3->ip_src),clone(set_field:192.168.4.4->ip_dst,output:2),clone(mod_dl_src:80:81:81:81:81:81,set_field:192.168.5.5->ip_dst,output:3),output:4
+table=1,in_port=1,priority=0,ip actions=clone(set_field:192.168.3.3->ip_src),clone(set_field:192.168.4.4->ip_dst,output:2),clone(ct(commit),output:3),output:4
+])
+
+AT_CHECK([ovs-ofctl --protocols=OpenFlow10 add-flows br0 flows.txt])
+AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x0800),ipv4(src=10.10.10.2,dst=10.10.10.1,proto=1,tos=1,ttl=128,frag=no),icmp(type=8,code=0)'], [0], [stdout])
+AT_CHECK([tail -1 stdout], [0], [dnl
+Datapath actions: check_pkt_len(size=200,gt(set(ipv4(src=10.10.10.2,dst=192.168.4.4)),2,set(eth(src=80:81:81:81:81:81)),set(ipv4(src=10.10.10.2,dst=192.168.5.5)),3,set(eth(src=50:54:00:00:00:09)),set(ipv4(src=10.10.10.2,dst=10.10.10.1)),4),le(set(ipv4(src=10.10.10.2,dst=192.168.4.4)),2,set(ipv4(src=10.10.10.2,dst=10.10.10.1)),clone(ct(commit),3),4))
+])
+
+AT_DATA([flows.txt], [dnl
+table=0,priority=0 actions=check_pkt_larger(200)->NXM_NX_REG0[[0]],resubmit(,1)
+table=1,in_port=1,priority=200,reg0=0x1/0x1,ip actions=clone(set_field:192.168.3.3->ip_src, resubmit(,0))
+table=1,in_port=1,priority=0,ip actions=clone(set_field:192.168.3.4->ip_src, resubmit(,0))
+])
+
+AT_CHECK([ovs-ofctl --protocols=OpenFlow10 add-flows br0 flows.txt])
+ovs-ofctl dump-flows br0
+
+AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x0800),ipv4(src=10.10.10.2,dst=10.10.10.1,proto=1,tos=1,ttl=128,frag=no),icmp(type=8,code=0)'], [0], [stdout])
+AT_CHECK([tail -3 stdout], [0], [dnl
+Megaflow: recirc_id=0,eth,ip,reg0=0/0x1,in_port=1,nw_src=10.10.10.2,nw_frag=no
+Datapath actions: drop
+Translation failed (Recursion too deep), packet is dropped.
+])
+
+ovs-ofctl del-flows br0
+AT_DATA([flows.txt], [dnl
+table=0,priority=0 actions=check_pkt_larger(200)->NXM_NX_REG0[[0]],resubmit(,1)
+table=1,ip,nw_src=192.168.3.3 actions=output:3
+table=1,ip,nw_src=192.168.3.4 actions=output:4
+table=1,reg0=0x1/0x1,ip actions=clone(set_field:192.168.3.3->ip_src, resubmit(,0))
+table=1,ip actions=clone(set_field:192.168.3.4->ip_src, resubmit(,0))
+])
+
+AT_CHECK([ovs-ofctl --protocols=OpenFlow10 add-flows br0 flows.txt])
+ovs-ofctl dump-flows br0
+
+AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x0800),ipv4(src=10.10.10.2,dst=10.10.10.1,proto=1,tos=1,ttl=128,frag=no),icmp(type=8,code=0)'], [0], [stdout])
+AT_CHECK([tail -1 stdout], [0], [dnl
+Datapath actions: check_pkt_len(size=200,gt(set(ipv4(src=192.168.3.3)),check_pkt_len(size=200,gt(3),le(3))),le(set(ipv4(src=192.168.3.4)),check_pkt_len(size=200,gt(4),le(4))))
+])
+
+ovs-ofctl del-flows br0
+AT_DATA([flows.txt], [dnl
+table=0,in_port=1 actions=check_pkt_larger(200)->NXM_NX_REG0[[0]],resubmit(,1)
+table=1,in_port=1,reg0=0x1/0x1 actions=mod_dl_dst:82:82:82:82:82:82,controller(),resubmit(,2)
+table=1,in_port=1 actions=resubmit(,2)
+table=2,ip,dl_dst=82:82:82:82:82:82 actions=ct(table=3)
+table=2,ip,dl_dst=50:54:00:00:00:0a actions=ct(table=3)
+table=3,ip,reg0=0x1/0x1 actions=output:2
+table=3,ip actions=output:4
+])
+
+AT_CHECK([ovs-ofctl --protocols=OpenFlow10 add-flows br0 flows.txt])
+AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x0800),ipv4(src=10.10.10.2,dst=10.10.10.1,proto=1,tos=1,ttl=128,frag=no),icmp(type=8,code=0)'], [0], [stdout])
+AT_CHECK([cat stdout | grep Datapath -B1], [0], [dnl
+Megaflow: recirc_id=0,eth,ip,in_port=1,dl_dst=50:54:00:00:00:0a,nw_frag=no
+Datapath actions: check_pkt_len(size=200,gt(set(eth(dst=82:82:82:82:82:82)),userspace(pid=0,controller(reason=1,dont_send=1,continuation=0,recirc_id=1,rule_cookie=0,controller_id=0,max_len=65535)),ct,recirc(0x2)),le(ct,recirc(0x3)))
+--
+Megaflow: recirc_id=0x2,eth,ip,in_port=1,nw_frag=no
+Datapath actions: 2
+--
+Megaflow: recirc_id=0x3,eth,ip,in_port=1,nw_frag=no
+Datapath actions: 4
+])
+
+OVS_VSWITCHD_STOP
+AT_CLEANUP
+
+AT_SETUP([ofproto-dpif - check_pkt_larger with continuation and ct])
+OVS_VSWITCHD_START
+add_of_ports --pcap br0 `seq 1 4`
+
+AT_CAPTURE_FILE([ofctl_monitor0.log])
+AT_CHECK([ovs-ofctl monitor br0 resume --detach --no-chdir --pidfile=ovs-ofctl0.pid 2> ofctl_monitor0.log])
+
+AT_DATA([flows.txt], [dnl
+table=0,in_port=1 actions=check_pkt_larger(150)->NXM_NX_REG0[[0]],resubmit(,1)
+table=1,ip,reg0=0x1/0x1 actions=mod_dl_dst:82:82:82:82:82:82,controller(pause),resubmit(,2)
+table=1,ip,reg0=0 actions=mod_dl_dst:83:83:83:83:83:83,controller(pause),resubmit(,2)
+table=2,ip,dl_dst=82:82:82:82:82:82 actions=ct(table=3)
+table=2,ip,dl_dst=83:83:83:83:83:83 actions=ct(table=3)
+table=3,ip,reg0=0x1/0x1 actions=ct(commit),output:2
+table=3,ip actions=ct(commit),output:4
+])
+
+AT_CHECK([ovs-ofctl --protocols=OpenFlow10 add-flows br0 flows.txt])
+
+flow="in_port(1),eth(src=50:54:00:00:00:09,dst=50:54:00:00:00:0a),eth_type(0x0800),ipv4(src=10.10.10.2,dst=10.10.10.1,proto=1,tos=1,ttl=128,frag=no),icmp(type=8,code=0)"
+
+AT_CHECK([ovs-appctl netdev-dummy/receive p1 "$flow"], [0], [stdout])
+
+OVS_WAIT_UNTIL([test 1 = `ovs-ofctl parse-pcap p4-tx.pcap \
+| grep dl_dst=83:83:83:83:83:83 | wc -l`])
+AT_CHECK([test 0 = `ovs-ofctl parse-pcap p2-tx.pcap | wc -l`])
+
+AT_CHECK([ovs-appctl netdev-dummy/receive p1 "$flow" --len 200], [0], [stdout])
+
+OVS_WAIT_UNTIL([test 1 = `ovs-ofctl parse-pcap p2-tx.pcap \
+| grep dl_dst=82:82:82:82:82:82 | wc -l`])
+AT_CHECK([test 1 = `ovs-ofctl parse-pcap p2-tx.pcap | wc -l`])
+
+OVS_VSWITCHD_STOP
+AT_CLEANUP
diff --git a/tests/ovn.at b/tests/ovn.at
index 4b14720f32..291330b3b2 100644
--- a/tests/ovn.at
+++ b/tests/ovn.at
@@ -12090,3 +12090,24 @@ ovn-nbctl list logical_switch_port
ovn-nbctl list logical_router_port
AT_CLEANUP
+
+# Run ovn-nbctl in daemon mode, change to a backup database and verify that
+# an insert operation is not allowed.
+AT_SETUP([ovn -- can't write to a backup database server instance])
+ovn_start
+on_exit 'kill $(cat ovn-nbctl.pid)'
+export OVN_NB_DAEMON=$(ovn-nbctl --pidfile --detach)
+
+AT_CHECK([ovn-nbctl ls-add sw0])
+as ovn-nb
+AT_CHECK([ovs-appctl -t ovsdb-server ovsdb-server/sync-status | grep active | wc -l], [0], [1
+])
+ovs-appctl -t ovsdb-server ovsdb-server/set-active-ovsdb-server tcp:192.0.2.2:6641
+ovs-appctl -t ovsdb-server ovsdb-server/connect-active-ovsdb-server
+AT_CHECK([ovs-appctl -t ovsdb-server ovsdb-server/sync-status | grep -c backup], [0], [1
+])
+AT_CHECK([ovn-nbctl ls-add sw1], [1], [ignore],
+[ovn-nbctl: transaction error: {"details":"insert operation not allowed when database server is in read only mode","error":"not allowed"}
+])
+
+AT_CLEANUP
diff --git a/tests/ovs-ofctl.at b/tests/ovs-ofctl.at
index 6ae3470425..82c89686f0 100644
--- a/tests/ovs-ofctl.at
+++ b/tests/ovs-ofctl.at
@@ -101,6 +101,7 @@ for test_case in \
'mpls,mpls_label=5 NXM,OXM,OpenFlow11' \
'mpls,mpls_tc=1 NXM,OXM,OpenFlow11' \
'mpls,mpls_bos=0 NXM,OXM' \
+ 'mpls,mpls_ttl=5 NXM,OXM' \
'ip,ip_src=1.2.3.4 any' \
'ip,ip_src=192.168.0.0/24 any' \
'ip,ip_src=192.0.168.0/255.0.255.0 NXM,OXM,OpenFlow11' \
@@ -434,6 +435,7 @@ tcp,actions=fin_timeout(idle_timeout=5,hard_timeout=15)
actions=controller(max_len=123,reason=invalid_ttl,id=555)
actions=sample(probability=12345,collector_set_id=23456,obs_domain_id=34567,obs_point_id=45678)
actions=sample(probability=12345,collector_set_id=23456,obs_domain_id=34567,obs_point_id=45678,sampling_port=56789)
+mpls,mpls_label=5,mpls_tc=1,mpls_ttl=1,mpls_bos=0,actions=drop
ip,actions=ct(commit,zone=5)
ip,actions=ct(commit,exec(load(1->NXM_NX_CT_MARK[])))
ip,actions=ct(commit,exec(load(0x1->NXM_NX_CT_LABEL[])))
@@ -490,6 +492,7 @@ NXT_FLOW_MOD: ADD table:255 tcp actions=fin_timeout(idle_timeout=5,hard_timeout=
NXT_FLOW_MOD: ADD table:255 actions=controller(reason=invalid_ttl,max_len=123,id=555)
NXT_FLOW_MOD: ADD table:255 actions=sample(probability=12345,collector_set_id=23456,obs_domain_id=34567,obs_point_id=45678)
NXT_FLOW_MOD: ADD table:255 actions=sample(probability=12345,collector_set_id=23456,obs_domain_id=34567,obs_point_id=45678,sampling_port=56789)
+NXT_FLOW_MOD: ADD table:255 mpls,mpls_label=5,mpls_tc=1,mpls_ttl=1,mpls_bos=0 actions=drop
NXT_FLOW_MOD: ADD table:255 ip actions=ct(commit,zone=5)
NXT_FLOW_MOD: ADD table:255 ip actions=ct(commit,exec(load:0x1->NXM_NX_CT_MARK[]))
NXT_FLOW_MOD: ADD table:255 ip actions=ct(commit,exec(load:0x1->NXM_NX_CT_LABEL[0..63],load:0->NXM_NX_CT_LABEL[64..127]))
diff --git a/tests/ovsdb-client.at b/tests/ovsdb-client.at
index 8d777a0275..5e3b26aea8 100644
--- a/tests/ovsdb-client.at
+++ b/tests/ovsdb-client.at
@@ -12,6 +12,30 @@ AT_CHECK([ovsdb-client get-schema-cksum unix:socket ordinals], [0], [12345678 9
OVSDB_SERVER_SHUTDOWN
AT_CLEANUP
+AT_SETUP([ovsdb-client needs-conversion (no conversion needed)])
+AT_KEYWORDS([ovsdb client file positive])
+ordinal_schema > schema
+touch .db.~lock~
+AT_CHECK([ovsdb-tool create db schema], [0], [], [ignore])
+AT_CHECK([ovsdb-server --detach --no-chdir --pidfile --remote=punix:socket db], [0], [ignore], [ignore])
+AT_CHECK([ovsdb-client needs-conversion unix:socket schema], [0], [no
+])
+OVSDB_SERVER_SHUTDOWN
+AT_CLEANUP
+
+AT_SETUP([ovsdb-client needs-conversion (conversion needed)])
+AT_KEYWORDS([ovsdb client file positive])
+ordinal_schema > schema
+touch .db.~lock~
+AT_CHECK([ovsdb-tool create db schema], [0], [], [ignore])
+AT_CHECK([ovsdb-server --detach --no-chdir --pidfile --remote=punix:socket db], [0], [ignore], [ignore])
+sed 's/5\.1\.3/5.1.4/' < schema > schema2
+AT_CHECK([diff schema schema2], [1], [ignore])
+AT_CHECK([ovsdb-client needs-conversion unix:socket schema2], [0], [yes
+])
+OVSDB_SERVER_SHUTDOWN
+AT_CLEANUP
+
AT_SETUP([ovsdb-client backup and restore])
AT_KEYWORDS([ovsdb client positive])
diff --git a/tests/ovsdb-cluster.at b/tests/ovsdb-cluster.at
index c7f1e344c9..115c9f7978 100644
--- a/tests/ovsdb-cluster.at
+++ b/tests/ovsdb-cluster.at
@@ -152,7 +152,7 @@ ovsdb|WARN|schema: changed 2 columns in 'OVN_Southbound' database from ephemeral
# Use file instead of var because code inside "while" runs in a subshell.
echo 0 > phase
i=0
- (while :; do echo; sleep 1; done) | while read REPLY; do
+ (while :; do echo || exit 0; sleep 1; done) | while read REPLY; do
printf "t=%2d s:" $i
done=0
for j in $(seq 0 $(expr $n1 - 1)); do
diff --git a/tests/ovsdb-idl.at b/tests/ovsdb-idl.at
index 8981b5e2f9..c41723dc61 100644
--- a/tests/ovsdb-idl.at
+++ b/tests/ovsdb-idl.at
@@ -983,6 +983,7 @@ AT_CHECK([sort stdout | uuidfilt], [0],
# Check that ovsdb-idl figured out that table link2 and column l2 are missing.
AT_CHECK([grep ovsdb_idl stderr | sort], [0], [dnl
test-ovsdb|ovsdb_idl|idltest database lacks link2 table (database needs upgrade?)
+test-ovsdb|ovsdb_idl|idltest database lacks simple5 table (database needs upgrade?)
test-ovsdb|ovsdb_idl|idltest database lacks singleton table (database needs upgrade?)
test-ovsdb|ovsdb_idl|link1 table in idltest database lacks l2 column (database needs upgrade?)
])
@@ -1193,6 +1194,7 @@ OVSDB_CHECK_IDL_TRACK([track, simple idl, initially populated],
"where": [],
"row": {"b": true}}]']],
[[000: i=1 r=2 b=true s=mystring u=<0> ia=[1 2 3] ra=[-0.5] ba=[true] sa=[abc def] ua=[<1> <2>] uuid=<3>
+000: inserted row: uuid=<3>
000: updated columns: b ba i ia r ra s sa u ua
001: {"error":null,"result":[{"count":2}]}
002: i=0 r=0 b=true s= u=<4> ia=[] ra=[] ba=[] sa=[] ua=[] uuid=<5>
@@ -1255,6 +1257,7 @@ OVSDB_CHECK_IDL_TRACK([track, simple idl, initially empty, various ops],
[[000: empty
001: {"error":null,"result":[{"uuid":["uuid","<0>"]},{"uuid":["uuid","<1>"]}]}
002: i=1 r=2 b=true s=mystring u=<2> ia=[1 2 3] ra=[-0.5] ba=[true] sa=[abc def] ua=[<3> <4>] uuid=<0>
+002: inserted row: uuid=<0>
002: updated columns: b ba i ia r ra s sa u ua
003: {"error":null,"result":[{"count":2}]}
004: i=0 r=0 b=true s= u=<5> ia=[] ra=[] ba=[] sa=[] ua=[] uuid=<1>
@@ -1266,6 +1269,7 @@ OVSDB_CHECK_IDL_TRACK([track, simple idl, initially empty, various ops],
006: updated columns: r
007: {"error":null,"result":[{"uuid":["uuid","<6>"]}]}
008: i=-1 r=125 b=false s= u=<5> ia=[1] ra=[1.5] ba=[false] sa=[] ua=[] uuid=<6>
+008: inserted row: uuid=<6>
008: updated columns: ba i ia r ra
009: {"error":null,"result":[{"count":2}]}
010: i=-1 r=125 b=false s=newstring u=<5> ia=[1] ra=[1.5] ba=[false] sa=[] ua=[] uuid=<6>
@@ -1273,7 +1277,7 @@ OVSDB_CHECK_IDL_TRACK([track, simple idl, initially empty, various ops],
010: updated columns: s
010: updated columns: s
011: {"error":null,"result":[{"count":1}]}
-012: ##deleted## uuid=<1>
+012: deleted row: uuid=<1>
013: reconnect
014: i=-1 r=125 b=false s=newstring u=<5> ia=[1] ra=[1.5] ba=[false] sa=[] ua=[] uuid=<6>
014: i=1 r=123.5 b=true s=mystring u=<2> ia=[1 2 3] ra=[-0.5] ba=[true] sa=[abc def] ua=[<3> <4>] uuid=<0>
@@ -1331,6 +1335,18 @@ OVSDB_CHECK_IDL_PY([partial-map idl],
009: done
]])
+OVSDB_CHECK_IDL_PY([partial-map update set refmap idl],
+[['["idltest", {"op":"insert", "table":"simple3", "row":{"name":"myString1"}},
+ {"op":"insert", "table":"simple5", "row":{"name":"myString2"}}]']],
+['partialmapmutateirefmap'],
+[[000: name=myString1 uset=[]
+000: name=myString2 irefmap=[]
+001: commit, status=success
+002: name=myString1 uset=[]
+002: name=myString2 irefmap=[(1 <0>)]
+003: done
+]])
+
m4_define([OVSDB_CHECK_IDL_PARTIAL_UPDATE_SET_COLUMN],
[AT_SETUP([$1 - C])
AT_KEYWORDS([ovsdb server idl partial update set column positive $5])
@@ -1414,6 +1430,26 @@ m4_define([OVSDB_CHECK_IDL_NOTIFY],
[OVSDB_CHECK_IDL_NOTIFY_PY($@)
OVSDB_CHECK_IDL_NOTIFY_SSL_PY($@)])
+OVSDB_CHECK_IDL_NOTIFY([simple link idl verify notify],
+ [['track-notify' \
+ '["idltest",
+ {"op": "insert",
+ "table": "link1",
+ "row": {"i": 1, "k": ["named-uuid", "l1row"], "l2": ["set", [["named-uuid", "l2row"]]]},
+ "uuid-name": "l1row"},
+ {"op": "insert",
+ "table": "link2",
+ "uuid-name": "l2row",
+ "row": {"i": 2, "l1": ["set", [["named-uuid", "l1row"]]]}}]']],
+[[000: empty
+001: {"error":null,"result":[{"uuid":["uuid","<0>"]},{"uuid":["uuid","<1>"]}]}
+002: event:create, row={i=1 uuid=<0> l2=[<1>]}, updates=None
+002: event:create, row={i=2 uuid=<1> l1=[<0>]}, updates=None
+002: i=1 k=1 ka=[] l2=2 uuid=<0>
+002: i=2 l1=1 uuid=<1>
+003: done
+]])
+
OVSDB_CHECK_IDL_NOTIFY([simple idl verify notify],
[['track-notify' \
'["idltest",
diff --git a/tests/ovsdb-replication.at b/tests/ovsdb-replication.at
index f81381bdb3..82c4160529 100644
--- a/tests/ovsdb-replication.at
+++ b/tests/ovsdb-replication.at
@@ -19,6 +19,29 @@ replication_schema () {
}
EOF
}
+replication_schema_v2 () {
+ cat <<'EOF'
+ {"name": "mydb",
+ "tables": {
+ "a": {
+ "columns": {
+ "number": {"type": "integer"},
+ "name": {"type": "string"}},
+ "indexes": [["number"]]},
+ "b": {
+ "columns": {
+ "number": {"type": "integer"},
+ "name": {"type": "string"},
+ "foo" : {"type": "string"}},
+ "indexes": [["number"]]},
+ "c": {
+ "columns": {
+ "number": {"type": "integer"},
+ "name": {"type": "string"}},
+ "indexes": [["number"]]}}
+ }
+EOF
+}
]
m4_divert_pop([PREPARE_TESTS])
diff --git a/tests/ovsdb-server.at b/tests/ovsdb-server.at
index 81f03d28b0..b128c4f0fb 100644
--- a/tests/ovsdb-server.at
+++ b/tests/ovsdb-server.at
@@ -1903,3 +1903,112 @@ AT_CHECK([uuidfilt output], [0], [[[{"details":"insert operation not allowed whe
], [ignore])
OVSDB_SERVER_SHUTDOWN
AT_CLEANUP
+
+AT_SETUP([ovsdb-server replication with schema mismatch])
+AT_KEYWORDS([ovsdb server replication])
+replication_schema > subset_schema
+replication_schema_v2 > superset_schema
+
+AT_CHECK([ovsdb-tool create db1 subset_schema], [0], [stdout], [ignore])
+AT_CHECK([ovsdb-tool create db2 superset_schema], [0], [stdout], [ignore])
+
+dnl Add some data to both DBs
+AT_CHECK([ovsdb-tool transact db1 \
+'[["mydb",
+ {"op": "insert",
+ "table": "a",
+ "row": {"number": 9, "name": "nine"}}]]'], [0], [ignore], [ignore])
+
+AT_CHECK([ovsdb-tool transact db2 \
+'[["mydb",
+ {"op": "insert",
+ "table": "a",
+ "row": {"number": 10, "name": "ten"}}]]'], [0], [ignore], [ignore])
+
+dnl Start both 'db1' and 'db2'.
+AT_CHECK([ovsdb-server --detach --no-chdir --log-file=ovsdb-server1.log --pidfile="`pwd`"/pid --remote=punix:db.sock --unixctl="`pwd`"/unixctl db1 --active ], [0], [ignore], [ignore])
+on_exit 'test ! -e pid || kill `cat pid`'
+
+
+AT_CHECK([ovsdb-server --detach --no-chdir --log-file=ovsdb-server2.log --pidfile="`pwd`"/pid2 --remote=punix:db2.sock --unixctl="`pwd`"/unixctl2 db2], [0], [ignore], [ignore])
+on_exit 'test ! -e pid2 || kill `cat pid2`'
+
+OVS_WAIT_UNTIL([ovs-appctl -t "`pwd`"/unixctl ovsdb-server/sync-status |grep active])
+OVS_WAIT_UNTIL([ovs-appctl -t "`pwd`"/unixctl2 ovsdb-server/sync-status |grep active])
+
+AT_CHECK([ovsdb-client dump unix:db.sock a number name], 0, [dnl
+a table
+name number
+---- ------
+nine 9
+])
+
+AT_CHECK([ovsdb-client dump unix:db2.sock a number name], 0, [dnl
+a table
+name number
+---- ------
+ten 10
+])
+
+# Replicate db1 from db2. It should fail since db2 schema
+# doesn't match with db1 and has additional tables/columns.
+AT_CHECK([ovs-appctl -t "`pwd`"/unixctl ovsdb-server/set-active-ovsdb-server unix:db2.sock])
+AT_CHECK([ovs-appctl -t "`pwd`"/unixctl ovsdb-server/connect-active-ovsdb-server])
+
+OVS_WAIT_UNTIL(
+ [test 1 = `cat ovsdb-server1.log | grep "Schema version mismatch, checking if mydb can still be replicated or not" | wc -l]`
+)
+
+OVS_WAIT_UNTIL(
+ [test 1 = `cat ovsdb-server1.log | grep "mydb cannot be replicated" | wc -l]`
+)
+
+OVS_WAIT_UNTIL([ovs-appctl -t "`pwd`"/unixctl ovsdb-server/sync-status |grep active])
+
+# Replicate db2 from db1. This should be successful.
+AT_CHECK([ovs-appctl -t "`pwd`"/unixctl ovsdb-server/disconnect-active-ovsdb-server])
+AT_CHECK([ovs-appctl -t "`pwd`"/unixctl2 ovsdb-server/set-active-ovsdb-server unix:db.sock])
+AT_CHECK([ovs-appctl -t "`pwd`"/unixctl2 ovsdb-server/connect-active-ovsdb-server])
+
+OVS_WAIT_UNTIL(
+ [test 1 = `cat ovsdb-server2.log | grep "Schema version mismatch, checking if mydb can still be replicated or not" | wc -l]`
+)
+
+OVS_WAIT_UNTIL(
+ [test 1 = `cat ovsdb-server2.log | grep "mydb can be replicated" | wc -l]`
+)
+
+OVS_WAIT_UNTIL([ovs-appctl -t "`pwd`"/unixctl2 ovsdb-server/sync-status |grep replicating])
+
+AT_CHECK([ovsdb-client dump unix:db.sock a number name], 0, [dnl
+a table
+name number
+---- ------
+nine 9
+])
+
+AT_CHECK([ovsdb-client dump unix:db2.sock a number name], 0, [dnl
+a table
+name number
+---- ------
+nine 9
+])
+
+AT_CHECK([ovsdb-client transact unix:db.sock \
+'[["mydb",
+ {"op": "insert",
+ "table": "a",
+ "row": {"number": 6, "name": "six"}}]]'], [0], [ignore], [ignore])
+
+OVS_WAIT_UNTIL([test 1 = `ovsdb-client dump unix:db2.sock a number name | grep six | wc -l`])
+
+AT_CHECK([
+ ovsdb-client dump unix:db2.sock a number name], 0, [dnl
+a table
+name number
+---- ------
+nine 9
+six 6
+])
+
+AT_CLEANUP
diff --git a/tests/system-route.at b/tests/system-route.at
new file mode 100644
index 0000000000..1714273e35
--- /dev/null
+++ b/tests/system-route.at
@@ -0,0 +1,28 @@
+AT_BANNER([system-route])
+
+dnl Add an interface, add/del ip address, check that OVS catches route updates.
+AT_SETUP([ovs-route - add/remove system route])
+AT_KEYWORDS([route])
+OVS_TRAFFIC_VSWITCHD_START()
+
+dnl Create tap port.
+AT_CHECK([ip tuntap add name p1-route mode tap])
+AT_CHECK([ip link set p1-route up])
+on_exit 'ip link del p1-route'
+
+dnl Add ip address.
+AT_CHECK([ip addr add 10.0.0.17/24 dev p1-route], [0], [stdout])
+
+dnl Check that OVS catches route updates.
+OVS_WAIT_UNTIL([ovs-appctl ovs/route/show | grep 'p1-route' | sort], [0], [dnl
+Cached: 10.0.0.17/24 dev p1-route SRC 10.0.0.17
+Cached: 10.0.0.17/32 dev p1-route SRC 10.0.0.17 local
+])
+
+dnl Delete ip address.
+AT_CHECK([ip addr del 10.0.0.17/24 dev p1-route], [0], [stdout])
+dnl Check that routes was removed from OVS.
+OVS_WAIT_UNTIL([test `ovs-appctl ovs/route/show | grep -c 'p1-route'` -eq 0 ])
+
+OVS_TRAFFIC_VSWITCHD_STOP
+AT_CLEANUP
diff --git a/tests/system-traffic.at b/tests/system-traffic.at
index e34f7a4fbd..be702ae597 100644
--- a/tests/system-traffic.at
+++ b/tests/system-traffic.at
@@ -340,6 +340,46 @@ NS_CHECK_EXEC([at_ns0], [ping -s 3200 -q -c 3 -i 0.3 -w 2 10.1.1.100 | FORMAT_PI
OVS_TRAFFIC_VSWITCHD_STOP
AT_CLEANUP
+AT_SETUP([datapath - ping over ip6gre L2 tunnel])
+OVS_CHECK_KERNEL_EXCL(3, 10, 4, 15)
+OVS_CHECK_GRE()
+OVS_CHECK_ERSPAN()
+
+OVS_TRAFFIC_VSWITCHD_START()
+ADD_BR([br-underlay])
+
+AT_CHECK([ovs-ofctl add-flow br0 "actions=normal"])
+AT_CHECK([ovs-ofctl add-flow br-underlay "actions=normal"])
+
+ADD_NAMESPACES(at_ns0)
+
+dnl Set up underlay link from host into the namespace using veth pair.
+ADD_VETH(p0, at_ns0, br-underlay, "fc00:100::1/96", [], [], nodad)
+AT_CHECK([ip addr add dev br-underlay "fc00:100::100/96" nodad])
+AT_CHECK([ip link set dev br-underlay up])
+
+dnl Set up tunnel endpoints on OVS outside the namespace and with a native
+dnl linux device inside the namespace.
+ADD_OVS_TUNNEL6([ip6gre], [br0], [at_gre0], [fc00:100::1], [10.1.1.100/24],
+ [options:packet_type=legacy_l2])
+ADD_NATIVE_TUNNEL6([ip6gretap], [ns_gretap0], [at_ns0], [fc00:100::100],
+ [10.1.1.1/24], [local fc00:100::1])
+
+OVS_WAIT_UNTIL([ip netns exec at_ns0 ping6 -c 2 fc00:100::100])
+
+dnl First, check the underlay
+NS_CHECK_EXEC([at_ns0], [ping6 -q -c 3 -i 0.3 -w 2 fc00:100::100 | FORMAT_PING], [0], [dnl
+3 packets transmitted, 3 received, 0% packet loss, time 0ms
+])
+
+dnl Okay, now check the overlay with different packet sizes
+NS_CHECK_EXEC([at_ns0], [ping -q -c 3 -i 0.3 -w 2 10.1.1.100 | FORMAT_PING], [0], [dnl
+3 packets transmitted, 3 received, 0% packet loss, time 0ms
+])
+OVS_TRAFFIC_VSWITCHD_STOP
+AT_CLEANUP
+
+
AT_SETUP([datapath - ping over erspan v1 tunnel])
OVS_CHECK_KERNEL_EXCL(3, 10, 4, 15)
OVS_CHECK_GRE()
diff --git a/tests/system-userspace-packet-type-aware.at b/tests/system-userspace-packet-type-aware.at
index 24a7698ab4..974304758f 100644
--- a/tests/system-userspace-packet-type-aware.at
+++ b/tests/system-userspace-packet-type-aware.at
@@ -129,6 +129,7 @@ AT_CHECK([
ip addr add 10.0.0.1/24 dev br-p1
ip link set br-p1 up
], [0], [stdout])
+OVS_WAIT_UNTIL([ovs-appctl ovs/route/show | grep -q br-p1])
AT_CHECK([
ovs-appctl ovs/route/add 10.0.0.0/24 br-p1
@@ -141,6 +142,7 @@ AT_CHECK([
ip addr add 20.0.0.2/24 dev br-p2
ip link set br-p2 up
], [0], [stdout])
+OVS_WAIT_UNTIL([ovs-appctl ovs/route/show | grep -q br-p2])
AT_CHECK([
ovs-appctl ovs/route/add 20.0.0.0/24 br-p2
@@ -153,6 +155,7 @@ AT_CHECK([
ip addr add 30.0.0.3/24 dev br-p3
ip link set br-p3 up
], [0], [stdout])
+OVS_WAIT_UNTIL([ovs-appctl ovs/route/show | grep -q br-p3])
AT_CHECK([
ovs-appctl ovs/route/add 30.0.0.0/24 br-p3
@@ -252,39 +255,39 @@ AT_CHECK([
### Verify datapath configuration
AT_CHECK([
- ovs-appctl dpif/show | grep -v hit | sed 's/\t/ /g'
+ ovs-appctl dpif/show | grep -v hit
], [0], [dnl
- br-in1:
- br-in1 65534/2: (tap)
- gre12 1020/14: (gre: remote_ip=10.0.0.2)
- gre12_l3 1021/14: (gre: packet_type=legacy_l3, remote_ip=10.0.0.2)
- gre13 1030/14: (gre: remote_ip=10.0.0.3)
- ovs-n1 10/15: (system)
- br-in2:
- br-in2 65534/3: (tap)
- gre21 2010/14: (gre: packet_type=ptap, remote_ip=20.0.0.1)
- gre23 2030/14: (gre: packet_type=ptap, remote_ip=20.0.0.3)
- ovs-n2 20/16: (system)
- br-in3:
- br-in3 65534/4: (tap)
- gre31 3010/14: (gre: remote_ip=30.0.0.1)
- gre32 3020/14: (gre: remote_ip=30.0.0.2)
- gre32_l3 3021/14: (gre: packet_type=legacy_l3, remote_ip=30.0.0.2)
- ovs-n3 30/17: (system)
- br-p1:
- br-p1 65534/5: (tap)
- p1-0 2/8: (system)
- br-p2:
- br-p2 65534/6: (tap)
- p2-0 2/9: (system)
- br-p3:
- br-p3 65534/7: (tap)
- p3-0 2/10: (system)
- br0:
- br0 65534/1: (tap)
- p0-1 10/11: (system)
- p0-2 20/12: (system)
- p0-3 30/13: (system)
+ br-in1:
+ br-in1 65534/2: (tap)
+ gre12 1020/14: (gre: remote_ip=10.0.0.2)
+ gre12_l3 1021/14: (gre: packet_type=legacy_l3, remote_ip=10.0.0.2)
+ gre13 1030/14: (gre: remote_ip=10.0.0.3)
+ ovs-n1 10/15: (system)
+ br-in2:
+ br-in2 65534/3: (tap)
+ gre21 2010/14: (gre: packet_type=ptap, remote_ip=20.0.0.1)
+ gre23 2030/14: (gre: packet_type=ptap, remote_ip=20.0.0.3)
+ ovs-n2 20/16: (system)
+ br-in3:
+ br-in3 65534/4: (tap)
+ gre31 3010/14: (gre: remote_ip=30.0.0.1)
+ gre32 3020/14: (gre: remote_ip=30.0.0.2)
+ gre32_l3 3021/14: (gre: packet_type=legacy_l3, remote_ip=30.0.0.2)
+ ovs-n3 30/17: (system)
+ br-p1:
+ br-p1 65534/5: (tap)
+ p1-0 2/8: (system)
+ br-p2:
+ br-p2 65534/6: (tap)
+ p2-0 2/9: (system)
+ br-p3:
+ br-p3 65534/7: (tap)
+ p3-0 2/10: (system)
+ br0:
+ br0 65534/1: (tap)
+ p0-1 10/11: (system)
+ p0-2 20/12: (system)
+ p0-3 30/13: (system)
])
### Test L3 forwarding flows
diff --git a/tests/system-userspace-testsuite.at b/tests/system-userspace-testsuite.at
index c0aaa606d0..4815d478ec 100644
--- a/tests/system-userspace-testsuite.at
+++ b/tests/system-userspace-testsuite.at
@@ -27,3 +27,4 @@ m4_include([tests/system-layer3-tunnels.at])
m4_include([tests/system-ovn.at])
m4_include([tests/system-interface.at])
m4_include([tests/system-userspace-packet-type-aware.at])
+m4_include([tests/system-route.at])
diff --git a/tests/test-classifier.c b/tests/test-classifier.c
index 6d53d016de..2d98fad485 100644
--- a/tests/test-classifier.c
+++ b/tests/test-classifier.c
@@ -512,8 +512,9 @@ verify_tries(struct classifier *cls)
int i;
for (i = 0; i < cls->n_tries; i++) {
- n_rules += trie_verify(&cls->tries[i].root, 0,
- cls->tries[i].field->n_bits);
+ const struct mf_field * cls_field
+ = ovsrcu_get(struct mf_field *, &cls->tries[i].field);
+ n_rules += trie_verify(&cls->tries[i].root, 0, cls_field->n_bits);
}
assert(n_rules <= cls->n_rules);
}
diff --git a/tests/test-ovsdb.c b/tests/test-ovsdb.c
index 187eb28671..c49f084b5f 100644
--- a/tests/test-ovsdb.c
+++ b/tests/test-ovsdb.c
@@ -2030,7 +2030,7 @@ print_idl(struct ovsdb_idl *idl, int step)
}
static void
-print_idl_track(struct ovsdb_idl *idl, int step, unsigned int seqno)
+print_idl_track(struct ovsdb_idl *idl, int step)
{
const struct idltest_simple *s;
const struct idltest_link1 *l1;
@@ -2038,26 +2038,42 @@ print_idl_track(struct ovsdb_idl *idl, int step, unsigned int seqno)
int n = 0;
IDLTEST_SIMPLE_FOR_EACH_TRACKED (s, idl) {
- if (idltest_simple_row_get_seqno(s, OVSDB_IDL_CHANGE_DELETE) >= seqno) {
- printf("%03d: ##deleted## uuid="UUID_FMT"\n", step, UUID_ARGS(&s->header_.uuid));
+ if (idltest_simple_is_deleted(s)) {
+ printf("%03d: deleted row: uuid="UUID_FMT"\n", step,
+ UUID_ARGS(&s->header_.uuid));
} else {
print_idl_row_simple(s, step);
+ if (idltest_simple_is_new(s)) {
+ printf("%03d: inserted row: uuid="UUID_FMT"\n", step,
+ UUID_ARGS(&s->header_.uuid));
+ }
}
n++;
}
IDLTEST_LINK1_FOR_EACH_TRACKED (l1, idl) {
- if (idltest_simple_row_get_seqno(s, OVSDB_IDL_CHANGE_DELETE) >= seqno) {
- printf("%03d: ##deleted## uuid="UUID_FMT"\n", step, UUID_ARGS(&s->header_.uuid));
+ if (idltest_link1_is_deleted(l1)) {
+ printf("%03d: deleted row: uuid="UUID_FMT"\n", step,
+ UUID_ARGS(&l1->header_.uuid));
} else {
print_idl_row_link1(l1, step);
+ if (idltest_link1_is_new(l1)) {
+ printf("%03d: inserted row: uuid="UUID_FMT"\n", step,
+ UUID_ARGS(&l1->header_.uuid));
+ }
}
n++;
}
IDLTEST_LINK2_FOR_EACH_TRACKED (l2, idl) {
- if (idltest_simple_row_get_seqno(s, OVSDB_IDL_CHANGE_DELETE) >= seqno) {
- printf("%03d: ##deleted## uuid="UUID_FMT"\n", step, UUID_ARGS(&s->header_.uuid));
+ if (idltest_link2_is_deleted(l2)) {
+ printf("%03d: deleted row: uuid="UUID_FMT"\n", step,
+ UUID_ARGS(&l2->header_.uuid));
} else {
print_idl_row_link2(l2, step);
+ if (idltest_link2_is_new(l2)) {
+ printf("%03d: inserted row: uuid="UUID_FMT"\n", step,
+ UUID_ARGS(&l2->header_.uuid));
+ }
+
}
n++;
}
@@ -2464,7 +2480,7 @@ do_idl(struct ovs_cmdl_context *ctx)
/* Print update. */
if (track) {
- print_idl_track(idl, step++, ovsdb_idl_get_seqno(idl));
+ print_idl_track(idl, step++);
ovsdb_idl_track_clear(idl);
} else {
print_idl(idl, step++);
diff --git a/tests/test-ovsdb.py b/tests/test-ovsdb.py
index 1d7c023da2..4e6cfb6eb5 100644
--- a/tests/test-ovsdb.py
+++ b/tests/test-ovsdb.py
@@ -30,6 +30,7 @@ import ovs.util
import ovs.vlog
from ovs.db import data
from ovs.db import error
+from ovs.db.idl import _row_to_uuid as row_to_uuid
from ovs.fatal_signal import signal_alarm
import six
@@ -163,7 +164,10 @@ def get_simple_printable_row_string(row, columns):
is ovs.db.data.Atom):
value = getattr(row, column)
if isinstance(value, dict):
- value = sorted(value.items())
+ value = sorted((row_to_uuid(k), row_to_uuid(v))
+ for k, v in value.items())
+ if isinstance(value, (list, tuple)):
+ value = sorted((row_to_uuid(v) for v in value))
s += "%s=%s " % (column, value)
s = s.strip()
s = re.sub('""|,|u?\'', "", s)
@@ -174,9 +178,10 @@ def get_simple_printable_row_string(row, columns):
return s
-def get_simple_table_printable_row(row):
+def get_simple_table_printable_row(row, *additional_columns):
simple_columns = ["i", "r", "b", "s", "u", "ia",
"ra", "ba", "sa", "ua", "uuid"]
+ simple_columns.extend(additional_columns)
return get_simple_printable_row_string(row, simple_columns)
@@ -216,6 +221,14 @@ def print_idl(idl, step):
print(s)
n += 1
+ if "simple5" in idl.tables:
+ simple5 = idl.tables["simple5"].rows
+ for row in simple5.values():
+ s = "%03d: " % step
+ s += get_simple_printable_row_string(row, ["name", "irefmap"])
+ print(s)
+ n += 1
+
if "link1" in idl.tables:
l1 = idl.tables["link1"].rows
for row in six.itervalues(l1):
@@ -307,6 +320,11 @@ def idltest_find_simple3(idl, i):
return next(idl.index_equal("simple3", "simple3_by_name", i), None)
+def idltest_find(idl, table, col, match):
+ return next((r for r in idl.tables[table].rows.values() if
+ getattr(r, col) == match), None)
+
+
def idl_set(idl, commands, step):
txn = ovs.db.idl.Transaction(idl)
increment = False
@@ -531,6 +549,12 @@ def idl_set(idl, commands, step):
setattr(new_row3, 'name', 'String3')
new_row3.addvalue('uset', new_row41.uuid)
assert len(getattr(new_row3, 'uset', [])) == 1
+ elif name == 'partialmapmutateirefmap':
+ row3 = idltest_find_simple3(idl, "myString1")
+ row5 = idltest_find(idl, "simple5", "name", "myString2")
+ row5.setkey('irefmap', 1, row3.uuid)
+ maplen = len(row5.irefmap)
+ assert maplen == 1, "expected 1, got %d" % maplen
else:
sys.stderr.write("unknown command %s\n" % name)
sys.exit(1)
@@ -623,7 +647,8 @@ def do_idl(schema_file, remote, *commands):
def mock_notify(event, row, updates=None):
output = "%03d: " % step
output += "event:" + str(event) + ", row={"
- output += get_simple_table_printable_row(row) + "}, updates="
+ output += get_simple_table_printable_row(row,
+ 'l2', 'l1') + "}, updates="
if updates is None:
output += "None"
else:
diff --git a/tests/test-sha1.c b/tests/test-sha1.c
index b7279db6aa..cc80888a7d 100644
--- a/tests/test-sha1.c
+++ b/tests/test-sha1.c
@@ -137,6 +137,42 @@ test_big_vector(void)
free(vec.data);
}
+static void
+test_huge_vector(void)
+{
+ enum { SIZE = 1000000000 };
+ struct test_vector vec = {
+ NULL, SIZE,
+ /* Computed by the sha1sum utility for a file with 10^9 symbols 'a'. */
+ { 0xD0, 0xF3, 0xE4, 0xF2, 0xF3, 0x1C, 0x66, 0x5A, 0xBB, 0xD8,
+ 0xF5, 0x18, 0xE8, 0x48, 0xD5, 0xCB, 0x80, 0xCA, 0x78, 0xF7 }
+ };
+ int chunk = random_range(SIZE / 10000);
+ uint8_t md[SHA1_DIGEST_SIZE];
+ struct sha1_ctx sha1;
+ size_t i, sz;
+
+ /* It's not user-friendly to allocate 1GB of memory for a unit test,
+ * so we're allocating only a small chunk and re-using it. */
+ vec.data = xmalloc(chunk);
+ for (i = 0; i < chunk; i++) {
+ vec.data[i] = 'a';
+ }
+
+ sha1_init(&sha1);
+ for (sz = 0; sz < SIZE; sz += chunk) {
+ int n = sz + chunk < SIZE ? chunk : SIZE - sz;
+
+ sha1_update(&sha1, vec.data, n);
+ }
+ sha1_final(&sha1, md);
+ ovs_assert(!memcmp(md, vec.output, SHA1_DIGEST_SIZE));
+
+ free(vec.data);
+ putchar('.');
+ fflush(stdout);
+}
+
static void
test_shar1_main(int argc OVS_UNUSED, char *argv[] OVS_UNUSED)
{
@@ -147,6 +183,7 @@ test_shar1_main(int argc OVS_UNUSED, char *argv[] OVS_UNUSED)
}
test_big_vector();
+ test_huge_vector();
putchar('\n');
}
diff --git a/tests/testsuite.at b/tests/testsuite.at
index b840dbfa70..922ba48fdf 100644
--- a/tests/testsuite.at
+++ b/tests/testsuite.at
@@ -82,3 +82,4 @@ m4_include([tests/ovn-controller-vtep.at])
m4_include([tests/mcast-snooping.at])
m4_include([tests/packet-type-aware.at])
m4_include([tests/nsh.at])
+m4_include([tests/drop-stats.at])
diff --git a/tests/tunnel-push-pop-ipv6.at b/tests/tunnel-push-pop-ipv6.at
index cbdd5a32f7..59723e63b8 100644
--- a/tests/tunnel-push-pop-ipv6.at
+++ b/tests/tunnel-push-pop-ipv6.at
@@ -1,5 +1,74 @@
AT_BANNER([tunnel_push_pop_ipv6])
+AT_SETUP([tunnel_push_pop_ipv6 - ip6gre])
+
+OVS_VSWITCHD_START([add-port br0 p0 -- set Interface p0 type=dummy ofport_request=1 other-config:hwaddr=aa:55:aa:55:00:00])
+AT_CHECK([ovs-vsctl add-br int-br -- set bridge int-br datapath_type=dummy], [0])
+AT_CHECK([ovs-vsctl add-port int-br t2 -- set Interface t2 type=ip6gre \
+ options:remote_ip=2001:cafe::92 ofport_request=2\
+ options:packet_type=legacy_l2
+ ], [0])
+
+AT_CHECK([ovs-appctl dpif/show], [0], [dnl
+dummy@ovs-dummy: hit:0 missed:0
+ br0:
+ br0 65534/100: (dummy-internal)
+ p0 1/1: (dummy)
+ int-br:
+ int-br 65534/2: (dummy-internal)
+ t2 2/6: (ip6gre: remote_ip=2001:cafe::92)
+])
+
+dnl First setup dummy interface IP address, then add the route
+dnl so that tnl-port table can get valid IP address for the device.
+AT_CHECK([ovs-appctl netdev-dummy/ip6addr br0 2001:cafe::88/24], [0], [OK
+])
+AT_CHECK([ovs-appctl netdev-dummy/ip4addr br0 1.1.2.88/24], [0], [OK
+])
+AT_CHECK([ovs-appctl ovs/route/add 2001:cafe::92/24 br0], [0], [OK
+])
+
+AT_CHECK([ovs-ofctl add-flow br0 action=normal])
+
+dnl Check Neighbour discovery.
+AT_CHECK([ovs-vsctl -- set Interface p0 options:pcap=p0.pcap])
+
+AT_CHECK([ovs-appctl netdev-dummy/receive int-br 'in_port(2),eth(src=aa:55:aa:55:00:00,dst=f8:bc:12:ff:ff:ff),eth_type(0x0800),ipv4(src=1.1.3.92,dst=1.1.3.88,proto=1,tos=0,ttl=64,frag=no),icmp(type=0,code=0)'])
+AT_CHECK([ovs-pcap p0.pcap > p0.pcap.txt 2>&1])
+
+AT_CHECK([cat p0.pcap.txt | grep 92aa55aa55000086dd6000000000203aff2001cafe | uniq], [0], [dnl
+3333ff000092aa55aa55000086dd6000000000203aff2001cafe000000000000000000000088ff0200000000000000000001ff00009287004d48000000002001cafe0000000000000000000000920101aa55aa550000
+])
+
+dnl
+AT_CHECK([ovs-appctl netdev-dummy/receive p0 'in_port(1),eth(src=f8:bc:12:44:34:b6,dst=aa:55:aa:55:00:00),eth_type(0x86dd),ipv6(src=2001:cafe::92,dst=2001:cafe::88,label=0,proto=58,tclass=0,hlimit=255,frag=no),icmpv6(type=136,code=0),nd(target=2001:cafe::92,sll=00:00:00:00:00:00,tll=f8:bc:12:44:34:b6)'])
+
+AT_CHECK([ovs-appctl tnl/arp/show | tail -n+3 | sort], [0], [dnl
+2001:cafe::92 f8:bc:12:44:34:b6 br0
+])
+
+AT_CHECK([ovs-appctl tnl/ports/show |sort], [0], [dnl
+Listening ports:
+ip6gre_sys (6) ref_cnt=1
+])
+
+dnl Check IPv6 GRE tunnel pop
+AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'in_port(1),eth(src=f8:bc:12:44:34:b6,dst=aa:55:aa:55:00:00),eth_type(0x86dd),ipv6(src=2001:cafe::92,dst=2001:cafe::88,label=0,proto=47,tclass=0x0,hlimit=64)'], [0], [stdout])
+AT_CHECK([tail -1 stdout], [0],
+ [Datapath actions: tnl_pop(6)
+])
+
+dnl Check IPv6 GRE tunnel push
+AT_CHECK([ovs-ofctl add-flow int-br action=2])
+AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'in_port(2),eth(src=f8:bc:12:44:34:b6,dst=aa:55:aa:55:00:01),eth_type(0x0800),ipv4(src=1.1.3.88,dst=1.1.3.112,proto=47,tos=0,ttl=64,frag=no)'], [0], [stdout])
+
+AT_CHECK([tail -1 stdout], [0],
+ [Datapath actions: clone(tnl_push(tnl_port(6),header(size=58,type=109,eth(dst=f8:bc:12:44:34:b6,src=aa:55:aa:55:00:00,dl_type=0x86dd),ipv6(src=2001:cafe::88,dst=2001:cafe::92,label=0,proto=47,tclass=0x0,hlimit=64),gre((flags=0x0,proto=0x6558))),out_port(100)),1)
+])
+
+OVS_VSWITCHD_STOP
+AT_CLEANUP
+
AT_SETUP([tunnel_push_pop_ipv6 - ip6erspan])
OVS_VSWITCHD_START([add-port br0 p0 -- set Interface p0 type=dummy ofport_request=1 other-config:hwaddr=aa:55:aa:55:00:00])
diff --git a/tests/tunnel-push-pop.at b/tests/tunnel-push-pop.at
index f7172433ee..6581c5ea09 100644
--- a/tests/tunnel-push-pop.at
+++ b/tests/tunnel-push-pop.at
@@ -447,6 +447,27 @@ AT_CHECK([ovs-ofctl dump-ports int-br | grep 'port 7'], [0], [dnl
port 7: rx pkts=3, bytes=252, drop=?, errs=?, frame=?, over=?, crc=?
])
+AT_CHECK([ovs-appctl netdev-dummy/receive p0 'aa55aa550000001b213cab6408004500007079464000402fba600101025c0101025820000800000001c845000054ba200000400184861e0000011e00000200004227e75400030af3195500000000f265010000000000101112131415161718191a1b1c1d1e1f202122232425262728292a2b2c2d2e2f3031323334353637'])
+
+ovs-appctl time/warp 5000
+
+AT_CHECK([
+ovs-appctl coverage/show | grep datapath_drop_tunnel_pop_error | awk '{ print $6 } END { if (!NR) print "0" }'
+], [0], [dnl
+1
+])
+
+AT_CHECK([ovs-appctl netdev-dummy/receive p0 'aa55aa550000001b213cab6408004503007079464000402fba600101025c0101025820000800000001c845000054ba200000400184861e0000011e00000200004227e75400030af3195500000000f265010000000000101112131415161718191a1b1c1d1e1f202122232425262728292a2b2c2d2e2f3031323334353637'])
+
+ovs-appctl time/warp 5000
+
+AT_CHECK([
+ovs-appctl coverage/show | grep drop_action_congestion | awk '{ print $6 } END { if (!NR) print "0" }'
+], [0], [dnl
+1
+])
+
+
dnl Check GREL3 only accepts non-fragmented packets?
AT_CHECK([ovs-appctl netdev-dummy/receive p0 'aa55aa550000001b213cab6408004500007e79464000402fba550101025c0101025820000800000001c8fe71d883724fbeb6f4e1494a080045000054ba200000400184861e0000011e00000200004227e75400030af3195500000000f265010000000000101112131415161718191a1b1c1d1e1f202122232425262728292a2b2c2d2e2f3031323334353637'])
@@ -455,7 +476,7 @@ ovs-appctl time/warp 1000
AT_CHECK([ovs-ofctl dump-ports int-br | grep 'port [[37]]' | sort], [0], [dnl
port 3: rx pkts=3, bytes=294, drop=?, errs=?, frame=?, over=?, crc=?
- port 7: rx pkts=4, bytes=350, drop=?, errs=?, frame=?, over=?, crc=?
+ port 7: rx pkts=5, bytes=434, drop=?, errs=?, frame=?, over=?, crc=?
])
dnl Check decapsulation of Geneve packet with options
@@ -478,7 +499,7 @@ AT_CHECK([ovs-ofctl dump-ports int-br | grep 'port 5'], [0], [dnl
port 5: rx pkts=1, bytes=98, drop=?, errs=?, frame=?, over=?, crc=?
])
AT_CHECK([ovs-appctl dpif/dump-flows int-br | grep 'in_port(6081)'], [0], [dnl
-tunnel(tun_id=0x7b,src=1.1.2.92,dst=1.1.2.88,geneve({class=0xffff,type=0x80,len=4,0xa/0xf}{class=0xffff,type=0,len=4}),flags(-df-csum+key)),recirc_id(0),in_port(6081),packet_type(ns=0,id=0),eth_type(0x0800),ipv4(frag=no), packets:0, bytes:0, used:never, actions:userspace(pid=0,controller(reason=1,dont_send=0,continuation=0,recirc_id=3,rule_cookie=0,controller_id=0,max_len=65535))
+tunnel(tun_id=0x7b,src=1.1.2.92,dst=1.1.2.88,geneve({class=0xffff,type=0x80,len=4,0xa/0xf}{class=0xffff,type=0,len=4}),flags(-df-csum+key)),recirc_id(0),in_port(6081),packet_type(ns=0,id=0),eth_type(0x0800),ipv4(frag=no), packets:0, bytes:0, used:never, actions:userspace(pid=0,controller(reason=1,dont_send=0,continuation=0,recirc_id=2,rule_cookie=0,controller_id=0,max_len=65535))
])
ovs-appctl time/warp 10000
@@ -510,7 +531,8 @@ AT_CHECK([ovs-appctl tnl/ports/show |sort], [0], [dnl
Listening ports:
])
-OVS_VSWITCHD_STOP
+OVS_VSWITCHD_STOP(["/dropping tunnel packet marked ECN CE but is not ECN capable/d
+/ip packet has invalid checksum/d"])
AT_CLEANUP
AT_SETUP([tunnel_push_pop - packet_out])
diff --git a/tests/tunnel.at b/tests/tunnel.at
index 417343e2c5..470cfc9b96 100644
--- a/tests/tunnel.at
+++ b/tests/tunnel.at
@@ -102,13 +102,43 @@ Datapath actions: set(ipv4(tos=0x3/0x3)),2
dnl Tunnel CE and encapsulated packet Non-ECT
AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'tunnel(src=1.1.1.1,dst=2.2.2.2,tos=0x3,ttl=64,flags()),in_port(1),eth(src=50:54:00:00:00:05,dst=50:54:00:00:00:07),eth_type(0x0800),ipv4(src=192.168.0.1,dst=192.168.0.2,proto=6,tos=0,ttl=64,frag=no),tcp(src=8,dst=9)'], [0], [stdout])
-AT_CHECK([tail -2 stdout], [0],
- [Megaflow: recirc_id=0,eth,ip,tun_id=0,tun_src=1.1.1.1,tun_dst=2.2.2.2,tun_tos=3,tun_flags=-df-csum-key,in_port=1,nw_ecn=0,nw_frag=no
+AT_CHECK([tail -3 stdout], [0],
+ [Final flow: unchanged
+Megaflow: recirc_id=0,eth,ip,tun_id=0,tun_src=1.1.1.1,tun_dst=2.2.2.2,tun_tos=3,tun_flags=-df-csum-key,in_port=1,nw_ecn=0,nw_frag=no
Datapath actions: drop
])
OVS_VSWITCHD_STOP(["/dropping tunnel packet marked ECN CE but is not ECN capable/d"])
AT_CLEANUP
+AT_SETUP([tunnel - too long nested attributes])
+OVS_VSWITCHD_START([add-port br0 p1 \
+ -- set Interface p1 type=gre options:remote_ip=1.1.1.1 ofport_request=1 \
+ -- add-port br0 p2 -- set Interface p2 type=dummy ofport_request=2])
+
+AT_CHECK([ovs-appctl dpif/show | tail -n +3], [0], [dnl
+ br0 65534/100: (dummy-internal)
+ p1 1/1: (gre: remote_ip=1.1.1.1)
+ p2 2/2: (dummy)
+])
+
+dst_single="dst=1.1.1.1"
+dst_rep=${dst_single}
+dnl Size of one OVS_TUNNEL_KEY_ATTR_IPV4_DST is 4 bytes + NLA_HDRLEN (4 bytes).
+dnl One nested message has room for UINT16_MAX - NLA_HDRLEN (4) bytes, i.e.
+dnl (UINT16_MAX - NLA_HDRLEN) / (4 + NLA_HDRLEN) = 8191.375 of dst addresses.
+for i in `seq 1 8192` ; do
+ dst_rep="${dst_rep},${dst_single}"
+done
+
+AT_CHECK([ovs-appctl dpctl/add-flow "tunnel(${dst_rep})" "2"],
+ [2], [ignore], [dnl
+ovs-vswitchd: parsing flow key (Argument list too long)
+ovs-appctl: ovs-vswitchd: server returned an error
+])
+
+OVS_VSWITCHD_STOP
+AT_CLEANUP
+
AT_SETUP([tunnel - output])
OVS_VSWITCHD_START([add-port br0 p1 -- set Interface p1 type=gre \
options:remote_ip=1.1.1.1 options:local_ip=2.2.2.2 \
@@ -193,6 +223,17 @@ AT_CHECK([ovs-appctl ofproto/trace ovs-dummy 'in_port(2),eth(src=50:54:00:00:00:
AT_CHECK([tail -1 stdout], [0],
[Datapath actions: set(tunnel(tun_id=0x5,src=2.2.2.2,dst=1.1.1.1,ttl=64,flags(df|key))),set(skb_mark(0x2)),1
])
+
+AT_CHECK([ovs-appctl netdev-dummy/receive p2 'aa55aa550001f8bc124434b6080045000054ba20000040018486010103580101037001004227e75400030af3195500000000f265010000000000101112131415161718191a1b1c1d1e1f202122232425262728292a2b2c2d2e2f3031323334353637'])
+
+ovs-appctl time/warp 5000
+
+AT_CHECK([
+ovs-appctl coverage/show | grep datapath_drop_invalid_port | awk '{ print $6 } END { if (!NR) print "0" }'
+], [0], [dnl
+1
+])
+
OVS_VSWITCHD_STOP
AT_CLEANUP
diff --git a/utilities/automake.mk b/utilities/automake.mk
index a5bb27e2b9..d8ae93ab87 100644
--- a/utilities/automake.mk
+++ b/utilities/automake.mk
@@ -150,6 +150,7 @@ endif
FLAKE8_PYFILES += utilities/ovs-pcap.in \
utilities/checkpatch.py utilities/ovs-dev.py \
+ utilities/ovs-check-dead-ifs.in \
utilities/ovs-tcpdump.in \
utilities/ovs-pipegen.py
diff --git a/utilities/ovs-check-dead-ifs.in b/utilities/ovs-check-dead-ifs.in
index ac54f6c9ce..73e4fd9e10 100755
--- a/utilities/ovs-check-dead-ifs.in
+++ b/utilities/ovs-check-dead-ifs.in
@@ -37,7 +37,7 @@ for ifname in os.listdir("/sys/class/net"):
except IOError:
pass
except ValueError:
- print "%s: unexpected format\n" % fn
+ print("%s: unexpected format\n" % fn)
# Get inodes for all packet sockets whose ifindexes don't exist.
invalid_inodes = set()
@@ -95,8 +95,8 @@ for pid in os.listdir("/proc"):
bad_pids.add(pid)
if bad_pids:
- print """
+ print("""
The following processes are listening for packets to arrive on network devices
-that no longer exist. You may want to restart them."""
+that no longer exist. You may want to restart them.""")
sys.stdout.flush()
- os.execvp("ps", ["ps"] + ["%s" % pid for pid in bad_pids])
+ os.execvp("ps", ["ps"] + ["%s" % pspid for pspid in bad_pids])
diff --git a/utilities/ovs-ctl.in b/utilities/ovs-ctl.in
index 9c2a092ea7..8c5cd70327 100644
--- a/utilities/ovs-ctl.in
+++ b/utilities/ovs-ctl.in
@@ -144,6 +144,7 @@ do_start_ovsdb () {
set "$@" --certificate=db:Open_vSwitch,SSL,certificate
set "$@" --bootstrap-ca-cert=db:Open_vSwitch,SSL,ca_cert
[ "$OVS_USER" != "" ] && set "$@" --user "$OVS_USER"
+ [ "$OVSDB_SERVER_OPTIONS" != "" ] && set "$@" $OVSDB_SERVER_OPTIONS
start_daemon "$OVSDB_SERVER_PRIORITY" "$OVSDB_SERVER_WRAPPER" "$@" \
|| return 1
@@ -213,6 +214,7 @@ do_start_forwarding () {
set "$@" --no-self-confinement
fi
[ "$OVS_USER" != "" ] && set "$@" --user "$OVS_USER"
+ [ "$OVS_VSWITCHD_OPTIONS" != "" ] &&set "$@" $OVS_VSWITCHD_OPTIONS
start_daemon "$OVS_VSWITCHD_PRIORITY" "$OVS_VSWITCHD_WRAPPER" "$@" ||
return 1
@@ -326,6 +328,8 @@ set_defaults () {
OVS_VSWITCHD_PRIORITY=-10
OVSDB_SERVER_WRAPPER=
OVS_VSWITCHD_WRAPPER=
+ OVSDB_SERVER_OPTIONS=
+ OVS_VSWITCHD_OPTIONS=
DB_FILE=$dbdir/conf.db
DB_SOCK=$rundir/db.sock
diff --git a/utilities/ovs-dpctl-top.in b/utilities/ovs-dpctl-top.in
index 7f0f1f8c22..fcb178be64 100755
--- a/utilities/ovs-dpctl-top.in
+++ b/utilities/ovs-dpctl-top.in
@@ -479,6 +479,8 @@ def elements_to_dict(elements):
""" Convert line to a hierarchy of dictionaries. """
result = {}
for element in elements:
+ if (element == "eth()"):
+ continue
match = FIELDS_CMPND.search(element)
if (match):
key = match.group(1)
diff --git a/utilities/ovs-tcpundump.in b/utilities/ovs-tcpundump.in
index c298700624..b729276a99 100755
--- a/utilities/ovs-tcpundump.in
+++ b/utilities/ovs-tcpundump.in
@@ -47,6 +47,7 @@ if __name__ == "__main__":
usage()
elif key in ['-V', '--version']:
print("ovs-tcpundump (Open vSwitch) @VERSION@")
+ sys.exit(0)
else:
sys.exit(0)
@@ -56,7 +57,7 @@ if __name__ == "__main__":
sys.exit(1)
packet = ''
- regex = re.compile(r'^\s+0x([0-9a-fA-F]+): ((?: [0-9a-fA-F]{4})+)')
+ regex = re.compile(r'^\s+0x([0-9a-fA-F]+): ((?: [0-9a-fA-F]{2,4})+)')
while True:
line = sys.stdin.readline()
if line == "":
diff --git a/vswitchd/bridge.c b/vswitchd/bridge.c
index 83708ee51c..15118af775 100644
--- a/vswitchd/bridge.c
+++ b/vswitchd/bridge.c
@@ -494,6 +494,7 @@ bridge_init(const char *remote)
ifaces_changed = seq_create();
last_ifaces_changed = seq_read(ifaces_changed);
ifnotifier = if_notifier_create(if_change_cb, NULL);
+ if_notifier_manual_set_cb(if_change_cb);
}
void
@@ -501,6 +502,7 @@ bridge_exit(bool delete_datapath)
{
struct bridge *br, *next_br;
+ if_notifier_manual_set_cb(NULL);
if_notifier_destroy(ifnotifier);
seq_destroy(ifaces_changed);
HMAP_FOR_EACH_SAFE (br, next_br, node, &all_bridges) {
@@ -1802,8 +1804,13 @@ iface_do_create(const struct bridge *br,
*ofp_portp = iface_pick_ofport(iface_cfg);
error = ofproto_port_add(br->ofproto, netdev, ofp_portp);
if (error) {
- VLOG_WARN_BUF(errp, "could not add network device %s to ofproto (%s)",
- iface_cfg->name, ovs_strerror(error));
+ static struct vlog_rate_limit rl = VLOG_RATE_LIMIT_INIT(1, 5);
+
+ *errp = xasprintf("could not add network device %s to ofproto (%s)",
+ iface_cfg->name, ovs_strerror(error));
+ if (!VLOG_DROP_WARN(&rl)) {
+ VLOG_WARN("%s", *errp);
+ }
goto error;
}
diff --git a/vswitchd/vswitch.xml b/vswitchd/vswitch.xml
index 1db4e86946..573fe4e4af 100644
--- a/vswitchd/vswitch.xml
+++ b/vswitchd/vswitch.xml
@@ -2535,10 +2535,16 @@
<dt><code>gre</code></dt>
<dd>
- Generic Routing Encapsulation (GRE) over IPv4/IPv6 tunnel,
+ Generic Routing Encapsulation (GRE) over IPv4 tunnel,
configurable to encapsulate layer 2 or layer 3 traffic.
</dd>
+ <dt><code>ip6gre</code></dt>
+ <dd>
+ Generic Routing Encapsulation (GRE) over IPv6 tunnel,
+ encapsulate layer 2 traffic.
+ </dd>
+
<dt><code>vxlan</code></dt>
<dd>
<p>
@@ -2597,8 +2603,8 @@
<group title="Tunnel Options">
<p>
These options apply to interfaces with <ref column="type"/> of
- <code>geneve</code>, <code>gre</code>, <code>vxlan</code>,
- <code>lisp</code> and <code>stt</code>.
+ <code>geneve</code>, <code>gre</code>, <code>ip6gre</code>,
+ <code>vxlan</code>, <code>lisp</code> and <code>stt</code>.
</p>
<p>
@@ -2895,10 +2901,10 @@
</column>
</group>
- <group title="Tunnel Options: gre, geneve, and vxlan">
+ <group title="Tunnel Options: gre, ip6gre, geneve, and vxlan">
<p>
- <code>gre</code>, <code>geneve</code>, and
- <code>vxlan</code> interfaces support these options.
+ <code>gre</code>, <code>ip6gre</code>, <code>geneve</code>,
+ and <code>vxlan</code> interfaces support these options.
</p>
<column name="options" key="csum" type='{"type": "boolean"}'>
@@ -2912,8 +2918,9 @@
<p>
When using the upstream Linux kernel module, computation of
checksums for <code>geneve</code> and <code>vxlan</code> requires
- Linux kernel version 4.0 or higher. <code>gre</code> supports
- checksums for all versions of Open vSwitch that support GRE.
+ Linux kernel version 4.0 or higher. <code>gre</code> and
+ <code>ip6gre</code> support checksums for all versions of
+ Open vSwitch that support GRE.
The out of tree kernel module distributed as part of OVS
can compute all tunnel checksums on any kernel version that it
is compatible with.
@@ -2925,10 +2932,11 @@
<group title="Tunnel Options: IPsec">
<p>
Setting any of these options enables IPsec support for a given
- tunnel. <code>gre</code>, <code>geneve</code>, <code>vxlan</code>,
- and <code>stt</code> interfaces support these options. See the
- <code>IPsec</code> section in the <ref table="Open_vSwitch"/> table
- for a description of each mode.
+ tunnel. <code>gre</code>, <code>ip6gre</code>,
+ <code>geneve</code>, <code>vxlan</code> and <code>stt</code>
+ interfaces support these options. See the <code>IPsec</code>
+ section in the <ref table="Open_vSwitch"/> table for a description
+ of each mode.
</p>
<column name="options" key="psk" type='{"type": "string"}'>
<p>
@@ -3100,6 +3108,18 @@ ovs-vsctl add-port br0 p0 -- set Interface p0 type=patch options:peer=p1 \
</p>
</column>
+ <column name="options" key="tx-retries-max"
+ type='{"type": "integer", "minInteger": 0, "maxInteger": 32}'>
+ <p>
+ The value specifies the maximum amount of vhost tx retries that can
+ be made while trying to send a batch of packets to an interface.
+ Only supported by dpdkvhostuserclient interfaces.
+ </p>
+ <p>
+ Default value is 8.
+ </p>
+ </column>
+
<column name="options" key="n_rxq_desc"
type='{"type": "integer", "minInteger": 1, "maxInteger": 4096}'>
<p>