e0c38a4d1f
Pull networking updates from David Miller: 1) New ipset extensions for matching on destination MAC addresses, from Stefano Brivio. 2) Add ipv4 ttl and tos, plus ipv6 flow label and hop limit offloads to nfp driver. From Stefano Brivio. 3) Implement GRO for plain UDP sockets, from Paolo Abeni. 4) Lots of work from Michał Mirosław to eliminate the VLAN_TAG_PRESENT bit so that we could support the entire vlan_tci value. 5) Rework the IPSEC policy lookups to better optimize more usecases, from Florian Westphal. 6) Infrastructure changes eliminating direct manipulation of SKB lists wherever possible, and to always use the appropriate SKB list helpers. This work is still ongoing... 7) Lots of PHY driver and state machine improvements and simplifications, from Heiner Kallweit. 8) Various TSO deferral refinements, from Eric Dumazet. 9) Add ntuple filter support to aquantia driver, from Dmitry Bogdanov. 10) Batch dropping of XDP packets in tuntap, from Jason Wang. 11) Lots of cleanups and improvements to the r8169 driver from Heiner Kallweit, including support for ->xmit_more. This driver has been getting some much needed love since he started working on it. 12) Lots of new forwarding selftests from Petr Machata. 13) Enable VXLAN learning in mlxsw driver, from Ido Schimmel. 14) Packed ring support for virtio, from Tiwei Bie. 15) Add new Aquantia AQtion USB driver, from Dmitry Bezrukov. 16) Add XDP support to dpaa2-eth driver, from Ioana Ciocoi Radulescu. 17) Implement coalescing on TCP backlog queue, from Eric Dumazet. 18) Implement carrier change in tun driver, from Nicolas Dichtel. 19) Support msg_zerocopy in UDP, from Willem de Bruijn. 20) Significantly improve garbage collection of neighbor objects when the table has many PERMANENT entries, from David Ahern. 21) Remove egdev usage from nfp and mlx5, and remove the facility completely from the tree as it no longer has any users. From Oz Shlomo and others. 22) Add a NETDEV_PRE_CHANGEADDR so that drivers can veto the change and therefore abort the operation before the commit phase (which is the NETDEV_CHANGEADDR event). From Petr Machata. 23) Add indirect call wrappers to avoid retpoline overhead, and use them in the GRO code paths. From Paolo Abeni. 24) Add support for netlink FDB get operations, from Roopa Prabhu. 25) Support bloom filter in mlxsw driver, from Nir Dotan. 26) Add SKB extension infrastructure. This consolidates the handling of the auxiliary SKB data used by IPSEC and bridge netfilter, and is designed to support the needs to MPTCP which could be integrated in the future. 27) Lots of XDP TX optimizations in mlx5 from Tariq Toukan. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1845 commits) net: dccp: fix kernel crash on module load drivers/net: appletalk/cops: remove redundant if statement and mask bnx2x: Fix NULL pointer dereference in bnx2x_del_all_vlans() on some hw net/net_namespace: Check the return value of register_pernet_subsys() net/netlink_compat: Fix a missing check of nla_parse_nested ieee802154: lowpan_header_create check must check daddr net/mlx4_core: drop useless LIST_HEAD mlxsw: spectrum: drop useless LIST_HEAD net/mlx5e: drop useless LIST_HEAD iptunnel: Set tun_flags in the iptunnel_metadata_reply from src net/mlx5e: fix semicolon.cocci warnings staging: octeon: fix build failure with XFRM enabled net: Revert recent Spectre-v1 patches. can: af_can: Fix Spectre v1 vulnerability packet: validate address length if non-zero nfc: af_nfc: Fix Spectre v1 vulnerability phonet: af_phonet: Fix Spectre v1 vulnerability net: core: Fix Spectre v1 vulnerability net: minor cleanup in skb_ext_add() net: drop the unused helper skb_ext_get() ...
tdc - Linux Traffic Control (tc) unit testing suite Author: Lucas Bates - lucasb@mojatatu.com tdc is a Python script to load tc unit tests from a separate JSON file and execute them inside a network namespace dedicated to the task. REQUIREMENTS ------------ * Minimum Python version of 3.4. Earlier 3.X versions may work but are not guaranteed. * The kernel must have network namespace support * The kernel must have veth support available, as a veth pair is created prior to running the tests. * The kernel must have the appropriate infrastructure enabled to run all tdc unit tests. See the config file in this directory for minimum required features. As new tests will be added, config options list will be updated. * All tc-related features being tested must be built in or available as modules. To check what is required in current setup run: ./tdc.py -c Note: In the current release, tdc run will abort due to a failure in setup or teardown commands - which includes not being able to run a test simply because the kernel did not support a specific feature. (This will be handled in a future version - the current workaround is to run the tests on specific test categories that your kernel supports) BEFORE YOU RUN -------------- The path to the tc executable that will be most commonly tested can be defined in the tdc_config.py file. Find the 'TC' entry in the NAMES dictionary and define the path. If you need to test a different tc executable on the fly, you can do so by using the -p option when running tdc: ./tdc.py -p /path/to/tc RUNNING TDC ----------- To use tdc, root privileges are required. This is because the commands being tested must be run as root. The code that enforces execution by root uid has been moved into a plugin (see PLUGIN ARCHITECTURE, below). If nsPlugin is linked, all tests are executed inside a network namespace to prevent conflicts within the host. Running tdc without any arguments will run all tests. Refer to the section on command line arguments for more information, or run: ./tdc.py -h tdc will list the test names as they are being run, and print a summary in TAP (Test Anything Protocol) format when they are done. If tests fail, output captured from the failing test will be printed immediately following the failed test in the TAP output. OVERVIEW OF TDC EXECUTION ------------------------- One run of tests is considered a "test suite" (this will be refined in the future). A test suite has one or more test cases in it. A test case has four stages: - setup - execute - verify - teardown The setup and teardown stages can run zero or more commands. The setup stage does some setup if the test needs it. The teardown stage undoes the setup and returns the system to a "neutral" state so any other test can be run next. These two stages require any commands run to return success, but do not otherwise verify the results. The execute and verify stages each run one command. The execute stage tests the return code against one or more acceptable values. The verify stage checks the return code for success, and also compares the stdout with a regular expression. Each of the commands in any stage will run in a shell instance. USER-DEFINED CONSTANTS ---------------------- The tdc_config.py file contains multiple values that can be altered to suit your needs. Any value in the NAMES dictionary can be altered without affecting the tests to be run. These values are used in the tc commands that will be executed as part of the test. More will be added as test cases require. Example: $TC qdisc add dev $DEV1 ingress The NAMES values are used to substitute into the commands in the test cases. COMMAND LINE ARGUMENTS ---------------------- Run tdc.py -h to see the full list of available arguments. usage: tdc.py [-h] [-p PATH] [-D DIR [DIR ...]] [-f FILE [FILE ...]] [-c [CATG [CATG ...]]] [-e ID [ID ...]] [-l] [-s] [-i] [-v] [-N] [-d DEVICE] [-P] [-n] [-V] Linux TC unit tests optional arguments: -h, --help show this help message and exit -p PATH, --path PATH The full path to the tc executable to use -v, --verbose Show the commands that are being run -N, --notap Suppress tap results for command under test -d DEVICE, --device DEVICE Execute the test case in flower category -P, --pause Pause execution just before post-suite stage selection: select which test cases: files plus directories; filtered by categories plus testids -D DIR [DIR ...], --directory DIR [DIR ...] Collect tests from the specified directory(ies) (default [tc-tests]) -f FILE [FILE ...], --file FILE [FILE ...] Run tests from the specified file(s) -c [CATG [CATG ...]], --category [CATG [CATG ...]] Run tests only from the specified category/ies, or if no category/ies is/are specified, list known categories. -e ID [ID ...], --execute ID [ID ...] Execute the specified test cases with specified IDs action: select action to perform on selected test cases -l, --list List all test cases, or those only within the specified category -s, --show Display the selected test cases -i, --id Generate ID numbers for new test cases netns: options for nsPlugin (run commands in net namespace) -n, --namespace Run commands in namespace as specified in tdc_config.py valgrind: options for valgrindPlugin (run command under test under Valgrind) -V, --valgrind Run commands under valgrind PLUGIN ARCHITECTURE ------------------- There is now a plugin architecture, and some of the functionality that was in the tdc.py script has been moved into the plugins. The plugins are in the directory plugin-lib. The are executed from directory plugins. Put symbolic links from plugins to plugin-lib, and name them according to the order you want them to run. Example: bjb@bee:~/work/tc-testing$ ls -l plugins total 4 lrwxrwxrwx 1 bjb bjb 27 Oct 4 16:12 10-rootPlugin.py -> ../plugin-lib/rootPlugin.py lrwxrwxrwx 1 bjb bjb 25 Oct 12 17:55 20-nsPlugin.py -> ../plugin-lib/nsPlugin.py -rwxr-xr-x 1 bjb bjb 0 Sep 29 15:56 __init__.py The plugins are a subclass of TdcPlugin, defined in TdcPlugin.py and must be called "SubPlugin" so tdc can find them. They are distinguished from each other in the python program by their module name. This base class supplies "hooks" to run extra functions. These hooks are as follows: pre- and post-suite pre- and post-case pre- and post-execute stage adjust-command (runs in all stages and receives the stage name) The pre-suite hook receives the number of tests and an array of test ids. This allows you to dump out the list of skipped tests in the event of a failure during setup or teardown stage. The pre-case hook receives the ordinal number and test id of the current test. The adjust-command hook receives the stage id (see list below) and the full command to be executed. This allows for last-minute adjustment of the command. The stages are identified by the following strings: - pre (pre-suite) - setup - command - verify - teardown - post (post-suite) To write a plugin, you need to inherit from TdcPlugin in TdcPlugin.py. To use the plugin, you have to put the implementation file in plugin-lib, and add a symbolic link to it from plugins. It will be detected at run time and invoked at the appropriate times. There are a few examples in the plugin-lib directory: - rootPlugin.py: implements the enforcement of running as root - nsPlugin.py: sets up a network namespace and runs all commands in that namespace - valgrindPlugin.py runs each command in the execute stage under valgrind, and checks for leaks. This plugin will output an extra test for each test in the test file, one is the existing output as to whether the test passed or failed, and the other is a test whether the command leaked memory or not. (This one is a preliminary version, it may not work quite right yet, but the overall template is there and it should only need tweaks.) - buildebpfPlugin.py: builds all programs in $EBPFDIR. ACKNOWLEDGEMENTS ---------------- Thanks to: Jamal Hadi Salim, for providing valuable test cases Keara Leibovitz, who wrote the CLI test driver that I used as a base for the first version of the tc testing suite. This work was presented at Netdev 1.2 Tokyo in October 2016. Samir Hussain, for providing help while I dove into Python for the first time and being a second eye for this code.