wireguard-linux/tools/testing/selftests/drivers/net/hw, branch update-toolchain

selftests: drv-net: rss_ctx: check for all-zero keys

2024-07-29T09:59:08Z

We had a handful of bugs relating to key being either all 0 or just reported incorrectly as all 0. Check for this in the tests. Signed-off-by: Jakub Kicinski Reviewed-by: Petr Machata Signed-off-by: David S. Miller

selftests: drv-net: rss_ctx: test flow rehashing without impacting traffic

2024-07-09T23:31:18Z

Some workloads may want to rehash the flows in response to an imbalance. Most effective way to do that is changing the RSS key. Check that changing the key does not cause link flaps or traffic disruption. Disrupting traffic for key update is not incorrect, but makes the key update unusable for rehashing under load. Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240708213627.226025-6-kuba@kernel.org Signed-off-by: Jakub Kicinski

selftests: drv-net: rss_ctx: check behavior of indirection table resizing

2024-07-09T23:31:18Z

Some devices dynamically increase and decrease the size of the RSS indirection table based on the number of enabled queues. When that happens driver must maintain the balance of entries (preferably duplicating the smaller table). Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240708213627.226025-5-kuba@kernel.org Signed-off-by: Jakub Kicinski

selftests: drv-net: rss_ctx: test queue changes vs user RSS config

2024-07-09T23:31:00Z

By default main RSS table should change to include all queues. When user sets a specific RSS config the driver should preserve it, even when queue count changes. Driver should refuse to deactivate queues used in the user-set RSS config. For additional contexts driver should still refuse to deactivate queues in use. Whether the contexts should get resized like context 0 when queue count increases is a bit unclear. I anticipate most drivers today don't do that. Since main use case for additional contexts is to set the indir table - it doesn't seem worthwhile to care about behavior of the default table too much. Don't test that. Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240708213627.226025-4-kuba@kernel.org Signed-off-by: Jakub Kicinski

selftests: drv-net: rss_ctx: factor out send traffic and check

2024-07-09T23:30:57Z

Wrap up sending traffic and checking in which queues it landed in a helper. The method used for testing is to send a lot of iperf traffic and check which queues received the most packets. Those should be the queues where we expect iperf to land - either because we installed a filter for the port iperf uses, or we didn't and expect it to use context 0. Contexts get disjoint queue sets, but the main context (AKA context 0) may receive some background traffic (noise). Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240708213627.226025-3-kuba@kernel.org Signed-off-by: Jakub Kicinski

selftests: drv-net: rss_ctx: fix cleanup in the basic test

2024-07-09T23:30:57Z

The basic test may fail without resetting the RSS indir table. Use the .exec() method to run cleanup early since we re-test with traffic that returning to default state works. While at it reformat the doc a tiny bit. Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240708213627.226025-2-kuba@kernel.org Signed-off-by: Jakub Kicinski

selftests: drv-net: rss_ctx: allow more noise on default context

2024-07-04T02:13:59Z

As predicted by David running the test on a machine with a single interface is a bit unreliable. We try to send 20k packets with iperf and expect fewer than 10k packets on the default context. The test isn't very quick, iperf will usually send 100k packets by the time we stop it. So we're off by 5x on the number of iperf packets but still expect default context to only get the hardcoded 10k. The intent is to make sure we get noticeably less traffic on the default context. Use half of the resulting iperf traffic instead of the hard coded 10k. Link: https://patch.msgid.link/20240702233728.4183387-1-kuba@kernel.org Signed-off-by: Jakub Kicinski

selftests: drv-net: rss_ctx: convert to defer()

2024-06-29T01:39:39Z

Use just added defer(). Reviewed-by: Petr Machata Link: https://patch.msgid.link/20240627185502.3069139-4-kuba@kernel.org Signed-off-by: Jakub Kicinski

selftests: drv-net: rss_ctx: add tests for RSS configuration and contexts

2024-06-27T02:07:16Z

Add tests focusing on indirection table configuration and creating extra RSS contexts in drivers which support it. $ export NETIF=eth0 REMOTE_... $ ./drivers/net/hw/rss_ctx.py KTAP version 1 1..8 ok 1 rss_ctx.test_rss_key_indir ok 2 rss_ctx.test_rss_context ok 3 rss_ctx.test_rss_context4 # Increasing queue count 44 -> 66 # Failed to create context 32, trying to test what we got ok 4 rss_ctx.test_rss_context32 # SKIP Tested only 31 contexts, wanted 32 ok 5 rss_ctx.test_rss_context_overlap ok 6 rss_ctx.test_rss_context_overlap2 # .. sprays traffic like a headless chicken .. not ok 7 rss_ctx.test_rss_context_out_of_order ok 8 rss_ctx.test_rss_context4_create_with_cfg # Totals: pass:6 fail:1 xfail:0 xpass:0 skip:1 error:0 Note that rss_ctx.test_rss_context_out_of_order fails with the device I tested with, but it seems to be a device / driver bug. Reviewed-by: Petr Machata Reviewed-by: Willem de Bruijn Link: https://patch.msgid.link/20240626012456.2326192-5-kuba@kernel.org Signed-off-by: Jakub Kicinski

selftests: drv-net: add checksum tests

2024-05-09T01:57:55Z

Run tools/testing/selftest/net/csum.c as part of drv-net. This binary covers multiple scenarios, based on arguments given, for both IPv4 and IPv6: - Accept UDP correct checksum - Detect UDP invalid checksum - Accept TCP correct checksum - Detect TCP invalid checksum - Transmit UDP: basic checksum offload - Transmit UDP: zero checksum conversion The test direction is reversed between receive and transmit tests, so that the NIC under test is always the local machine. In total this adds up to 12 testcases, with more to follow. For conciseness, I replaced individual functions with a function factory. Also detect hardware offload feature availability using Ethtool netlink and skip tests when either feature is off. This need may be common for offload feature tests and eventually deserving of a thin wrapper in lib.py. Missing are the PF_PACKET based send tests ('-P'). These use virtio_net_hdr to program hardware checksum offload. Which requires looking up the local MAC address and (harder) the MAC of the next hop. I'll have to give it some though how to do that robustly and where that code would belong. Tested: make -C tools/testing/selftests/ \ TARGETS="drivers/net drivers/net/hw" \ install INSTALL_PATH=/tmp/ksft cd /tmp/ksft sudo NETIF=ens4 REMOTE_TYPE=ssh \ REMOTE_ARGS="root@10.40.0.2" \ LOCAL_V4="10.40.0.1" \ REMOTE_V4="10.40.0.2" \ ./run_kselftest.sh -t drivers/net/hw:csum.py Signed-off-by: Willem de Bruijn Link: https://lore.kernel.org/r/20240507154216.501111-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski