selftest build is fairly noisy, it's easy to miss warnings.
It's standard practice to add alternative messages in
the Makefile. I was grepping for existing solutions,
and found that bpf already has the right knobs.
Move them to lib.mk and adopt in net.
Convert the basic rules in lib.mk.
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20240411190534.444918-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Andrew Oates reported that some macOS hosts could repeatedly
send FIN packets even if the remote peer drops them and
send back DUP ACK RWIN 0 packets.
<quoting Andrew>
20:27:16.968254 gif0 In IP macos > victim: Flags [SEW], seq 1950399762, win 65535, options [mss 1460,nop,wscale 6,nop,nop,TS val 501897188 ecr 0,sackOK,eol], length 0
20:27:16.968339 gif0 Out IP victim > macos: Flags [S.E], seq 2995489058, ack 1950399763, win 1448, options [mss 1460,sackOK,TS val 3829877593 ecr 501897188,nop,wscale 0], length 0
20:27:16.968833 gif0 In IP macos > victim: Flags [.], ack 1, win 2058, options [nop,nop,TS val 501897188 ecr 3829877593], length 0
20:27:16.968885 gif0 In IP macos > victim: Flags [P.], seq 1:1449, ack 1, win 2058, options [nop,nop,TS val 501897188 ecr 3829877593], length 1448
20:27:16.968896 gif0 Out IP victim > macos: Flags [.], ack 1449, win 0, options [nop,nop,TS val 3829877593 ecr 501897188], length 0
20:27:19.454593 gif0 In IP macos > victim: Flags [F.], seq 1449, ack 1, win 2058, options [nop,nop,TS val 501899674 ecr 3829877593], length 0
20:27:19.454675 gif0 Out IP victim > macos: Flags [.], ack 1449, win 0, options [nop,nop,TS val 3829880079 ecr 501899674], length 0
20:27:19.455116 gif0 In IP macos > victim: Flags [F.], seq 1449, ack 1, win 2058, options [nop,nop,TS val 501899674 ecr 3829880079], length 0
The retransmits/dup-ACKs then repeat in a tight loop.
</quoting Andrew>
RFC 9293 3.4. Sequence Numbers states :
Note that when the receive window is zero no segments should be
acceptable except ACK segments. Thus, it is be possible for a TCP to
maintain a zero receive window while transmitting data and receiving
ACKs. However, even when the receive window is zero, a TCP must
process the RST and URG fields of all incoming segments.
Even if we could consider a bare FIN.ACK packet to be an ACK in RFC terms,
the retransmits should use exponential backoff.
Accepting the FIN in linux does not add extra memory costs,
because the FIN flag will simply be merged to the tail skb in
the receive queue, and incoming packet is freed.
Reported-by: Andrew Oates <aoates@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Christoph Paasch <cpaasch@apple.com>
Cc: Vidhi Goel <vidhi_goel@apple.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Netfilter tests have been moved to a subdir under selftests/net by
patch series [1]. Fix the path in selftests/Makefile accordingly.
This helps fix the following error:
tools/testing/selftests$ make
...
make[1]: Entering directory 'tools/testing/selftests'
make[1]: *** netfilter: No such file or directory. Stop.
make[1]: Leaving directory 'tools/testing/selftests'
[1] https://lore.kernel.org/all/20240411233624.8129-1-fw@strlen.de/
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Yujie Liu <yujie.liu@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The mediatek-ge PHY driver already disables EEE advertisement on the switch
PHYs but my testing [1] shows that it is somehow enabled afterwards.
Disabling EEE advertisement before the PHY driver initialises keeps it off.
Therefore, remove disabling EEE advertisement here as it's useless.
Link: https://lore.kernel.org/netdev/d286ea27-e911-4dcb-9037-b75f22b437b8@arinc9.com/ [1]
Signed-off-by: Arınç ÜNAL <arinc.unal@arinc9.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit 18ff0bcda6 ("ethtool: add interface to interact with Ethernet
Power Equipment"), the 'pse_control_config' structure was introduced,
housing a single member labeled 'admin_cotrol' responsible for maintaining
the operational state of the PoDL PSE functions.
A noticeable typographical error exists in the naming of this field
('cotrol' should be corrected to 'control'), which this commit aims to
rectify.
Furthermore, with upcoming extensions of this structure to encompass PoE
functionalities, the field is being renamed to 'podl_admin_state' to
distinctly indicate that this state is tailored specifically for PoDL."
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://lore.kernel.org/r/20240414-feature_poe-v8-3-e4bf1e860da5@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit dcf70df204 ("af_unix: Fix up unix_edge.successor for embryo
socket.") added spin_lock(&unix_gc_lock) in accept() path, and it
caused regression in a stress test as reported by kernel test robot.
If the embryo socket is not part of the inflight graph, we need not
hold the lock.
To decide that in O(1) time and avoid the regression in the normal
use case,
1. add a new stat unix_sk(sk)->scm_stat.nr_unix_fds
2. count the number of inflight AF_UNIX sockets in the receive
queue under unix_state_lock()
3. move unix_update_edges() call under unix_state_lock()
4. avoid locking if nr_unix_fds is 0 in unix_update_edges()
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202404101427.92a08551-oliver.sang@intel.com
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240413021928.20946-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Tony Nguyen says:
====================
This series contains updates to ice driver only.
Lukasz removes unnecessary argument from ice_fdir_comp_rules().
Jakub adds support for ethtool 'ether' flow-type rules.
Jake moves setting of VF MSI-X value to initialization function and adds
tracking of VF relative MSI-X index.
* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
ice: store VF relative MSI-X index in q_vector->vf_reg_idx
ice: set vf->num_msix in ice_initialize_vf_entry()
ice: Implement 'flow-type ether' rules
ice: Remove unnecessary argument from ice_fdir_comp_rules()
====================
Link: https://lore.kernel.org/r/20240412210534.916756-1-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Petr Machata says:
====================
selftests: Assortment of fixes
This is a loose follow-up to the Kernel CI patchset posted recently. It
contains various fixes that were supposed to be part of said patchset, but
didn't fit due to its size. The latter 4 patches were written independently
of the CI effort, but again didn't fit in their intended patchsets.
- Patch #1 unifies code of two very similar looking functions, busywait()
and slowwait().
- Patch #2 adds sanity checks around the setting of NETIFS, which carries
list of interfaces to run on.
- Patch #3 changes bail_on_lldpad() to SKIP instead of FAILing.
- Patches #4 to #7 fix issues in selftests.
- Patches #8 to #10 add topology diagrams to several selftests.
This should have been part of the mlxsw leg of NH group stats patches,
but again, it did not fit in due to size.
====================
Link: https://lore.kernel.org/r/cover.1712940759.git.petrm@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This test lacks a topology diagram, making the setup not obvious.
Add one.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
This test lacks a topology diagram, making the setup not obvious.
Add one.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The ethtool dump includes the lanes parameter only when the port is up.
Therefore, the ethtool_lanes.sh test waits for ports to come before testing
the lanes parameter.
In some cases, the test considers the port as up, but the lanes parameter
is not yet dumped although assumed to be, resulting in ethtool_lanes.sh
test failure.
To avoid that, ensure that the lanes parameter is indeed dumped by waiting
for it explicitly, before preforming the test cases.
Signed-off-by: Danielle Ratson <danieller@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The tests use the constant TC_HIT_TIMEOUT when waiting on the counter
values. However it does not include tc_common.sh where the counter is
specified. The test has been robust in our testing, which means the counter
is bumped quickly enough that the updated value is available already on the
first iteration. Nevertheless it's not correct. Include tc_common.sh as
appropriate.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Some log_test calls are done in a loop, and lead to the same log output.
This might prove tricky to deduplicate for automated tools. Instead, roll
the unique information from log_info to log_test, and drop the log_info.
This also leads to more compact and clearer output.
This change prompts rewording the messages so that they are not excessively
long.
Some check_err messages do not indicate what the issue actually is, so
reword them to say it's a "ping with", like is the case in some other
instances in this test.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
When rx-pktsNtoM reports a range that involves very low-valued range, such
as 0-64, the calculated length of the packet will be -4, because FCS is
subtracted from the value. mausezahn then confuses the value for an option
and bails out. As a result, the test dumps many mausezahn error messages.
Instead, cap the value at 0. mausezahn will use an appropriate minimum
packet length.
Cc: Vladimir Oltean <vladimir.oltean@nxp.com>
Cc: Tobias Waldekranz <tobias@waldekranz.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
$ksft_skip is used to mark selftests that have tooling issues. The fact
that LLDPad is running, but shouldn't, is one such issue. Therefore have
bail_on_lldpad() bail with $ksft_skip.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
The variable should contain at least NUM_NETIFS interfaces, stored
as keys named "p$i", for i in `seq $NUM_NETIFS`.
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Bodies of busywait() and slowwait() functions are almost identical. Extract
the common code into a helper, loopy_wait, and convert busywait() and
slowwait() into trivial wrappers.
Moreover, the fact that slowwait() uses seconds for units is really not
intuitive, and the comment does not help much. Instead make the unit part
of the name of the argument to further clarify what units are expected.
Cc: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Benjamin Poirier <bpoirier@nvidia.com>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Convert lantiq_gswip to provide its own phylink MAC operations, thus
avoiding the shim layer in DSA's port.c. For lantiq_gswip, it means
we end up with a common instance of phylink MAC operations that are
shared between the different variants, rather than having duplicated
initialisers in dsa_switch_ops.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://lore.kernel.org/r/E1rvIcj-006bQo-B3@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Developing Python tests is a bit annoying because when test fails
we only print the fail message and no info about which exact check
led to it. Print the location (the first line of this example is new):
# At /root/ksft-net-drv/./net/nl_netdev.py line 38:
# Check failed 0 != 10
not ok 3 nl_netdev.page_pool_check
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://lore.kernel.org/r/20240412141436.828666-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
YNL currently reports None for empty dump:
$ cli.py ...netdev.yaml --dump page-pool-get
None
This doesn't matter for the CLI but when writing YNL based tests
having to deal with either list or None is annoying. Limit the
None conversion to non-dump ops:
$ cli.py ...netdev.yaml --dump page-pool-get
[]
Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://lore.kernel.org/r/20240412141436.828666-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add very basic page pool use so that we can exercise
the netlink uAPI in a selftest.
Page pool gets created on open, destroyed on close.
But we control allocating of a single page thru debugfs.
This page may survive past the page pool itself so that
we can test orphaned page pools.
Link: https://lore.kernel.org/r/20240412141436.828666-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Breno Leitao says:
====================
net: dqs: optimize if stall threshold is not set
Here are four patches aimed at enhancing the Dynamic Queue Limit (DQL)
subsystem within the networking stack.
The first two commits involve code refactoring, while the third patch
introduces the actual change. The fourth patch just improves the cache
locality.
Typically, when DQL is enabled, stall information is always populated
through dql_queue_stall(). However, this information is only necessary
if a stall threshold is set, which is stored in struct dql->stall_thrs.
Although dql_queue_stall() is relatively inexpensive, it is not entirely
free due to memory barriers and similar overheads.
To optimize performance, refrain from calling dql_queue_stall() when no
stall threshold is set, thus avoiding the processing of unnecessary
information.
v1: https://lore.kernel.org/all/20240404145939.3601097-1-leitao@debian.org/
====================
Link: https://lore.kernel.org/r/20240411192241.2498631-1-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
With the previous change, struct dqs->stall_thrs will be in the hot path
(at queue side), even if DQS is disabled.
The other fields accessed in this function (last_obj_cnt and num_queued)
are in the first cache line, let's move this field (stall_thrs) to the
very first cache line, since there is a hole there.
This does not change the structure size, since it moves an short (2
bytes) to 4-bytes whole in the first cache line.
This is the new structure format now:
struct dql {
unsigned int num_queued;
unsigned int last_obj_cnt;
...
short unsigned int stall_thrs;
/* XXX 2 bytes hole, try to pack */
...
/* --- cacheline 1 boundary (64 bytes) --- */
...
/* Longest stall detected, reported to user */
short unsigned int stall_max;
/* XXX 2 bytes hole, try to pack */
};
Also, read the stall_thrs (now in the very first cache line) earlier,
together with dql->num_queued (also in the first cache line).
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240411192241.2498631-5-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When Dynamic Queue Limit (DQL) is set, it always populate stall
information through dql_queue_stall(). However, this information is
only necessary if a stall threshold is set, stored in struct
dql->stall_thrs.
dql_queue_stall() is cheap, but not free, since it does have memory
barriers and so forth.
Do not call dql_queue_stall() if there is no stall threshold set, and
save some CPU cycles.
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240411192241.2498631-4-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The dql_queued() function currently handles both queuing object counts
and populating bitmaps for reporting stalls.
This commit splits the bitmap population into a separate function,
allowing for conditional invocation in scenarios where the feature is
disabled.
This refactor maintains functionality while improving code
organization.
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240411192241.2498631-3-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
If the dql_queued() function receives an invalid argument, WARN about it
and continue, instead of crashing the kernel.
This was raised by checkpatch, when I am refactoring this code (see
following patch/commit)
WARNING: Do not crash the kernel unless it is absolutely unavoidable--use WARN_ON_ONCE() plus recovery code (if feasible) instead of BUG() or variants
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20240411192241.2498631-2-leitao@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Julien Panis says:
====================
Add minimal XDP support to TI AM65 CPSW Ethernet driver
This patch adds XDP support to TI AM65 CPSW Ethernet driver.
The following features are implemented: NETDEV_XDP_ACT_BASIC,
NETDEV_XDP_ACT_REDIRECT, and NETDEV_XDP_ACT_NDO_XMIT.
Zero-copy and non-linear XDP buffer supports are NOT implemented.
Besides, the page pool memory model is used to get better performance.
====================
Signed-off-by: Julien Panis <jpanis@baylibre.com>
This patch adds XDP (eXpress Data Path) support to TI AM65 CPSW
Ethernet driver. The following features are implemented:
- NETDEV_XDP_ACT_BASIC (XDP_PASS, XDP_TX, XDP_DROP, XDP_ABORTED)
- NETDEV_XDP_ACT_REDIRECT (XDP_REDIRECT)
- NETDEV_XDP_ACT_NDO_XMIT (ndo_xdp_xmit callback)
The page pool memory model is used to get better performance.
Below are benchmark results obtained for the receiver with iperf3 default
parameters:
- Without page pool: 495 Mbits/sec
- With page pool: 605 Mbits/sec (actually 610 Mbits/sec, with a 5 Mbits/sec
loss due to extra processing in the hot path to handle XDP).
Signed-off-by: Julien Panis <jpanis@baylibre.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch introduces a member and the related accessors which can be
used to store descriptor specific additional information. This member
can store, for instance, an ID to differentiate a skb TX buffer type
from a xdpf TX buffer type.
Signed-off-by: Julien Panis <jpanis@baylibre.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch adds accessors for desc_size and cpumem members. They may be
used, for instance, to compute a descriptor index.
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Julien Panis <jpanis@baylibre.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We've observed a 7-12% performance regression in iperf3 UDP ipv4 and
ipv6 tests with multiple sockets on Zen3 cpus, which we traced back to
commit f0ea27e7bf ("udp: re-score reuseport groups when connected
sockets are present"). The failing tests were those that would spawn
UDP sockets per-cpu on systems that have a high number of cpus.
Unsurprisingly, it is not caused by the extra re-scoring of the reused
socket, but due to the compiler no longer inlining compute_score, once
it has the extra call site in udp4_lib_lookup2. This is augmented by
the "Safe RET" mitigation for SRSO, needed in our Zen3 cpus.
We could just explicitly inline it, but compute_score() is quite a large
function, around 300b. Inlining in two sites would almost double
udp4_lib_lookup2, which is a silly thing to do just to workaround a
mitigation. Instead, this patch shuffles the code a bit to avoid the
multiple calls to compute_score. Since it is a static function used in
one spot, the compiler can safely fold it in, as it did before, without
increasing the text size.
With this patch applied I ran my original iperf3 testcases. The failing
cases all looked like this (ipv4):
iperf3 -c 127.0.0.1 --udp -4 -f K -b $R -l 8920 -t 30 -i 5 -P 64 -O 2
where $R is either 1G/10G/0 (max, unlimited). I ran 3 times each.
baseline is v6.9-rc3. harmean == harmonic mean; CV == coefficient of
variation.
ipv4:
1G 10G MAX
HARMEAN (CV) HARMEAN (CV) HARMEAN (CV)
baseline 1743852.66(0.0208) 1725933.02(0.0167) 1705203.78(0.0386)
patched 1968727.61(0.0035) 1962283.22(0.0195) 1923853.50(0.0256)
ipv6:
1G 10G MAX
HARMEAN (CV) HARMEAN (CV) HARMEAN (CV)
baseline 1729020.03(0.0028) 1691704.49(0.0243) 1692251.34(0.0083)
patched 1900422.19(0.0067) 1900968.01(0.0067) 1568532.72(0.1519)
This restores the performance we had before the change above with this
benchmark. We obviously don't expect any real impact when mitigations
are disabled, but just to be sure it also doesn't regresses:
mitigations=off ipv4:
1G 10G MAX
HARMEAN (CV) HARMEAN (CV) HARMEAN (CV)
baseline 3230279.97(0.0066) 3229320.91(0.0060) 2605693.19(0.0697)
patched 3242802.36(0.0073) 3239310.71(0.0035) 2502427.19(0.0882)
Cc: Lorenz Bauer <lmb@isovalent.com>
Fixes: f0ea27e7bf ("udp: re-score reuseport groups when connected sockets are present")
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
