Shannon Nelson [Wed, 6 Mar 2024 23:29:47 +0000 (15:29 -0800)]
ionic: drop q mapping
Now that we're not using desc_info pointers mapped in every q
we can simplify and drop the unnecessary utility functions.
Reviewed-by: Brett Creeley <brett.creeley@amd.com> Signed-off-by: Shannon Nelson <shannon.nelson@amd.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Shannon Nelson [Wed, 6 Mar 2024 23:29:46 +0000 (15:29 -0800)]
ionic: remove desc, sg_desc and cmb_desc from desc_info
Remove the struct pointers from desc_info to use less space.
Instead of pointers in every desc_info to its descriptor,
we can use the queue descriptor index to find the individual
desc, desc_info, and sgl structs in their parallel arrays.
Suggested-by: Neel Patel <npatel2@amd.com> Reviewed-by: Brett Creeley <brett.creeley@amd.com> Signed-off-by: Shannon Nelson <shannon.nelson@amd.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Wed, 6 Mar 2024 15:47:03 +0000 (07:47 -0800)]
Add Jeff Kirsher to .get_maintainer.ignore
Jeff was retired as the Intel driver maintainer in
commit 6667df916fce ("MAINTAINERS: Update MAINTAINERS for
Intel ethernet drivers"), and his address bounces.
But he has signed-off a lot of patches over the years
so get_maintainer insists on CCing him.
We haven't heard from him since he left Intel, so remapping
the address via mailmap is also pointless. Add to ignored
addresses.
Signed-off-by: Jakub Kicinski <kuba@kernel.org> Acked-by: Tony Nguyen <anthony.l.nguyen@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Eric Dumazet [Wed, 6 Mar 2024 15:51:41 +0000 (15:51 +0000)]
ipv6: make inet6_fill_ifaddr() lockless
Make inet6_fill_ifaddr() lockless, and add approriate annotations
on ifa->tstamp, ifa->valid_lft, ifa->preferred_lft, ifa->ifa_proto
and ifa->rt_priority.
Also constify 2nd argument of inet6_fill_ifaddr(), inet6_fill_ifmcaddr()
and inet6_fill_ifacaddr().
Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
David S. Miller [Fri, 8 Mar 2024 10:35:48 +0000 (10:35 +0000)]
Merge branch 'nexthop-group-stats'
Petr Machata says:
====================
Support for nexthop group statistics
ECMP is a fundamental component in L3 designs. However, it's fragile. Many
factors influence whether an ECMP group will operate as intended: hash
policy (i.e. the set of fields that contribute to ECMP hash calculation),
neighbor validity, hash seed (which might lead to polarization) or the type
of ECMP group used (hash-threshold or resilient).
At the same time, collection of statistics that would help an operator
determine that the group performs as desired, is difficult.
A solution that we present in this patchset is to add counters to next hop
group entries. For SW-datapath deployments, this will on its own allow
collection and evaluation of relevant statistics. For HW-datapath
deployments, we further add a way to request that HW counters be installed
for a given group, in-kernel interfaces to collect the HW statistics, and
netlink interfaces to query them.
For example:
# ip nexthop replace id 4000 group 4001/4002 hw_stats on
# ip -s -d nexthop show id 4000
id 4000 group 4001/4002 scope global proto unspec offload hw_stats on used on
stats:
id 4001 packets 5002 packets_hw 5000
id 4002 packets 4999 packets_hw 4999
The point of the patchset is visibility of ECMP balance, and that is
influenced by packet headers, not their payload. Correspondingly, we only
include packet counters in the statistics, not byte counters.
We also decided to model HW statistics as a nexthop group attribute, not an
arbitrary nexthop one. The latter would count any traffic going through a
given nexthop, regardless of which ECMP group it is in, or any at all. The
reason is again hat the point of the patchset is ECMP balance visibility,
not arbitrary inspection of how busy a particular nexthop is.
Implementation of individual-nexthop statistics is certainly possible, and
could well follow the general approach we are taking in this patchset.
For resilient groups, per-bucket statistics could be done in a similar
manner as well.
This patchset contains the core code. mlxsw support will be sent in a
follow-up patch set.
This patchset progresses as follows:
- Patches #1 and #2 add support for a new next-hop object attribute,
NHA_OP_FLAGS. That is meant to carry various op-specific signaling, in
particular whether SW- and HW-collected nexthop stats should be part of
the get or dump response. The idea is to avoid wasting message space, and
time for collection of HW statistics, when the values are not needed.
- Patches #3 and #4 add SW-datapath stats and corresponding UAPI.
- Patches #5, #6 and #7 add support fro HW-datapath stats and UAPI.
Individual drivers still need to contribute the appropriate HW-specific
support code.
v4:
- Patch #2:
- s/nla_get_bitfield32/nla_get_u32/ in __nh_valid_dump_req().
v3:
- Patch #3:
- Convert to u64_stats_t
- Patch #4:
- Give a symbolic name to the set of all valid dump flags
for the NHA_OP_FLAGS attribute.
- Convert to u64_stats_t
- Patch #6:
- Use a named constant for the NHA_HW_STATS_ENABLE policy.
v2:
- Patch #2:
- Change OP_FLAGS to u32, enforce through NLA_POLICY_MASK
- Patch #3:
- Set err on nexthop_create_group() error path
- Patch #4:
- Use uint to encode NHA_GROUP_STATS_ENTRY_PACKETS
- Rename jump target in nla_put_nh_group_stats() to avoid
having to rename further in the patchset.
- Patch #7:
- Use uint to encode NHA_GROUP_STATS_ENTRY_PACKETS_HW
- Do not cancel outside of nesting in nla_put_nh_group_stats()
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Wed, 6 Mar 2024 12:49:21 +0000 (13:49 +0100)]
net: nexthop: Expose nexthop group HW stats to user space
Add netlink support for reading NH group hardware stats.
Stats collection is done through a new notifier,
NEXTHOP_EVENT_HW_STATS_REPORT_DELTA. Drivers that implement HW counters for
a given NH group are thereby asked to collect the stats and report back to
core by calling nh_grp_hw_stats_report_delta(). This is similar to what
netdevice L3 stats do.
Besides exposing number of packets that passed in the HW datapath, also
include information on whether any driver actually realizes the counters.
The core can tell based on whether it got any _report_delta() reports from
the drivers. This allows enabling the statistics at the group at any time,
with drivers opting into supporting them. This is also in line with what
netdevice L3 stats are doing.
So as not to waste time and space, tie the collection and reporting of HW
stats with a new op flag, NHA_OP_FLAG_DUMP_HW_STATS.
Co-developed-by: Petr Machata <petrm@nvidia.com> Signed-off-by: Petr Machata <petrm@nvidia.com> Signed-off-by: Ido Schimmel <idosch@nvidia.com> Reviewed-by: Kees Cook <keescook@chromium.org> # For the __counted_by bits Reviewed-by: David Ahern <dsahern@kernel.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Wed, 6 Mar 2024 12:49:20 +0000 (13:49 +0100)]
net: nexthop: Add ability to enable / disable hardware statistics
Add netlink support for enabling collection of HW statistics on nexthop
groups.
Signed-off-by: Ido Schimmel <idosch@nvidia.com> Reviewed-by: David Ahern <dsahern@kernel.org> Signed-off-by: Petr Machata <petrm@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Add hw_stats field to several notifier structures to communicate to the
drivers that HW statistics should be configured for nexthops within a given
group.
Signed-off-by: Ido Schimmel <idosch@nvidia.com> Reviewed-by: David Ahern <dsahern@kernel.org> Signed-off-by: Petr Machata <petrm@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Wed, 6 Mar 2024 12:49:18 +0000 (13:49 +0100)]
net: nexthop: Expose nexthop group stats to user space
Add netlink support for reading NH group stats.
This data is only for statistics of the traffic in the SW datapath. HW
nexthop group statistics will be added in the following patches.
Emission of the stats is keyed to a new op_stats flag to avoid cluttering
the netlink message with stats if the user doesn't need them:
NHA_OP_FLAG_DUMP_STATS.
Co-developed-by: Petr Machata <petrm@nvidia.com> Signed-off-by: Petr Machata <petrm@nvidia.com> Signed-off-by: Ido Schimmel <idosch@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Ido Schimmel [Wed, 6 Mar 2024 12:49:17 +0000 (13:49 +0100)]
net: nexthop: Add nexthop group entry stats
Add nexthop group entry stats to count the number of packets forwarded
via each nexthop in the group. The stats will be exposed to user space
for better data path observability in the next patch.
The per-CPU stats pointer is placed at the beginning of 'struct
nh_grp_entry', so that all the fields accessed for the data path reside
on the same cache line:
/* size: 72, cachelines: 2, members: 6 */
/* sum members: 65, holes: 1, sum holes: 7 */
/* last cacheline: 8 bytes */
};
Co-developed-by: Petr Machata <petrm@nvidia.com> Signed-off-by: Petr Machata <petrm@nvidia.com> Signed-off-by: Ido Schimmel <idosch@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Petr Machata [Wed, 6 Mar 2024 12:49:16 +0000 (13:49 +0100)]
net: nexthop: Add NHA_OP_FLAGS
In order to add per-nexthop statistics, but still not increase netlink
message size for consumers that do not care about them, there needs to be a
toggle through which the user indicates their desire to get the statistics.
To that end, add a new attribute, NHA_OP_FLAGS. The idea is to be able to
use the attribute for carrying of arbitrary operation-specific flags, i.e.
not make it specific for get / dump.
Add the new attribute to get and dump policies, but do not actually allow
any flags yet -- those will come later as the flags themselves are defined.
Add the necessary parsing code.
Signed-off-by: Petr Machata <petrm@nvidia.com> Reviewed-by: David Ahern <dsahern@kernel.org> Reviewed-by: Ido Schimmel <idosch@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Petr Machata [Wed, 6 Mar 2024 12:49:15 +0000 (13:49 +0100)]
net: nexthop: Adjust netlink policy parsing for a new attribute
A following patch will introduce a new attribute, op-specific flags to
adjust the behavior of an operation. Different operations will recognize
different flags.
- To make the differentiation possible, stop sharing the policies for get
and del operations.
- To allow querying for presence of the attribute, have all the attribute
arrays sized to NHA_MAX, regardless of what is permitted by policy, and
pass the corresponding value to nlmsg_parse() as well.
Signed-off-by: Petr Machata <petrm@nvidia.com> Reviewed-by: David Ahern <dsahern@kernel.org> Reviewed-by: Ido Schimmel <idosch@nvidia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
fuyuanli [Tue, 5 Mar 2024 03:04:17 +0000 (11:04 +0800)]
tcp: Add skb addr and sock addr to arguments of tracepoint tcp_probe.
It is useful to expose skb addr and sock addr to user in tracepoint
tcp_probe, so that we can get more information while monitoring
receiving of tcp data, by ebpf or other ways.
For example, we need to identify a packet by seq and end_seq when
calculate transmit latency between layer 2 and layer 4 by ebpf, but which is
not available in tcp_probe, so we can only use kprobe hooking
tcp_rcv_established to get them. But we can use tcp_probe directly if skb
addr and sock addr are available, which is more efficient.
Signed-off-by: fuyuanli <fuyuanli@didiglobal.com> Reviewed-by: Jason Xing <kerneljasonxing@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Jakub Kicinski [Mon, 4 Mar 2024 14:08:47 +0000 (06:08 -0800)]
net: dqs: add NIC stall detector based on BQL
softnet_data->time_squeeze is sometimes used as a proxy for
host overload or indication of scheduling problems. In practice
this statistic is very noisy and has hard to grasp units -
e.g. is 10 squeezes a second to be expected, or high?
Delaying network (NAPI) processing leads to drops on NIC queues
but also RTT bloat, impacting pacing and CA decisions.
Stalls are a little hard to detect on the Rx side, because
there may simply have not been any packets received in given
period of time. Packet timestamps help a little bit, but
again we don't know if packets are stale because we're
not keeping up or because someone (*cough* cgroups)
disabled IRQs for a long time.
We can, however, use Tx as a proxy for Rx stalls. Most drivers
use combined Rx+Tx NAPIs so if Tx gets starved so will Rx.
On the Tx side we know exactly when packets get queued,
and completed, so there is no uncertainty.
This patch adds stall checks to BQL. Why BQL? Because
it's a convenient place to add such checks, already
called by most drivers, and it has copious free space
in its structures (this patch adds no extra cache
references or dirtying to the fast path).
The algorithm takes one parameter - max delay AKA stall
threshold and increments a counter whenever NAPI got delayed
for at least that amount of time. It also records the length
of the longest stall.
To be precise every time NAPI has not polled for at least
stall thrs we check if there were any Tx packets queued
between last NAPI run and now - stall_thrs/2.
Unlike the classic Tx watchdog this mechanism does not
ignore stalls caused by Tx being disabled, or loss of link.
I don't think the check is worth the complexity, and
stall is a stall, whether due to host overload, flow
control, link down... doesn't matter much to the application.
We have been running this detector in production at Meta
for 2 years, with the threshold of 8ms. It's the lowest
value where false positives become rare. There's still
a constant stream of reported stalls (especially without
the ksoftirqd deferral patches reverted), those who like
their stall metrics to be 0 may prefer higher value.
Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Breno Leitao <leitao@debian.org> Signed-off-by: David S. Miller <davem@davemloft.net>
Per queue stats keep coming up, so it's about time someone laid
the foundation. This series adds the uAPI, a handful of stats
and a sample support for bnxt. It's not very comprehensive in
terms of stat types or driver support. The expectation is that
the support will grow organically. If we have the basic pieces
in place it will be easy for reviewers to request new stats,
or use of the API in place of ethtool -S.
Jakub Kicinski [Wed, 6 Mar 2024 19:55:07 +0000 (11:55 -0800)]
netdev: add per-queue statistics
The ethtool-nl family does a good job exposing various protocol
related and IEEE/IETF statistics which used to get dumped under
ethtool -S, with creative names. Queue stats don't have a netlink
API, yet, and remain a lion's share of ethtool -S output for new
drivers. Not only is that bad because the names differ driver to
driver but it's also bug-prone. Intuitively drivers try to report
only the stats for active queues, but querying ethtool stats
involves multiple system calls, and the number of stats is
read separately from the stats themselves. Worse still when user
space asks for values of the stats, it doesn't inform the kernel
how big the buffer is. If number of stats increases in the meantime
kernel will overflow user buffer.
Add a netlink API for dumping queue stats. Queue information is
exposed via the netdev-genl family, so add the stats there.
Support per-queue and sum-for-device dumps. Latter will be useful
when subsequent patches add more interesting common stats than
just bytes and packets.
The API does not currently distinguish between HW and SW stats.
The expectation is that the source of the stats will either not
matter much (good packets) or be obvious (skb alloc errors).
Acked-by: Stanislav Fomichev <sdf@google.com> Reviewed-by: Amritha Nambiar <amritha.nambiar@intel.com> Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com> Link: https://lore.kernel.org/r/20240306195509.1502746-2-kuba@kernel.org Signed-off-by: Jakub Kicinski <kuba@kernel.org>
If the cpu was idle or busy in other layers,
it has to pull many cache lines.
This series adds a new net_hotdata structure, where
some critical (and read-mostly) data used in
rx and tx path is packed in a small number of cache lines.
Synthetic benchmarks will not see much difference,
but latency of single packet should improve.
net_hodata current size on 64bit is 416 bytes,
but might grow in the future.
Also move RPS definitions to a new include file.
====================
====================
selftests: mptcp: share code and fix shellcheck warnings
This series cleans MPTCP selftests code.
Patch 1 stops using 'iptables-legacy' if available, but uses 'iptables',
which is likely 'iptables-nft' behind.
Patches 2, 4 and 6 move duplicated code to mptcp_lib.sh. Patch 3 is a
preparation for patch 4, and patch 5 adds generic actions at the
creation and deletion of netns.
Patches 7 to 11 disable a few shellcheck warnings, and fix the rest, so
it is easy to spot real issues later. MPTCP CI is checking that now.
Patch 12 avoids redoing some actions at init time twice, e.g. restarting
the pm events tool.
shellcheck recently helped to prevent issues. It is then good to fix the
other harmless issues in order to spot "real" ones later.
Here, two categories of warnings are now ignored:
- SC2317: Command appears to be unreachable. The cleanup() function is
invoked indirectly via the EXIT trap.
- SC2086: Double quote to prevent globbing and word splitting. This is
recommended, but the current usage is correct and there is no need to
do all these modifications to be compliant with this rule.
For the modifications:
- SC2034: ksft_skip appears unused.
- SC2004: $/${} is unnecessary on arithmetic variables.
Now this script is shellcheck (0.9.0) compliant. We can easily spot new
issues.
shellcheck recently helped to prevent issues. It is then good to fix the
other harmless issues in order to spot "real" ones later.
Here, two categories of warnings are now ignored:
- SC2317: Command appears to be unreachable. The cleanup() function is
invoked indirectly via the EXIT trap.
- SC2086: Double quote to prevent globbing and word splitting. This is
recommended, but the current usage is correct and there is no need to
do all these modifications to be compliant with this rule.
For the modifications:
- SC2034: ksft_skip appears unused.
- SC2154: optstring is referenced but not assigned.
- SC2006: Use $(...) notation instead of legacy backticks `...`.
Now this script is shellcheck (0.9.0) compliant. We can easily spot new
issues.
shellcheck recently helped to prevent issues. It is then good to fix the
other harmless issues in order to spot "real" ones later.
Here, two categories of warnings are now ignored:
- SC2317: Command appears to be unreachable. The cleanup() function is
invoked indirectly via the EXIT trap.
- SC2086: Double quote to prevent globbing and word splitting. This is
recommended, but the current usage is correct and there is no need to
do all these modifications to be compliant with this rule.
For the modifications:
- SC2034: ksft_skip appears unused.
- SC2006: Use $(...) notation instead of legacy backticks `...`.
- SC2145: Argument mixes string and array. Use * or separate argument.
Now this script is shellcheck (0.9.0) compliant. We can easily spot new
issues.
shellcheck recently helped to prevent issues. It is then good to fix the
other harmless issues in order to spot "real" ones later.
Here, two categories of warnings are now ignored:
- SC2317: Command appears to be unreachable. The cleanup() function is
invoked indirectly via the EXIT trap.
- SC2086: Double quote to prevent globbing and word splitting. This is
recommended, but the current usage is correct and there is no need to
do all these modifications to be compliant with this rule.
For the modifications:
- SC2034: ksft_skip appears unused.
- SC2181: Check exit code directly with e.g. 'if mycmd;', not
indirectly with $?.
- SC2004: $/${} is unnecessary on arithmetic variables.
- SC2155: Declare and assign separately to avoid masking return
values.
- SC2166: Prefer [ p ] && [ q ] as [ p -a q ] is not well defined.
- SC2059: Don't use variables in the printf format string. Use printf
'..%s..' "$foo".
Now this script is shellcheck (0.9.0) compliant. We can easily spot new
issues.
shellcheck recently helped to prevent issues. It is then good to fix the
other harmless issues in order to spot "real" ones later.
Here, two categories of warnings are now ignored:
- SC2317: Command appears to be unreachable. The cleanup() function is
invoked indirectly via the EXIT trap.
- SC2086: Double quote to prevent globbing and word splitting. This is
recommended, but the current usage is correct and there is no need to
do all these modifications to be compliant with this rule.
For the modifications:
- SC2034: ksft_skip appears unused.
- SC2046: Quote '$(get_msk_inuse)' to prevent word splitting.
- SC2006: Use $(...) notation instead of legacy backticks `...`.
Now this script is shellcheck (0.9.0) compliant. We can easily spot new
issues.
Geliang Tang [Wed, 6 Mar 2024 09:42:55 +0000 (10:42 +0100)]
selftests: mptcp: add mptcp_lib_events helper
To avoid duplicated code in different MPTCP selftests, we can add and
use helpers defined in mptcp_lib.sh.
This patch unifies "pm_nl_ctl events" related code in userspace_pm.sh
and mptcp_join.sh into a helper mptcp_lib_events(). Define it in
mptcp_lib.sh and use it in both scripts.
Note that mptcp_lib_kill_wait is now call before starting 'events' for
mptcp_join.sh as well, but that's fine: each test is started from a new
netns, so there will not be any existing pid there, and nothing is done
when mptcp_lib_kill_wait is called with 0.
Geliang Tang [Wed, 6 Mar 2024 09:42:54 +0000 (10:42 +0100)]
selftests: mptcp: more operations in ns_init/exit
Set more the default sysctl values in mptcp_lib_ns_init(). It is fine to
do that everywhere, because they could be overridden latter if needed.
mptcp_lib_ns_exit() now also try to remove temp netns files used for the
stats even for selftests not using them. That's fine to do that because
these files have a unique name.
Add helpers mptcp_lib_ns_init() and mptcp_lib_ns_exit() in mptcp_lib.sh
to initialize and delete the given namespaces. Then every test script
can invoke these helpers and use all namespaces.
Geliang Tang [Wed, 6 Mar 2024 09:42:52 +0000 (10:42 +0100)]
selftests: mptcp: add local variables rndh
This patch adds local variables rndh in do_transfer() functions both in
mptcp_connect.sh and simult_flows.sh, setting it with ${ns1:4}, not the
global variable rndh. The global one is hidden in the next commit.
This patch exports check_tools() helper from mptcp_join.sh into
mptcp_lib.sh as a public one mptcp_lib_check_tools(). The arguments
"ip", "ss", "iptables" and "ip6tables" are passed into this helper
to indicate whether to check ip tool, ss tool, iptables and ip6tables
tools.
Commit 0c4cd3f86a40 ("selftests: mptcp: join: use 'iptables-legacy' if
available") and commit a5a5990c099d ("selftests: mptcp: sockopt: use
'iptables-legacy' if available") forced using iptables-legacy if
available.
This was needed because of some issues that were visible when testing
the kselftests on a v5.15.x with iptables-nft as default backend. It
looks like these errors are no longer present. As mentioned by Pablo [1],
the errors were maybe due to missing kernel config. We can then use
iptables-nft if it is the default one, instead of using a legacy tool.
We can then check the variables iptables and ip6tables are valid. We can
keep the variables to easily change it later or add options.
Jakub Kicinski [Fri, 8 Mar 2024 04:59:57 +0000 (20:59 -0800)]
Merge tag 'rxrpc-iothread-20240305' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs
David Howells says:
====================
Here are some changes to AF_RXRPC:
(1) Cache the transmission serial number of ACK and DATA packets in the
rxrpc_txbuf struct and log this in the retransmit tracepoint.
(2) Don't use atomics on rxrpc_txbuf::flags[*] and cache the intended wire
header flags there too to avoid duplication.
(3) Cache the wire checksum in rxrpc_txbuf to make it easier to create
jumbo packets in future (which will require altering the wire header
to a jumbo header and restoring it back again for retransmission).
(4) Fix the protocol names in the wire ACK trailer struct.
(5) Strip all the barriers and atomics out of the call timer tracking[*].
(6) Remove atomic handling from call->tx_transmitted and
call->acks_prev_seq[*].
(7) Don't bother resetting the DF flag after UDP packet transmission. To
change it, we now call directly into UDP code, so it's quick just to
set it every time.
(8) Merge together the DF/non-DF branches of the DATA transmission to
reduce duplication in the code.
(9) Add a kvec array into rxrpc_txbuf and start moving things over to it.
This paves the way for using page frags.
(10) Split (sub)packet preparation and timestamping out of the DATA
transmission function. This helps pave the way for future jumbo
packet generation.
(11) In rxkad, don't pick values out of the wire header stored in
rxrpc_txbuf, buf rather find them elsewhere so we can remove the wire
header from there.
(12) Move rxrpc_send_ACK() to output.c so that it can be merged with
rxrpc_send_ack_packet().
(13) Use rxrpc_txbuf::kvec[0] to access the wire header for the packet
rather than directly accessing the copy in rxrpc_txbuf. This will
allow that to be removed to a page frag.
(14) Switch from keeping the transmission buffers in rxrpc_txbuf allocated
in the slab to allocating them using page fragment allocators. There
are separate allocators for DATA packets (which persist for a while)
and control packets (which are discarded immediately).
We can then turn on MSG_SPLICE_PAGES when transmitting DATA and ACK
packets.
We can also get rid of the RCU cleanup on rxrpc_txbufs, preferring
instead to release the page frags as soon as possible.
(15) Parse received packets before handling timeouts as the former may
reset the latter.
(16) Make sure we don't retransmit DATA packets after all the packets have
been ACK'd.
(17) Differentiate traces for PING ACK transmission.
(18) Switch to keeping timeouts as ktime_t rather than a number of jiffies
as the latter is too coarse a granularity. Only set the call timer at
the end of the call event function from the aggregate of all the
timeouts, thereby reducing the number of timer calls made. In future,
it might be possible to reduce the number of timers from one per call
to one per I/O thread and to use a high-precision timer.
(19) Record RTT probes after successful transmission rather than recording
it before and then cancelling it after if unsuccessful[*]. This
allows a number of calls to get the current time to be removed.
(20) Clean up the resend algorithm as there's now no need to walk the
transmission buffer under lock[*]. DATA packets can be retransmitted
as soon as they're found rather than being queued up and transmitted
when the locked is dropped.
(21) When initially parsing a received ACK packet, extract some of the
fields from the ack info to the skbuff private data. This makes it
easier to do path MTU discovery in the future when the call to which a
PING RESPONSE ACK refers has been deallocated.
[*] Possible with the move of almost all code from softirq context to the
I/O thread.
Link: https://lore.kernel.org/r/20240301163807.385573-1-dhowells@redhat.com/ Link: https://lore.kernel.org/r/20240304084322.705539-1-dhowells@redhat.com/
* tag 'rxrpc-iothread-20240305' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs: (21 commits)
rxrpc: Extract useful fields from a received ACK to skb priv data
rxrpc: Clean up the resend algorithm
rxrpc: Record probes after transmission and reduce number of time-gets
rxrpc: Use ktimes for call timeout tracking and set the timer lazily
rxrpc: Differentiate PING ACK transmission traces.
rxrpc: Don't permit resending after all Tx packets acked
rxrpc: Parse received packets before dealing with timeouts
rxrpc: Do zerocopy using MSG_SPLICE_PAGES and page frags
rxrpc: Use rxrpc_txbuf::kvec[0] instead of rxrpc_txbuf::wire
rxrpc: Move rxrpc_send_ACK() to output.c with rxrpc_send_ack_packet()
rxrpc: Don't pick values out of the wire header when setting up security
rxrpc: Split up the DATA packet transmission function
rxrpc: Add a kvec[] to the rxrpc_txbuf struct
rxrpc: Merge together DF/non-DF branches of data Tx function
rxrpc: Do lazy DF flag resetting
rxrpc: Remove atomic handling on some fields only used in I/O thread
rxrpc: Strip barriers and atomics off of timer tracking
rxrpc: Fix the names of the fields in the ACK trailer struct
rxrpc: Note cksum in txbuf
rxrpc: Convert rxrpc_txbuf::flags into a mask and don't use atomics
...
====================
Breno Leitao [Wed, 6 Mar 2024 14:26:42 +0000 (06:26 -0800)]
net: usbnet: Remove generic .ndo_get_stats64
Commit 3e2f544dd8a33 ("net: get stats64 if device if driver is
configured") moved the callback to dev_get_tstats64() to net core, so,
unless the driver is doing some custom stats collection, it does not
need to set .ndo_get_stats64.
Since this driver is now relying in NETDEV_PCPU_STAT_TSTATS, then, it
doesn't need to set the dev_get_tstats64() generic .ndo_get_stats64
function pointer.
Breno Leitao [Wed, 6 Mar 2024 14:26:41 +0000 (06:26 -0800)]
net: usbnet: Leverage core stats allocator
With commit 34d21de99cea9 ("net: Move {l,t,d}stats allocation to core and
convert veth & vrf"), stats allocation could be done on net core
instead of in this driver.
With this new approach, the driver doesn't have to bother with error
handling (allocation failure checking, making sure free happens in the
right spot, etc). This is core responsibility now.
Remove the allocation in the usbnet driver and leverage the network
core allocation instead.
net: dsa: mv88e6xxx: update 88e6185 PCS driver to use neg_mode
Update the Marvell 88e6185 PCS driver to use neg_mode rather than the
mode argument to match the other updated PCS drivers.
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com> Link: https://lore.kernel.org/r/E1rhosE-003yuc-FM@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Kui-Feng Lee [Tue, 5 Mar 2024 18:39:49 +0000 (10:39 -0800)]
selftests/net: fix waiting time for ipv6_gc test in fib_tests.sh.
ipv6_gc fails occasionally. According to the study, fib6_run_gc() using
jiffies_round() to round the GC interval could increase the waiting time up
to 750ms (3/4 seconds). The timer has a granularity of 512ms at the range
4s to 32s. That means a route with an expiration time E seconds can wait
for more than E * 2 + 1 seconds if the GC interval is also E seconds.
E * 2 + 2 seconds should be enough for waiting for removing routes.
Also remove a check immediately after replacing 5 routes since it is very
likely to remove some of routes before completing the last route with a
slow environment.
We observed that TCP-pacing was falling back to the TCP-layer pacing
instead of utilizing sch_fq for the pacing. This causes significant
CPU-usage due to the hrtimer running on a per-TCP-connection basis.
The issue is that mpls_xmit() calls skb_orphan() and thus sets
skb->sk to NULL. Which implies that many of the goodies of TCP won't
work. Pacing falls back to TCP-layer pacing. TCP Small Queues does not
work, ...
It is safe to remove this call to skb_orphan() in mpls_xmit() as there
really is not reason for it to be there. It appears that this call to
skb_orphan comes from the very initial implementation of MPLS.
With commit 34d21de99cea9 ("net: Move {l,t,d}stats allocation to core
and convert veth & vrf"), stats allocation could be done on net core
instead of in this driver.
With this new approach, the driver doesn't have to bother with error
handling (allocation failure checking, making sure free happens in the
right spot, etc). This is core responsibility now.
Remove the allocation in the DSA user network device code and leverage
the network core allocation instead.
atm: fore200e: Convert to platform remove callback returning void
The .remove() callback for a platform driver returns an int which makes
many driver authors wrongly assume it's possible to do error handling by
returning an error code. However the value returned is ignored (apart
from emitting a warning) and this typically results in resource leaks.
To improve here there is a quest to make the remove callback return
void. In the first step of this quest all drivers are converted to
.remove_new(), which already returns void. Eventually after all drivers
are converted, .remove_new() will be renamed to .remove().
Trivially convert this driver from always returning zero in the remove
callback to the void returning variant.
Donald Hunter [Wed, 6 Mar 2024 23:10:42 +0000 (23:10 +0000)]
tools/net/ynl: Report netlink errors without stacktrace
ynl does not handle NlError exceptions so they get reported like program
failures. Handle the NlError exceptions and report the netlink errors
more cleanly.
Example now:
Netlink error: No such file or directory
nl_len = 44 (28) nl_flags = 0x300 nl_type = 2
error: -2 extack: {'bad-attr': '.op'}
Example before:
Traceback (most recent call last):
File "/home/donaldh/net-next/./tools/net/ynl/cli.py", line 81, in <module>
main()
File "/home/donaldh/net-next/./tools/net/ynl/cli.py", line 69, in main
reply = ynl.dump(args.dump, attrs)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/donaldh/net-next/tools/net/ynl/lib/ynl.py", line 906, in dump
return self._op(method, vals, [], dump=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/donaldh/net-next/tools/net/ynl/lib/ynl.py", line 872, in _op
raise NlError(nl_msg)
lib.ynl.NlError: Netlink error: No such file or directory
nl_len = 44 (28) nl_flags = 0x300 nl_type = 2
error: -2 extack: {'bad-attr': '.op'}
Since commit 43a7206b0963 ("driver core: class: make class_register() take
a const *"), the driver core allows for struct class to be in read-only
memory, so move the capi_class structure to be declared at build time
placing it into read-only memory, instead of having to be dynamically
allocated at boot time.
Since commit 43a7206b0963 ("driver core: class: make class_register() take
a const *"), the driver core allows for struct class to be in read-only
memory, so move the elements_class structure to be declared at build time
placing it into read-only memory, instead of having to be dynamically
allocated at boot time.
Drop reference to the 25MHz clock as it has nothing to do with connecting
the PHY and the MAC.
Add info about the reference clock direction between the PHY and the MAC
as it depends on the selected rmii mode.
Suggested-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Jérémie Dautheribes <jeremie.dautheribes@bootlin.com> Reviewed-by: Andrew Lunn <andrew@lunn.ch> Acked-by: Conor Dooley <conor.dooley@microchip.com> Link: https://lore.kernel.org/r/20240305141309.127669-1-jeremie.dautheribes@bootlin.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Justin Swartz [Wed, 6 Mar 2024 11:26:59 +0000 (13:26 +0200)]
net: x25: remove dead links from Kconfig
Remove the "You can read more about X.25 at" links provided in
Kconfig as they have not pointed at any relevant pages for quite
a while.
An old copy of https://www.sangoma.com/tutorials/x25/ can be
retrieved via https://archive.org/web/ but nothing useful seems
to have been preserved for http://docwiki.cisco.com/wiki/X.25
For the sake of necromancy and those who really did want to
read more about X.25, a previous incarnation of Kconfig included
a link to:
http://www.cisco.com/univercd/cc/td/doc/product/software/ios11/cbook/cx25.htm
Which can still be read at:
https://web.archive.org/web/20071013101232/http://cisco.com/en/US/docs/ios/11_0/router/configuration/guide/cx25.html
Jakub Kicinski [Tue, 5 Mar 2024 18:50:00 +0000 (10:50 -0800)]
tools: ynl: check for overflow of constructed messages
Donald points out that we don't check for overflows.
Stash the length of the message on nlmsg_pid (nlmsg_seq would
do as well). This allows the attribute helpers to remain
self-contained (no extra arguments). Also let the put
helpers continue to return nothing. The error is checked
only in (newly introduced) ynl_msg_end().
Linus Torvalds [Thu, 7 Mar 2024 17:23:33 +0000 (09:23 -0800)]
Merge tag 'net-6.8-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Paolo Abeni:
"Including fixes from bpf, ipsec and netfilter.
No solution yet for the stmmac issue mentioned in the last PR, but it
proved to be a lockdep false positive, not a blocker.
Current release - regressions:
- dpll: move all dpll<>netdev helpers to dpll code, fix build
regression with old compilers
Current release - new code bugs:
- page_pool: fix netlink dump stop/resume
Previous releases - regressions:
- bpf: fix verifier to check bpf_func_state->callback_depth when
pruning states as otherwise unsafe programs could get accepted
- ipv6: avoid possible UAF in ip6_route_mpath_notify()
- ice: reconfig host after changing MSI-X on VF
- mlx5:
- e-switch, change flow rule destination checking
- add a memory barrier to prevent a possible null-ptr-deref
- switch to using _bh variant of of spinlock where needed
Previous releases - always broken:
- netfilter: nf_conntrack_h323: add protection for bmp length out of
range
- bpf: fix to zero-initialise xdp_rxq_info struct before running XDP
program in CPU map which led to random xdp_md fields
- xfrm: fix UDP encapsulation in TX packet offload
- igc: avoid returning frame twice in XDP_REDIRECT
- i40e: disable NAPI right after disabling irqs when handling
xsk_pool
- geneve: make sure to pull inner header in geneve_rx()
- sparx5: fix use after free inside sparx5_del_mact_entry
- dsa: microchip: fix register write order in ksz8_ind_write8()
Misc:
- selftests: mptcp: fixes for diag.sh"
* tag 'net-6.8-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (63 commits)
net: pds_core: Fix possible double free in error handling path
netrom: Fix data-races around sysctl_net_busy_read
netrom: Fix a data-race around sysctl_netrom_link_fails_count
netrom: Fix a data-race around sysctl_netrom_routing_control
netrom: Fix a data-race around sysctl_netrom_transport_no_activity_timeout
netrom: Fix a data-race around sysctl_netrom_transport_requested_window_size
netrom: Fix a data-race around sysctl_netrom_transport_busy_delay
netrom: Fix a data-race around sysctl_netrom_transport_acknowledge_delay
netrom: Fix a data-race around sysctl_netrom_transport_maximum_tries
netrom: Fix a data-race around sysctl_netrom_transport_timeout
netrom: Fix data-races around sysctl_netrom_network_ttl_initialiser
netrom: Fix a data-race around sysctl_netrom_obsolescence_count_initialiser
netrom: Fix a data-race around sysctl_netrom_default_path_quality
netfilter: nf_conntrack_h323: Add protection for bmp length out of range
netfilter: nf_tables: mark set as dead when unbinding anonymous set with timeout
netfilter: nft_ct: fix l3num expectations with inet pseudo family
netfilter: nf_tables: reject constant set with timeout
netfilter: nf_tables: disallow anonymous set with timeout flag
net/rds: fix WARNING in rds_conn_connect_if_down
net: dsa: microchip: fix register write order in ksz8_ind_write8()
...
====================
tcp: add two missing addresses when using trace
When I reviewed other people's patch [1], I noticed that similar things
also happen in tcp_event_skb class and tcp_event_sk_skb class. They
don't print those two addrs of skb/sk which already exist.
In this patch, I just do as other trace functions do, like
trace_net_dev_start_xmit(), to know the exact flow or skb we would like
to know in case some systems doesn't support BPF programs well or we
have to use /sys/kernel/debug/tracing only for some reasons.
Jason Xing [Mon, 4 Mar 2024 09:29:33 +0000 (17:29 +0800)]
tcp: add tracing of skb/skaddr in tcp_event_sk_skb class
Printing the addresses can help us identify the exact skb/sk
for those system in which it's not that easy to run BPF program.
As we can see, it already fetches those, then use it directly
and it will print like below:
====================
doc: sfp-phylink: update the porting guide
Here's a V3 for an update on the phylink porting guide. The only
difference with V2 is a whitespace fix along with a line-wrap.
The main point of the update is the description of a basic process to
follow to expose one or more PCS to phylink. Let me know if you spot any
inaccuracies in the guide.
The second patch is a simple fixup on some in-code doc that was spotted
while updating the guide.
Link to V2: https://lore.kernel.org/netdev/20240228095755.1499577-1-maxime.chevallier@bootlin.com/
Link to V1: https://lore.kernel.org/netdev/20240220160406.3363002-1-maxime.chevallier@bootlin.com/
====================
net: phylink: clean the pcs_get_state documentation
commit 4d72c3bb60dd ("net: phylink: strip out pre-March 2020 legacy code")
dropped the mac_pcs_get_state ops in phylink_mac_ops in favor of
dedicated PCS operation pcs_get_state. However, the documentation for
the pcs_get_state ops was incorrectly converted and now self-references.
Drop the extra comment.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
doc: sfp-phylink: update the porting guide with PCS handling
Now that phylink has a comprehensive PCS support, update the porting
guide to explain the process of supporting the PCS configuration. This
also removed outdated references to phylink_config fields that no longer
exists.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Yongzhi Liu [Wed, 6 Mar 2024 10:57:14 +0000 (18:57 +0800)]
net: pds_core: Fix possible double free in error handling path
When auxiliary_device_add() returns error and then calls
auxiliary_device_uninit(), Callback function pdsc_auxbus_dev_release
calls kfree(padev) to free memory. We shouldn't call kfree(padev)
again in the error handling path.
Fix this by cleaning up the redundant kfree() and putting
the error handling back to where the errors happened.
Fixes: 4569cce43bc6 ("pds_core: add auxiliary_bus devices") Signed-off-by: Yongzhi Liu <hyperlyzcs@gmail.com> Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com> Reviewed-by: Shannon Nelson <shannon.nelson@amd.com> Link: https://lore.kernel.org/r/20240306105714.20597-1-hyperlyzcs@gmail.com Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Paolo Abeni [Thu, 7 Mar 2024 10:06:13 +0000 (11:06 +0100)]
Merge tag 'nf-24-03-07' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf
Pablo Neira Ayuso says:
====================
Netfilter fixes for net
The following patchset contains fixes for net:
Patch #1 disallows anonymous sets with timeout, except for dynamic sets.
Anonymous sets with timeouts using the pipapo set backend makes
no sense from userspace perspective.
Patch #2 rejects constant sets with timeout which has no practical usecase.
This kind of set, once bound, contains elements that expire but
no new elements can be added.
Patch #3 restores custom conntrack expectations with NFPROTO_INET,
from Florian Westphal.
Patch #4 marks rhashtable anonymous set with timeout as dead from the
commit path to avoid that async GC collects these elements. Rules
that refers to the anonymous set get released with no mutex held
from the commit path.
Patch #5 fixes a UBSAN shift overflow in H.323 conntrack helper,
from Lena Wang.
netfilter pull request 24-03-07
* tag 'nf-24-03-07' of git://git.kernel.org/pub/scm/linux/kernel/git/netfilter/nf:
netfilter: nf_conntrack_h323: Add protection for bmp length out of range
netfilter: nf_tables: mark set as dead when unbinding anonymous set with timeout
netfilter: nft_ct: fix l3num expectations with inet pseudo family
netfilter: nf_tables: reject constant set with timeout
netfilter: nf_tables: disallow anonymous set with timeout flag
====================
====================
netrom: Fix all the data-races around sysctls
As the title said, in this patchset I fix the data-race issues because
the writer and the reader can manipulate the same value concurrently.
====================
projects / mirror_ubuntu-kernels.git / log