[ Upstream commit b650d953cd ]
Under certain circumstances, the tcp receive buffer memory limit
set by autotuning (sk_rcvbuf) is increased due to incoming data
packets as a result of the window not closing when it should be.
This can result in the receive buffer growing all the way up to
tcp_rmem[2], even for tcp sessions with a low BDP.
To reproduce: Connect a TCP session with the receiver doing
nothing and the sender sending small packets (an infinite loop
of socket send() with 4 bytes of payload with a sleep of 1 ms
in between each send()). This will cause the tcp receive buffer
to grow all the way up to tcp_rmem[2].
As a result, a host can have individual tcp sessions with receive
buffers of size tcp_rmem[2], and the host itself can reach tcp_mem
limits, causing the host to go into tcp memory pressure mode.
The fundamental issue is the relationship between the granularity
of the window scaling factor and the number of byte ACKed back
to the sender. This problem has previously been identified in
RFC 7323, appendix F [1].
The Linux kernel currently adheres to never shrinking the window.
In addition to the overallocation of memory mentioned above, the
current behavior is functionally incorrect, because once tcp_rmem[2]
is reached when no remediations remain (i.e. tcp collapse fails to
free up any more memory and there are no packets to prune from the
out-of-order queue), the receiver will drop in-window packets
resulting in retransmissions and an eventual timeout of the tcp
session. A receive buffer full condition should instead result
in a zero window and an indefinite wait.
In practice, this problem is largely hidden for most flows. It
is not applicable to mice flows. Elephant flows can send data
fast enough to "overrun" the sk_rcvbuf limit (in a single ACK),
triggering a zero window.
But this problem does show up for other types of flows. Examples
are websockets and other type of flows that send small amounts of
data spaced apart slightly in time. In these cases, we directly
encounter the problem described in [1].
RFC 7323, section 2.4 [2], says there are instances when a retracted
window can be offered, and that TCP implementations MUST ensure
that they handle a shrinking window, as specified in RFC 1122,
section 4.2.2.16 [3]. All prior RFCs on the topic of tcp window
management have made clear that sender must accept a shrunk window
from the receiver, including RFC 793 [4] and RFC 1323 [5].
This patch implements the functionality to shrink the tcp window
when necessary to keep the right edge within the memory limit by
autotuning (sk_rcvbuf). This new functionality is enabled with
the new sysctl: net.ipv4.tcp_shrink_window
Additional information can be found at:
https://blog.cloudflare.com/unbounded-memory-usage-by-tcp-for-receive-buffers-and-how-we-fixed-it/
[1] https://www.rfc-editor.org/rfc/rfc7323#appendix-F
[2] https://www.rfc-editor.org/rfc/rfc7323#section-2.4
[3] https://www.rfc-editor.org/rfc/rfc1122#page-91
[4] https://www.rfc-editor.org/rfc/rfc793
[5] https://www.rfc-editor.org/rfc/rfc1323
Signed-off-by: Mike Freemon <mfreemon@cloudflare.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 5027d54a9c upstream.
accept_ra_min_rtr_lft only considered the lifetime of the default route
and discarded entire RAs accordingly.
This change renames accept_ra_min_rtr_lft to accept_ra_min_lft, and
applies the value to individual RA sections; in particular, router
lifetime, PIO preferred lifetime, and RIO lifetime. If any of those
lifetimes are lower than the configured value, the specific RA section
is ignored.
In order for the sysctl to be useful to Android, it should really apply
to all lifetimes in the RA, since that is what determines the minimum
frequency at which RAs must be processed by the kernel. Android uses
hardware offloads to drop RAs for a fraction of the minimum of all
lifetimes present in the RA (some networks have very frequent RAs (5s)
with high lifetimes (2h)). Despite this, we have encountered networks
that set the router lifetime to 30s which results in very frequent CPU
wakeups. Instead of disabling IPv6 (and dropping IPv6 ethertype in the
WiFi firmware) entirely on such networks, it seems better to ignore the
misconfigured routers while still processing RAs from other IPv6 routers
on the same network (i.e. to support IoT applications).
The previous implementation dropped the entire RA based on router
lifetime. This turned out to be hard to expand to the other lifetimes
present in the RA in a consistent manner; dropping the entire RA based
on RIO/PIO lifetimes would essentially require parsing the whole thing
twice.
Fixes: 1671bcfd76 ("net: add sysctl accept_ra_min_rtr_lft")
Cc: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: Patrick Rohr <prohr@google.com>
Reviewed-by: Maciej Żenczykowski <maze@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230726230701.919212-1-prohr@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 1671bcfd76 upstream.
This change adds a new sysctl accept_ra_min_rtr_lft to specify the
minimum acceptable router lifetime in an RA. If the received RA router
lifetime is less than the configured value (and not 0), the RA is
ignored.
This is useful for mobile devices, whose battery life can be impacted
by networks that configure RAs with a short lifetime. On such networks,
the device should never gain IPv6 provisioning and should attempt to
drop RAs via hardware offload, if available.
Signed-off-by: Patrick Rohr <prohr@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit f7306acec9 ]
Initial creation of an AF_XDP socket requires CAP_NET_RAW capability. A
privileged process might create the socket and pass it to a non-privileged
process for later use. However, that process will be able to bind the socket
to any network interface. Even though it will not be able to receive any
traffic without modification of the BPF map, the situation is not ideal.
Sockets already have a mechanism that can be used to restrict what interface
they can be attached to. That is SO_BINDTODEVICE.
To change the SO_BINDTODEVICE binding the process will need CAP_NET_RAW.
Make xsk_bind() honor the SO_BINDTODEVICE in order to allow safer workflow
when non-privileged process is using AF_XDP.
The intended workflow is following:
1. First process creates a bare socket with socket(AF_XDP, ...).
2. First process loads the XSK program to the interface.
3. First process adds the socket fd to a BPF map.
4. First process ties socket fd to a particular interface using
SO_BINDTODEVICE.
5. First process sends socket fd to a second process.
6. Second process allocates UMEM.
7. Second process binds socket to the interface with bind(...).
8. Second process sends/receives the traffic.
All the steps above are possible today if the first process is privileged
and the second one has sufficient RLIMIT_MEMLOCK and no capabilities.
However, the second process will be able to bind the socket to any interface
it wants on step 7 and send traffic from it. With the proposed change, the
second process will be able to bind the socket only to a specific interface
chosen by the first process at step 4.
Fixes: 965a990984 ("xsk: add support for bind for Rx")
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Magnus Karlsson <magnus.karlsson@intel.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://lore.kernel.org/bpf/20230703175329.3259672-1-i.maximets@ovn.org
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit e209fee411 ]
With this commit, all the GIDs ("0 4294967294") can be written to the
"net.ipv4.ping_group_range" sysctl.
Note that 4294967295 (0xffffffff) is an invalid GID (see gid_valid() in
include/linux/uidgid.h), and an attempt to register this number will cause
-EINVAL.
Prior to this commit, only up to GID 2147483647 could be covered.
Documentation/networking/ip-sysctl.rst had "0 4294967295" as an example
value, but this example was wrong and causing -EINVAL.
Fixes: c319b4d76b ("net: ipv4: add IPPROTO_ICMP socket kind")
Co-developed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Akihiro Suda <akihiro.suda.cz@hco.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit dc5110c2d9 ]
UBSAN: shift-out-of-bounds in net/ipv4/tcp_input.c:555:23
shift exponent 255 is too large for 32-bit type 'int'
CPU: 1 PID: 7907 Comm: ssh Not tainted 6.3.0-rc4-00161-g62bad54b26db-dirty #206
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014
Call Trace:
<TASK>
dump_stack_lvl+0x136/0x150
__ubsan_handle_shift_out_of_bounds+0x21f/0x5a0
tcp_init_transfer.cold+0x3a/0xb9
tcp_finish_connect+0x1d0/0x620
tcp_rcv_state_process+0xd78/0x4d60
tcp_v4_do_rcv+0x33d/0x9d0
__release_sock+0x133/0x3b0
release_sock+0x58/0x1b0
'maxwin' is int, shifting int for 32 or more bits is undefined behaviour.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
The documentation refers to invalid web page under www.linuxfoundation.org
The patch refers to a working URL under wiki.linuxfoundation.org
Signed-off-by: Nir Levy <bhr166@gmail.com>
Link: https://lore.kernel.org/all/20221120220630.7443-1-bhr166@gmail.com/
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
-----BEGIN PGP SIGNATURE-----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=M+mV
-----END PGP SIGNATURE-----
Merge tag 'random-6.1-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random
Pull more random number generator updates from Jason Donenfeld:
"This time with some large scale treewide cleanups.
The intent of this pull is to clean up the way callers fetch random
integers. The current rules for doing this right are:
- If you want a secure or an insecure random u64, use get_random_u64()
- If you want a secure or an insecure random u32, use get_random_u32()
The old function prandom_u32() has been deprecated for a while
now and is just a wrapper around get_random_u32(). Same for
get_random_int().
- If you want a secure or an insecure random u16, use get_random_u16()
- If you want a secure or an insecure random u8, use get_random_u8()
- If you want secure or insecure random bytes, use get_random_bytes().
The old function prandom_bytes() has been deprecated for a while
now and has long been a wrapper around get_random_bytes()
- If you want a non-uniform random u32, u16, or u8 bounded by a
certain open interval maximum, use prandom_u32_max()
I say "non-uniform", because it doesn't do any rejection sampling
or divisions. Hence, it stays within the prandom_*() namespace, not
the get_random_*() namespace.
I'm currently investigating a "uniform" function for 6.2. We'll see
what comes of that.
By applying these rules uniformly, we get several benefits:
- By using prandom_u32_max() with an upper-bound that the compiler
can prove at compile-time is ≤65536 or ≤256, internally
get_random_u16() or get_random_u8() is used, which wastes fewer
batched random bytes, and hence has higher throughput.
- By using prandom_u32_max() instead of %, when the upper-bound is
not a constant, division is still avoided, because
prandom_u32_max() uses a faster multiplication-based trick instead.
- By using get_random_u16() or get_random_u8() in cases where the
return value is intended to indeed be a u16 or a u8, we waste fewer
batched random bytes, and hence have higher throughput.
This series was originally done by hand while I was on an airplane
without Internet. Later, Kees and I worked on retroactively figuring
out what could be done with Coccinelle and what had to be done
manually, and then we split things up based on that.
So while this touches a lot of files, the actual amount of code that's
hand fiddled is comfortably small"
* tag 'random-6.1-rc1-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/crng/random:
prandom: remove unused functions
treewide: use get_random_bytes() when possible
treewide: use get_random_u32() when possible
treewide: use get_random_{u8,u16}() when possible, part 2
treewide: use get_random_{u8,u16}() when possible, part 1
treewide: use prandom_u32_max() when possible, part 2
treewide: use prandom_u32_max() when possible, part 1
The prandom_u32() function has been a deprecated inline wrapper around
get_random_u32() for several releases now, and compiles down to the
exact same code. Replace the deprecated wrapper with a direct call to
the real function. The same also applies to get_random_int(), which is
just a wrapper around get_random_u32(). This was done as a basic find
and replace.
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Yury Norov <yury.norov@gmail.com>
Reviewed-by: Jan Kara <jack@suse.cz> # for ext4
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk> # for sch_cake
Acked-by: Chuck Lever <chuck.lever@oracle.com> # for nfsd
Acked-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com> # for thunderbolt
Acked-by: Darrick J. Wong <djwong@kernel.org> # for xfs
Acked-by: Helge Deller <deller@gmx.de> # for parisc
Acked-by: Heiko Carstens <hca@linux.ibm.com> # for s390
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Add interface to support Power Sourcing Equipment. At current step it
provides generic way to address all variants of PSE devices as defined
in IEEE 802.3-2018 but support only objects specified for IEEE 802.3-2018 104.4
PoDL Power Sourcing Equipment (PSE).
Currently supported and mandatory objects are:
IEEE 802.3-2018 30.15.1.1.3 aPoDLPSEPowerDetectionStatus
IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState
IEEE 802.3-2018 30.15.1.2.1 acPoDLPSEAdminControl
This is minimal interface needed to control PSE on each separate
ethernet port but it provides not all mandatory objects specified in
IEEE 802.3-2018.
Since "PoDL PSE" and "PSE" have similar names, but some different values
I decide to not merge them and keep separate naming schema. This should
allow as to be as close to IEEE 802.3 spec as possible and avoid name
conflicts in the future.
This implementation is connected to PHYs instead of MACs because PSE
auto classification can potentially interfere with PHY auto negotiation.
So, may be some extra PHY related initialization will be needed.
With WIP version of ethtools interaction with PSE capable link looks
as following:
$ ip l
...
5: t1l1@eth0: <BROADCAST,MULTICAST> ..
...
$ ethtool --show-pse t1l1
PSE attributs for t1l1:
PoDL PSE Admin State: disabled
PoDL PSE Power Detection Status: disabled
$ ethtool --set-pse t1l1 podl-pse-admin-control enable
$ ethtool --show-pse t1l1
PSE attributs for t1l1:
PoDL PSE Admin State: enabled
PoDL PSE Power Detection Status: delivering power
Signed-off-by: kernel test robot <lkp@intel.com>
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This adds support for rate matching (also known as rate adaptation) to
the phy subsystem. The general idea is that the phy interface runs at
one speed, and the MAC throttles the rate at which it sends packets to
the link speed. There's a good overview of several techniques for
achieving this at [1]. This patch adds support for three: pause-frame
based (such as in Aquantia phys), CRS-based (such as in 10PASS-TS and
2BASE-TL), and open-loop-based (such as in 10GBASE-W).
This patch makes a few assumptions and a few non assumptions about the
types of rate matching available. First, it assumes that different phys
may use different forms of rate matching. Second, it assumes that phys
can use rate matching for any of their supported link speeds (e.g. if a
phy supports 10BASE-T and XGMII, then it can adapt XGMII to 10BASE-T).
Third, it does not assume that all interface modes will use the same
form of rate matching. Fourth, it does not assume that all phy devices
will support rate matching (even if some do). Relaxing or strengthening
these (non-)assumptions could result in a different API. For example, if
all interface modes were assumed to use the same form of rate matching,
then a bitmask of interface modes supportting rate matching would
suffice.
For some better visibility into the process, the current rate matching
mode is exposed as part of the ethtool ksettings. For the moment, only
read access is supported. I'm not sure what userspace might want to
configure yet (disable it altogether, disable just one mode, specify the
mode to use, etc.). For the moment, since only pause-based rate
adaptation support is added in the next few commits, rate matching can
be disabled altogether by adjusting the advertisement.
802.3 calls this feature "rate adaptation" in clause 49 (10GBASE-R) and
"rate matching" in clause 61 (10PASS-TL and 2BASE-TS). Aquantia also calls
this feature "rate adaptation". I chose "rate matching" because it is
shorter, and because Russell doesn't think "adaptation" is correct in this
context.
Signed-off-by: Sean Anderson <sean.anderson@seco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, SMC uses smc->sk.sk_{rcv|snd}buf to create buffers for
send buffer and RMB. And the values of buffer size are from tcp_{w|r}mem
in clcsock.
The buffer size from TCP socket doesn't fit SMC well. Generally, buffers
are usually larger than TCP for SMC-R/-D to get higher performance, for
they are different underlay devices and paths.
So this patch unbinds buffer size from TCP, and introduces two sysctl
knobs to tune them independently. Also, these knobs are per net
namespace and work for containers.
Signed-off-by: Tony Lu <tonylu@linux.alibaba.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
SMC-R tests the viability of link by sending out TEST_LINK LLC
messages over RoCE fabric when connections on link have been
idle for a time longer than keepalive interval (testlink time).
But using tcp_keepalive_time as testlink time maybe not quite
suitable because it is default no less than two hours[1], which
is too long for single link to find peer dead. The active host
will still use peer-dead link (QP) sending messages, and can't
find out until get IB_WC_RETRY_EXC_ERR error CQEs, which takes
more time than TEST_LINK timeout (SMC_LLC_WAIT_TIME) normally.
So this patch introduces a independent sysctl for SMC-R to set
link keepalive time, in order to detect link down in time. The
default value is 30 seconds.
[1] https://www.rfc-editor.org/rfc/rfc1122#page-101
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
There's no clear explanation of what VF Representors are for, their
semantics, etc., outside of vendor docs and random conference slides.
Add a document explaining Representors and defining what drivers that
implement them are expected to do.
Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Link: https://lore.kernel.org/r/20220905135557.39233-1-ecree@xilinx.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This toggle has been already remove by b118509076 ("netfilter: remove
nf_conntrack_helper sysctl and modparam toggles").
Remove the documentation entry for this toggle too.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Florian Westphal <fw@strlen.de>
The more sockets we have in the hash table, the longer we spend looking
up the socket. While running a number of small workloads on the same
host, they penalise each other and cause performance degradation.
The root cause might be a single workload that consumes much more
resources than the others. It often happens on a cloud service where
different workloads share the same computing resource.
On EC2 c5.24xlarge instance (196 GiB memory and 524288 (1Mi / 2) ehash
entries), after running iperf3 in different netns, creating 24Mi sockets
without data transfer in the root netns causes about 10% performance
regression for the iperf3's connection.
thash_entries sockets length Gbps
524288 1 1 50.7
24Mi 48 45.1
It is basically related to the length of the list of each hash bucket.
For testing purposes to see how performance drops along the length,
I set 131072 (1Mi / 8) to thash_entries, and here's the result.
thash_entries sockets length Gbps
131072 1 1 50.7
1Mi 8 49.9
2Mi 16 48.9
4Mi 32 47.3
8Mi 64 44.6
16Mi 128 40.6
24Mi 192 36.3
32Mi 256 32.5
40Mi 320 27.0
48Mi 384 25.0
To resolve the socket lookup degradation, we introduce an optional
per-netns hash table for TCP, but it's just ehash, and we still share
the global bhash, bhash2 and lhash2.
With a smaller ehash, we can look up non-listener sockets faster and
isolate such noisy neighbours. In addition, we can reduce lock contention.
We can control the ehash size by a new sysctl knob. However, depending
on workloads, it will require very sensitive tuning, so we disable the
feature by default (net.ipv4.tcp_child_ehash_entries == 0). Moreover,
we can fall back to using the global ehash in case we fail to allocate
enough memory for a new ehash. The maximum size is 16Mi, which is large
enough that even if we have 48Mi sockets, the average list length is 3,
and regression would be less than 1%.
We can check the current ehash size by another read-only sysctl knob,
net.ipv4.tcp_ehash_entries. A negative value means the netns shares
the global ehash (per-netns ehash is disabled or failed to allocate
memory).
# dmesg | cut -d ' ' -f 5- | grep "established hash"
TCP established hash table entries: 524288 (order: 10, 4194304 bytes, vmalloc hugepage)
# sysctl net.ipv4.tcp_ehash_entries
net.ipv4.tcp_ehash_entries = 524288 # can be changed by thash_entries
# sysctl net.ipv4.tcp_child_ehash_entries
net.ipv4.tcp_child_ehash_entries = 0 # disabled by default
# ip netns add test1
# ip netns exec test1 sysctl net.ipv4.tcp_ehash_entries
net.ipv4.tcp_ehash_entries = -524288 # share the global ehash
# sysctl -w net.ipv4.tcp_child_ehash_entries=100
net.ipv4.tcp_child_ehash_entries = 100
# ip netns add test2
# ip netns exec test2 sysctl net.ipv4.tcp_ehash_entries
net.ipv4.tcp_ehash_entries = 128 # own a per-netns ehash with 2^n buckets
When more than two processes in the same netns create per-netns ehash
concurrently with different sizes, we need to guarantee the size in
one of the following ways:
1) Share the global ehash and create per-netns ehash
First, unshare() with tcp_child_ehash_entries==0. It creates dedicated
netns sysctl knobs where we can safely change tcp_child_ehash_entries
and clone()/unshare() to create a per-netns ehash.
2) Control write on sysctl by BPF
We can use BPF_PROG_TYPE_CGROUP_SYSCTL to allow/deny read/write on
sysctl knobs.
Note that the global ehash allocated at the boot time is spread over
available NUMA nodes, but inet_pernet_hashinfo_alloc() will allocate
pages for each per-netns ehash depending on the current process's NUMA
policy. By default, the allocation is done in the local node only, so
the per-netns hash table could fully reside on a random node. Thus,
depending on the NUMA policy the netns is created with and the CPU the
current thread is running on, we could see some performance differences
for highly optimised networking applications.
Note also that the default values of two sysctl knobs depend on the ehash
size and should be tuned carefully:
tcp_max_tw_buckets : tcp_child_ehash_entries / 2
tcp_max_syn_backlog : max(128, tcp_child_ehash_entries / 128)
As a bonus, we can dismantle netns faster. Currently, while destroying
netns, we call inet_twsk_purge(), which walks through the global ehash.
It can be potentially big because it can have many sockets other than
TIME_WAIT in all netns. Splitting ehash changes that situation, where
it's only necessary for inet_twsk_purge() to clean up TIME_WAIT sockets
in each netns.
With regard to this, we do not free the per-netns ehash in inet_twsk_kill()
to avoid UAF while iterating the per-netns ehash in inet_twsk_purge().
Instead, we do it in tcp_sk_exit_batch() after calling tcp_twsk_purge() to
keep it protocol-family-independent.
In the future, we could optimise ehash lookup/iteration further by removing
netns comparison for the per-netns ehash.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
DSA now supports multiple CPU ports, explain the use cases that are
covered, the new UAPI, the permitted degrees of freedom, the driver API,
and remove some old "hanging fruits".
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
-----BEGIN PGP SIGNATURE-----
iQFHBAABCgAxFiEEBsvAIBsPu6mG7thcrX5LkNig010FAmMi3OwTHG1rbEBwZW5n
dXRyb25peC5kZQAKCRCtfkuQ2KDTXafhCACHLzDn9otKPWe+w6Lt1RSuhKvhbuhO
XywQ4EBEUddOrqYarEuFiuWZMq1/PLGnkWVQotzElZR9HtkTUUetXgfsWHv39uo+
SqUK7P+DnuT9AvvUkk1ZoyVYxs8FnVWoPlcBli+zXZCjtg/XYn/2qPGJlaNPovLv
hzVokS/RVxlPIrQiNWVmkHyTb6LyLdLit802dtdaxKmQcUCgYVAiz+DwR0PwBEWs
e1K046RIfl5QejpkVq+pIXpTGu1C4m2bv1umPCts1OLtBGkHf7Dwu9HmgWPDwY91
0oJt/00NpQLgg77vnOJnv0M/TZE9cP9gp7zFh7b43qg0TpIzHhJJYJut
=UEkq
-----END PGP SIGNATURE-----
Merge tag 'linux-can-next-for-6.1-20220915' of git://git.kernel.org/pub/scm/linux/kernel/git/mkl/linux-can-next
Marc Kleine-Budde says:
====================
Sept. 15, 2022, 8:19 a.m. UTC
Hello Jakub, hello David,
this is a pull request of 23 patches for net-next/master.
the first 2 patches are by me and fix a typo in the rx-offload helper
and the flexcan driver.
Christophe JAILLET's patch cleans up the error handling in
rcar_canfd driver's probe function.
Kenneth Lee's patch converts the kvaser_usb driver from kcalloc() to
kzalloc().
Biju Das contributes 2 patches to the sja1000 driver which update the
DT bindings and support for the RZ/N1 SJA1000 CAN controller.
Jinpeng Cui provides 2 patches that remove redundant variables from
the sja1000 and kvaser_pciefd driver.
2 patches by John Whittington and me add hardware timestamp support to
the gs_usb driver.
Gustavo A. R. Silva's patch converts the etas_es58x driver to make use
of DECLARE_FLEX_ARRAY().
Krzysztof Kozlowski's patch cleans up the sja1000 DT bindings.
Dario Binacchi fixes his invalid email in the flexcan driver
documentation.
Ziyang Xuan contributes 2 patches that clean up the CAN RAW protocol.
Yang Yingliang's patch switches the flexcan driver to dev_err_probe().
The last 7 patches are by Oliver Hartkopp and add support for the next
generation of the CAN protocol: CAN with eXtended data Length (CAN XL).
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
drivers/net/ethernet/freescale/fec.h
7d650df99d ("net: fec: add pm_qos support on imx6q platform")
40c79ce13b ("net: fec: add stop mode support for imx8 platform")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Add 1000BASE-KX interface mode. This 1G backplane ethernet as described in
clause 70. Clause 73 autonegotiation is mandatory, and only full duplex
operation is supported.
Although at the PMA level this interface mode is identical to
1000BASE-X, it uses a different form of in-band autonegation. This
justifies a separate interface mode, since the interface mode (along
with the MLO_AN_* autonegotiation mode) sets the type of autonegotiation
which will be used on a link. This results in more than just electrical
differences between the link modes.
With regard to 1000BASE-X, 1000BASE-KX holds a similar position to
SGMII: same signaling, but different autonegotiation. PCS drivers
(which typically handle in-band autonegotiation) may only support
1000BASE-X, and not 1000BASE-KX. Similarly, the phy mode is used to
configure serdes phys with phy_set_mode_ext. Due to the different
electrical standards (SFI or XFI vs Clause 70), they will likely want to
use different configuration. Adding a phy interface mode for
1000BASE-KX helps simplify configuration in these areas.
Signed-off-by: Sean Anderson <sean.anderson@seco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-----BEGIN PGP SIGNATURE-----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=GW48
-----END PGP SIGNATURE-----
Merge tag 'rxrpc-fixes-20220901' of git://git.kernel.org/pub/scm/linux/kernel/git/dhowells/linux-fs
David Howells says:
====================
rxrpc fixes
Here are some fixes for AF_RXRPC:
(1) Fix the handling of ICMP/ICMP6 packets. This is a problem due to
rxrpc being switched to acting as a UDP tunnel, thereby allowing it to
steal the packets before they go through the UDP Rx queue. UDP
tunnels can't get ICMP/ICMP6 packets, however. This patch adds an
additional encap hook so that they can.
(2) Fix the encryption routines in rxkad to handle packets that have more
than three parts correctly. The problem is that ->nr_frags doesn't
count the initial fragment, so the sglist ends up too short.
(3) Fix a problem with destruction of the local endpoint potentially
getting repeated.
(4) Fix the calculation of the time at which to resend.
jiffies_to_usecs() gives microseconds, not nanoseconds.
(5) Fix AFS to work out when callback promises and locks expire based on
the time an op was issued rather than the time the first reply packet
arrives. We don't know how long the server took between calculating
the expiry interval and transmitting the reply.
(6) Given (5), rxrpc_get_reply_time() is no longer used, so remove it.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Remove rxrpc_get_reply_time() as that is no longer used now that the call
issue time is used instead of the reply time.
Signed-off-by: David Howells <dhowells@redhat.com>
Because per host rate limiting has been proven problematic (side channel
attacks can be based on it), per host rate limiting of challenge acks ideally
should be per netns and turned off by default.
This is a long due followup of following commits:
083ae30828 ("tcp: enable per-socket rate limiting of all 'challenge acks'")
f2b2c582e8 ("tcp: mitigate ACK loops for connections as tcp_sock")
75ff39ccc1 ("tcp: make challenge acks less predictable")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Jason Baron <jbaron@akamai.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Change occurrences of "it's" that are possessive to "its"
so that they don't read as "it is".
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20220829235414.17110-1-rdunlap@infradead.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
tlb_dynamic_lb bonding option is compatible with balance-tlb and balance-alb
modes. In order to be consistent with other option documentation, it should
mention both modes not only balance-tlb.
Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net>
Acked-by: Jay Vosburgh <jay.vosburgh@canonical.com>
Link: https://lore.kernel.org/r/20220826154738.4039-1-ffmancera@riseup.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Tony Nguyen says:
====================
Intel Wired LAN Driver Updates 2022-08-24 (ice)
This series contains updates to ice driver only.
Marcin adds support for TC parsing on TTL and ToS fields.
Anatolli adds support for devlink port split command to allow
configuration of various port configurations.
Jake allows for passing and writing an additional NVM write activate
field by expanding current cmd_flag.
Ani makes PHY debug output more readable.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
As all callbacks are converted now, fix the text reflecting that change.
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Link: https://lore.kernel.org/r/20220823070213.1008956-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Allow to configure port split options using the devlink port split
interface. Support port splitting only for port 0, as the FW has
a predefined set of available port split options for the whole device.
Add ice_devlink_port_options_print() function to print the table with
all available FW port split options. It will be printed after each port
split and unsplit command.
Add documentation for devlink port split interface usage for the ice
driver.
Co-developed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Signed-off-by: Anatolii Gerasymenko <anatolii.gerasymenko@intel.com>
Tested-by: Gurucharan <gurucharanx.g@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
DECnet is an obsolete network protocol that receives more attention
from kernel janitors than users. It belongs in computer protocol
history museum not in Linux kernel.
It has been "Orphaned" in kernel since 2010. The iproute2 support
for DECnet was dropped in 5.0 release. The documentation link on
Sourceforge says it is abandoned there as well.
Leave the UAPI alone to keep userspace programs compiling.
This means that there is still an empty neighbour table
for AF_DECNET.
The table of /proc/sys/net entries was updated to match
current directories and reformatted to be alphabetical.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Acked-by: David Ahern <dsahern@kernel.org>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
The QUSGMII mode is a derivative of Cisco's USXGMII standard. This
standard is pretty similar to SGMII, but allows for faster speeds, and
has the build-in bits for Quad and Octa variants (like QSGMII).
The main difference with SGMII/QSGMII is that USXGMII/QUSGMII re-uses
the preamble to carry various information, named 'Extensions'.
As of today, the USXGMII standard only mentions the "PCH" extension,
which is used to convey timestamps, allowing in-band signaling of PTP
timestamps without having to modify the frame itself.
This commit adds support for that mode. When no extension is in use, it
behaves exactly like QSGMII, although it's not compatible with QSGMII.
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Document the t7xx devlink commands usage for fw flashing &
coredump collection.
Refer to t7xx.rst file for details.
Signed-off-by: M Chetan Kumar <m.chetan.kumar@linux.intel.com>
Signed-off-by: Devegowda Chandrashekar <chandrashekar.devegowda@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ARP monitoring no longer depends on dev->last_rx or dev_trans_start(),
so delete this information.
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The tcp_reflect_tos option was introduced in Linux 5.10 but was still
undocumented.
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a framework for running selftests.
Framework exposes devlink commands and test suite(s) to the user
to execute and query the supported tests by the driver.
Below are new entries in devlink_nl_ops
devlink_nl_cmd_selftests_show_doit/dumpit: To query the supported
selftests by the drivers.
devlink_nl_cmd_selftests_run: To execute selftests. Users can
provide a test mask for executing group tests or standalone tests.
Documentation/networking/devlink/ path is already part of MAINTAINERS &
the new files come under this path. Hence no update needed to the
MAINTAINERS
Signed-off-by: Vikas Gupta <vikas.gupta@broadcom.com>
Reviewed-by: Andy Gospodarek <gospo@broadcom.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Use tunneled MGIR to obtain PSID of line card device and extend
device_info_get() op to fill up the info with that.
Example:
$ devlink dev info auxiliary/mlxsw_core.lc.0
auxiliary/mlxsw_core.lc.0:
versions:
fixed:
hw.revision 0
fw.psid MT_0000000749
running:
ini.version 4
fw 19.2010.1312
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In case the line card is active, go over all possible existing
devices (gearboxes) on it and expose FW version of the flashable one.
Example:
$ devlink dev info auxiliary/mlxsw_core.lc.0
auxiliary/mlxsw_core.lc.0:
versions:
fixed:
hw.revision 0
running:
ini.version 4
fw 19.2010.1312
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Implement info_get() to expose HW revision of a linecard and loaded INI
version.
Example:
$ devlink dev info auxiliary/mlxsw_core.lc.0
auxiliary/mlxsw_core.lc.0:
versions:
fixed:
hw.revision 0
running:
ini.version 4
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Since commit 1033990ac5 ("sctp: implement memory accounting on tx path"),
SCTP has supported memory accounting on tx path where 'sctp_wmem' is used
by sk_wmem_schedule(). So we should fix the description for this option in
ip-sysctl.rst accordingly.
v1->v2:
- Improve the description as Marcelo suggested.
Fixes: 1033990ac5 ("sctp: implement memory accounting on tx path")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Tony Nguyen says:
====================
100GbE Intel Wired LAN Driver Updates 2022-07-21
This series contains updates to ice driver only.
Karol adds implementation for GNSS write; data is written to the GNSS
module through TTY device using u-blox UBX protocol.
* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue:
ice: add write functionality for GNSS TTY
ice: add i2c write command
====================
Link: https://lore.kernel.org/r/20220721202842.3276257-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Add the possibility to write raw bytes to the GNSS module through the
first TTY device. This allows user to configure the module.
Create a second read-only TTY device.
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Gurucharan <gurucharanx.g@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
mfreemon@cloudflare.com