commit db53cd3d88dc328dea2e968c9c8d3b4294a8a674 upstream.
Ido reported that the commit referenced in the Fixes tag broke
a gre use case with dummy devices. Add a check to ip_tunnel_init_flow
to see if the oif is an l3mdev port and if so set the oif to 0 to
avoid the oif comparison in fib_lookup_good_nhc.
Fixes: 40867d74c374 ("net: Add l3mdev index to flow struct and avoid oif reset for port devices")
Reported-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 05ef7055debc804e8083737402127975e7244fc4 ]
We need to init l3mdev unconditionally, else main routing table is searched
and incorrect result is returned unless strict (iif keyword) matching is
requested.
Next patch adds a selftest for this.
Fixes: 2a8a7c0eaa87 ("netfilter: nft_fib: Fix for rpath check with VRF devices")
Closes: https://bugzilla.netfilter.org/show_bug.cgi?id=1761
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 1fcc064b305a1aadeff0d4bff961094d27660acd ]
Currently netfilter's rpfilter and fib modules implicitely initialise
->flowic_uid with 0. This is normally the root UID. However, this isn't
the case in user namespaces, where user ID 0 is mapped to a different
kernel UID. By initialising ->flowic_uid with sock_net_uid(), we get
the root UID of the user namespace, thus keeping the same behaviour
whether or not we're running in a user namepspace.
Note, this is similar to commit 8bcfd0925ef1 ("ipv4: add missing
initialization for flowi4_uid"), which fixed the rp_filter sysctl.
Fixes: 622ec2c9d524 ("net: core: add UID to flows, rules, and routes")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Stable-dep-of: 05ef7055debc ("netfilter: fib: check correct rtable in vrf setups")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit acc641ab95b66b813c1ce856c377a2bbe71e7f52 ]
Use the introduced field for correct operation with VRF devices instead
of conditionally overwriting flowic_oif. This is a partial revert of
commit b575b24b8eee3 ("netfilter: Fix rpfilter dropping vrf packets by
mistake"), implementing a simpler solution.
Signed-off-by: Phil Sutter <phil@nwl.cc>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Stable-dep-of: 05ef7055debc ("netfilter: fib: check correct rtable in vrf setups")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 40867d74c374b235e14d839f3a77f26684feefe5 ]
The fundamental premise of VRF and l3mdev core code is binding a socket
to a device (l3mdev or netdev with an L3 domain) to indicate L3 scope.
Legacy code resets flowi_oif to the l3mdev losing any original port
device binding. Ben (among others) has demonstrated use cases where the
original port device binding is important and needs to be retained.
This patch handles that by adding a new entry to the common flow struct
that can indicate the l3mdev index for later rule and table matching
avoiding the need to reset flowi_oif.
In addition to allowing more use cases that require port device binds,
this patch brings a few datapath simplications:
1. l3mdev_fib_rule_match is only called when walking fib rules and
always after l3mdev_update_flow. That allows an optimization to bail
early for non-VRF type uses cases when flowi_l3mdev is not set. Also,
only that index needs to be checked for the FIB table id.
2. l3mdev_update_flow can be called with flowi_oif set to a l3mdev
(e.g., VRF) device. By resetting flowi_oif only for this case the
FLOWI_FLAG_SKIP_NH_OIF flag is not longer needed and can be removed,
removing several checks in the datapath. The flowi_iif path can be
simplified to only be called if the it is not loopback (loopback can
not be assigned to an L3 domain) and the l3mdev index is not already
set.
3. Avoid another device lookup in the output path when the fib lookup
returns a reject failure.
Note: 2 functional tests for local traffic with reject fib rules are
updated to reflect the new direct failure at FIB lookup time for ping
rather than the failure on packet path. The current code fails like this:
HINT: Fails since address on vrf device is out of device scope
COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1
ping: Warning: source address might be selected on device other than: eth1
PING 172.16.3.1 (172.16.3.1) from 172.16.3.1 eth1: 56(84) bytes of data.
--- 172.16.3.1 ping statistics ---
1 packets transmitted, 0 received, 100% packet loss, time 0ms
where the test now directly fails:
HINT: Fails since address on vrf device is out of device scope
COMMAND: ip netns exec ns-A ping -c1 -w1 -I eth1 172.16.3.1
ping: connect: No route to host
Signed-off-by: David Ahern <dsahern@kernel.org>
Tested-by: Ben Greear <greearb@candelatech.com>
Link: https://lore.kernel.org/r/20220314204551.16369-1-dsahern@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 05ef7055debc ("netfilter: fib: check correct rtable in vrf setups")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit b41b4cbd9655bcebcce941bef3601db8110335be ]
Fix tcp_enter_recovery() so that if there are no retransmits out then
we zero retrans_stamp when entering fast recovery. This is necessary
to fix two buggy behaviors.
Currently a non-zero retrans_stamp value can persist across multiple
back-to-back loss recovery episodes. This is because we generally only
clears retrans_stamp if we are completely done with loss recoveries,
and get to tcp_try_to_open() and find !tcp_any_retrans_done(sk). This
behavior causes two bugs:
(1) When a loss recovery episode (CA_Loss or CA_Recovery) is followed
immediately by a new CA_Recovery, the retrans_stamp value can persist
and can be a time before this new CA_Recovery episode starts. That
means that timestamp-based undo will be using the wrong retrans_stamp
(a value that is too old) when comparing incoming TS ecr values to
retrans_stamp to see if the current fast recovery episode can be
undone.
(2) If there is a roughly minutes-long sequence of back-to-back fast
recovery episodes, one after another (e.g. in a shallow-buffered or
policed bottleneck), where each fast recovery successfully makes
forward progress and recovers one window of sequence space (but leaves
at least one retransmit in flight at the end of the recovery),
followed by several RTOs, then the ETIMEDOUT check may be using the
wrong retrans_stamp (a value set at the start of the first fast
recovery in the sequence). This can cause a very premature ETIMEDOUT,
killing the connection prematurely.
This commit changes the code to zero retrans_stamp when entering fast
recovery, when this is known to be safe (no retransmits are out in the
network). That ensures that when starting a fast recovery episode, and
it is safe to do so, retrans_stamp is set when we send the fast
retransmit packet. That addresses both bug (1) and bug (2) by ensuring
that (if no retransmits are out when we start a fast recovery) we use
the initial fast retransmit of this fast recovery as the time value
for undo and ETIMEDOUT calculations.
This makes intuitive sense, since the start of a new fast recovery
episode (in a scenario where no lost packets are out in the network)
means that the connection has made forward progress since the last RTO
or fast recovery, and we should thus "restart the clock" used for both
undo and ETIMEDOUT logic.
Note that if when we start fast recovery there *are* retransmits out
in the network, there can still be undesirable (1)/(2) issues. For
example, after this patch we can still have the (1) and (2) problems
in cases like this:
+ round 1: sender sends flight 1
+ round 2: sender receives SACKs and enters fast recovery 1,
retransmits some packets in flight 1 and then sends some new data as
flight 2
+ round 3: sender receives some SACKs for flight 2, notes losses, and
retransmits some packets to fill the holes in flight 2
+ fast recovery has some lost retransmits in flight 1 and continues
for one or more rounds sending retransmits for flight 1 and flight 2
+ fast recovery 1 completes when snd_una reaches high_seq at end of
flight 1
+ there are still holes in the SACK scoreboard in flight 2, so we
enter fast recovery 2, but some retransmits in the flight 2 sequence
range are still in flight (retrans_out > 0), so we can't execute the
new retrans_stamp=0 added here to clear retrans_stamp
It's not yet clear how to fix these remaining (1)/(2) issues in an
efficient way without breaking undo behavior, given that retrans_stamp
is currently used for undo and ETIMEDOUT. Perhaps the optimal (but
expensive) strategy would be to set retrans_stamp to the timestamp of
the earliest outstanding retransmit when entering fast recovery. But
at least this commit makes things better.
Note that this does not change the semantics of retrans_stamp; it
simply makes retrans_stamp accurate in some cases where it was not
before:
(1) Some loss recovery, followed by an immediate entry into a fast
recovery, where there are no retransmits out when entering the fast
recovery.
(2) When a TFO server has a SYNACK retransmit that sets retrans_stamp,
and then the ACK that completes the 3-way handshake has SACK blocks
that trigger a fast recovery. In this case when entering fast recovery
we want to zero out the retrans_stamp from the TFO SYNACK retransmit,
and set the retrans_stamp based on the timestamp of the fast recovery.
We introduce a tcp_retrans_stamp_cleanup() helper, because this
two-line sequence already appears in 3 places and is about to appear
in 2 more as a result of this bug fix patch series. Once this bug fix
patches series in the net branch makes it into the net-next branch
we'll update the 3 other call sites to use the new helper.
This is a long-standing issue. The Fixes tag below is chosen to be the
oldest commit at which the patch will apply cleanly, which is from
Linux v3.5 in 2012.
Fixes: 1fbc340514fc ("tcp: early retransmit: tcp_enter_recovery()")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20241001200517.2756803-3-ncardwell.sw@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit e37ab7373696e650d3b6262a5b882aadad69bb9e ]
Fix the TCP loss recovery undo logic in tcp_packet_delayed() so that
it can trigger undo even if TSQ prevents a fast recovery episode from
reaching tcp_retransmit_skb().
Geumhwan Yu <geumhwan.yu@samsung.com> recently reported that after
this commit from 2019:
commit bc9f38c8328e ("tcp: avoid unconditional congestion window undo
on SYN retransmit")
...and before this fix we could have buggy scenarios like the
following:
+ Due to reordering, a TCP connection receives some SACKs and enters a
spurious fast recovery.
+ TSQ prevents all invocations of tcp_retransmit_skb(), because many
skbs are queued in lower layers of the sending machine's network
stack; thus tp->retrans_stamp remains 0.
+ The connection receives a TCP timestamp ECR value echoing a
timestamp before the fast recovery, indicating that the fast
recovery was spurious.
+ The connection fails to undo the spurious fast recovery because
tp->retrans_stamp is 0, and thus tcp_packet_delayed() returns false,
due to the new logic in the 2019 commit: commit bc9f38c8328e ("tcp:
avoid unconditional congestion window undo on SYN retransmit")
This fix tweaks the logic to be more similar to the
tcp_packet_delayed() logic before bc9f38c8328e, except that we take
care not to be fooled by the FLAG_SYN_ACKED code path zeroing out
tp->retrans_stamp (the bug noted and fixed by Yuchung in
bc9f38c8328e).
Note that this returns the high-level behavior of tcp_packet_delayed()
to again match the comment for the function, which says: "Nothing was
retransmitted or returned timestamp is less than timestamp of the
first retransmission." Note that this comment is in the original
2005-04-16 Linux git commit, so this is evidently long-standing
behavior.
Fixes: bc9f38c8328e ("tcp: avoid unconditional congestion window undo on SYN retransmit")
Reported-by: Geumhwan Yu <geumhwan.yu@samsung.com>
Diagnosed-by: Geumhwan Yu <geumhwan.yu@samsung.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20241001200517.2756803-2-ncardwell.sw@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 0d9e5df4a257afc3a471a82961ace9a22b88295a ]
We found that one close-wait socket was reset by the other side
due to a new connection reusing the same port which is beyond our
expectation, so we have to investigate the underlying reason.
The following experiment is conducted in the test environment. We
limit the port range from 40000 to 40010 and delay the time to close()
after receiving a fin from the active close side, which can help us
easily reproduce like what happened in production.
Here are three connections captured by tcpdump:
127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965525191
127.0.0.1.9999 > 127.0.0.1.40002: Flags [S.], seq 2769915070
127.0.0.1.40002 > 127.0.0.1.9999: Flags [.], ack 1
127.0.0.1.40002 > 127.0.0.1.9999: Flags [F.], seq 1, ack 1
// a few seconds later, within 60 seconds
127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965590730
127.0.0.1.9999 > 127.0.0.1.40002: Flags [.], ack 2
127.0.0.1.40002 > 127.0.0.1.9999: Flags [R], seq 2965525193
// later, very quickly
127.0.0.1.40002 > 127.0.0.1.9999: Flags [S], seq 2965590730
127.0.0.1.9999 > 127.0.0.1.40002: Flags [S.], seq 3120990805
127.0.0.1.40002 > 127.0.0.1.9999: Flags [.], ack 1
As we can see, the first flow is reset because:
1) client starts a new connection, I mean, the second one
2) client tries to find a suitable port which is a timewait socket
(its state is timewait, substate is fin_wait2)
3) client occupies that timewait port to send a SYN
4) server finds a corresponding close-wait socket in ehash table,
then replies with a challenge ack
5) client sends an RST to terminate this old close-wait socket.
I don't think the port selection algo can choose a FIN_WAIT2 socket
when we turn on tcp_tw_reuse because on the server side there
remain unread data. In some cases, if one side haven't call close() yet,
we should not consider it as expendable and treat it at will.
Even though, sometimes, the server isn't able to call close() as soon
as possible like what we expect, it can not be terminated easily,
especially due to a second unrelated connection happening.
After this patch, we can see the expected failure if we start a
connection when all the ports are occupied in fin_wait2 state:
"Ncat: Cannot assign requested address."
Reported-by: Jade Dong <jadedong@tencent.com>
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240823001152.31004-1-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 8fed54758cd248cd311a2b5c1e180abef1866237 ]
The NETLINK_FIB_LOOKUP netlink family can be used to perform a FIB
lookup according to user provided parameters and communicate the result
back to user space.
However, unlike other users of the FIB lookup API, the upper DSCP bits
and the ECN bits of the DS field are not masked, which can result in the
wrong result being returned.
Solve this by masking the upper DSCP bits and the ECN bits using
IPTOS_RT_MASK.
The structure that communicates the request and the response is not
exported to user space, so it is unlikely that this netlink family is
actually in use [1].
[1] https://lore.kernel.org/netdev/ZpqpB8vJU%2FQ6LSqa@debian/
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit e3af3d3c5b26c33a7950e34e137584f6056c4319 ]
dev->ip_ptr could be NULL if we set an invalid MTU.
Even then, if we issue ioctl(SIOCSIFADDR) for a new IPv4 address,
devinet_ioctl() allocates struct in_ifaddr and fails later in
inet_set_ifa() because in_dev is NULL.
Let's move the check earlier.
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240809235406.50187-2-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit c4a14f6d9d17ad1e41a36182dd3b8a5fd91efbd7 ]
Regression Description:
Depending on the options specified for the GRE tunnel device, small
packets may be dropped. This occurs because the pskb_network_may_pull
function fails due to the packet's insufficient length.
For example, if only the okey option is specified for the tunnel device,
original (before encapsulation) packets smaller than 28 bytes (including
the IPv4 header) will be dropped. This happens because the required
length is calculated relative to the network header, not the skb->head.
Here is how the required length is computed and checked:
* The pull_len variable is set to 28 bytes, consisting of:
* IPv4 header: 20 bytes
* GRE header with Key field: 8 bytes
* The pskb_network_may_pull function adds the network offset, shifting
the checkable space further to the beginning of the network header and
extending it to the beginning of the packet. As a result, the end of
the checkable space occurs beyond the actual end of the packet.
Instead of ensuring that 28 bytes are present in skb->head, the function
is requesting these 28 bytes starting from the network header. For small
packets, this requested length exceeds the actual packet size, causing
the check to fail and the packets to be dropped.
This issue affects both locally originated and forwarded packets in
DMVPN-like setups.
How to reproduce (for local originated packets):
ip link add dev gre1 type gre ikey 1.9.8.4 okey 1.9.8.4 \
local <your-ip> remote 0.0.0.0
ip link set mtu 1400 dev gre1
ip link set up dev gre1
ip address add 192.168.13.1/24 dev gre1
ip neighbor add 192.168.13.2 lladdr <remote-ip> dev gre1
ping -s 1374 -c 10 192.168.13.2
tcpdump -vni gre1
tcpdump -vni <your-ext-iface> 'ip proto 47'
ip -s -s -d link show dev gre1
Solution:
Use the pskb_may_pull function instead the pskb_network_may_pull.
Fixes: 80d875cfc9d3 ("ipv4: ip_gre: Avoid skb_pull() failure in ipgre_xmit()")
Signed-off-by: Anton Danilov <littlesmilingcloud@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240924235158.106062-1-littlesmilingcloud@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 18685451fc4e546fc0e718580d32df3c0e5c8272 upstream.
ip_local_out() and other functions can pass skb->sk as function argument.
If the skb is a fragment and reassembly happens before such function call
returns, the sk must not be released.
This affects skb fragments reassembled via netfilter or similar
modules, e.g. openvswitch or ct_act.c, when run as part of tx pipeline.
Eric Dumazet made an initial analysis of this bug. Quoting Eric:
Calling ip_defrag() in output path is also implying skb_orphan(),
which is buggy because output path relies on sk not disappearing.
A relevant old patch about the issue was :
8282f27449bf ("inet: frag: Always orphan skbs inside ip_defrag()")
[..]
net/ipv4/ip_output.c depends on skb->sk being set, and probably to an
inet socket, not an arbitrary one.
If we orphan the packet in ipvlan, then downstream things like FQ
packet scheduler will not work properly.
We need to change ip_defrag() to only use skb_orphan() when really
needed, ie whenever frag_list is going to be used.
Eric suggested to stash sk in fragment queue and made an initial patch.
However there is a problem with this:
If skb is refragmented again right after, ip_do_fragment() will copy
head->sk to the new fragments, and sets up destructor to sock_wfree.
IOW, we have no choice but to fix up sk_wmem accouting to reflect the
fully reassembled skb, else wmem will underflow.
This change moves the orphan down into the core, to last possible moment.
As ip_defrag_offset is aliased with sk_buff->sk member, we must move the
offset into the FRAG_CB, else skb->sk gets clobbered.
This allows to delay the orphaning long enough to learn if the skb has
to be queued or if the skb is completing the reasm queue.
In the former case, things work as before, skb is orphaned. This is
safe because skb gets queued/stolen and won't continue past reasm engine.
In the latter case, we will steal the skb->sk reference, reattach it to
the head skb, and fix up wmem accouting when inet_frag inflates truesize.
Fixes: 7026b1ddb6b8 ("netfilter: Pass socket pointer down through okfn().")
Diagnosed-by: Eric Dumazet <edumazet@google.com>
Reported-by: xingwei lee <xrivendell7@gmail.com>
Reported-by: yue sun <samsun1006219@gmail.com>
Reported-by: syzbot+e5167d7144a62715044c@syzkaller.appspotmail.com
Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240326101845.30836-1-fw@strlen.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Saeed Mirzamohammadi <saeed.mirzamohammadi@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 4c8002277167125078e6b9b90137bdf443ebaa08 ]
The grc must be initialize first. There can be a condition where if
fou is NULL, goto out will be executed and grc would be used
uninitialized.
Fixes: 7e4196935069 ("fou: Fix null-ptr-deref in GRO.")
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240906102839.202798-1-usama.anjum@collabora.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 627b94f75b82d13d1530b59155a545fd99d807db ]
All gro_complete() handlers are called from napi_gro_complete()
while rcu_read_lock() has been called.
There is no point stacking more rcu_read_lock()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 7e4196935069 ("fou: Fix null-ptr-deref in GRO.")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit fc1ca3348a74a1afaa7ffebc2b2f2cc149e11278 ]
All gro_receive() handlers are called from dev_gro_receive()
while rcu_read_lock() has been called.
There is no point stacking more rcu_read_lock()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 7e4196935069 ("fou: Fix null-ptr-deref in GRO.")
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 871019b22d1bcc9fab2d1feba1b9a564acbb6e99 upstream.
We've started to see the following kernel traces:
WARNING: CPU: 83 PID: 0 at net/core/filter.c:6641 sk_lookup+0x1bd/0x1d0
Call Trace:
<IRQ>
__bpf_skc_lookup+0x10d/0x120
bpf_sk_lookup+0x48/0xd0
bpf_sk_lookup_tcp+0x19/0x20
bpf_prog_<redacted>+0x37c/0x16a3
cls_bpf_classify+0x205/0x2e0
tcf_classify+0x92/0x160
__netif_receive_skb_core+0xe52/0xf10
__netif_receive_skb_list_core+0x96/0x2b0
napi_complete_done+0x7b5/0xb70
<redacted>_poll+0x94/0xb0
net_rx_action+0x163/0x1d70
__do_softirq+0xdc/0x32e
asm_call_irq_on_stack+0x12/0x20
</IRQ>
do_softirq_own_stack+0x36/0x50
do_softirq+0x44/0x70
__inet_hash can race with lockless (rcu) readers on the other cpus:
__inet_hash
__sk_nulls_add_node_rcu
<- (bpf triggers here)
sock_set_flag(SOCK_RCU_FREE)
Let's move the SOCK_RCU_FREE part up a bit, before we are inserting
the socket into hashtables. Note, that the race is really harmless;
the bpf callers are handling this situation (where listener socket
doesn't have SOCK_RCU_FREE set) correctly, so the only
annoyance is a WARN_ONCE.
More details from Eric regarding SOCK_RCU_FREE timeline:
Commit 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under
synflood") added SOCK_RCU_FREE. At that time, the precise location of
sock_set_flag(sk, SOCK_RCU_FREE) did not matter, because the thread calling
__inet_hash() owns a reference on sk. SOCK_RCU_FREE was only tested
at dismantle time.
Commit 6acc9b432e67 ("bpf: Add helper to retrieve socket in BPF")
started checking SOCK_RCU_FREE _after_ the lookup to infer whether
the refcount has been taken care of.
Fixes: 6acc9b432e67 ("bpf: Add helper to retrieve socket in BPF")
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[Resolved conflict for 5.10 and below.]
Signed-off-by: Siddh Raman Pant <siddh.raman.pant@oracle.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 6d745cd0e9720282cd291d36b9db528aea18add2 ]
struct nexthop_grp contains two reserved fields that are not initialized by
nla_put_nh_group(), and carry garbage. This can be observed e.g. with
strace (edited for clarity):
# ip nexthop add id 1 dev lo
# ip nexthop add id 101 group 1
# strace -e recvmsg ip nexthop get id 101
...
recvmsg(... [{nla_len=12, nla_type=NHA_GROUP},
[{id=1, weight=0, resvd1=0x69, resvd2=0x67}]] ...) = 52
The fields are reserved and therefore not currently used. But as they are, they
leak kernel memory, and the fact they are not just zero complicates repurposing
of the fields for new ends. Initialize the full structure.
Fixes: 430a049190de ("nexthop: Add support for nexthop groups")
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.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>
[ Upstream commit cc73bbab4b1fb8a4f53a24645871dafa5f81266a ]
The Record Route IP option records the addresses of the routers that
routed the packet. In the case of forwarded packets, the kernel performs
a route lookup via fib_lookup() and fills in the preferred source
address of the matched route.
The lookup is performed with the DS field of the forwarded packet, but
using the RT_TOS() macro which only masks one of the two ECN bits. If
the packet is ECT(0) or CE, the matched route might be different than
the route via which the packet was forwarded as the input path masks
both of the ECN bits, resulting in the wrong address being filled in the
Record Route option.
Fix by masking both of the ECN bits.
Fixes: 8e36360ae876 ("ipv4: Remove route key identity dependencies in ip_rt_get_source().")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/20240718123407.434778-1-idosch@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 96f887a612e4cda89efc3f54bc10c1997e3ab0e9 ]
xmit() functions should consume skb or return error codes in error
paths.
When the configuration "CONFIG_INET_ESPINTCP" is not set, the
implementation of the function "esp_output_tail_tcp" violates this rule.
The function frees the skb and returns the error code.
This change removes the kfree_skb from both functions, for both
esp4 and esp6.
WARN_ON is added because esp_output_tail_tcp() should never be called if
CONFIG_INET_ESPINTCP is not set.
This bug was discovered and resolved using Coverity Static Analysis
Security Testing (SAST) by Synopsys, Inc.
Fixes: e27cca96cd68 ("xfrm: add espintcp (RFC 8229)")
Signed-off-by: Hagar Hemdan <hagarhem@amazon.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Forcing TCP no-delay will disable Nagle's algorithm, which basically collects small outgoing packets to send all at once. Disabling this will lead to all the packets being sent at their respective times, leading to better latency.
Read https://brooker.co.za/blog/2024/05/09/nagle.html for details.
Signed-off-by: prathamdubey2005 <134331217+prathamdubey2005@users.noreply.github.com>
commit 97a9063518f198ec0adb2ecb89789de342bb8283 upstream.
If a TCP socket is using TCP_USER_TIMEOUT, and the other peer
retracted its window to zero, tcp_retransmit_timer() can
retransmit a packet every two jiffies (2 ms for HZ=1000),
for about 4 minutes after TCP_USER_TIMEOUT has 'expired'.
The fix is to make sure tcp_rtx_probe0_timed_out() takes
icsk->icsk_user_timeout into account.
Before blamed commit, the socket would not timeout after
icsk->icsk_user_timeout, but would use standard exponential
backoff for the retransmits.
Also worth noting that before commit e89688e3e978 ("net: tcp:
fix unexcepted socket die when snd_wnd is 0"), the issue
would last 2 minutes instead of 4.
Fixes: b701a99e431d ("tcp: Add tcp_clamp_rto_to_user_timeout() helper to improve accuracy")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Jon Maxwell <jmaxwell37@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20240710001402.2758273-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 36534d3c54537bf098224a32dc31397793d4594d upstream.
Due to timer wheel implementation, a timer will usually fire
after its schedule.
For instance, for HZ=1000, a timeout between 512ms and 4s
has a granularity of 64ms.
For this range of values, the extra delay could be up to 63ms.
For TCP, this means that tp->rcv_tstamp may be after
inet_csk(sk)->icsk_timeout whenever the timer interrupt
finally triggers, if one packet came during the extra delay.
We need to make sure tcp_rtx_probe0_timed_out() handles this case.
Fixes: e89688e3e978 ("net: tcp: fix unexcepted socket die when snd_wnd is 0")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Menglong Dong <imagedong@tencent.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://lore.kernel.org/r/20240607125652.1472540-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 0ec986ed7bab6801faed1440e8839dcc710331ff ]
Loss recovery undo_retrans bookkeeping had a long-standing bug where a
DSACK from a spurious TLP retransmit packet could cause an erroneous
undo of a fast recovery or RTO recovery that repaired a single
really-lost packet (in a sequence range outside that of the TLP
retransmit). Basically, because the loss recovery state machine didn't
account for the fact that it sent a TLP retransmit, the DSACK for the
TLP retransmit could erroneously be implicitly be interpreted as
corresponding to the normal fast recovery or RTO recovery retransmit
that plugged a real hole, thus resulting in an improper undo.
For example, consider the following buggy scenario where there is a
real packet loss but the congestion control response is improperly
undone because of this bug:
+ send packets P1, P2, P3, P4
+ P1 is really lost
+ send TLP retransmit of P4
+ receive SACK for original P2, P3, P4
+ enter fast recovery, fast-retransmit P1, increment undo_retrans to 1
+ receive DSACK for TLP P4, decrement undo_retrans to 0, undo (bug!)
+ receive cumulative ACK for P1-P4 (fast retransmit plugged real hole)
The fix: when we initialize undo machinery in tcp_init_undo(), if
there is a TLP retransmit in flight, then increment tp->undo_retrans
so that we make sure that we receive a DSACK corresponding to the TLP
retransmit, as well as DSACKs for all later normal retransmits, before
triggering a loss recovery undo. Note that we also have to move the
line that clears tp->tlp_high_seq for RTO recovery, so that upon RTO
we remember the tp->tlp_high_seq value until tcp_init_undo() and clear
it only afterward.
Also note that the bug dates back to the original 2013 TLP
implementation, commit 6ba8a3b19e76 ("tcp: Tail loss probe (TLP)").
However, this patch will only compile and work correctly with kernels
that have tp->tlp_retrans, which was added only in v5.8 in 2020 in
commit 76be93fc0702 ("tcp: allow at most one TLP probe per flight").
So we associate this fix with that later commit.
Fixes: 76be93fc0702 ("tcp: allow at most one TLP probe per flight")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Kevin Yang <yyd@google.com>
Link: https://patch.msgid.link/20240703171246.1739561-1-ncardwell.sw@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit d8616ee2affcff37c5d315310da557a694a3303d upstream.
During TCP sockmap redirect pressure test, the following warning is triggered:
WARNING: CPU: 3 PID: 2145 at net/core/stream.c:205 sk_stream_kill_queues+0xbc/0xd0
CPU: 3 PID: 2145 Comm: iperf Kdump: loaded Tainted: G W 5.10.0+ #9
Call Trace:
inet_csk_destroy_sock+0x55/0x110
inet_csk_listen_stop+0xbb/0x380
tcp_close+0x41b/0x480
inet_release+0x42/0x80
__sock_release+0x3d/0xa0
sock_close+0x11/0x20
__fput+0x9d/0x240
task_work_run+0x62/0x90
exit_to_user_mode_prepare+0x110/0x120
syscall_exit_to_user_mode+0x27/0x190
entry_SYSCALL_64_after_hwframe+0x44/0xa9
The reason we observed is that:
When the listener is closing, a connection may have completed the three-way
handshake but not accepted, and the client has sent some packets. The child
sks in accept queue release by inet_child_forget()->inet_csk_destroy_sock(),
but psocks of child sks have not released.
To fix, add sock_map_destroy to release psocks.
Signed-off-by: Wang Yufen <wangyufen@huawei.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jakub Sitnicki <jakub@cloudflare.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20220524075311.649153-1-wangyufen@huawei.com
[ Conflict in include/linux/bpf.h due to function declaration position
and remove non-existed sk_psock_stop helper from sock_map_destroy. ]
Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 66be40e622e177316ae81717aa30057ba9e61dff ]
I don't see anything checking that TCP_METRICS_ATTR_SADDR_IPV4
is at least 4 bytes long, and the policy doesn't have an entry
for this attribute at all (neither does it for IPv6 but v6 is
manually validated).
Reviewed-by: Eric Dumazet <edumazet@google.com>
Fixes: 3e7013ddf55a ("tcp: metrics: Allow selective get/del of tcp-metrics based on src IP")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit a6458ab7fd4f427d4f6f54380453ad255b7fde83 ]
In some production workloads we noticed that connections could
sometimes close extremely prematurely with ETIMEDOUT after
transmitting only 1 TLP and RTO retransmission (when we would normally
expect roughly tcp_retries2 = TCP_RETR2 = 15 RTOs before a connection
closes with ETIMEDOUT).
From tracing we determined that these workloads can suffer from a
scenario where in fast recovery, after some retransmits, a DSACK undo
can happen at a point where the scoreboard is totally clear (we have
retrans_out == sacked_out == lost_out == 0). In such cases, calling
tcp_try_keep_open() means that we do not execute any code path that
clears tp->retrans_stamp to 0. That means that tp->retrans_stamp can
remain erroneously set to the start time of the undone fast recovery,
even after the fast recovery is undone. If minutes or hours elapse,
and then a TLP/RTO/RTO sequence occurs, then the start_ts value in
retransmits_timed_out() (which is from tp->retrans_stamp) will be
erroneously ancient (left over from the fast recovery undone via
DSACKs). Thus this ancient tp->retrans_stamp value can cause the
connection to die very prematurely with ETIMEDOUT via
tcp_write_err().
The fix: we change DSACK undo in fast recovery (TCP_CA_Recovery) to
call tcp_try_to_open() instead of tcp_try_keep_open(). This ensures
that if no retransmits are in flight at the time of DSACK undo in fast
recovery then we properly zero retrans_stamp. Note that calling
tcp_try_to_open() is more consistent with other loss recovery
behavior, since normal fast recovery (CA_Recovery) and RTO recovery
(CA_Loss) both normally end when tp->snd_una meets or exceeds
tp->high_seq and then in tcp_fastretrans_alert() the "default" switch
case executes tcp_try_to_open(). Also note that by inspection this
change to call tcp_try_to_open() implies at least one other nice bug
fix, where now an ECE-marked DSACK that causes an undo will properly
invoke tcp_enter_cwr() rather than ignoring the ECE mark.
Fixes: c7d9d6a185a7 ("tcp: undo on DSACK during recovery")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit f49cd2f4d6170d27a2c61f1fecb03d8a70c91f57 upstream.
setsockopt(IPV6_ADDRFORM) and tcp_v6_connect() change icsk->icsk_af_ops
under lock_sock(), but tcp_(get|set)sockopt() read it locklessly. To
avoid load/store tearing, we need to add READ_ONCE() and WRITE_ONCE()
for the reads and writes.
Thanks to Eric Dumazet for providing the syzbot report:
BUG: KCSAN: data-race in tcp_setsockopt / tcp_v6_connect
write to 0xffff88813c624518 of 8 bytes by task 23936 on cpu 0:
tcp_v6_connect+0x5b3/0xce0 net/ipv6/tcp_ipv6.c:240
__inet_stream_connect+0x159/0x6d0 net/ipv4/af_inet.c:660
inet_stream_connect+0x44/0x70 net/ipv4/af_inet.c:724
__sys_connect_file net/socket.c:1976 [inline]
__sys_connect+0x197/0x1b0 net/socket.c:1993
__do_sys_connect net/socket.c:2003 [inline]
__se_sys_connect net/socket.c:2000 [inline]
__x64_sys_connect+0x3d/0x50 net/socket.c:2000
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
read to 0xffff88813c624518 of 8 bytes by task 23937 on cpu 1:
tcp_setsockopt+0x147/0x1c80 net/ipv4/tcp.c:3789
sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3585
__sys_setsockopt+0x212/0x2b0 net/socket.c:2252
__do_sys_setsockopt net/socket.c:2263 [inline]
__se_sys_setsockopt net/socket.c:2260 [inline]
__x64_sys_setsockopt+0x62/0x70 net/socket.c:2260
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x2b/0x70 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x63/0xcd
value changed: 0xffffffff8539af68 -> 0xffffffff8539aff8
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 23937 Comm: syz-executor.5 Not tainted
6.0.0-rc4-syzkaller-00331-g4ed9c1e971b1-dirty #0
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS Google 08/26/2022
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot <syzkaller@googlegroups.com>
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Kazunori Kobayashi <kazunori.kobayashi@miraclelinux.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 364f997b5cfe1db0d63a390fe7c801fa2b3115f6 upstream.
Commit 086d49058cd8 ("ipv6: annotate some data-races around sk->sk_prot")
fixed some data-races around sk->sk_prot but it was not enough.
Some functions in inet6_(stream|dgram)_ops still access sk->sk_prot
without lock_sock() or rtnl_lock(), so they need READ_ONCE() to avoid
load tearing.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Kazunori Kobayashi <kazunori.kobayashi@miraclelinux.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 9f36169912331fa035d7b73a91252d7c2512eb1a ]
As evident from the definition of ip_options_get(), the IP option
IPOPT_END is used to pad the IP option data array, not IPOPT_NOP. Yet
the loop that walks the IP options to determine the total IP options
length in cipso_v4_delopt() doesn't take IPOPT_END into account.
Fix it by recognizing the IPOPT_END value as the end of actual options.
Fixes: 014ab19a69c3 ("selinux: Set socket NetLabel based on connection endpoint")
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit a46d0ea5c94205f40ecf912d1bb7806a8a64704f ]
According to RFC 1213, we should also take CLOSE-WAIT sockets into
consideration:
"tcpCurrEstab OBJECT-TYPE
...
The number of TCP connections for which the current state
is either ESTABLISHED or CLOSE- WAIT."
After this, CurrEstab counter will display the total number of
ESTABLISHED and CLOSE-WAIT sockets.
The logic of counting
When we increment the counter?
a) if we change the state to ESTABLISHED.
b) if we change the state from SYN-RECEIVED to CLOSE-WAIT.
When we decrement the counter?
a) if the socket leaves ESTABLISHED and will never go into CLOSE-WAIT,
say, on the client side, changing from ESTABLISHED to FIN-WAIT-1.
b) if the socket leaves CLOSE-WAIT, say, on the server side, changing
from CLOSE-WAIT to LAST-ACK.
Please note: there are two chances that old state of socket can be changed
to CLOSE-WAIT in tcp_fin(). One is SYN-RECV, the other is ESTABLISHED.
So we have to take care of the former case.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Jason Xing <kernelxing@tencent.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 92f1655aa2b2294d0b49925f3b875a634bd3b59e upstream.
__dst_negative_advice() does not enforce proper RCU rules when
sk->dst_cache must be cleared, leading to possible UAF.
RCU rules are that we must first clear sk->sk_dst_cache,
then call dst_release(old_dst).
Note that sk_dst_reset(sk) is implementing this protocol correctly,
while __dst_negative_advice() uses the wrong order.
Given that ip6_negative_advice() has special logic
against RTF_CACHE, this means each of the three ->negative_advice()
existing methods must perform the sk_dst_reset() themselves.
Note the check against NULL dst is centralized in
__dst_negative_advice(), there is no need to duplicate
it in various callbacks.
Many thanks to Clement Lecigne for tracking this issue.
This old bug became visible after the blamed commit, using UDP sockets.
Fixes: a87cb3e48ee8 ("net: Facility to report route quality of connected sockets")
Reported-by: Clement Lecigne <clecigne@google.com>
Diagnosed-by: Clement Lecigne <clecigne@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Tom Herbert <tom@herbertland.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20240528114353.1794151-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
[Lee: Stable backport]
Signed-off-by: Lee Jones <lee@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 21a673bddc8fd4873c370caf9ae70ffc6d47e8d3 ]
syzbot reports:
general protection fault, probably for non-canonical address 0xdffffc0000000003: 0000 [#1] PREEMPT SMP KASAN PTI
KASAN: null-ptr-deref in range [0x0000000000000018-0x000000000000001f]
[..]
RIP: 0010:nf_tproxy_laddr4+0xb7/0x340 net/ipv4/netfilter/nf_tproxy_ipv4.c:62
Call Trace:
nft_tproxy_eval_v4 net/netfilter/nft_tproxy.c:56 [inline]
nft_tproxy_eval+0xa9a/0x1a00 net/netfilter/nft_tproxy.c:168
__in_dev_get_rcu() can return NULL, so check for this.
Reported-and-tested-by: syzbot+b94a6818504ea90d7661@syzkaller.appspotmail.com
Fixes: cc6eb4338569 ("tproxy: use the interface primary IP address as a default value for --on-ip")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit ec00ed472bdb7d0af840da68c8c11bff9f4d9caa ]
While testing TCP performance with latest trees,
I saw suspect SOCKET_BACKLOG drops.
tcp_add_backlog() computes its limit with :
limit = (u32)READ_ONCE(sk->sk_rcvbuf) +
(u32)(READ_ONCE(sk->sk_sndbuf) >> 1);
limit += 64 * 1024;
This does not take into account that sk->sk_backlog.len
is reset only at the very end of __release_sock().
Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach
sk_rcvbuf in normal conditions.
We should double sk->sk_rcvbuf contribution in the formula
to absorb bubbles in the backlog, which happen more often
for very fast flows.
This change maintains decent protection against abuses.
Fixes: c377411f2494 ("net: sk_add_backlog() take rmem_alloc into account")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240423125620.3309458-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 50aee97d15113b95a68848db1f0cb2a6c09f753a ]
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 f0ea27e7bfe1 ("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: f0ea27e7bfe1 ("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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 0f495f7617229772403e683033abc473f0f0553c ]
There are currently four copies of reuseport_lookup: one each for
(TCP, UDP)x(IPv4, IPv6). This forces us to duplicate all callers of
those functions as well. This is already the case for sk_lookup
helpers (inet,inet6,udp4,udp6)_lookup_run_bpf.
There are two differences between the reuseport_lookup helpers:
1. They call different hash functions depending on protocol
2. UDP reuseport_lookup checks that sk_state != TCP_ESTABLISHED
Move the check for sk_state into the caller and use the INDIRECT_CALL
infrastructure to cut down the helpers to one per IP version.
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-4-7021b683cdae@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Stable-dep-of: 50aee97d1511 ("udp: Avoid call to compute_score on multiple sites")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit ce796e60b3b196b61fcc565df195443cbb846ef0 ]
Rename the existing reuseport helpers for IPv4 and IPv6 so that they
can be invoked in the follow up commit. Export them so that building
DCCP and IPv6 as a module works.
No change in functionality.
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Lorenz Bauer <lmb@isovalent.com>
Link: https://lore.kernel.org/r/20230720-so-reuseport-v6-3-7021b683cdae@isovalent.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Stable-dep-of: 50aee97d1511 ("udp: Avoid call to compute_score on multiple sites")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 58fbfecab965014b6e3cc956a76b4a96265a1add ]
The software GRO path for esp transport mode uses skb_mac_header_rebuild
prior to re-injecting the packet via the xfrm_napi_dev. This only
copies skb->mac_len bytes of header which may not be sufficient if the
packet contains 802.1Q tags or other VLAN tags. Worse copying only the
initial header will leave a packet marked as being VLAN tagged but
without the corresponding tag leading to mangling when it is later
untagged.
The VLAN tags are important when receiving the decrypted esp transport
mode packet after GRO processing to ensure it is received on the correct
interface.
Therefore record the full mac header length in xfrm*_transport_input for
later use in corresponding xfrm*_transport_finish to copy the entire mac
header when rebuilding the mac header for GRO. The skb->data pointer is
left pointing skb->mac_header bytes after the start of the mac header as
is expected by the network stack and network and transport header
offsets reset to this location.
Fixes: 7785bba299a8 ("esp: Add a software GRO codepath")
Signed-off-by: Paul Davey <paul.davey@alliedtelesis.co.nz>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 5babae777c61aa8a8679d59d3cdc54165ad96d42 ]
GRO-GSO path is supposed to be transparent and as such L3 flush checks are
relevant to all UDP flows merging in GRO. This patch uses the same logic
and code from tcp_gro_receive, terminating merge if flush is non zero.
Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.")
Signed-off-by: Richard Gobert <richardbgobert@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 680d11f6e5427b6af1321932286722d24a8b16c1 upstream.
If "udp_cmsg_send()" returned 0 (i.e. only UDP cmsg),
"connected" should not be set to 0. Otherwise it stops
the connected socket from using the cached route.
Fixes: 2e8de8576343 ("udp: add gso segment cmsg")
Signed-off-by: Yick Xie <yick.xie@gmail.com>
Cc: stable@vger.kernel.org
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/20240418170610.867084-1-yick.xie@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Yick Xie <yick.xie@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 1c4e97dd2d3c9a3e84f7e26346aa39bc426d3249 upstream.
inet_twsk_purge() uses rcu to find TIME_WAIT and NEW_SYN_RECV
objects to purge.
These objects use SLAB_TYPESAFE_BY_RCU semantic and need special
care. We need to use refcount_inc_not_zero(&sk->sk_refcnt).
Reuse the existing correct logic I wrote for TIME_WAIT,
because both structures have common locations for
sk_state, sk_family, and netns pointer.
If after the refcount_inc_not_zero() the object fields longer match
the keys, use sock_gen_put(sk) to release the refcount.
Then we can call inet_twsk_deschedule_put() for TIME_WAIT,
inet_csk_reqsk_queue_drop_and_put() for NEW_SYN_RECV sockets,
with BH disabled.
Then we need to restart the loop because we had drop rcu_read_lock().
Fixes: 740ea3c4a0b2 ("tcp: Clean up kernel listener's reqsk in inet_twsk_purge()")
Link: https://lore.kernel.org/netdev/CANn89iLvFuuihCtt9PME2uS1WJATnf5fKjDToa1WzVnRzHnPfg@mail.gmail.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240308200122.64357-2-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
[shaozhengchao: resolved conflicts in 5.10]
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 740ea3c4a0b2e326b23d7cdf05472a0e92aa39bc upstream.
Eric Dumazet reported a use-after-free related to the per-netns ehash
series. [0]
When we create a TCP socket from userspace, the socket always holds a
refcnt of the netns. This guarantees that a reqsk timer is always fired
before netns dismantle. Each reqsk has a refcnt of its listener, so the
listener is not freed before the reqsk, and the net is not freed before
the listener as well.
OTOH, when in-kernel users create a TCP socket, it might not hold a refcnt
of its netns. Thus, a reqsk timer can be fired after the netns dismantle
and access freed per-netns ehash.
To avoid the use-after-free, we need to clean up TCP_NEW_SYN_RECV sockets
in inet_twsk_purge() if the netns uses a per-netns ehash.
[0]: https://lore.kernel.org/netdev/CANn89iLXMup0dRD_Ov79Xt8N9FM0XdhCHEN05sf3eLwxKweM6w@mail.gmail.com/
BUG: KASAN: use-after-free in tcp_or_dccp_get_hashinfo
include/net/inet_hashtables.h:181 [inline]
BUG: KASAN: use-after-free in reqsk_queue_unlink+0x320/0x350
net/ipv4/inet_connection_sock.c:913
Read of size 8 at addr ffff88807545bd80 by task syz-executor.2/8301
CPU: 1 PID: 8301 Comm: syz-executor.2 Not tainted
6.0.0-syzkaller-02757-gaf7d23f9d96a #0
Hardware name: Google Google Compute Engine/Google Compute Engine,
BIOS Google 09/22/2022
Call Trace:
<IRQ>
__dump_stack lib/dump_stack.c:88 [inline]
dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106
print_address_description mm/kasan/report.c:317 [inline]
print_report.cold+0x2ba/0x719 mm/kasan/report.c:433
kasan_report+0xb1/0x1e0 mm/kasan/report.c:495
tcp_or_dccp_get_hashinfo include/net/inet_hashtables.h:181 [inline]
reqsk_queue_unlink+0x320/0x350 net/ipv4/inet_connection_sock.c:913
inet_csk_reqsk_queue_drop net/ipv4/inet_connection_sock.c:927 [inline]
inet_csk_reqsk_queue_drop_and_put net/ipv4/inet_connection_sock.c:939 [inline]
reqsk_timer_handler+0x724/0x1160 net/ipv4/inet_connection_sock.c:1053
call_timer_fn+0x1a0/0x6b0 kernel/time/timer.c:1474
expire_timers kernel/time/timer.c:1519 [inline]
__run_timers.part.0+0x674/0xa80 kernel/time/timer.c:1790
__run_timers kernel/time/timer.c:1768 [inline]
run_timer_softirq+0xb3/0x1d0 kernel/time/timer.c:1803
__do_softirq+0x1d0/0x9c8 kernel/softirq.c:571
invoke_softirq kernel/softirq.c:445 [inline]
__irq_exit_rcu+0x123/0x180 kernel/softirq.c:650
irq_exit_rcu+0x5/0x20 kernel/softirq.c:662
sysvec_apic_timer_interrupt+0x93/0xc0 arch/x86/kernel/apic/apic.c:1107
</IRQ>
Fixes: d1e5e6408b30 ("tcp: Introduce optional per-netns ehash.")
Reported-by: syzbot <syzkaller@googlegroups.com>
Reported-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20221012145036.74960-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
[shaozhengchao: resolved conflicts in 5.10]
Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 65acf6e0501ac8880a4f73980d01b5d27648b956 ]
In my recent commit, I missed that do_replace() handlers
use copy_from_sockptr() (which I fixed), followed
by unsafe copy_from_sockptr_offset() calls.
In all functions, we can perform the @optlen validation
before even calling xt_alloc_table_info() with the following
check:
if ((u64)optlen < (u64)tmp.size + sizeof(tmp))
return -EINVAL;
Fixes: 0c83842df40f ("netfilter: validate user input for expected length")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Pablo Neira Ayuso <pablo@netfilter.org>
Link: https://lore.kernel.org/r/20240409120741.3538135-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit cf1b7201df59fb936f40f4a807433fe3f2ce310a ]
The log_martians variable is only used in an #ifdef, causing a 'make W=1'
warning with gcc:
net/ipv4/route.c: In function 'ip_rt_send_redirect':
net/ipv4/route.c:880:13: error: variable 'log_martians' set but not used [-Werror=unused-but-set-variable]
Change the #ifdef to an equivalent IS_ENABLED() to let the compiler
see where the variable is used.
Fixes: 30038fc61adf ("net: ip_rt_send_redirect() optimization")
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240408074219.3030256-2-arnd@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 3d010c8031e39f5fa1e8b13ada77e0321091011f ]
When rx-udp-gro-forwarding is enabled UDP packets might be GROed when
being forwarded. If such packets might land in a tunnel this can cause
various issues and udp_gro_receive makes sure this isn't the case by
looking for a matching socket. This is performed in
udp4/6_gro_lookup_skb but only in the current netns. This is an issue
with tunneled packets when the endpoint is in another netns. In such
cases the packets will be GROed at the UDP level, which leads to various
issues later on. The same thing can happen with rx-gro-list.
We saw this with geneve packets being GROed at the UDP level. In such
case gso_size is set; later the packet goes through the geneve rx path,
the geneve header is pulled, the offset are adjusted and frag_list skbs
are not adjusted with regard to geneve. When those skbs hit
skb_fragment, it will misbehave. Different outcomes are possible
depending on what the GROed skbs look like; from corrupted packets to
kernel crashes.
One example is a BUG_ON[1] triggered in skb_segment while processing the
frag_list. Because gso_size is wrong (geneve header was pulled)
skb_segment thinks there is "geneve header size" of data in frag_list,
although it's in fact the next packet. The BUG_ON itself has nothing to
do with the issue. This is only one of the potential issues.
Looking up for a matching socket in udp_gro_receive is fragile: the
lookup could be extended to all netns (not speaking about performances)
but nothing prevents those packets from being modified in between and we
could still not find a matching socket. It's OK to keep the current
logic there as it should cover most cases but we also need to make sure
we handle tunnel packets being GROed too early.
This is done by extending the checks in udp_unexpected_gso: GSO packets
lacking the SKB_GSO_UDP_TUNNEL/_CSUM bits and landing in a tunnel must
be segmented.
[1] kernel BUG at net/core/skbuff.c:4408!
RIP: 0010:skb_segment+0xd2a/0xf70
__udp_gso_segment+0xaa/0x560
Fixes: 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.")
Fixes: 36707061d6ba ("udp: allow forwarding of plain (non-fraglisted) UDP GRO packets")
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit f0b8c30345565344df2e33a8417a27503589247d upstream.
UDP GRO validates checksums and in udp4/6_gro_complete fraglist packets
are converted to CHECKSUM_UNNECESSARY to avoid later checks. However
this is an issue for CHECKSUM_PARTIAL packets as they can be looped in
an egress path and then their partial checksums are not fixed.
Different issues can be observed, from invalid checksum on packets to
traces like:
gen01: hw csum failure
skb len=3008 headroom=160 headlen=1376 tailroom=0
mac=(106,14) net=(120,40) trans=160
shinfo(txflags=0 nr_frags=0 gso(size=0 type=0 segs=0))
csum(0xffff232e ip_summed=2 complete_sw=0 valid=0 level=0)
hash(0x77e3d716 sw=1 l4=1) proto=0x86dd pkttype=0 iif=12
...
Fix this by only converting CHECKSUM_NONE packets to
CHECKSUM_UNNECESSARY by reusing __skb_incr_checksum_unnecessary. All
other checksum types are kept as-is, including CHECKSUM_COMPLETE as
fraglist packets being segmented back would have their skb->csum valid.
Fixes: 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.")
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 151c9c724d05d5b0dd8acd3e11cb69ef1f2dbada ]
We had various syzbot reports about tcp timers firing after
the corresponding netns has been dismantled.
Fortunately Josef Bacik could trigger the issue more often,
and could test a patch I wrote two years ago.
When TCP sockets are closed, we call inet_csk_clear_xmit_timers()
to 'stop' the timers.
inet_csk_clear_xmit_timers() can be called from any context,
including when socket lock is held.
This is the reason it uses sk_stop_timer(), aka del_timer().
This means that ongoing timers might finish much later.
For user sockets, this is fine because each running timer
holds a reference on the socket, and the user socket holds
a reference on the netns.
For kernel sockets, we risk that the netns is freed before
timer can complete, because kernel sockets do not hold
reference on the netns.
This patch adds inet_csk_clear_xmit_timers_sync() function
that using sk_stop_timer_sync() to make sure all timers
are terminated before the kernel socket is released.
Modules using kernel sockets close them in their netns exit()
handler.
Also add sock_not_owned_by_me() helper to get LOCKDEP
support : inet_csk_clear_xmit_timers_sync() must not be called
while socket lock is held.
It is very possible we can revert in the future commit
3a58f13a881e ("net: rds: acquire refcount on TCP sockets")
which attempted to solve the issue in rds only.
(net/smc/af_smc.c and net/mptcp/subflow.c have similar code)
We probably can remove the check_net() tests from
tcp_out_of_resources() and __tcp_close() in the future.
Reported-by: Josef Bacik <josef@toxicpanda.com>
Closes: https://lore.kernel.org/netdev/20240314210740.GA2823176@perftesting/
Fixes: 26abe14379f8 ("net: Modify sk_alloc to not reference count the netns of kernel sockets.")
Fixes: 8a68173691f0 ("net: sk_clone_lock() should only do get_net() if the parent is not a kernel socket")
Link: https://lore.kernel.org/bpf/CANn89i+484ffqb93aQm1N-tjxxvb3WDKX0EbD7318RwRgsatjw@mail.gmail.com/
Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Josef Bacik <josef@toxicpanda.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Link: https://lore.kernel.org/r/20240322135732.1535772-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 4bb3ba7b74fceec6f558745b25a43c6521cf5506 ]
The 'len' variable can't be negative when assigned the result of
'min_t' because all 'min_t' parameters are cast to unsigned int,
and then the minimum one is chosen.
To fix the logic, check 'len' as read from 'optlen',
where the types of relevant variables are (signed) int.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Gavrilov Ilia <Ilia.Gavrilov@infotecs.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 5c3be3e0eb44b7f978bb6cbb20ad956adb93f736 ]
The 'olr' variable can't be negative when assigned the result of
'min_t' because all 'min_t' parameters are cast to unsigned int,
and then the minimum one is chosen.
To fix the logic, check 'olr' as read from 'optlen',
where the types of relevant variables are (signed) int.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Gavrilov Ilia <Ilia.Gavrilov@infotecs.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 728f064cd7ebea8c182e99e6f152c8b4a0a6b071 ]
Similar to the earlier patch that changes sk_getsockopt() to
take the sockptr_t argument. This patch also changes
do_ip_getsockopt() to take the sockptr_t argument such that
a latter patch can make bpf_getsockopt(SOL_IP) to reuse
do_ip_getsockopt().
Note on the change in ip_mc_gsfget(). This function is to
return an array of sockaddr_storage in optval. This function
is shared between ip_get_mcast_msfilter() and
compat_ip_get_mcast_msfilter(). However, the sockaddr_storage
is stored at different offset of the optval because of
the difference between group_filter and compat_group_filter.
Thus, a new 'ss_offset' argument is added to ip_mc_gsfget().
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://lore.kernel.org/r/20220902002828.2890585-1-kafai@fb.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Stable-dep-of: 5c3be3e0eb44 ("ipmr: fix incorrect parameter validation in the ip_mroute_getsockopt() function")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 4167a960574fcadc9067f4280951a35b8c021c68 ]
Revert the use of structr_size() and stay with IP_MSFILTER_SIZE() for
now, as in this case, the size of struct ip_msfilter didn't change with
the addition of the flexible array imsf_slist_flex[]. So, if we use
struct_size() we will be allocating and calculating the size of
struct ip_msfilter with one too many items for imsf_slist_flex[].
We might use struct_size() in the future, but for now let's stay
with IP_MSFILTER_SIZE().
Fixes: 2d3e5caf96b9 ("net/ipv4: Replace one-element array with flexible-array member")
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Stable-dep-of: 5c3be3e0eb44 ("ipmr: fix incorrect parameter validation in the ip_mroute_getsockopt() function")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 2d3e5caf96b9449af951e63476657acd759c1a30 ]
There is a regular need in the kernel to provide a way to declare having
a dynamically sized set of trailing elements in a structure. Kernel code
should always use “flexible array members”[1] for these cases. The older
style of one-element or zero-length arrays should no longer be used[2].
Use an anonymous union with a couple of anonymous structs in order to
keep userspace unchanged:
$ pahole -C ip_msfilter net/ipv4/ip_sockglue.o
struct ip_msfilter {
union {
struct {
__be32 imsf_multiaddr_aux; /* 0 4 */
__be32 imsf_interface_aux; /* 4 4 */
__u32 imsf_fmode_aux; /* 8 4 */
__u32 imsf_numsrc_aux; /* 12 4 */
__be32 imsf_slist[1]; /* 16 4 */
}; /* 0 20 */
struct {
__be32 imsf_multiaddr; /* 0 4 */
__be32 imsf_interface; /* 4 4 */
__u32 imsf_fmode; /* 8 4 */
__u32 imsf_numsrc; /* 12 4 */
__be32 imsf_slist_flex[0]; /* 16 0 */
}; /* 0 16 */
}; /* 0 20 */
/* size: 20, cachelines: 1, members: 1 */
/* last cacheline: 20 bytes */
};
Also, refactor the code accordingly and make use of the struct_size()
and flex_array_size() helpers.
This helps with the ongoing efforts to globally enable -Warray-bounds
and get us closer to being able to tighten the FORTIFY_SOURCE routines
on memcpy().
[1] https://en.wikipedia.org/wiki/Flexible_array_member
[2] https://www.kernel.org/doc/html/v5.10/process/deprecated.html#zero-length-and-one-element-arrays
Link: https://github.com/KSPP/linux/issues/79
Link: https://github.com/KSPP/linux/issues/109
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Stable-dep-of: 5c3be3e0eb44 ("ipmr: fix incorrect parameter validation in the ip_mroute_getsockopt() function")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 716edc9706deb3bb2ff56e2eeb83559cea8f22db ]
The 'len' variable can't be negative when assigned the result of
'min_t' because all 'min_t' parameters are cast to unsigned int,
and then the minimum one is chosen.
To fix the logic, check 'len' as read from 'optlen',
where the types of relevant variables are (signed) int.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Gavrilov Ilia <Ilia.Gavrilov@infotecs.ru>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 5ae1e9922bbdbaeb9cfbe91085ab75927488ac0f ]
syzkaller triggered following kasan splat:
BUG: KASAN: use-after-free in __skb_flow_dissect+0x19d1/0x7a50 net/core/flow_dissector.c:1170
Read of size 1 at addr ffff88812fb4000e by task syz-executor183/5191
[..]
kasan_report+0xda/0x110 mm/kasan/report.c:588
__skb_flow_dissect+0x19d1/0x7a50 net/core/flow_dissector.c:1170
skb_flow_dissect_flow_keys include/linux/skbuff.h:1514 [inline]
___skb_get_hash net/core/flow_dissector.c:1791 [inline]
__skb_get_hash+0xc7/0x540 net/core/flow_dissector.c:1856
skb_get_hash include/linux/skbuff.h:1556 [inline]
ip_tunnel_xmit+0x1855/0x33c0 net/ipv4/ip_tunnel.c:748
ipip_tunnel_xmit+0x3cc/0x4e0 net/ipv4/ipip.c:308
__netdev_start_xmit include/linux/netdevice.h:4940 [inline]
netdev_start_xmit include/linux/netdevice.h:4954 [inline]
xmit_one net/core/dev.c:3548 [inline]
dev_hard_start_xmit+0x13d/0x6d0 net/core/dev.c:3564
__dev_queue_xmit+0x7c1/0x3d60 net/core/dev.c:4349
dev_queue_xmit include/linux/netdevice.h:3134 [inline]
neigh_connected_output+0x42c/0x5d0 net/core/neighbour.c:1592
...
ip_finish_output2+0x833/0x2550 net/ipv4/ip_output.c:235
ip_finish_output+0x31/0x310 net/ipv4/ip_output.c:323
..
iptunnel_xmit+0x5b4/0x9b0 net/ipv4/ip_tunnel_core.c:82
ip_tunnel_xmit+0x1dbc/0x33c0 net/ipv4/ip_tunnel.c:831
ipgre_xmit+0x4a1/0x980 net/ipv4/ip_gre.c:665
__netdev_start_xmit include/linux/netdevice.h:4940 [inline]
netdev_start_xmit include/linux/netdevice.h:4954 [inline]
xmit_one net/core/dev.c:3548 [inline]
dev_hard_start_xmit+0x13d/0x6d0 net/core/dev.c:3564
...
The splat occurs because skb->data points past skb->head allocated area.
This is because neigh layer does:
__skb_pull(skb, skb_network_offset(skb));
... but skb_network_offset() returns a negative offset and __skb_pull()
arg is unsigned. IOW, we skb->data gets "adjusted" by a huge value.
The negative value is returned because skb->head and skb->data distance is
more than 64k and skb->network_header (u16) has wrapped around.
The bug is in the ip_tunnel infrastructure, which can cause
dev->needed_headroom to increment ad infinitum.
The syzkaller reproducer consists of packets getting routed via a gre
tunnel, and route of gre encapsulated packets pointing at another (ipip)
tunnel. The ipip encapsulation finds gre0 as next output device.
This results in the following pattern:
1). First packet is to be sent out via gre0.
Route lookup found an output device, ipip0.
2).
ip_tunnel_xmit for gre0 bumps gre0->needed_headroom based on the future
output device, rt.dev->needed_headroom (ipip0).
3).
ip output / start_xmit moves skb on to ipip0. which runs the same
code path again (xmit recursion).
4).
Routing step for the post-gre0-encap packet finds gre0 as output device
to use for ipip0 encapsulated packet.
tunl0->needed_headroom is then incremented based on the (already bumped)
gre0 device headroom.
This repeats for every future packet:
gre0->needed_headroom gets inflated because previous packets' ipip0 step
incremented rt->dev (gre0) headroom, and ipip0 incremented because gre0
needed_headroom was increased.
For each subsequent packet, gre/ipip0->needed_headroom grows until
post-expand-head reallocations result in a skb->head/data distance of
more than 64k.
Once that happens, skb->network_header (u16) wraps around when
pskb_expand_head tries to make sure that skb_network_offset() is unchanged
after the headroom expansion/reallocation.
After this skb_network_offset(skb) returns a different (and negative)
result post headroom expansion.
The next trip to neigh layer (or anything else that would __skb_pull the
network header) makes skb->data point to a memory location outside
skb->head area.
v2: Cap the needed_headroom update to an arbitarily chosen upperlimit to
prevent perpetual increase instead of dropping the headroom increment
completely.
Reported-and-tested-by: syzbot+bfde3bef047a81b8fde6@syzkaller.appspotmail.com
Closes: https://groups.google.com/g/syzkaller-bugs/c/fL9G6GtWskY/m/VKk_PR5FBAAJ
Fixes: 243aad830e8a ("ip_gre: include route header_len in max_headroom calculation")
Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://lore.kernel.org/r/20240220135606.4939-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 081a0e3b0d4c061419d3f4679dec9f68725b17e4 ]
net->dev_base_seq and ipv4.dev_addr_genid are monotonically increasing.
If we XOR their values, we could miss to detect if both values
were changed with the same amount.
Fixes: 0465277f6b3f ("ipv4: provide addr and netconf dump consistency info")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit eef00a82c568944f113f2de738156ac591bbd5cd ]
inet_recv_error() is called without holding the socket lock.
IPv6 socket could mutate to IPv4 with IPV6_ADDRFORM
socket option and trigger a KCSAN warning.
Fixes: f4713a3dfad0 ("net-timestamp: make tcp_recvmsg call ipv6_recv_error for AF_INET6 socks")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit d75abeec401f8c86b470e7028a13fcdc87e5dd06 ]
If the ICMPv6 error is built from a non-linear skb we get the following
splat,
BUG: KASAN: slab-out-of-bounds in do_csum+0x220/0x240
Read of size 4 at addr ffff88811d402c80 by task netperf/820
CPU: 0 PID: 820 Comm: netperf Not tainted 6.8.0-rc1+ #543
...
kasan_report+0xd8/0x110
do_csum+0x220/0x240
csum_partial+0xc/0x20
skb_tunnel_check_pmtu+0xeb9/0x3280
vxlan_xmit_one+0x14c2/0x4080
vxlan_xmit+0xf61/0x5c00
dev_hard_start_xmit+0xfb/0x510
__dev_queue_xmit+0x7cd/0x32a0
br_dev_queue_push_xmit+0x39d/0x6a0
Use skb_checksum instead of csum_partial who cannot deal with non-linear
SKBs.
Fixes: 4cb47a8644cc ("tunnels: PMTU discovery support for directly bridged IP packets")
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 5dee6d6923458e26966717f2a3eae7d09fc10bf6 ]
When inetdev_valid_mtu fails, cork->opt should be freed if it is
allocated in ip_setup_cork. Otherwise there could be a memleak.
Fixes: 501a90c94510 ("inet: protect against too small mtu values.")
Signed-off-by: Zhipeng Lu <alexious@zju.edu.cn>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240129091017.2938835-1-alexious@zju.edu.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 577e4432f3ac810049cb7e6b71f4d96ec7c6e894 ]
TCP rx zerocopy intent is to map pages initially allocated
from NIC drivers, not pages owned by a fs.
This patch adds to can_map_frag() these additional checks:
- Page must not be a compound one.
- page->mapping must be NULL.
This fixes the panic reported by ZhangPeng.
syzbot was able to loopback packets built with sendfile(),
mapping pages owned by an ext4 file to TCP rx zerocopy.
r3 = socket$inet_tcp(0x2, 0x1, 0x0)
mmap(&(0x7f0000ff9000/0x4000)=nil, 0x4000, 0x0, 0x12, r3, 0x0)
r4 = socket$inet_tcp(0x2, 0x1, 0x0)
bind$inet(r4, &(0x7f0000000000)={0x2, 0x4e24, @multicast1}, 0x10)
connect$inet(r4, &(0x7f00000006c0)={0x2, 0x4e24, @empty}, 0x10)
r5 = openat$dir(0xffffffffffffff9c, &(0x7f00000000c0)='./file0\x00',
0x181e42, 0x0)
fallocate(r5, 0x0, 0x0, 0x85b8)
sendfile(r4, r5, 0x0, 0x8ba0)
getsockopt$inet_tcp_TCP_ZEROCOPY_RECEIVE(r4, 0x6, 0x23,
&(0x7f00000001c0)={&(0x7f0000ffb000/0x3000)=nil, 0x3000, 0x0, 0x0, 0x0,
0x0, 0x0, 0x0, 0x0}, &(0x7f0000000440)=0x40)
r6 = openat$dir(0xffffffffffffff9c, &(0x7f00000000c0)='./file0\x00',
0x181e42, 0x0)
Fixes: 93ab6cc69162 ("tcp: implement mmap() for zero copy receive")
Link: https://lore.kernel.org/netdev/5106a58e-04da-372a-b836-9d3d0bd2507b@huawei.com/T/
Reported-and-bisected-by: ZhangPeng <zhangpeng362@huawei.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Arjun Roy <arjunroy@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: linux-mm@vger.kernel.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 98917cf0d6eda01e8c3c34d35398d46b247b6fd3 ]
Refactor frag-is-remappable test for tcp receive zerocopy. This is
part of a patch set that introduces short-circuited hybrid copies
for small receive operations, which results in roughly 33% fewer
syscalls for small RPC scenarios.
Signed-off-by: Arjun Roy <arjunroy@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 577e4432f3ac ("tcp: add sanity checks to rx zerocopy")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 7267e8dcad6b2f9fce05a6a06335d7040acbc2b6 ]
On CPUs with weak memory models, reads and updates performed by tcp_push
to the sk variables can get reordered leaving the socket throttled when
it should not. The tasklet running tcp_wfree() may also not observe the
memory updates in time and will skip flushing any packets throttled by
tcp_push(), delaying the sending. This can pathologically cause 40ms
extra latency due to bad interactions with delayed acks.
Adding a memory barrier in tcp_push removes the bug, similarly to the
previous commit bf06200e732d ("tcp: tsq: fix nonagle handling").
smp_mb__after_atomic() is used to not incur in unnecessary overhead
on x86 since not affected.
Patch has been tested using an AWS c7g.2xlarge instance with Ubuntu
22.04 and Apache Tomcat 9.0.83 running the basic servlet below:
import java.io.IOException;
import java.io.OutputStreamWriter;
import java.io.PrintWriter;
import javax.servlet.ServletException;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;
public class HelloWorldServlet extends HttpServlet {
@Override
protected void doGet(HttpServletRequest request, HttpServletResponse response)
throws ServletException, IOException {
response.setContentType("text/html;charset=utf-8");
OutputStreamWriter osw = new OutputStreamWriter(response.getOutputStream(),"UTF-8");
String s = "a".repeat(3096);
osw.write(s,0,s.length());
osw.flush();
}
}
Load was applied using wrk2 (https://github.com/kinvolk/wrk2) from an AWS
c6i.8xlarge instance. Before the patch an additional 40ms latency from P99.99+
values is observed while, with the patch, the extra latency disappears.
No patch and tcp_autocorking=1
./wrk -t32 -c128 -d40s --latency -R10000 http://172.31.60.173:8080/hello/hello
...
50.000% 0.91ms
75.000% 1.13ms
90.000% 1.46ms
99.000% 1.74ms
99.900% 1.89ms
99.990% 41.95ms <<< 40+ ms extra latency
99.999% 48.32ms
100.000% 48.96ms
With patch and tcp_autocorking=1
./wrk -t32 -c128 -d40s --latency -R10000 http://172.31.60.173:8080/hello/hello
...
50.000% 0.90ms
75.000% 1.13ms
90.000% 1.45ms
99.000% 1.72ms
99.900% 1.83ms
99.990% 2.11ms <<< no 40+ ms extra latency
99.999% 2.53ms
100.000% 2.62ms
Patch has been also tested on x86 (m7i.2xlarge instance) which it is not
affected by this issue and the patch doesn't introduce any additional
delay.
Fixes: 7aa5470c2c09 ("tcp: tsq: move tsq_flags close to sk_wmem_alloc")
Signed-off-by: Salvatore Dipietro <dipiets@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240119190133.43698-1-dipiets@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 3d501dd326fb1c73f1b8206d4c6e1d7b15c07e27 ]
This patch is based on a detailed report and ideas from Yepeng Pan
and Christian Rossow.
ACK seq validation is currently following RFC 5961 5.2 guidelines:
The ACK value is considered acceptable only if
it is in the range of ((SND.UNA - MAX.SND.WND) <= SEG.ACK <=
SND.NXT). All incoming segments whose ACK value doesn't satisfy the
above condition MUST be discarded and an ACK sent back. It needs to
be noted that RFC 793 on page 72 (fifth check) says: "If the ACK is a
duplicate (SEG.ACK < SND.UNA), it can be ignored. If the ACK
acknowledges something not yet sent (SEG.ACK > SND.NXT) then send an
ACK, drop the segment, and return". The "ignored" above implies that
the processing of the incoming data segment continues, which means
the ACK value is treated as acceptable. This mitigation makes the
ACK check more stringent since any ACK < SND.UNA wouldn't be
accepted, instead only ACKs that are in the range ((SND.UNA -
MAX.SND.WND) <= SEG.ACK <= SND.NXT) get through.
This can be refined for new (and possibly spoofed) flows,
by not accepting ACK for bytes that were never sent.
This greatly improves TCP security at a little cost.
I added a Fixes: tag to make sure this patch will reach stable trees,
even if the 'blamed' patch was adhering to the RFC.
tp->bytes_acked was added in linux-4.2
Following packetdrill test (courtesy of Yepeng Pan) shows
the issue at hand:
0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0 bind(3, ..., ...) = 0
+0 listen(3, 1024) = 0
// ---------------- Handshake ------------------- //
// when window scale is set to 14 the window size can be extended to
// 65535 * (2^14) = 1073725440. Linux would accept an ACK packet
// with ack number in (Server_ISN+1-1073725440. Server_ISN+1)
// ,though this ack number acknowledges some data never
// sent by the server.
+0 < S 0:0(0) win 65535 <mss 1400,nop,wscale 14>
+0 > S. 0:0(0) ack 1 <...>
+0 < . 1:1(0) ack 1 win 65535
+0 accept(3, ..., ...) = 4
// For the established connection, we send an ACK packet,
// the ack packet uses ack number 1 - 1073725300 + 2^32,
// where 2^32 is used to wrap around.
// Note: we used 1073725300 instead of 1073725440 to avoid possible
// edge cases.
// 1 - 1073725300 + 2^32 = 3221241997
// Oops, old kernels happily accept this packet.
+0 < . 1:1001(1000) ack 3221241997 win 65535
// After the kernel fix the following will be replaced by a challenge ACK,
// and prior malicious frame would be dropped.
+0 > . 1:1(0) ack 1001
Fixes: 354e4aa391ed ("tcp: RFC 5961 5.2 Blind Data Injection Attack Mitigation")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Yepeng Pan <yepeng.pan@cispa.de>
Reported-by: Christian Rossow <rossow@cispa.de>
Acked-by: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20231205161841.2702925-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 80d875cfc9d3711a029f234ef7d680db79e8fa4b ]
In ipgre_xmit(), skb_pull() may fail even if pskb_inet_may_pull() returns
true. For example, applications can use PF_PACKET to create a malformed
packet with no IP header. This type of packet causes a problem such as
uninit-value access.
This patch ensures that skb_pull() can pull the required size by checking
the skb with pskb_network_may_pull() before skb_pull().
Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.")
Signed-off-by: Shigeru Yoshida <syoshida@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Suman Ghosh <sumang@marvell.com>
Link: https://lore.kernel.org/r/20231202161441.221135-1-syoshida@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit eb44ad4e635132754bfbcb18103f1dcb7058aedd ]
This field can be read or written without socket lock being held.
Add annotations to avoid load-store tearing.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 73ed8e03388d16c12fc577e5c700b58a29045a15 ]
cookie_init_timestamp() is supposed to return a 64bit timestamp
suitable for both TSval determination and setting of skb->tstamp.
Unfortunately it uses 32bit fields and overflows after
2^32 * 10^6 nsec (~49 days) of uptime.
Generated TSval are still correct, but skb->tstamp might be set
far away in the past, potentially confusing other layers.
tcp_ns_to_ts() is changed to return a full 64bit value,
ts and ts_now variables are changed to u64 type,
and TSMASK is removed in favor of shifts operations.
While we are at it, change this sequence:
ts >>= TSBITS;
ts--;
ts <<= TSBITS;
ts |= options;
to:
ts -= (1UL << TSBITS);
Fixes: 9a568de4818d ("tcp: switch TCP TS option (RFC 7323) to 1ms clock")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit a135798e6e200ecb2f864cecca6d257ba278370c ]
tcp_init_metrics() only wants to get metrics if they were
previously stored in the cache. Creating an entry is adding
useless costs, especially when tcp_no_metrics_save is set.
Fixes: 51c5d0c4b169 ("tcp: Maintain dynamic metrics in local cache.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 081480014a64a69d901f8ef1ffdd56d6085cf87e ]
We need to set tp->snd_ssthresh to TCP_INFINITE_SSTHRESH
in the case tcp_get_metrics() fails for some reason.
Fixes: 9ad7c049f0f7 ("tcp: RFC2988bis + taking RTT sample from 3WHS for the passive open side")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit cbc3a153222805d65f821e10f4f78b6afce06f86 ]
When removing an item from RCU protected list, we must prevent
store-tearing, using rcu_assign_pointer() or WRITE_ONCE().
Fixes: 04f721c671656 ("tcp_metrics: Rewrite tcp_metrics_flush_all")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit e326578a21414738de45f77badd332fb00bd0f58 ]
For passive TCP Fast Open sockets that had SYN/ACK timeout and did not
send more data in SYN_RECV, upon receiving the final ACK in 3WHS, the
congestion state may awkwardly stay in CA_Loss mode unless the CA state
was undone due to TCP timestamp checks. However, if
tcp_rcv_synrecv_state_fastopen() decides not to undo, then we should
enter CA_Open, because at that point we have received an ACK covering
the retransmitted SYNACKs. Currently, the icsk_ca_state is only set to
CA_Open after we receive an ACK for a data-packet. This is because
tcp_ack does not call tcp_fastretrans_alert (and tcp_process_loss) if
!prior_packets
Note that tcp_process_loss() calls tcp_try_undo_recovery(), so having
tcp_rcv_synrecv_state_fastopen() decide that if we're in CA_Loss we
should call tcp_try_undo_recovery() is consistent with that, and
low risk.
Fixes: dad8cea7add9 ("tcp: fix TFO SYNACK undo to avoid double-timestamp-undo")
Signed-off-by: Aananth V <aananthv@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.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>
[ Upstream commit 6d5a12eb91224d707f8691dccb40a5719fe5466d ]
UDP_ENCAP_ESPINUDP_NON_IKE setsockopt() writes over up->encap_rcv
while other cpus read it.
Fixes: 067b207b281d ("[UDP]: Cleanup UDP encapsulation code")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit d2a0fc372aca561556e765d0a9ec365c7c12f0ad ]
This commit fix wrong RTO timeout when received SACK reneging.
When an ACK arrived pointing to a SACK reneging, tcp_check_sack_reneging()
will rearm the RTO timer for min(1/2*srtt, 10ms) into to the future.
But since the commit 62d9f1a6945b ("tcp: fix TLP timer not set when
CA_STATE changes from DISORDER to OPEN") merged, the tcp_set_xmit_timer()
is moved after tcp_fastretrans_alert()(which do the SACK reneging check),
so the RTO timeout will be overwrited by tcp_set_xmit_timer() with
icsk_rto instead of 1/2*srtt.
Here is a packetdrill script to check this bug:
0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 bind(3, ..., ...) = 0
+0 listen(3, 1) = 0
// simulate srtt to 100ms
+0 < S 0:0(0) win 32792 <mss 1000, sackOK,nop,nop,nop,wscale 7>
+0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 7>
+.1 < . 1:1(0) ack 1 win 1024
+0 accept(3, ..., ...) = 4
+0 write(4, ..., 10000) = 10000
+0 > P. 1:10001(10000) ack 1
// inject sack
+.1 < . 1:1(0) ack 1 win 257 <sack 1001:10001,nop,nop>
+0 > . 1:1001(1000) ack 1
// inject sack reneging
+.1 < . 1:1(0) ack 1001 win 257 <sack 9001:10001,nop,nop>
// we expect rto fired in 1/2*srtt (50ms)
+.05 > . 1001:2001(1000) ack 1
This fix remove the FLAG_SET_XMIT_TIMER from ack_flag when
tcp_check_sack_reneging() set RTO timer with 1/2*srtt to avoid
being overwrited later.
Fixes: 62d9f1a6945b ("tcp: fix TLP timer not set when CA_STATE changes from DISORDER to OPEN")
Signed-off-by: Fred Chen <fred.chenchen03@gmail.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
This is now the default for all connections in iOS 11+, and we have
RFC 3168 ECN fallback to detect and disable ECN for broken flows.
Signed-off-by: Danny Lin <danny@kdrag0n.dev>
[ Upstream commit 4b2b606075e50cdae62ab2356b0a1e206947c354 ]
After deleting an interface address in fib_del_ifaddr(), the function
scans the fib_info list for stray entries and calls fib_flush() and
fib_table_flush(). Then the stray entries will be deleted silently and no
RTM_DELROUTE notification will be sent.
This lack of notification can make routing daemons, or monitor like
`ip monitor route` miss the routing changes. e.g.
+ ip link add dummy1 type dummy
+ ip link add dummy2 type dummy
+ ip link set dummy1 up
+ ip link set dummy2 up
+ ip addr add 192.168.5.5/24 dev dummy1
+ ip route add 7.7.7.0/24 dev dummy2 src 192.168.5.5
+ ip -4 route
7.7.7.0/24 dev dummy2 scope link src 192.168.5.5
192.168.5.0/24 dev dummy1 proto kernel scope link src 192.168.5.5
+ ip monitor route
+ ip addr del 192.168.5.5/24 dev dummy1
Deleted 192.168.5.0/24 dev dummy1 proto kernel scope link src 192.168.5.5
Deleted broadcast 192.168.5.255 dev dummy1 table local proto kernel scope link src 192.168.5.5
Deleted local 192.168.5.5 dev dummy1 table local proto kernel scope host src 192.168.5.5
As Ido reminded, fib_table_flush() isn't only called when an address is
deleted, but also when an interface is deleted or put down. The lack of
notification in these cases is deliberate. And commit 7c6bb7d2faaf
("net/ipv6: Add knob to skip DELROUTE message on device down") introduced
a sysctl to make IPv6 behave like IPv4 in this regard. So we can't send
the route delete notify blindly in fib_table_flush().
To fix this issue, let's add a new flag in "struct fib_info" to track the
deleted prefer source address routes, and only send notify for them.
After update:
+ ip monitor route
+ ip addr del 192.168.5.5/24 dev dummy1
Deleted 192.168.5.0/24 dev dummy1 proto kernel scope link src 192.168.5.5
Deleted broadcast 192.168.5.255 dev dummy1 table local proto kernel scope link src 192.168.5.5
Deleted local 192.168.5.5 dev dummy1 table local proto kernel scope host src 192.168.5.5
Deleted 7.7.7.0/24 dev dummy2 scope link src 192.168.5.5
Suggested-by: Thomas Haller <thaller@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20230922075508.848925-1-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit f921a4a5bffa8a0005b190fb9421a7fc1fd716b6 upstream.
In commit 75eefc6c59fd ("tcp: tsq: add a shortcut in tcp_small_queue_check()")
we allowed to send an skb regardless of TSQ limits being hit if rtx queue
was empty or had a single skb, in order to better fill the pipe
when/if TX completions were slow.
Then later, commit 75c119afe14f ("tcp: implement rb-tree based
retransmit queue") accidentally removed the special case for
one skb in rtx queue.
Stefan Wahren reported a regression in single TCP flow throughput
using a 100Mbit fec link, starting from commit 65466904b015 ("tcp: adjust
TSO packet sizes based on min_rtt"). This last commit only made the
regression more visible, because it locked the TCP flow on a particular
behavior where TSQ prevented two skbs being pushed downstream,
adding silences on the wire between each TSO packet.
Many thanks to Stefan for his invaluable help !
Fixes: 75c119afe14f ("tcp: implement rb-tree based retransmit queue")
Link: https://lore.kernel.org/netdev/7f31ddc8-9971-495e-a1f6-819df542e0af@gmx.net/
Reported-by: Stefan Wahren <wahrenst@gmx.net>
Tested-by: Stefan Wahren <wahrenst@gmx.net>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20231017124526.4060202-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 1c2709cfff1dedbb9591e989e2f001484208d914 upstream.
We discovered from packet traces of slow loss recovery on kernels with
the default HZ=250 setting (and min_rtt < 1ms) that after reordering,
when receiving a SACKed sequence range, the RACK reordering timer was
firing after about 16ms rather than the desired value of roughly
min_rtt/4 + 2ms. The problem is largely due to the RACK reorder timer
calculation adding in TCP_TIMEOUT_MIN, which is 2 jiffies. On kernels
with HZ=250, this is 2*4ms = 8ms. The TLP timer calculation has the
exact same issue.
This commit fixes the TLP transmit timer and RACK reordering timer
floor calculation to more closely match the intended 2ms floor even on
kernels with HZ=250. It does this by adding in a new
TCP_TIMEOUT_MIN_US floor of 2000 us and then converting to jiffies,
instead of the current approach of converting to jiffies and then
adding th TCP_TIMEOUT_MIN value of 2 jiffies.
Our testing has verified that on kernels with HZ=1000, as expected,
this does not produce significant changes in behavior, but on kernels
with the default HZ=250 the latency improvement can be large. For
example, our tests show that for HZ=250 kernels at low RTTs this fix
roughly halves the latency for the RACK reorder timer: instead of
mostly firing at 16ms it mostly fires at 8ms.
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Fixes: bb4d991a28cc ("tcp: adjust tail loss probe timeout")
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20231015174700.2206872-1-ncardwell.sw@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 513f61e2193350c7a345da98559b80f61aec4fa6 upstream.
In esp_remove_trailer(), to avoid an unexpected result returned by
pskb_trim, we should check the return value of pskb_trim().
Signed-off-by: Ma Ke <make_ruc2021@163.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 6db8a37dfc541e059851652cfd4f0bb13b8ff6af upstream.
The MPTCP protocol can acquire the subflow-level socket lock and
cause the tcp backlog usage. When inserting new skbs into the
backlog, the stack will try to coalesce them.
Currently, we have no check in place to ensure that such coalescing
will respect the MPTCP-level DSS, and that may cause data stream
corruption, as reported by Christoph.
Address the issue by adding the relevant admission check for coalescing
in tcp_add_backlog().
Note the issue is not easy to reproduce, as the MPTCP protocol tries
hard to avoid acquiring the subflow-level socket lock.
Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path")
Cc: stable@vger.kernel.org
Reported-by: Christoph Paasch <cpaasch@apple.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/420
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Mat Martineau <martineau@kernel.org>
Link: https://lore.kernel.org/r/20231018-send-net-20231018-v1-2-17ecb002e41d@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Paolo Abeni