[ Upstream commit b8469721034300bbb6dec5b4bf32492c95e16a0c ]
The series in the "fixes" tag added the ability to consider L4 attributes
in routing rules.
The dst lookup on the outer packet of encapsulated traffic in the xfrm
code was not adapted to this change, thus routing behavior that relies
on L4 information is not respected.
Pass the ip protocol information when performing dst lookups.
Fixes: a25724b05a ("Merge branch 'fib_rules-support-sport-dport-and-proto-match'")
Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Tested-by: Antony Antony <antony.antony@secunet.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit e8c526f2bdf1845bedaf6a478816a3d06fa78b8f ]
Martin KaFai Lau reported use-after-free [0] in reqsk_timer_handler().
"""
We are seeing a use-after-free from a bpf prog attached to
trace_tcp_retransmit_synack. The program passes the req->sk to the
bpf_sk_storage_get_tracing kernel helper which does check for null
before using it.
"""
The commit 83fccfc394 ("inet: fix potential deadlock in
reqsk_queue_unlink()") added timer_pending() in reqsk_queue_unlink() not
to call del_timer_sync() from reqsk_timer_handler(), but it introduced a
small race window.
Before the timer is called, expire_timers() calls detach_timer(timer, true)
to clear timer->entry.pprev and marks it as not pending.
If reqsk_queue_unlink() checks timer_pending() just after expire_timers()
calls detach_timer(), TCP will miss del_timer_sync(); the reqsk timer will
continue running and send multiple SYN+ACKs until it expires.
The reported UAF could happen if req->sk is close()d earlier than the timer
expiration, which is 63s by default.
The scenario would be
1. inet_csk_complete_hashdance() calls inet_csk_reqsk_queue_drop(),
but del_timer_sync() is missed
2. reqsk timer is executed and scheduled again
3. req->sk is accept()ed and reqsk_put() decrements rsk_refcnt, but
reqsk timer still has another one, and inet_csk_accept() does not
clear req->sk for non-TFO sockets
4. sk is close()d
5. reqsk timer is executed again, and BPF touches req->sk
Let's not use timer_pending() by passing the caller context to
__inet_csk_reqsk_queue_drop().
Note that reqsk timer is pinned, so the issue does not happen in most
use cases. [1]
[0]
BUG: KFENCE: use-after-free read in bpf_sk_storage_get_tracing+0x2e/0x1b0
Use-after-free read at 0x00000000a891fb3a (in kfence-#1):
bpf_sk_storage_get_tracing+0x2e/0x1b0
bpf_prog_5ea3e95db6da0438_tcp_retransmit_synack+0x1d20/0x1dda
bpf_trace_run2+0x4c/0xc0
tcp_rtx_synack+0xf9/0x100
reqsk_timer_handler+0xda/0x3d0
run_timer_softirq+0x292/0x8a0
irq_exit_rcu+0xf5/0x320
sysvec_apic_timer_interrupt+0x6d/0x80
asm_sysvec_apic_timer_interrupt+0x16/0x20
intel_idle_irq+0x5a/0xa0
cpuidle_enter_state+0x94/0x273
cpu_startup_entry+0x15e/0x260
start_secondary+0x8a/0x90
secondary_startup_64_no_verify+0xfa/0xfb
kfence-#1: 0x00000000a72cc7b6-0x00000000d97616d9, size=2376, cache=TCPv6
allocated by task 0 on cpu 9 at 260507.901592s:
sk_prot_alloc+0x35/0x140
sk_clone_lock+0x1f/0x3f0
inet_csk_clone_lock+0x15/0x160
tcp_create_openreq_child+0x1f/0x410
tcp_v6_syn_recv_sock+0x1da/0x700
tcp_check_req+0x1fb/0x510
tcp_v6_rcv+0x98b/0x1420
ipv6_list_rcv+0x2258/0x26e0
napi_complete_done+0x5b1/0x2990
mlx5e_napi_poll+0x2ae/0x8d0
net_rx_action+0x13e/0x590
irq_exit_rcu+0xf5/0x320
common_interrupt+0x80/0x90
asm_common_interrupt+0x22/0x40
cpuidle_enter_state+0xfb/0x273
cpu_startup_entry+0x15e/0x260
start_secondary+0x8a/0x90
secondary_startup_64_no_verify+0xfa/0xfb
freed by task 0 on cpu 9 at 260507.927527s:
rcu_core_si+0x4ff/0xf10
irq_exit_rcu+0xf5/0x320
sysvec_apic_timer_interrupt+0x6d/0x80
asm_sysvec_apic_timer_interrupt+0x16/0x20
cpuidle_enter_state+0xfb/0x273
cpu_startup_entry+0x15e/0x260
start_secondary+0x8a/0x90
secondary_startup_64_no_verify+0xfa/0xfb
Fixes: 83fccfc394 ("inet: fix potential deadlock in reqsk_queue_unlink()")
Reported-by: Martin KaFai Lau <martin.lau@kernel.org>
Closes: https://lore.kernel.org/netdev/eb6684d0-ffd9-4bdc-9196-33f690c25824@linux.dev/
Link: https://lore.kernel.org/netdev/b55e2ca0-42f2-4b7c-b445-6ffd87ca74a0@linux.dev/ [1]
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20241014223312.4254-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 22600596b6756b166fd052d5facb66287e6f0bad ]
After commit 8d7017fd62 ("blackhole_netdev: use blackhole_netdev to
invalidate dst entries"), blackhole_netdev was introduced to invalidate
dst cache entries on the TX path whenever the cache times out or is
flushed.
When two UDP sockets (sk1 and sk2) send messages to the same destination
simultaneously, they are using the same dst cache. If the dst cache is
invalidated on one path (sk2) while the other (sk1) is still transmitting,
sk1 may try to use the invalid dst entry.
CPU1 CPU2
udp_sendmsg(sk1) udp_sendmsg(sk2)
udp_send_skb()
ip_output()
<--- dst timeout or flushed
dst_dev_put()
ip_finish_output2()
ip_neigh_for_gw()
This results in a scenario where ip_neigh_for_gw() returns -EINVAL because
blackhole_dev lacks an in_dev, which is needed to initialize the neigh in
arp_constructor(). This error is then propagated back to userspace,
breaking the UDP application.
The patch fixes this issue by assigning an in_dev to blackhole_dev for
IPv4, similar to what was done for IPv6 in commit e5f80fcf86 ("ipv6:
give an IPv6 dev to blackhole_netdev"). This ensures that even when the
dst entry is invalidated with blackhole_dev, it will not fail to create
the neigh entry.
As devinet_init() is called ealier than blackhole_netdev_init() in system
booting, it can not assign the in_dev to blackhole_dev in devinet_init().
As Paolo suggested, add a separate late_initcall() in devinet.c to ensure
inet_blackhole_dev_init() is called after blackhole_netdev_init().
Fixes: 8d7017fd62 ("blackhole_netdev: use blackhole_netdev to invalidate dst entries")
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/3000792d45ca44e16c785ebe2b092e610e5b3df1.1728499633.git.lucien.xin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.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: 2a8a7c0eaa ("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 27c80efcc20486c82698f05f00e288b44513c86b ]
Fix tcp_rcv_synrecv_state_fastopen() to not zero retrans_stamp
if retransmits are outstanding.
tcp_fastopen_synack_timer() sets retrans_stamp, so typically we'll
need to zero retrans_stamp here to prevent spurious
retransmits_timed_out(). The logic to zero retrans_stamp is from this
2019 commit:
commit cd736d8b67 ("tcp: fix retrans timestamp on passive Fast Open")
However, in the corner case where the ACK of our TFO SYNACK carried
some SACK blocks that caused us to enter TCP_CA_Recovery then that
non-zero retrans_stamp corresponds to the active fast recovery, and we
need to leave retrans_stamp with its current non-zero value, for
correct ETIMEDOUT and undo behavior.
Fixes: cd736d8b67 ("tcp: fix retrans timestamp on passive Fast Open")
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/20241001200517.2756803-4-ncardwell.sw@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 3868ab0f192581eff978501a05f3dc2e01541d77 ]
The 2023 SIGCOMM paper "Improving Network Availability with Protective
ReRoute" has indicated Linux TCP's RTO-triggered txhash rehashing can
effectively reduce application disruption during outages. To better
measure the efficacy of this feature, this patch adds three more
detailed stats during RTO recovery and exports via TCP_INFO.
Applications and monitoring systems can leverage this data to measure
the network path diversity and end-to-end repair latency during network
outages to improve their network infrastructure.
The following counters are added to tcp_sock in order to track RTO
events over the lifetime of a TCP socket.
1. u16 total_rto - Counts the total number of RTO timeouts.
2. u16 total_rto_recoveries - Counts the total number of RTO recoveries.
3. u32 total_rto_time - Counts the total time spent (ms) in RTO
recoveries. (time spent in CA_Loss and
CA_Recovery states)
To compute total_rto_time, we add a new u32 rto_stamp field to
tcp_sock. rto_stamp records the start timestamp (ms) of the last RTO
recovery (CA_Loss).
Corresponding fields are also added to the tcp_info struct.
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>
Stable-dep-of: 27c80efcc204 ("tcp: fix TFO SYN_RECV to not zero retrans_stamp with retransmits out")
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: 1fbc340514 ("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 bc9f38c832 ("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 bc9f38c832 ("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 bc9f38c832, 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
bc9f38c832).
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: bc9f38c832 ("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 fc56878ca1c288e49b5cbb43860a5938e3463654 ]
If CONFIG_BRIDGE_NETFILTER is not enabled, which is the case for x86_64
defconfig, then building nf_reject_ipv4.c and nf_reject_ipv6.c with W=1
using gcc-14 results in the following warnings, which are treated as
errors:
net/ipv4/netfilter/nf_reject_ipv4.c: In function 'nf_send_reset':
net/ipv4/netfilter/nf_reject_ipv4.c:243:23: error: variable 'niph' set but not used [-Werror=unused-but-set-variable]
243 | struct iphdr *niph;
| ^~~~
cc1: all warnings being treated as errors
net/ipv6/netfilter/nf_reject_ipv6.c: In function 'nf_send_reset6':
net/ipv6/netfilter/nf_reject_ipv6.c:286:25: error: variable 'ip6h' set but not used [-Werror=unused-but-set-variable]
286 | struct ipv6hdr *ip6h;
| ^~~~
cc1: all warnings being treated as errors
Address this by reducing the scope of these local variables to where
they are used, which is code only compiled when CONFIG_BRIDGE_NETFILTER
enabled.
Compile tested and run through netfilter selftests.
Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Closes: https://lore.kernel.org/netfilter-devel/20240906145513.567781-1-andriy.shevchenko@linux.intel.com/
Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit a1e40ac5b5e9077fe1f7ae0eb88034db0f9ae1ab upstream.
Detect gso fraglist skbs with corrupted geometry (see below) and
pass these to skb_segment instead of skb_segment_list, as the first
can segment them correctly.
Valid SKB_GSO_FRAGLIST skbs
- consist of two or more segments
- the head_skb holds the protocol headers plus first gso_size
- one or more frag_list skbs hold exactly one segment
- all but the last must be gso_size
Optional datapath hooks such as NAT and BPF (bpf_skb_pull_data) can
modify these skbs, breaking these invariants.
In extreme cases they pull all data into skb linear. For UDP, this
causes a NULL ptr deref in __udpv4_gso_segment_list_csum at
udp_hdr(seg->next)->dest.
Detect invalid geometry due to pull, by checking head_skb size.
Don't just drop, as this may blackhole a destination. Convert to be
able to pass to regular skb_segment.
Link: https://lore.kernel.org/netdev/20240428142913.18666-1-shiming.cheng@mediatek.com/
Fixes: 9fd1ff5d2a ("udp: Support UDP fraglist GRO/GSO.")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20241001171752.107580-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.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 8c2bd38b95f75f3d2a08c93e35303e26d480d24e upstream.
ICMP messages are ratelimited :
After the blamed commits, the two rate limiters are applied in this order:
1) host wide ratelimit (icmp_global_allow())
2) Per destination ratelimit (inetpeer based)
In order to avoid side-channels attacks, we need to apply
the per destination check first.
This patch makes the following change :
1) icmp_global_allow() checks if the host wide limit is reached.
But credits are not yet consumed. This is deferred to 3)
2) The per destination limit is checked/updated.
This might add a new node in inetpeer tree.
3) icmp_global_consume() consumes tokens if prior operations succeeded.
This means that host wide ratelimit is still effective
in keeping inetpeer tree small even under DDOS.
As a bonus, I removed icmp_global.lock as the fast path
can use a lock-free operation.
Fixes: c0303efeab ("net: reduce cycles spend on ICMP replies that gets rate limited")
Fixes: 4cdf507d54 ("icmp: add a global rate limitation")
Reported-by: Keyu Man <keyu.man@email.ucr.edu>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Cc: Jesper Dangaard Brouer <hawk@kernel.org>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20240829144641.3880376-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
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>
commit c1668292689ad2ee16c9c1750a8044b0b0aad663 upstream.
The 'Fixes' commit recently changed the behaviour of TCP by skipping the
processing of the 3rd ACK when a sk->sk_socket is set. The goal was to
skip tcp_ack_snd_check() in tcp_rcv_state_process() not to send an
unnecessary ACK in case of simultaneous connect(). Unfortunately, that
had an impact on TFO and MPTCP.
I started to look at the impact on MPTCP, because the MPTCP CI found
some issues with the MPTCP Packetdrill tests [1]. Then Paolo Abeni
suggested me to look at the impact on TFO with "plain" TCP.
For MPTCP, when receiving the 3rd ACK of a request adding a new path
(MP_JOIN), sk->sk_socket will be set, and point to the MPTCP sock that
has been created when the MPTCP connection got established before with
the first path. The newly added 'goto' will then skip the processing of
the segment text (step 7) and not go through tcp_data_queue() where the
MPTCP options are validated, and some actions are triggered, e.g.
sending the MPJ 4th ACK [2] as demonstrated by the new errors when
running a packetdrill test [3] establishing a second subflow.
This doesn't fully break MPTCP, mainly the 4th MPJ ACK that will be
delayed. Still, we don't want to have this behaviour as it delays the
switch to the fully established mode, and invalid MPTCP options in this
3rd ACK will not be caught any more. This modification also affects the
MPTCP + TFO feature as well, and being the reason why the selftests
started to be unstable the last few days [4].
For TFO, the existing 'basic-cookie-not-reqd' test [5] was no longer
passing: if the 3rd ACK contains data, and the connection is accept()ed
before receiving them, these data would no longer be processed, and thus
not ACKed.
One last thing about MPTCP, in case of simultaneous connect(), a
fallback to TCP will be done, which seems fine:
`../common/defaults.sh`
0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_MPTCP) = 3
+0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+0 > S 0:0(0) <mss 1460, sackOK, TS val 100 ecr 0, nop, wscale 8, mpcapable v1 flags[flag_h] nokey>
+0 < S 0:0(0) win 1000 <mss 1460, sackOK, TS val 407 ecr 0, nop, wscale 8, mpcapable v1 flags[flag_h] nokey>
+0 > S. 0:0(0) ack 1 <mss 1460, sackOK, TS val 330 ecr 0, nop, wscale 8, mpcapable v1 flags[flag_h] nokey>
+0 < S. 0:0(0) ack 1 win 65535 <mss 1460, sackOK, TS val 700 ecr 100, nop, wscale 8, mpcapable v1 flags[flag_h] key[skey=2]>
+0 > . 1:1(0) ack 1 <nop, nop, TS val 845707014 ecr 700, nop, nop, sack 0:1>
Simultaneous SYN-data crossing is also not supported by TFO, see [6].
Kuniyuki Iwashima suggested to restrict the processing to SYN+ACK only:
that's a more generic solution than the one initially proposed, and
also enough to fix the issues described above.
Later on, Eric Dumazet mentioned that an ACK should still be sent in
reaction to the second SYN+ACK that is received: not sending a DUPACK
here seems wrong and could hurt:
0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+0 > S 0:0(0) <mss 1460, sackOK, TS val 1000 ecr 0,nop,wscale 8>
+0 < S 0:0(0) win 1000 <mss 1000, sackOK, nop, nop>
+0 > S. 0:0(0) ack 1 <mss 1460, sackOK, TS val 3308134035 ecr 0,nop,wscale 8>
+0 < S. 0:0(0) ack 1 win 1000 <mss 1000, sackOK, nop, nop>
+0 > . 1:1(0) ack 1 <nop, nop, sack 0:1> // <== Here
So in this version, the 'goto consume' is dropped, to always send an ACK
when switching from TCP_SYN_RECV to TCP_ESTABLISHED. This ACK will be
seen as a DUPACK -- with DSACK if SACK has been negotiated -- in case of
simultaneous SYN crossing: that's what is expected here.
Link: https://github.com/multipath-tcp/mptcp_net-next/actions/runs/9936227696 [1]
Link: https://datatracker.ietf.org/doc/html/rfc8684#fig_tokens [2]
Link: https://github.com/multipath-tcp/packetdrill/blob/mptcp-net-next/gtests/net/mptcp/syscalls/accept.pkt#L28 [3]
Link: https://netdev.bots.linux.dev/contest.html?executor=vmksft-mptcp-dbg&test=mptcp-connect-sh [4]
Link: https://github.com/google/packetdrill/blob/master/gtests/net/tcp/fastopen/server/basic-cookie-not-reqd.pkt#L21 [5]
Link: https://github.com/google/packetdrill/blob/master/gtests/net/tcp/fastopen/client/simultaneous-fast-open.pkt [6]
Fixes: 23e89e8ee7be ("tcp: Don't drop SYN+ACK for simultaneous connect().")
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Suggested-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240724-upstream-net-next-20240716-tcp-3rd-ack-consume-sk_socket-v3-1-d48339764ce9@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 23e89e8ee7be73e21200947885a6d3a109a2c58d ]
RFC 9293 states that in the case of simultaneous connect(), the connection
gets established when SYN+ACK is received. [0]
TCP Peer A TCP Peer B
1. CLOSED CLOSED
2. SYN-SENT --> <SEQ=100><CTL=SYN> ...
3. SYN-RECEIVED <-- <SEQ=300><CTL=SYN> <-- SYN-SENT
4. ... <SEQ=100><CTL=SYN> --> SYN-RECEIVED
5. SYN-RECEIVED --> <SEQ=100><ACK=301><CTL=SYN,ACK> ...
6. ESTABLISHED <-- <SEQ=300><ACK=101><CTL=SYN,ACK> <-- SYN-RECEIVED
7. ... <SEQ=100><ACK=301><CTL=SYN,ACK> --> ESTABLISHED
However, since commit 0c24604b68 ("tcp: implement RFC 5961 4.2"), such a
SYN+ACK is dropped in tcp_validate_incoming() and responded with Challenge
ACK.
For example, the write() syscall in the following packetdrill script fails
with -EAGAIN, and wrong SNMP stats get incremented.
0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3
+0 connect(3, ..., ...) = -1 EINPROGRESS (Operation now in progress)
+0 > S 0:0(0) <mss 1460,sackOK,TS val 1000 ecr 0,nop,wscale 8>
+0 < S 0:0(0) win 1000 <mss 1000>
+0 > S. 0:0(0) ack 1 <mss 1460,sackOK,TS val 3308134035 ecr 0,nop,wscale 8>
+0 < S. 0:0(0) ack 1 win 1000
+0 write(3, ..., 100) = 100
+0 > P. 1:101(100) ack 1
--
# packetdrill cross-synack.pkt
cross-synack.pkt:13: runtime error in write call: Expected result 100 but got -1 with errno 11 (Resource temporarily unavailable)
# nstat
...
TcpExtTCPChallengeACK 1 0.0
TcpExtTCPSYNChallenge 1 0.0
The problem is that bpf_skops_established() is triggered by the Challenge
ACK instead of SYN+ACK. This causes the bpf prog to miss the chance to
check if the peer supports a TCP option that is expected to be exchanged
in SYN and SYN+ACK.
Let's accept a bare SYN+ACK for active-open TCP_SYN_RECV sockets to avoid
such a situation.
Note that tcp_ack_snd_check() in tcp_rcv_state_process() is skipped not to
send an unnecessary ACK, but this could be a bit risky for net.git, so this
targets for net-next.
Link: https://www.rfc-editor.org/rfc/rfc9293.html#section-3.5-7 [0]
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240710171246.87533-2-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 61e2bbafb00e4b9a5de45e6448a7b6b818658576 ]
When I was doing some experiments, I found that when using the first
parameter, namely, struct net, in ip_metrics_convert() always triggers NULL
pointer crash. Then I digged into this part, realizing that we can remove
this one due to its uselessness.
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit c51db4ac10d57c366f9a92121e3889bfc6c324cd upstream.
After commit 1eeb50435739 ("tcp/dccp: do not care about
families in inet_twsk_purge()") tcp_twsk_purge() is
no longer potentially called from a module.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit b128ed5ab27330deeeaf51ea8bb69f1442a96f7f ]
When assembling fraglist GSO packets, udp4_gro_complete does not set
skb->csum_start, which makes the extra validation in __udp_gso_segment fail.
Fixes: 89add40066f9 ("net: drop bad gso csum_start and offset in virtio_net_hdr")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240819150621.59833-1-nbd@nbd.name
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 565d121b69980637f040eb4d84289869cdaabedf ]
Its possible that two threads call tcp_sk_exit_batch() concurrently,
once from the cleanup_net workqueue, once from a task that failed to clone
a new netns. In the latter case, error unwinding calls the exit handlers
in reverse order for the 'failed' netns.
tcp_sk_exit_batch() calls tcp_twsk_purge().
Problem is that since commit b099ce2602 ("net: Batch inet_twsk_purge"),
this function picks up twsk in any dying netns, not just the one passed
in via exit_batch list.
This means that the error unwind of setup_net() can "steal" and destroy
timewait sockets belonging to the exiting netns.
This allows the netns exit worker to proceed to call
WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount));
without the expected 1 -> 0 transition, which then splats.
At same time, error unwind path that is also running inet_twsk_purge()
will splat as well:
WARNING: .. at lib/refcount.c:31 refcount_warn_saturate+0x1ed/0x210
...
refcount_dec include/linux/refcount.h:351 [inline]
inet_twsk_kill+0x758/0x9c0 net/ipv4/inet_timewait_sock.c:70
inet_twsk_deschedule_put net/ipv4/inet_timewait_sock.c:221
inet_twsk_purge+0x725/0x890 net/ipv4/inet_timewait_sock.c:304
tcp_sk_exit_batch+0x1c/0x170 net/ipv4/tcp_ipv4.c:3522
ops_exit_list+0x128/0x180 net/core/net_namespace.c:178
setup_net+0x714/0xb40 net/core/net_namespace.c:375
copy_net_ns+0x2f0/0x670 net/core/net_namespace.c:508
create_new_namespaces+0x3ea/0xb10 kernel/nsproxy.c:110
... because refcount_dec() of tw_refcount unexpectedly dropped to 0.
This doesn't seem like an actual bug (no tw sockets got lost and I don't
see a use-after-free) but as erroneous trigger of debug check.
Add a mutex to force strict ordering: the task that calls tcp_twsk_purge()
blocks other task from doing final _dec_and_test before mutex-owner has
removed all tw sockets of dying netns.
Fixes: e9bd0cca09 ("tcp: Don't allocate tcp_death_row outside of struct netns_ipv4.")
Reported-by: syzbot+8ea26396ff85d23a8929@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/0000000000003a5292061f5e4e19@google.com/
Link: https://lore.kernel.org/netdev/20240812140104.GA21559@breakpoint.cc/
Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240812222857.29837-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 1eeb5043573981f3a1278876515851b7f6b1df1b ]
We lost ability to unload ipv6 module a long time ago.
Instead of calling expensive inet_twsk_purge() twice,
we can handle all families in one round.
Also remove an extra line added in my prior patch,
per Kuniyuki Iwashima feedback.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/netdev/20240327192934.6843-1-kuniyu@amazon.com/
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240329153203.345203-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 565d121b6998 ("tcp: prevent concurrent execution of tcp_sk_exit_batch")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 50e2907ef8bb52cf80ecde9eec5c4dac07177146 ]
TCP ehash table is often sparsely populated.
inet_twsk_purge() spends too much time calling cond_resched().
This patch can reduce time spent in inet_twsk_purge() by 20x.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://lore.kernel.org/r/20240327191206.508114-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 565d121b6998 ("tcp: prevent concurrent execution of tcp_sk_exit_batch")
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit a2cbb1603943281a604f5adc48079a148db5cb0d ]
This patch is based on the discussions between Neal Cardwell and
Eric Dumazet in the link
https://lore.kernel.org/netdev/20240726204105.1466841-1-quic_subashab@quicinc.com/
It was correctly pointed out that tp->window_clamp would not be
updated in cases where net.ipv4.tcp_moderate_rcvbuf=0 or if
(copied <= tp->rcvq_space.space). While it is expected for most
setups to leave the sysctl enabled, the latter condition may
not end up hitting depending on the TCP receive queue size and
the pattern of arriving data.
The updated check should be hit only on initial MSS update from
TCP_MIN_MSS to measured MSS value and subsequently if there was
an update to a larger value.
Fixes: 05f76b2d634e ("tcp: Adjust clamping window for applications specifying SO_RCVBUF")
Signed-off-by: Sean Tranchetti <quic_stranche@quicinc.com>
Signed-off-by: Subash Abhinov Kasiviswanathan <quic_subashab@quicinc.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit dd89a81d850fa9a65f67b4527c0e420d15bf836c ]
Drop the WARN_ON_ONCE inn gue_gro_receive if the encapsulated type is
not known or does not have a GRO handler.
Such a packet is easily constructed. Syzbot generates them and sets
off this warning.
Remove the warning as it is expected and not actionable.
The warning was previously reduced from WARN_ON to WARN_ON_ONCE in
commit 270136613b ("fou: Do WARN_ON_ONCE in gue_gro_receive for bad
proto callbacks").
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20240614122552.1649044-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 6532e257aa73645e28dee5b2232cc3c88be62083 ]
This is inspired by several syzbot reports where
tcp_metrics_flush_all() was seen in the traces.
We can avoid acquiring tcp_metrics_lock for empty buckets,
and we should add one cond_resched() to break potential long loops.
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>
commit 89add40066f9ed9abe5f7f886fe5789ff7e0c50e upstream.
Tighten csum_start and csum_offset checks in virtio_net_hdr_to_skb
for GSO packets.
The function already checks that a checksum requested with
VIRTIO_NET_HDR_F_NEEDS_CSUM is in skb linear. But for GSO packets
this might not hold for segs after segmentation.
Syzkaller demonstrated to reach this warning in skb_checksum_help
offset = skb_checksum_start_offset(skb);
ret = -EINVAL;
if (WARN_ON_ONCE(offset >= skb_headlen(skb)))
By injecting a TSO packet:
WARNING: CPU: 1 PID: 3539 at net/core/dev.c:3284 skb_checksum_help+0x3d0/0x5b0
ip_do_fragment+0x209/0x1b20 net/ipv4/ip_output.c:774
ip_finish_output_gso net/ipv4/ip_output.c:279 [inline]
__ip_finish_output+0x2bd/0x4b0 net/ipv4/ip_output.c:301
iptunnel_xmit+0x50c/0x930 net/ipv4/ip_tunnel_core.c:82
ip_tunnel_xmit+0x2296/0x2c70 net/ipv4/ip_tunnel.c:813
__gre_xmit net/ipv4/ip_gre.c:469 [inline]
ipgre_xmit+0x759/0xa60 net/ipv4/ip_gre.c:661
__netdev_start_xmit include/linux/netdevice.h:4850 [inline]
netdev_start_xmit include/linux/netdevice.h:4864 [inline]
xmit_one net/core/dev.c:3595 [inline]
dev_hard_start_xmit+0x261/0x8c0 net/core/dev.c:3611
__dev_queue_xmit+0x1b97/0x3c90 net/core/dev.c:4261
packet_snd net/packet/af_packet.c:3073 [inline]
The geometry of the bad input packet at tcp_gso_segment:
[ 52.003050][ T8403] skb len=12202 headroom=244 headlen=12093 tailroom=0
[ 52.003050][ T8403] mac=(168,24) mac_len=24 net=(192,52) trans=244
[ 52.003050][ T8403] shinfo(txflags=0 nr_frags=1 gso(size=1552 type=3 segs=0))
[ 52.003050][ T8403] csum(0x60000c7 start=199 offset=1536
ip_summed=3 complete_sw=0 valid=0 level=0)
Mitigate with stricter input validation.
csum_offset: for GSO packets, deduce the correct value from gso_type.
This is already done for USO. Extend it to TSO. Let UFO be:
udp[46]_ufo_fragment ignores these fields and always computes the
checksum in software.
csum_start: finding the real offset requires parsing to the transport
header. Do not add a parser, use existing segmentation parsing. Thanks
to SKB_GSO_DODGY, that also catches bad packets that are hw offloaded.
Again test both TSO and USO. Do not test UFO for the above reason, and
do not test UDP tunnel offload.
GSO packet are almost always CHECKSUM_PARTIAL. USO packets may be
CHECKSUM_NONE since commit 10154dbded6d6 ("udp: Allow GSO transmit
from devices with no checksum offload"), but then still these fields
are initialized correctly in udp4_hwcsum/udp6_hwcsum_outgoing. So no
need to test for ip_summed == CHECKSUM_PARTIAL first.
This revises an existing fix mentioned in the Fixes tag, which broke
small packets with GSO offload, as detected by kselftests.
Link: https://syzkaller.appspot.com/bug?extid=e1db31216c789f552871
Link: https://lore.kernel.org/netdev/20240723223109.2196886-1-kuba@kernel.org
Fixes: e269d79c7d35 ("net: missing check virtio")
Cc: stable@vger.kernel.org
Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240729201108.1615114-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 05f76b2d634e65ab34472802d9b142ea9e03f74e ]
tp->scaling_ratio is not updated based on skb->len/skb->truesize once
SO_RCVBUF is set leading to the maximum window scaling to be 25% of
rcvbuf after
commit dfa2f04833 ("tcp: get rid of sysctl_tcp_adv_win_scale")
and 50% of rcvbuf after
commit 697a6c8cec03 ("tcp: increase the default TCP scaling ratio").
50% tries to emulate the behavior of older kernels using
sysctl_tcp_adv_win_scale with default value.
Systems which were using a different values of sysctl_tcp_adv_win_scale
in older kernels ended up seeing reduced download speeds in certain
cases as covered in https://lists.openwall.net/netdev/2024/05/15/13
While the sysctl scheme is no longer acceptable, the value of 50% is
a bit conservative when the skb->len/skb->truesize ratio is later
determined to be ~0.66.
Applications not specifying SO_RCVBUF update the window scaling and
the receiver buffer every time data is copied to userspace. This
computation is now used for applications setting SO_RCVBUF to update
the maximum window scaling while ensuring that the receive buffer
is within the application specified limit.
Fixes: dfa2f04833 ("tcp: get rid of sysctl_tcp_adv_win_scale")
Signed-off-by: Sean Tranchetti <quic_stranche@quicinc.com>
Signed-off-by: Subash Abhinov Kasiviswanathan <quic_subashab@quicinc.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 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: 430a049190 ("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: 8e36360ae8 ("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>
commit 6807352353561187a718e87204458999dbcbba1b upstream.
By default, an address assigned to the output interface is selected when
the source address is not specified. This is problematic when a route,
configured in a vrf, uses an interface from another vrf (aka route leak).
The original vrf does not own the selected source address.
Let's add a check against the output interface and call the appropriate
function to select the source address.
CC: stable@vger.kernel.org
Fixes: 8cbb512c92 ("net: Add source address lookup op for VRF")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240710081521.3809742-2-nicolas.dichtel@6wind.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit f036e68212c11e5a7edbb59b5e25299341829485 ]
The TOS value that is returned to user space in the route get reply is
the one with which the lookup was performed ('fl4->flowi4_tos'). This is
fine when the matched route is configured with a TOS as it would not
match if its TOS value did not match the one with which the lookup was
performed.
However, matching on TOS is only performed when the route's TOS is not
zero. It is therefore possible to have the kernel incorrectly return a
non-zero TOS:
# ip link add name dummy1 up type dummy
# ip address add 192.0.2.1/24 dev dummy1
# ip route get fibmatch 192.0.2.2 tos 0xfc
192.0.2.0/24 tos 0x1c dev dummy1 proto kernel scope link src 192.0.2.1
Fix by instead returning the DSCP field from the FIB result structure
which was populated during the route lookup.
Output after the patch:
# ip link add name dummy1 up type dummy
# ip address add 192.0.2.1/24 dev dummy1
# ip route get fibmatch 192.0.2.2 tos 0xfc
192.0.2.0/24 dev dummy1 proto kernel scope link src 192.0.2.1
Extend the existing selftests to not only verify that the correct route
is returned, but that it is also returned with correct "tos" value (or
without it).
Fixes: b61798130f ("net: ipv4: RTM_GETROUTE: return matched fib result when requested")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
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 338bb57e4c2a1c2c6fc92f9c0bd35be7587adca7 ]
The TOS value that is returned to user space in the route get reply is
the one with which the lookup was performed ('fl4->flowi4_tos'). This is
fine when the matched route is configured with a TOS as it would not
match if its TOS value did not match the one with which the lookup was
performed.
However, matching on TOS is only performed when the route's TOS is not
zero. It is therefore possible to have the kernel incorrectly return a
non-zero TOS:
# ip link add name dummy1 up type dummy
# ip address add 192.0.2.1/24 dev dummy1
# ip route get 192.0.2.2 tos 0xfc
192.0.2.2 tos 0x1c dev dummy1 src 192.0.2.1 uid 0
cache
Fix by adding a DSCP field to the FIB result structure (inside an
existing 4 bytes hole), populating it in the route lookup and using it
when filling the route get reply.
Output after the patch:
# ip link add name dummy1 up type dummy
# ip address add 192.0.2.1/24 dev dummy1
# ip route get 192.0.2.2 tos 0xfc
192.0.2.2 dev dummy1 src 192.0.2.1 uid 0
cache
Fixes: 1a00fee4ff ("ipv4: Remove rt_key_{src,dst,tos} from struct rtable.")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
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 fde6f897f2a184546bf5516ac736523ef24dc6a7 ]
These functions have races when they:
1) Write sk->sk_err
2) call sk_error_report(sk)
3) call tcp_done(sk)
As described in prior patches in this series:
An smp_wmb() is missing.
We should call tcp_done() before sk_error_report(sk)
to have consistent tcp_poll() results on SMP hosts.
Use tcp_done_with_error() where we centralized the
correct sequence.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20240528125253.1966136-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 853c3bd7b7917670224c9fe5245bd045cac411dd ]
I noticed flakes in a packetdrill test, expecting an epoll_wait()
to return EPOLLERR | EPOLLHUP on a failed connect() attempt,
after multiple SYN retransmits. It sometimes return EPOLLERR only.
The issue is that tcp_write_err():
1) writes an error in sk->sk_err,
2) calls sk_error_report(),
3) then calls tcp_done().
tcp_done() is writing SHUTDOWN_MASK into sk->sk_shutdown,
among other things.
Problem is that the awaken user thread (from 2) sk_error_report())
might call tcp_poll() before tcp_done() has written sk->sk_shutdown.
tcp_poll() only sees a non zero sk->sk_err and returns EPOLLERR.
This patch fixes the issue by making sure to call sk_error_report()
after tcp_done().
tcp_write_err() also lacks an smp_wmb().
We can reuse tcp_done_with_error() to factor out the details,
as Neal suggested.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20240528125253.1966136-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 5e514f1cba090e1c8fff03e92a175eccfe46305f ]
tcp_reset() ends with a sequence that is carefuly ordered.
We need to fix [e]poll bugs in the following patches,
it makes sense to use a common helper.
Suggested-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Link: https://lore.kernel.org/r/20240528125253.1966136-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Stable-dep-of: 853c3bd7b791 ("tcp: fix race in tcp_write_err()")
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: e27cca96cd ("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>
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 e89688e3e9 ("net: tcp:
fix unexcepted socket die when snd_wnd is 0"), the issue
would last 2 minutes instead of 4.
Fixes: b701a99e43 ("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: e89688e3e9 ("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 6ba8a3b19e ("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 76be93fc07 ("tcp: allow at most one TLP probe per flight").
So we associate this fix with that later commit.
Fixes: 76be93fc07 ("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>
Eyal Birger