IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an
email to Administrator. User accounts are meant only to access repo
and report issues and/or generate pull requests.
This is a purpose-specific Git hosting for
BaseALT
projects. Thank you for your understanding!
Только зарегистрированные пользователи имеют доступ к сервису!
Для получения аккаунта, обратитесь к администратору.
commit 158390e45612ef0fde160af0826f1740c36daf21 upstream.
The max number of UDP gso segments is intended to cap to UDP_MAX_SEGMENTS,
this is checked in udp_send_skb():
if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
kfree_skb(skb);
return -EINVAL;
}
skb->len contains network and transport header len here, we should use
only data len instead.
Fixes: bec1f6f69736 ("udp: generate gso with UDP_SEGMENT")
Signed-off-by: Jianguo Wu <wujianguo@chinatelecom.cn>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/r/900742e5-81fb-30dc-6e0b-375c6cdd7982@163.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 213f5f8f31f10aa1e83187ae20fb7fa4e626b724 upstream.
Before commit faa041a40b9f ("ipv4: Create cleanup helper for fib_nh")
changes to net->ipv4.fib_num_tclassid_users were protected by RTNL.
After the change, this is no longer the case, as free_fib_info_rcu()
runs after rcu grace period, without rtnl being held.
Fixes: faa041a40b9f ("ipv4: Create cleanup helper for fib_nh")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: David Ahern <dsahern@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit cdef485217d30382f3bf6448c54b4401648fe3f1 upstream.
The kernel leaks memory when a `fib` rule is present in IPv6 nftables
firewall rules and a suppress_prefix rule is present in the IPv6 routing
rules (used by certain tools such as wg-quick). In such scenarios, every
incoming packet will leak an allocation in `ip6_dst_cache` slab cache.
After some hours of `bpftrace`-ing and source code reading, I tracked
down the issue to ca7a03c41753 ("ipv6: do not free rt if
FIB_LOOKUP_NOREF is set on suppress rule").
The problem with that change is that the generic `args->flags` always have
`FIB_LOOKUP_NOREF` set[1][2] but the IPv6-specific flag
`RT6_LOOKUP_F_DST_NOREF` might not be, leading to `fib6_rule_suppress` not
decreasing the refcount when needed.
How to reproduce:
- Add the following nftables rule to a prerouting chain:
meta nfproto ipv6 fib saddr . mark . iif oif missing drop
This can be done with:
sudo nft create table inet test
sudo nft create chain inet test test_chain '{ type filter hook prerouting priority filter + 10; policy accept; }'
sudo nft add rule inet test test_chain meta nfproto ipv6 fib saddr . mark . iif oif missing drop
- Run:
sudo ip -6 rule add table main suppress_prefixlength 0
- Watch `sudo slabtop -o | grep ip6_dst_cache` to see memory usage increase
with every incoming ipv6 packet.
This patch exposes the protocol-specific flags to the protocol
specific `suppress` function, and check the protocol-specific `flags`
argument for RT6_LOOKUP_F_DST_NOREF instead of the generic
FIB_LOOKUP_NOREF when decreasing the refcount, like this.
[1]: ca7a03c417/net/ipv6/fib6_rules.c (L71)
[2]: ca7a03c417/net/ipv6/fib6_rules.c (L99)
Link: https://bugzilla.kernel.org/show_bug.cgi?id=215105
Fixes: ca7a03c41753 ("ipv6: do not free rt if FIB_LOOKUP_NOREF is set on suppress rule")
Cc: stable@vger.kernel.org
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 6def480181f15f6d9ec812bca8cbc62451ba314c ]
When kmemdup called failed and register_net_sysctl return NULL, should
return ENOMEM instead of ENOBUFS
Signed-off-by: liuguoqiang <liuguoqiang@uniontech.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit e0fecb289ad3fd2245cdc50bf450b97fcca39884 ]
A prior patch increased the size of struct tcp_zerocopy_receive
but did not update do_tcp_getsockopt() handling to properly account
for this.
This patch simply reintroduces content erroneously cut from the
referenced prior patch that handles the new struct size.
Fixes: 18fb76ed5386 ("net-zerocopy: Copy straggler unaligned data for TCP Rx. zerocopy.")
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: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 4e1fddc98d2585ddd4792b5e44433dcee7ece001 ]
While testing BIG TCP patch series, I was expecting that TCP_RR workloads
with 80KB requests/answers would send one 80KB TSO packet,
then being received as a single GRO packet.
It turns out this was not happening, and the root cause was that
cubic Hystart ACK train was triggering after a few (2 or 3) rounds of RPC.
Hystart was wrongly setting CWND/SSTHRESH to 30, while my RPC
needed a budget of ~20 segments.
Ideally these TCP_RR flows should not exit slow start.
Cubic Hystart should reset itself at each round, instead of assuming
every TCP flow is a bulk one.
Note that even after this patch, Hystart can still trigger, depending
on scheduling artifacts, but at a higher CWND/SSTHRESH threshold,
keeping optimal TSO packet sizes.
Tested:
ip link set dev eth0 gro_ipv6_max_size 131072 gso_ipv6_max_size 131072
nstat -n; netperf -H ... -t TCP_RR -l 5 -- -r 80000,80000 -K cubic; nstat|egrep "Ip6InReceives|Hystart|Ip6OutRequests"
Before:
8605
Ip6InReceives 87541 0.0
Ip6OutRequests 129496 0.0
TcpExtTCPHystartTrainDetect 1 0.0
TcpExtTCPHystartTrainCwnd 30 0.0
After:
8760
Ip6InReceives 88514 0.0
Ip6OutRequests 87975 0.0
Fixes: ae27e98a5152 ("[TCP] CUBIC v2.3")
Co-developed-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Link: https://lore.kernel.org/r/20211123202535.1843771-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 1005f19b9357b81aa64e1decd08d6e332caaa284 ]
When replacing a nexthop group, we must release the IPv6 per-cpu dsts of
the removed nexthop entries after an RCU grace period because they
contain references to the nexthop's net device and to the fib6 info.
With specific series of events[1] we can reach net device refcount
imbalance which is unrecoverable. IPv4 is not affected because dsts
don't take a refcount on the route.
[1]
$ ip nexthop list
id 200 via 2002:db8::2 dev bridge.10 scope link onlink
id 201 via 2002:db8::3 dev bridge scope link onlink
id 203 group 201/200
$ ip -6 route
2001:db8::10 nhid 203 metric 1024 pref medium
nexthop via 2002:db8::3 dev bridge weight 1 onlink
nexthop via 2002:db8::2 dev bridge.10 weight 1 onlink
Create rt6_info through one of the multipath legs, e.g.:
$ taskset -a -c 1 ./pkt_inj 24 bridge.10 2001:db8::10
(pkt_inj is just a custom packet generator, nothing special)
Then remove that leg from the group by replace (let's assume it is id
200 in this case):
$ ip nexthop replace id 203 group 201
Now remove the IPv6 route:
$ ip -6 route del 2001:db8::10/128
The route won't be really deleted due to the stale rt6_info holding 1
refcnt in nexthop id 200.
At this point we have the following reference count dependency:
(deleted) IPv6 route holds 1 reference over nhid 203
nh 203 holds 1 ref over id 201
nh 200 holds 1 ref over the net device and the route due to the stale
rt6_info
Now to create circular dependency between nh 200 and the IPv6 route, and
also to get a reference over nh 200, restore nhid 200 in the group:
$ ip nexthop replace id 203 group 201/200
And now we have a permanent circular dependncy because nhid 203 holds a
reference over nh 200 and 201, but the route holds a ref over nh 203 and
is deleted.
To trigger the bug just delete the group (nhid 203):
$ ip nexthop del id 203
It won't really be deleted due to the IPv6 route dependency, and now we
have 2 unlinked and deleted objects that reference each other: the group
and the IPv6 route. Since the group drops the reference it holds over its
entries at free time (i.e. its own refcount needs to drop to 0) that will
never happen and we get a permanent ref on them, since one of the entries
holds a reference over the IPv6 route it will also never be released.
At this point the dependencies are:
(deleted, only unlinked) IPv6 route holds reference over group nh 203
(deleted, only unlinked) group nh 203 holds reference over nh 201 and 200
nh 200 holds 1 ref over the net device and the route due to the stale
rt6_info
This is the last point where it can be fixed by running traffic through
nh 200, and specifically through the same CPU so the rt6_info (dst) will
get released due to the IPv6 genid, that in turn will free the IPv6
route, which in turn will free the ref count over the group nh 203.
If nh 200 is deleted at this point, it will never be released due to the
ref from the unlinked group 203, it will only be unlinked:
$ ip nexthop del id 200
$ ip nexthop
$
Now we can never release that stale rt6_info, we have IPv6 route with ref
over group nh 203, group nh 203 with ref over nh 200 and 201, nh 200 with
rt6_info (dst) with ref over the net device and the IPv6 route. All of
these objects are only unlinked, and cannot be released, thus they can't
release their ref counts.
Message from syslogd@dev at Nov 19 14:04:10 ...
kernel:[73501.828730] unregister_netdevice: waiting for bridge.10 to become free. Usage count = 3
Message from syslogd@dev at Nov 19 14:04:20 ...
kernel:[73512.068811] unregister_netdevice: waiting for bridge.10 to become free. Usage count = 3
Fixes: 7bf4796dd099 ("nexthops: add support for replace")
Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 70701b83e208767f2720d8cd3e6a62cddafb3a30 ]
TCP Receive zerocopy iterates through the SKB queue via
tcp_recv_skb(), acquiring a pointer to an SKB and an offset within
that SKB to read from. From there, it iterates the SKB frags array to
determine which offset to start remapping pages from.
However, this is built on the assumption that the offset read so far
within the SKB is smaller than the SKB length. If this assumption is
violated, we can attempt to read an invalid frags array element, which
would cause a fault.
tcp_recv_skb() can cause such an SKB to be returned when the TCP FIN
flag is set. Therefore, we must guard against this occurrence inside
skb_advance_frag().
One way that we can reproduce this error follows:
1) In a receiver program, call getsockopt(TCP_ZEROCOPY_RECEIVE) with:
char some_array[32 * 1024];
struct tcp_zerocopy_receive zc = {
.copybuf_address = (__u64) &some_array[0],
.copybuf_len = 32 * 1024,
};
2) In a sender program, after a TCP handshake, send the following
sequence of packets:
i) Seq = [X, X+4000]
ii) Seq = [X+4000, X+5000]
iii) Seq = [X+4000, X+5000], Flags = FIN | URG, urgptr=1000
(This can happen without URG, if we have a signal pending, but URG is
a convenient way to reproduce the behaviour).
In this case, the following event sequence will occur on the receiver:
tcp_zerocopy_receive():
-> receive_fallback_to_copy() // copybuf_len >= inq
-> tcp_recvmsg_locked() // reads 5000 bytes, then breaks due to URG
-> tcp_recv_skb() // yields skb with skb->len == offset
-> tcp_zerocopy_set_hint_for_skb()
-> skb_advance_to_frag() // will returns a frags ptr. >= nr_frags
-> find_next_mappable_frag() // will dereference this bad frags ptr.
With this patch, skb_advance_to_frag() will no longer return an
invalid frags pointer, and will return NULL instead, fixing the issue.
Signed-off-by: Arjun Roy <arjunroy@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 05255b823a61 ("tcp: add TCP_ZEROCOPY_RECEIVE support for zerocopy receive")
Link: https://lore.kernel.org/r/20211111235215.2605384-1-arjunroy.kdev@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 7fba5309efe24e4f0284ef4b8663cdf401035e72 ]
Refactor skb frag fast-forwarding 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.
skb_advance_to_frag(), given a skb and an offset into the skb,
iterates from the first frag for the skb until we're at the frag
specified by the offset. Assuming the offset provided refers to how
many bytes in the skb are already read, the returned frag points to
the next frag we may read from, while offset_frag is set to the number
of bytes from this frag that we have already read.
If frag is not null and offset_frag is equal to 0, then we may be able
to map this frag's page into the process address space with
vm_insert_page(). However, if offset_frag is not equal to 0, then we
cannot do so.
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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 18fb76ed53865c1b5d5f0157b1b825704590beb5 ]
When TCP receive zerocopy does not successfully map the entire
requested space, it outputs a 'hint' that the caller should recvmsg().
Augment zerocopy to accept a user buffer that it tries to copy this
hint into - if it is possible to copy the entire hint, it will do so.
This elides a recvmsg() call for received traffic that isn't exactly
page-aligned in size.
This was tested with RPC-style traffic of arbitrary sizes. Normally,
each received message required at least one getsockopt() call, and one
recvmsg() call for the remaining unaligned data.
With this change, almost all of the recvmsg() calls are eliminated,
leading to a savings of about 25%-50% in number of system calls
for RPC-style workloads.
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>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit b8b8315e39ffaca82e79d86dde26e9144addf66b ]
We do not need to handle unhash from BPF side we can simply wait for the
close to happen. The original concern was a socket could transition from
ESTABLISHED state to a new state while the BPF hook was still attached.
But, we convinced ourself this is no longer possible and we also improved
BPF sockmap to handle listen sockets so this is no longer a problem.
More importantly though there are cases where unhash is called when data is
in the receive queue. The BPF unhash logic will flush this data which is
wrong. To be correct it should keep the data in the receive queue and allow
a receiving application to continue reading the data. This may happen when
tcp_abort() is received for example. Instead of complicating the logic in
unhash simply moving all this to tcp_close() hook solves this.
Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Tested-by: Jussi Maki <joamaki@gmail.com>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/20211103204736.248403-3-john.fastabend@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit cf12e6f9124629b18a6182deefc0315f0a73a199 ]
v1: Implement a more general statement as recommended by Eric Dumazet. The
sequence number will be advanced, so this check will fix the FIN case and
other cases.
A customer reported sockets stuck in the CLOSING state. A Vmcore revealed that
the write_queue was not empty as determined by tcp_write_queue_empty() but the
sk_buff containing the FIN flag had been freed and the socket was zombied in
that state. Corresponding pcaps show no FIN from the Linux kernel on the wire.
Some instrumentation was added to the kernel and it was found that there is a
timing window where tcp_sendmsg() can run after tcp_send_fin().
tcp_sendmsg() will hit an error, for example:
1269 ▹ if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))↩
1270 ▹ ▹ goto do_error;↩
tcp_remove_empty_skb() will then free the FIN sk_buff as "skb->len == 0". The
TCP socket is now wedged in the FIN-WAIT-1 state because the FIN is never sent.
If the other side sends a FIN packet the socket will transition to CLOSING and
remain that way until the system is rebooted.
Fix this by checking for the FIN flag in the sk_buff and don't free it if that
is the case. Testing confirmed that fixed the issue.
Fixes: fdfc5c8594c2 ("tcp: remove empty skb from write queue in error cases")
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Reported-by: Monir Zouaoui <Monir.Zouaoui@mail.schwarz>
Reported-by: Simon Stier <simon.stier@mail.schwarz>
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 19757cebf0c5016a1f36f7fe9810a9f0b33c0832 ]
Use of percpu_counter structure to track count of orphaned
sockets is causing problems on modern hosts with 256 cpus
or more.
Stefan Bach reported a serious spinlock contention in real workloads,
that I was able to reproduce with a netfilter rule dropping
incoming FIN packets.
53.56% server [kernel.kallsyms] [k] queued_spin_lock_slowpath
|
---queued_spin_lock_slowpath
|
--53.51%--_raw_spin_lock_irqsave
|
--53.51%--__percpu_counter_sum
tcp_check_oom
|
|--39.03%--__tcp_close
| tcp_close
| inet_release
| inet6_release
| sock_close
| __fput
| ____fput
| task_work_run
| exit_to_usermode_loop
| do_syscall_64
| entry_SYSCALL_64_after_hwframe
| __GI___libc_close
|
--14.48%--tcp_out_of_resources
tcp_write_timeout
tcp_retransmit_timer
tcp_write_timer_handler
tcp_write_timer
call_timer_fn
expire_timers
__run_timers
run_timer_softirq
__softirqentry_text_start
As explained in commit cf86a086a180 ("net/dst: use a smaller percpu_counter
batch for dst entries accounting"), default batch size is too big
for the default value of tcp_max_orphans (262144).
But even if we reduce batch sizes, there would still be cases
where the estimated count of orphans is beyond the limit,
and where tcp_too_many_orphans() has to call the expensive
percpu_counter_sum_positive().
One solution is to use plain per-cpu counters, and have
a timer to periodically refresh this cache.
Updating this cache every 100ms seems about right, tcp pressure
state is not radically changing over shorter periods.
percpu_counter was nice 15 years ago while hosts had less
than 16 cpus, not anymore by current standards.
v2: Fix the build issue for CONFIG_CRYPTO_DEV_CHELSIO_TLS=m,
reported by kernel test robot <lkp@intel.com>
Remove unused socket argument from tcp_too_many_orphans()
Fixes: dd24c00191d5 ("net: Use a percpu_counter for orphan_count")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Stefan Bach <sfb@google.com>
Cc: Neal Cardwell <ncardwell@google.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>
commit cd9733f5d75c94a32544d6ce5be47e14194cf137 upstream.
With two Msgs, msgA and msgB and a user doing nonblocking sendmsg calls (or
multiple cores) on a single socket 'sk' we could get the following flow.
msgA, sk msgB, sk
----------- ---------------
tcp_bpf_sendmsg()
lock(sk)
psock = sk->psock
tcp_bpf_sendmsg()
lock(sk) ... blocking
tcp_bpf_send_verdict
if (psock->eval == NONE)
psock->eval = sk_psock_msg_verdict
..
< handle SK_REDIRECT case >
release_sock(sk) < lock dropped so grab here >
ret = tcp_bpf_sendmsg_redir
psock = sk->psock
tcp_bpf_send_verdict
lock_sock(sk) ... blocking on B
if (psock->eval == NONE) <- boom.
psock->eval will have msgA state
The problem here is we dropped the lock on msgA and grabbed it with msgB.
Now we have old state in psock and importantly psock->eval has not been
cleared. So msgB will run whatever action was done on A and the verdict
program may never see it.
Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: Liu Jian <liujian56@huawei.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20211012052019.184398-1-liujian56@huawei.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 86f1e3a8489f6a0232c1f3bc2bdb379f5ccdecec ]
With net.ipv4.tcp_l3mdev_accept=1 it is possible for a listen socket to
accept connection from the same client address in different VRFs. It is
also possible to set different MD5 keys for these clients which differ
only in the tcpm_l3index field.
This appears to work when distinguishing between different VRFs but not
between non-VRF and VRF connections. In particular:
* tcp_md5_do_lookup_exact will match a non-vrf key against a vrf key.
This means that adding a key with l3index != 0 after a key with l3index
== 0 will cause the earlier key to be deleted. Both keys can be present
if the non-vrf key is added later.
* _tcp_md5_do_lookup can match a non-vrf key before a vrf key. This
casues failures if the passwords differ.
Fix this by making tcp_md5_do_lookup_exact perform an actual exact
comparison on l3index and by making __tcp_md5_do_lookup perfer
vrf-bound keys above other considerations like prefixlen.
Fixes: dea53bb80e07 ("tcp: Add l3index to tcp_md5sig_key and md5 functions")
Signed-off-by: Leonard Crestez <cdleonard@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 8d6c414cd2fb74aa6812e9bfec6178f8246c4f3a ]
The commit 6da5b0f027a8 ("net: ensure unbound datagram socket to be
chosen when not in a VRF") modified compute_score() so that a device
match is always made, not just in the case of an l3mdev skb, then
increments the score also for unbound sockets. This ensures that
sockets bound to an l3mdev are never selected when not in a VRF.
But as unbound and bound sockets are now scored equally, this results
in the last opened socket being selected if there are matches in the
default VRF for an unbound socket and a socket bound to a dev that is
not an l3mdev. However, handling prior to this commit was to always
select the bound socket in this case. Reinstate this handling by
incrementing the score only for bound sockets. The required isolation
due to choosing between an unbound socket and a socket bound to an
l3mdev remains in place due to the device match always being made.
The same approach is taken for compute_score() for stream sockets.
Fixes: 6da5b0f027a8 ("net: ensure unbound datagram socket to be chosen when not in a VRF")
Fixes: e78190581aff ("net: ensure unbound stream socket to be chosen when not in a VRF")
Signed-off-by: Mike Manning <mmanning@vyatta.att-mail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/cf0a8523-b362-1edf-ee78-eef63cbbb428@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit a9f5970767d11eadc805d5283f202612c7ba1f59 upstream.
up->corkflag field can be read or written without any lock.
Annotate accesses to avoid possible syzbot/KCSAN reports.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 597aa16c782496bf74c5dc3b45ff472ade6cee64 ]
Multipath RTA_FLOW is embedded in nexthop. Dump it in fib_add_nexthop()
to get the length of rtnexthop correct.
Fixes: b0f60193632e ("ipv4: Refactor nexthop attributes in fib_dump_info")
Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 8a0ed250f911da31a2aef52101bc707846a800ff ]
The GRE tunnel device can pull existing outer headers in ipge_xmit.
This is a rare path, apparently unique to this device. The below
commit ensured that pulling does not move skb->data beyond csum_start.
But it has a false positive if ip_summed is not CHECKSUM_PARTIAL and
thus csum_start is irrelevant.
Refine to exclude this. At the same time simplify and strengthen the
test.
Simplify, by moving the check next to the offending pull, making it
more self documenting and removing an unnecessary branch from other
code paths.
Strengthen, by also ensuring that the transport header is correct and
therefore the inner headers will be after skb_reset_inner_headers.
The transport header is set to csum_start in skb_partial_csum_set.
Link: https://lore.kernel.org/netdev/YS+h%2FtqCJJiQei+W@shredder/
Fixes: 1d011c4803c7 ("ip_gre: add validation for csum_start")
Reported-by: Ido Schimmel <idosch@idosch.org>
Suggested-by: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit e50e711351bdc656a8e6ca1022b4293cae8dcd59 upstream.
Turn udp_tunnel_nic work-queue to an ordered work-queue. This queue
holds the UDP-tunnel configuration commands of the different netdevs.
When the netdevs are functions of the same NIC the order of
execution may be crucial.
Problem example:
NIC with 2 PFs, both PFs declare offload quota of up to 3 UDP-ports.
$ifconfig eth2 1.1.1.1/16 up
$ip link add eth2_19503 type vxlan id 5049 remote 1.1.1.2 dev eth2 dstport 19053
$ip link set dev eth2_19503 up
$ip link add eth2_19504 type vxlan id 5049 remote 1.1.1.3 dev eth2 dstport 19054
$ip link set dev eth2_19504 up
$ip link add eth2_19505 type vxlan id 5049 remote 1.1.1.4 dev eth2 dstport 19055
$ip link set dev eth2_19505 up
$ip link add eth2_19506 type vxlan id 5049 remote 1.1.1.5 dev eth2 dstport 19056
$ip link set dev eth2_19506 up
NIC RX port offload infrastructure offloads the first 3 UDP-ports (on
all devices which sets NETIF_F_RX_UDP_TUNNEL_PORT feature) and not
UDP-port 19056. So both PFs gets this offload configuration.
$ip link set dev eth2_19504 down
This triggers udp-tunnel-core to remove the UDP-port 19504 from
offload-ports-list and offload UDP-port 19056 instead.
In this scenario it is important that the UDP-port of 19504 will be
removed from both PFs before trying to add UDP-port 19056. The NIC can
stop offloading a UDP-port only when all references are removed.
Otherwise the NIC may report exceeding of the offload quota.
Fixes: cc4e3835eff4 ("udp_tunnel: add central NIC RX port offload infrastructure")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 4f884f3962767877d7aabbc1ec124d2c307a4257 upstream.
Commit 10d3be569243 ("tcp-tso: do not split TSO packets at retransmit
time") may directly retrans a multiple segments TSO/GSO packet without
split, Since this commit, we can no longer assume that a retransmitted
packet is a single segment.
This patch fixes the tp->undo_retrans accounting in tcp_sacktag_one()
that use the actual segments(pcount) of the retransmitted packet.
Before that commit (10d3be569243), the assumption underlying the
tp->undo_retrans-- seems correct.
Fixes: 10d3be569243 ("tcp-tso: do not split TSO packets at retransmit time")
Signed-off-by: zhenggy <zhenggy@chinatelecom.cn>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit e3faa49bcecdfcc80e94dd75709d6acb1a5d89f6 ]
Since the original TFO server code was implemented in commit
168a8f58059a22feb9e9a2dcc1b8053dbbbc12ef ("tcp: TCP Fast Open Server -
main code path") the TFO server code has supported the sysctl bit flag
TFO_SERVER_COOKIE_NOT_REQD. Currently, when the TFO_SERVER_ENABLE and
TFO_SERVER_COOKIE_NOT_REQD sysctl bit flags are set, a server connection
will accept a SYN with N bytes of data (N > 0) that has no TFO cookie,
create a new fast open connection, process the incoming data in the SYN,
and make the connection ready for accepting. After accepting, the
connection is ready for read()/recvmsg() to read the N bytes of data in
the SYN, ready for write()/sendmsg() calls and data transmissions to
transmit data.
This commit changes an edge case in this feature by changing this
behavior to apply to (N >= 0) bytes of data in the SYN rather than only
(N > 0) bytes of data in the SYN. Now, a server will accept a data-less
SYN without a TFO cookie if TFO_SERVER_COOKIE_NOT_REQD is set.
Caveat! While this enables a new kind of TFO (data-less empty-cookie
SYN), some firewall rules setup may not work if they assume such packets
are not legit TFOs and will filter them.
Signed-off-by: Luke Hsiao <lukehsiao@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20210816205105.2533289-1-luke.w.hsiao@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 6321c7acb82872ef6576c520b0e178eaad3a25c0 ]
Fix the following out-of-bounds warning:
In function 'ip_copy_addrs',
inlined from '__ip_queue_xmit' at net/ipv4/ip_output.c:517:2:
net/ipv4/ip_output.c:449:2: warning: 'memcpy' offset [40, 43] from the object at 'fl' is out of the bounds of referenced subobject 'saddr' with type 'unsigned int' at offset 36 [-Warray-bounds]
449 | memcpy(&iph->saddr, &fl4->saddr,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
450 | sizeof(fl4->saddr) + sizeof(fl4->daddr));
| ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The problem is that the original code is trying to copy data into a
couple of struct members adjacent to each other in a single call to
memcpy(). This causes a legitimate compiler warning because memcpy()
overruns the length of &iph->saddr and &fl4->saddr. As these are just
a couple of struct members, fix this by using direct assignments,
instead of memcpy().
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().
Link: https://github.com/KSPP/linux/issues/109
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/lkml/d5ae2e65-1f18-2577-246f-bada7eee6ccd@intel.com/
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 92548b0ee220e000d81c27ac9a80e0ede895a881 ]
The UDP length field should be in network order.
This removes the following sparse error:
net/ipv4/route.c:3173:27: warning: incorrect type in assignment (different base types)
net/ipv4/route.c:3173:27: expected restricted __be16 [usertype] len
net/ipv4/route.c:3173:27: got unsigned long
Fixes: 404eb77ea766 ("ipv4: support sport, dport and ip_proto in RTM_GETROUTE")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Roopa Prabhu <roopa@nvidia.com>
Cc: David Ahern <dsahern@kernel.org>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 67d6d681e15b578c1725bad8ad079e05d1c48a8e ]
Even after commit 6457378fe796 ("ipv4: use siphash instead of Jenkins in
fnhe_hashfun()"), an attacker can still use brute force to learn
some secrets from a victim linux host.
One way to defeat these attacks is to make the max depth of the hash
table bucket a random value.
Before this patch, each bucket of the hash table used to store exceptions
could contain 6 items under attack.
After the patch, each bucket would contains a random number of items,
between 6 and 10. The attacker can no longer infer secrets.
This is slightly increasing memory size used by the hash table,
by 50% in average, we do not expect this to be a problem.
This patch is more complex than the prior one (IPv6 equivalent),
because IPv4 was reusing the oldest entry.
Since we need to be able to evict more than one entry per
update_or_create_fnhe() call, I had to replace
fnhe_oldest() with fnhe_remove_oldest().
Also note that we will queue extra kfree_rcu() calls under stress,
which hopefully wont be a too big issue.
Fixes: 4895c771c7f0 ("ipv4: Add FIB nexthop exceptions.")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Keyu Man <kman001@ucr.edu>
Cc: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Reviewed-by: David Ahern <dsahern@kernel.org>
Tested-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 525e2f9fd0229eb10cb460a9e6d978257f24804e ]
st->bucket stores the current bucket number.
st->offset stores the offset within this bucket that is the sk to be
seq_show(). Thus, st->offset only makes sense within the same
st->bucket.
These two variables are an optimization for the common no-lseek case.
When resuming the seq_file iteration (i.e. seq_start()),
tcp_seek_last_pos() tries to continue from the st->offset
at bucket st->bucket.
However, it is possible that the bucket pointed by st->bucket
has changed and st->offset may end up skipping the whole st->bucket
without finding a sk. In this case, tcp_seek_last_pos() currently
continues to satisfy the offset condition in the next (and incorrect)
bucket. Instead, regardless of the offset value, the first sk of the
next bucket should be returned. Thus, "bucket == st->bucket" check is
added to tcp_seek_last_pos().
The chance of hitting this is small and the issue is a decade old,
so targeting for the next tree.
Fixes: a8b690f98baf ("tcp: Fix slowness in read /proc/net/tcp")
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Yonghong Song <yhs@fb.com>
Link: https://lore.kernel.org/bpf/20210701200541.1033917-1-kafai@fb.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 6457378fe796815c973f631a1904e147d6ee33b1 ]
A group of security researchers brought to our attention
the weakness of hash function used in fnhe_hashfun().
Lets use siphash instead of Jenkins Hash, to considerably
reduce security risks.
Also remove the inline keyword, this really is distracting.
Fixes: d546c621542d ("ipv4: harden fnhe_hashfun()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Keyu Man <kman001@ucr.edu>
Cc: Willy Tarreau <w@1wt.eu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 1d011c4803c72f3907eccfc1ec63caefb852fcbf ]
Validate csum_start in gre_handle_offloads before we call _gre_xmit so
that we do not crash later when the csum_start value is used in the
lco_csum function call.
This patch deals with ipv4 code.
Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.")
Reported-by: syzbot+ff8e1b9f2f36481e2efc@syzkaller.appspotmail.com
Signed-off-by: Shreyansh Chouhan <chouhan.shreyansh630@gmail.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 b69dd5b3780a7298bd893816a09da751bc0636f7 ]
Some arches support cmpxchg() on 4-byte and 8-byte only.
Increase mr_ifc_count width to 32bit to fix this problem.
Fixes: 4a2b285e7e10 ("net: igmp: fix data-race in igmp_ifc_timer_expire()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20210811195715.3684218-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 6de035fec045f8ae5ee5f3a02373a18b939e91fb ]
Currently if BBR congestion control is initialized after more than 2B
packets have been delivered, depending on the phase of the
tp->delivered counter the tracking of BBR round trips can get stuck.
The bug arises because if tp->delivered is between 2^31 and 2^32 at
the time the BBR congestion control module is initialized, then the
initialization of bbr->next_rtt_delivered to 0 will cause the logic to
believe that the end of the round trip is still billions of packets in
the future. More specifically, the following check will fail
repeatedly:
!before(rs->prior_delivered, bbr->next_rtt_delivered)
and thus the connection will take up to 2B packets delivered before
that check will pass and the connection will set:
bbr->round_start = 1;
This could cause many mechanisms in BBR to fail to trigger, for
example bbr_check_full_bw_reached() would likely never exit STARTUP.
This bug is 5 years old and has not been observed, and as a practical
matter this would likely rarely trigger, since it would require
transferring at least 2B packets, or likely more than 3 terabytes of
data, before switching congestion control algorithms to BBR.
This patch is a stable candidate for kernels as far back as v4.9,
when tcp_bbr.c was added.
Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Kevin Yang <yyd@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20210811024056.235161-1-ncardwell@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit d51c5907e9809a803b276883d203f45849abd4d6 ]
GSO expects inner transport header offset to be valid when
skb->encapsulation flag is set. GSO uses this value to calculate the length
of an individual segment of a GSO packet in skb_gso_transport_seglen().
However, tcp/udp gro_complete callbacks don't update the
skb->inner_transport_header when processing an encapsulated TCP/UDP
segment. As a result a GRO skb has ->inner_transport_header set to a value
carried over from earlier skb processing.
This can have mild to tragic consequences. From miscalculating the GSO
segment length to triggering a page fault [1], when trying to read TCP/UDP
header at an address past the skb->data page.
The latter scenario leads to an oops report like so:
BUG: unable to handle page fault for address: ffff9fa7ec00d008
#PF: supervisor read access in kernel mode
#PF: error_code(0x0000) - not-present page
PGD 123f201067 P4D 123f201067 PUD 123f209067 PMD 0
Oops: 0000 [#1] SMP NOPTI
CPU: 44 PID: 0 Comm: swapper/44 Not tainted 5.4.53-cloudflare-2020.7.21 #1
Hardware name: HYVE EDGE-METAL-GEN10/HS-1811DLite1, BIOS V2.15 02/21/2020
RIP: 0010:skb_gso_transport_seglen+0x44/0xa0
Code: c0 41 83 e0 11 f6 87 81 00 00 00 20 74 30 0f b7 87 aa 00 00 00 0f [...]
RSP: 0018:ffffad8640bacbb8 EFLAGS: 00010202
RAX: 000000000000feda RBX: ffff9fcc8d31bc00 RCX: ffff9fa7ec00cffc
RDX: ffff9fa7ebffdec0 RSI: 000000000000feda RDI: 0000000000000122
RBP: 00000000000005c4 R08: 0000000000000001 R09: 0000000000000000
R10: ffff9fe588ae3800 R11: ffff9fe011fc92f0 R12: ffff9fcc8d31bc00
R13: ffff9fe0119d4300 R14: 00000000000005c4 R15: ffff9fba57d70900
FS: 0000000000000000(0000) GS:ffff9fe68df00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffff9fa7ec00d008 CR3: 0000003e99b1c000 CR4: 0000000000340ee0
Call Trace:
<IRQ>
skb_gso_validate_network_len+0x11/0x70
__ip_finish_output+0x109/0x1c0
ip_sublist_rcv_finish+0x57/0x70
ip_sublist_rcv+0x2aa/0x2d0
? ip_rcv_finish_core.constprop.0+0x390/0x390
ip_list_rcv+0x12b/0x14f
__netif_receive_skb_list_core+0x2a9/0x2d0
netif_receive_skb_list_internal+0x1b5/0x2e0
napi_complete_done+0x93/0x140
veth_poll+0xc0/0x19f [veth]
? mlx5e_napi_poll+0x221/0x610 [mlx5_core]
net_rx_action+0x1f8/0x790
__do_softirq+0xe1/0x2bf
irq_exit+0x8e/0xc0
do_IRQ+0x58/0xe0
common_interrupt+0xf/0xf
</IRQ>
The bug can be observed in a simple setup where we send IP/GRE/IP/TCP
packets into a netns over a veth pair. Inside the netns, packets are
forwarded to dummy device:
trafgen -> [veth A]--[veth B] -forward-> [dummy]
For veth B to GRO aggregate packets on receive, it needs to have an XDP
program attached (for example, a trivial XDP_PASS). Additionally, for UDP,
we need to enable GSO_UDP_L4 feature on the device:
ip netns exec A ethtool -K AB rx-udp-gro-forwarding on
The last component is an artificial delay to increase the chances of GRO
batching happening:
ip netns exec A tc qdisc add dev AB root \
netem delay 200us slot 5ms 10ms packets 2 bytes 64k
With such a setup in place, the bug can be observed by tracing the skb
outer and inner offsets when GSO skb is transmitted from the dummy device:
tcp:
FUNC DEV SKB_LEN NH TH ENC INH ITH GSO_SIZE GSO_TYPE
ip_finish_output dumB 2830 270 290 1 294 254 1383 (tcpv4,gre,)
^^^
udp:
FUNC DEV SKB_LEN NH TH ENC INH ITH GSO_SIZE GSO_TYPE
ip_finish_output dumB 2818 270 290 1 294 254 1383 (gre,udp_l4,)
^^^
Fix it by updating the inner transport header offset in tcp/udp
gro_complete callbacks, similar to how {inet,ipv6}_gro_complete callbacks
update the inner network header offset, when skb->encapsulation flag is
set.
[1] https://lore.kernel.org/netdev/CAKxSbF01cLpZem2GFaUaifh0S-5WYViZemTicAg7FCHOnh6kug@mail.gmail.com/
Fixes: bf296b125b21 ("tcp: Add GRO support")
Fixes: f993bc25e519 ("net: core: handle encapsulation offloads when computing segment lengths")
Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.")
Reported-by: Alex Forster <aforster@cloudflare.com>
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 227adfb2b1dfbc53dfc53b9dd7a93a6298ff7c56 ]
In cases where the header straight after the tunnel header was
another ethernet header (TEB), instead of the network header,
the ECN decapsulation code would treat the ethernet header as if
it was an IP header, resulting in mishandling and possible
wrong drops or corruption of the IP header.
In this case, ECT(1) is sent, so IP_ECN_decapsulate tries to copy it to the
inner IPv4 header, and correct its checksum.
The offset of the ECT bits in an IPv4 header corresponds to the
lower 2 bits of the second octet of the destination MAC address
in the ethernet header.
The IPv4 checksum corresponds to end of the source address.
In order to reproduce:
$ ip netns add A
$ ip netns add B
$ ip -n A link add _v0 type veth peer name _v1 netns B
$ ip -n A link set _v0 up
$ ip -n A addr add dev _v0 10.254.3.1/24
$ ip -n A route add default dev _v0 scope global
$ ip -n B link set _v1 up
$ ip -n B addr add dev _v1 10.254.1.6/24
$ ip -n B route add default dev _v1 scope global
$ ip -n B link add gre1 type gretap local 10.254.1.6 remote 10.254.3.1 key 0x49000000
$ ip -n B link set gre1 up
# Now send an IPv4/GRE/Eth/IPv4 frame where the outer header has ECT(1),
# and the inner header has no ECT bits set:
$ cat send_pkt.py
#!/usr/bin/env python3
from scapy.all import *
pkt = IP(b'E\x01\x00\xa7\x00\x00\x00\x00@/`%\n\xfe\x03\x01\n\xfe\x01\x06 \x00eXI\x00'
b'\x00\x00\x18\xbe\x92\xa0\xee&\x18\xb0\x92\xa0l&\x08\x00E\x00\x00}\x8b\x85'
b'@\x00\x01\x01\xe4\xf2\x82\x82\x82\x01\x82\x82\x82\x02\x08\x00d\x11\xa6\xeb'
b'3\x1e\x1e\\xf3\\xf7`\x00\x00\x00\x00ZN\x00\x00\x00\x00\x00\x00\x10\x11\x12'
b'\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&\'()*+,-./01234'
b'56789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ')
send(pkt)
$ sudo ip netns exec B tcpdump -neqlllvi gre1 icmp & ; sleep 1
$ sudo ip netns exec A python3 send_pkt.py
In the original packet, the source/destinatio MAC addresses are
dst=18:be:92:a0:ee:26 src=18:b0:92:a0:6c:26
In the received packet, they are
dst=18:bd:92:a0:ee:26 src=18:b0:92:a0:6c:27
Thanks to Lahav Schlesinger <lschlesinger@drivenets.com> and Isaac Garzon <isaac@speed.io>
for helping me pinpoint the origin.
Fixes: b723748750ec ("tunnel: Propagate ECT(1) when decapsulating as recommended by RFC6040")
Cc: David S. Miller <davem@davemloft.net>
Cc: Hideaki YOSHIFUJI <yoshfuji@linux-ipv6.org>
Cc: David Ahern <dsahern@kernel.org>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Gilad Naaman <gnaaman@drivenets.com>
Acked-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 213ad73d06073b197a02476db3a4998e219ddb06 ]
Multiple complaints have been raised from the TFO users on the internet
stating that the TFO blackhole logic is too aggressive and gets falsely
triggered too often.
(e.g. https://blog.apnic.net/2021/07/05/tcp-fast-open-not-so-fast/)
Considering that most middleboxes no longer drop TFO packets, we decide
to disable the blackhole logic by setting
/proc/sys/net/ipv4/tcp_fastopen_blackhole_timeout_set to 0 by default.
Fixes: cf1ef3f0719b4 ("net/tcp_fastopen: Disable active side TFO in certain scenarios")
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 6f20c8adb1813467ea52c1296d52c4e95978cb2f ]
tfo_active_disable_stamp is read and written locklessly.
We need to annotate these accesses appropriately.
Then, we need to perform the atomic_inc(tfo_active_disable_times)
after the timestamp has been updated, and thus add barriers
to make sure tcp_fastopen_active_should_disable() wont read
a stale timestamp.
Fixes: cf1ef3f0719b ("net/tcp_fastopen: Disable active side TFO in certain scenarios")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Wei Wang <weiwan@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Wei Wang <weiwan@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 54ea2f49fd9400dd698c25450be3352b5613b3b4 ]
The proc socket stats use sk_prot->inuse_idx value to record inuse sock
stats. We currently do not set this correctly from sockmap side. The
result is reading sock stats '/proc/net/sockstat' gives incorrect values.
The socket counter is incremented correctly, but because we don't set the
counter correctly when we replace sk_prot we may omit the decrement.
To get the correct inuse_idx value move the core_initcall that initializes
the UDP proto handlers to late_initcall. This way it is initialized after
UDP has the chance to assign the inuse_idx value from the register protocol
handler.
Fixes: edc6741cc660 ("bpf: Add sockmap hooks for UDP sockets")
Signed-off-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Cong Wang <cong.wang@bytedance.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20210714154750.528206-1-jakub@cloudflare.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 228a4a7ba8e99bb9ef980b62f71e3be33f4aae69 ]
The proc socket stats use sk_prot->inuse_idx value to record inuse sock
stats. We currently do not set this correctly from sockmap side. The
result is reading sock stats '/proc/net/sockstat' gives incorrect values.
The socket counter is incremented correctly, but because we don't set the
counter correctly when we replace sk_prot we may omit the decrement.
To get the correct inuse_idx value move the core_initcall that initializes
the TCP proto handlers to late_initcall. This way it is initialized after
TCP has the chance to assign the inuse_idx value from the register protocol
handler.
Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface")
Suggested-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Cong Wang <cong.wang@bytedance.com>
Link: https://lore.kernel.org/bpf/20210712195546.423990-3-john.fastabend@gmail.com
Signed-off-by: Sasha Levin <sashal@kernel.org>
commit 358ed624207012f03318235017ac6fb41f8af592 upstream.
sk_wmem_schedule makes sure that sk_forward_alloc has enough
bytes for charging that is going to be done by sk_mem_charge.
In the transmit zerocopy path, there is sk_mem_charge but there was
no call to sk_wmem_schedule. This change adds that call.
Without this call to sk_wmem_schedule, sk_forward_alloc can go
negetive which is a bug because sk_forward_alloc is a per-socket
space that has been forward charged so this can't be negative.
Fixes: f214f915e7db ("tcp: enable MSG_ZEROCOPY")
Signed-off-by: Talal Ahmad <talalahmad@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Wei Wang <weiwan@google.com>
Reviewed-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit c7bb4b89033b764eb07db4e060548a6311d801ee upstream.
While TCP stack scales reasonably well, there is still one part that
can be used to DDOS it.
IPv6 Packet too big messages have to lookup/insert a new route,
and if abused by attackers, can easily put hosts under high stress,
with many cpus contending on a spinlock while one is stuck in fib6_run_gc()
ip6_protocol_deliver_rcu()
icmpv6_rcv()
icmpv6_notify()
tcp_v6_err()
tcp_v6_mtu_reduced()
inet6_csk_update_pmtu()
ip6_rt_update_pmtu()
__ip6_rt_update_pmtu()
ip6_rt_cache_alloc()
ip6_dst_alloc()
dst_alloc()
ip6_dst_gc()
fib6_run_gc()
spin_lock_bh() ...
Some of our servers have been hit by malicious ICMPv6 packets
trying to _increase_ the MTU/MSS of TCP flows.
We believe these ICMPv6 packets are a result of a bug in one ISP stack,
since they were blindly sent back for _every_ (small) packet sent to them.
These packets are for one TCP flow:
09:24:36.266491 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240
09:24:36.266509 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240
09:24:36.316688 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240
09:24:36.316704 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240
09:24:36.608151 IP6 Addr1 > Victim ICMP6, packet too big, mtu 1460, length 1240
TCP stack can filter some silly requests :
1) MTU below IPV6_MIN_MTU can be filtered early in tcp_v6_err()
2) tcp_v6_mtu_reduced() can drop requests trying to increase current MSS.
This tests happen before the IPv6 routing stack is entered, thus
removing the potential contention and route exhaustion.
Note that IPv6 stack was performing these checks, but too late
(ie : after the route has been added, and after the potential
garbage collect war)
v2: fix typo caught by Martin, thanks !
v3: exports tcp_mtu_to_mss(), caught by David, thanks !
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Maciej Żenczykowski <maze@google.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit be5d1b61a2ad28c7e57fe8bfa277373e8ecffcdc upstream.
This commit fixes a bug (found by syzkaller) that could cause spurious
double-initializations for congestion control modules, which could cause
memory leaks or other problems for congestion control modules (like CDG)
that allocate memory in their init functions.
The buggy scenario constructed by syzkaller was something like:
(1) create a TCP socket
(2) initiate a TFO connect via sendto()
(3) while socket is in TCP_SYN_SENT, call setsockopt(TCP_CONGESTION),
which calls:
tcp_set_congestion_control() ->
tcp_reinit_congestion_control() ->
tcp_init_congestion_control()
(4) receive ACK, connection is established, call tcp_init_transfer(),
set icsk_ca_initialized=0 (without first calling cc->release()),
call tcp_init_congestion_control() again.
Note that in this sequence tcp_init_congestion_control() is called
twice without a cc->release() call in between. Thus, for CC modules
that allocate memory in their init() function, e.g, CDG, a memory leak
may occur. The syzkaller tool managed to find a reproducer that
triggered such a leak in CDG.
The bug was introduced when that commit 8919a9b31eb4 ("tcp: Only init
congestion control if not initialized already")
introduced icsk_ca_initialized and set icsk_ca_initialized to 0 in
tcp_init_transfer(), missing the possibility for a sequence like the
one above, where a process could call setsockopt(TCP_CONGESTION) in
state TCP_SYN_SENT (i.e. after the connect() or TFO open sendmsg()),
which would call tcp_init_congestion_control(). It did not intend to
reset any initialization that the user had already explicitly made;
it just missed the possibility of that particular sequence (which
syzkaller managed to find).
Fixes: 8919a9b31eb4 ("tcp: Only init congestion control if not initialized already")
Reported-by: syzbot+f1e24a0594d4e3a895d3@syzkaller.appspotmail.com
Signed-off-by: Nguyen Dinh Phi <phind.uet@gmail.com>
Acked-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: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 561022acb1ce62e50f7a8258687a21b84282a4cb upstream.
While tp->mtu_info is read while socket is owned, the write
sides happen from err handlers (tcp_v[46]_mtu_reduced)
which only own the socket spinlock.
Fixes: 563d34d05786 ("tcp: dont drop MTU reduction indications")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 9992a078b1771da354ac1f9737e1e639b687caa2 upstream.
Commit 28e104d00281 ("net: ip_tunnel: fix mtu calculation") removed
dev->hard_header_len subtraction when calculate MTU for tunnel devices
as there is an overhead for device that has header_ops.
But there are ETHER tunnel devices, like gre_tap or erspan, which don't
have header_ops but set dev->hard_header_len during setup. This makes
pkts greater than (MTU - ETH_HLEN) could not be xmited. Fix it by
subtracting the ETHER tunnel devices' dev->hard_header_len for MTU
calculation.
Fixes: 28e104d00281 ("net: ip_tunnel: fix mtu calculation")
Reported-by: Jianlin Shi <jishi@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 6d123b81ac615072a8525c13c6c41b695270a15d ]
Dave observed number of machines hitting OOM on the UDP send
path. The workload seems to be sending large UDP packets over
loopback. Since loopback has MTU of 64k kernel will try to
allocate an skb with up to 64k of head space. This has a good
chance of failing under memory pressure. What's worse if
the message length is <32k the allocation may trigger an
OOM killer.
This is entirely avoidable, we can use an skb with page frags.
af_unix solves a similar problem by limiting the head
length to SKB_MAX_ALLOC. This seems like a good and simple
approach. It means that UDP messages > 16kB will now
use fragments if underlying device supports SG, if extra
allocator pressure causes regressions in real workloads
we can switch to trying the large allocation first and
falling back.
v4: pre-calculate all the additions to alloclen so
we can be sure it won't go over order-2
Reported-by: Dave Jones <dsj@fb.com>
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 a29cb6914681a55667436a9eb7a42e28da8cf387 ]
This patch aims to improve the situation when reordering and loss are
ocurring in the same flight of packets.
Previously the reordering would first induce a spurious recovery, then
the subsequent ACK may undo the cwnd (based on the timestamps e.g.).
However the current loss recovery does not proceed to invoke
RACK to install a reordering timer. If some packets are also lost, this
may lead to a long RTO-based recovery. An example is
https://groups.google.com/g/bbr-dev/c/OFHADvJbTEI
The solution is to after reverting the recovery, always invoke RACK
to either mount the RACK timer to fast retransmit after the reordering
window, or restarts the recovery if new loss is identified. Hence
it is possible the sender may go from Recovery to Disorder/Open to
Recovery again in one ACK.
Reported-by: mingkun bian <bianmingkun@gmail.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@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>
[ Upstream commit fade56410c22cacafb1be9f911a0afd3701d8366 ]
Commit 14972cbd34ff ("net: lwtunnel: Handle fragmentation") moved
fragmentation logic away from lwtunnel by carry encap headroom and
use it in output MTU calculation. But the forwarding part was not
covered and created difference in MTU for output and forwarding and
further to silent drops on ipv4 forwarding path. Fix it by taking
into account lwtunnel encap headroom.
The same commit also introduced difference in how to treat RTAX_MTU
in IPv4 and IPv6 where latter explicitly removes lwtunnel encap
headroom from route MTU. Make IPv4 version do the same.
Fixes: 14972cbd34ff ("net: lwtunnel: Handle fragmentation")
Suggested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Vadim Fedorenko <vfedorenko@novek.ru>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit c69f114d09891adfa3e301a35d9e872b8b7b5a50 ]
When doing source address validation, the flowi4 struct used for
fib_lookup should be in the reverse direction to the given skb.
fl4_dport and fl4_sport returned by fib4_rules_early_flow_dissect
should thus be swapped.
Fixes: 5a847a6e1477 ("net/ipv4: Initialize proto and ports in flow struct")
Signed-off-by: Miao Wang <shankerwangmiao@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Jianguo Wu
Eric Dumazet
msizanoen1
liuguoqiang
Arjun Roy
Nikolay Aleksandrov
John Fastabend
Jon Maxwell
Liu Jian
Leonard Crestez
Mike Manning
Xiao Liang
Willem de Bruijn
Ryoga Saito
Aya Levin
zhenggy
Luke Hsiao
Gustavo A. R. Silva
Martin KaFai Lau
Shreyansh Chouhan
Neal Cardwell
Jakub Sitnicki
Gilad Naaman
Wei Wang
Talal Ahmad
Nguyen Dinh Phi
Hangbin Liu
Jakub Kicinski
Yuchung Cheng
Vadim Fedorenko
Miao Wang