[ Upstream commit 1ebf179037 ]
When inet_rtm_getroute() was converted to use the RCU variants of
ip_route_input() and ip_route_output_key(), the TOS parameters
stopped being masked with IPTOS_RT_MASK before doing the route lookup.
As a result, "ip route get" can return a different route than what
would be used when sending real packets.
For example:
$ ip route add 192.0.2.11/32 dev eth0
$ ip route add unreachable 192.0.2.11/32 tos 2
$ ip route get 192.0.2.11 tos 2
RTNETLINK answers: No route to host
But, packets with TOS 2 (ECT(0) if interpreted as an ECN bit) would
actually be routed using the first route:
$ ping -c 1 -Q 2 192.0.2.11
PING 192.0.2.11 (192.0.2.11) 56(84) bytes of data.
64 bytes from 192.0.2.11: icmp_seq=1 ttl=64 time=0.173 ms
--- 192.0.2.11 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.173/0.173/0.173/0.000 ms
This patch re-applies IPTOS_RT_MASK in inet_rtm_getroute(), to
return results consistent with real route lookups.
Fixes: 3765d35ed8 ("net: ipv4: Convert inet_rtm_getroute to rcu versions of route lookup")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/b2d237d08317ca55926add9654a48409ac1b8f5b.1606412894.git.gnault@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 55472017a4 ]
When setting congestion control via a BPF program it is seen that the
SYN/ACK for packets within a given flow will not include the ECT0 flag. A
bit of simple printk debugging shows that when this is configured without
BPF we will see the value INET_ECN_xmit value initialized in
tcp_assign_congestion_control however when we configure this via BPF the
socket is in the closed state and as such it isn't configured, and I do not
see it being initialized when we transition the socket into the listen
state. The result of this is that the ECT0 bit is configured based on
whatever the default state is for the socket.
Any easy way to reproduce this is to monitor the following with tcpdump:
tools/testing/selftests/bpf/test_progs -t bpf_tcp_ca
Without this patch the SYN/ACK will follow whatever the default is. If dctcp
all SYN/ACK packets will have the ECT0 bit set, and if it is not then ECT0
will be cleared on all SYN/ACK packets. With this patch applied the SYN/ACK
bit matches the value seen on the other packets in the given stream.
Fixes: 91b5b21c7c ("bpf: Add support for changing congestion control")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit c09c8a27b9 upstream.
Checking for ifdef CONFIG_x fails if CONFIG_x=m.
Use IS_ENABLED instead, which is true for both built-ins and modules.
Otherwise, a
> ip -4 route add 1.2.3.4/32 via inet6 fe80::2 dev eth1
fails with the message "Error: IPv6 support not enabled in kernel." if
CONFIG_IPV6 is `m`.
In the spirit of b8127113d0.
Fixes: d15662682d ("ipv4: Allow ipv6 gateway with ipv4 routes")
Cc: Kim Phillips <kim.phillips@arm.com>
Signed-off-by: Florian Klink <flokli@flokli.de>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20201115224509.2020651-1-flokli@flokli.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 36cd0e696a ]
Fix sockmap sk_skb programs so that they observe sk_rcvbuf limits. This
allows users to tune SO_RCVBUF and sockmap will honor them.
We can refactor the if(charge) case out in later patches. But, keep this
fix to the point.
Fixes: 51199405f9 ("bpf: skb_verdict, support SK_PASS on RX BPF path")
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: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/160556568657.73229.8404601585878439060.stgit@john-XPS-13-9370
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit c9c89dcd87 ]
If copy_page_to_iter() fails or even partially completes, but with fewer
bytes copied than expected we currently reset sg.start and return EFAULT.
This proves problematic if we already copied data into the user buffer
before we return an error. Because we leave the copied data in the user
buffer and fail to unwind the scatterlist so kernel side believes data
has been copied and user side believes data has _not_ been received.
Expected behavior should be to return number of bytes copied and then
on the next read we need to return the error assuming its still there. This
can happen if we have a copy length spanning multiple scatterlist elements
and one or more complete before the error is hit.
The error is rare enough though that my normal testing with server side
programs, such as nginx, httpd, envoy, etc., I have never seen this. The
only reliable way to reproduce that I've found is to stream movies over
my browser for a day or so and wait for it to hang. Not very scientific,
but with a few extra WARN_ON()s in the code the bug was obvious.
When we review the errors from copy_page_to_iter() it seems we are hitting
a page fault from copy_page_to_iter_iovec() where the code checks
fault_in_pages_writeable(buf, copy) where buf is the user buffer. It
also seems typical server applications don't hit this case.
The other way to try and reproduce this is run the sockmap selftest tool
test_sockmap with data verification enabled, but it doesn't reproduce the
fault. Perhaps we can trigger this case artificially somehow from the
test tools. I haven't sorted out a way to do that yet though.
Fixes: 604326b41a ("bpf, sockmap: convert to generic sk_msg interface")
Signed-off-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Link: https://lore.kernel.org/bpf/160556566659.73229.15694973114605301063.stgit@john-XPS-13-9370
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 1b9e2a8c99 ]
During loss recovery, retransmitted packets are forced to use TCP
timestamps to calculate the RTT samples, which have a millisecond
granularity. BBR is designed using a microsecond granularity. As a
result, multiple RTT samples could be truncated to the same RTT value
during loss recovery. This is problematic, as BBR will not enter
PROBE_RTT if the RTT sample is <= the current min_rtt sample, meaning
that if there are persistent losses, PROBE_RTT will constantly be
pushed off and potentially never re-entered. This patch makes sure
that BBR enters PROBE_RTT by checking if RTT sample is < the current
min_rtt sample, rather than <=.
The Netflix transport/TCP team discovered this bug in the Linux TCP
BBR code during lab tests.
Fixes: 0f8782ea14 ("tcp_bbr: add BBR congestion control")
Signed-off-by: Ryan Sharpelletti <sharpelletti@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Link: https://lore.kernel.org/r/20201116174412.1433277-1-sharpelletti.kdev@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit e33de7c531 ]
nlmsg_cancel() needs to be called in the error path of
inet_req_diag_fill to cancel the message.
Fixes: d545caca82 ("net: inet: diag: expose the socket mark to privileged processes.")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Link: https://lore.kernel.org/r/20201116082018.16496-1-wanghai38@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 8cf8821e15 ]
Commit 58956317c8 ("neighbor: Improve garbage collection")
guarantees neighbour table entries a five-second lifetime. Processes
which make heavy use of multicast can fill the neighour table with
multicast addresses in five seconds. At that point, neighbour entries
can't be GC-ed because they aren't five seconds old yet, the kernel
log starts to fill up with "neighbor table overflow!" messages, and
sends start to fail.
This patch allows multicast addresses to be thrown out before they've
lived out their five seconds. This makes room for non-multicast
addresses and makes messages to all addresses more reliable in these
circumstances.
Fixes: 58956317c8 ("neighbor: Improve garbage collection")
Signed-off-by: Jeff Dike <jdike@akamai.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20201113015815.31397-1-jdike@akamai.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 909172a149 ]
When net.ipv4.tcp_syncookies=1 and syn flood is happened,
cookie_v4_check or cookie_v6_check tries to redo what
tcp_v4_send_synack or tcp_v6_send_synack did,
rsk_window_clamp will be changed if SOCK_RCVBUF is set,
which will make rcv_wscale is different, the client
still operates with initial window scale and can overshot
granted window, the client use the initial scale but local
server use new scale to advertise window value, and session
work abnormally.
Fixes: e88c64f0a4 ("tcp: allow effective reduction of TCP's rcv-buffer via setsockopt")
Signed-off-by: Mao Wenan <wenan.mao@linux.alibaba.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/1604967391-123737-1-git-send-email-wenan.mao@linux.alibaba.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 4b1a86281c ]
UDP GRO uses udp_hdr(skb) in its .gro_receive() callback. While it's
probably OK for non-frag0 paths (when all headers or even the entire
frame are already in skb head), this inline points to junk when
using Fast GRO (napi_gro_frags() or napi_gro_receive() with only
Ethernet header in skb head and all the rest in the frags) and breaks
GRO packet compilation and the packet flow itself.
To support both modes, skb_gro_header_fast() + skb_gro_header_slow()
are typically used. UDP even has an inline helper that makes use of
them, udp_gro_udphdr(). Use that instead of troublemaking udp_hdr()
to get rid of the out-of-order delivers.
Present since the introduction of plain UDP GRO in 5.0-rc1.
Fixes: e20cf8d3f1 ("udp: implement GRO for plain UDP sockets.")
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Alexander Lobakin <alobakin@pm.me>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 46d6c5ae95 ]
If netfilter changes the packet mark when mangling, the packet is
rerouted using the route_me_harder set of functions. Prior to this
commit, there's one big difference between route_me_harder and the
ordinary initial routing functions, described in the comment above
__ip_queue_xmit():
/* Note: skb->sk can be different from sk, in case of tunnels */
int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
That function goes on to correctly make use of sk->sk_bound_dev_if,
rather than skb->sk->sk_bound_dev_if. And indeed the comment is true: a
tunnel will receive a packet in ndo_start_xmit with an initial skb->sk.
It will make some transformations to that packet, and then it will send
the encapsulated packet out of a *new* socket. That new socket will
basically always have a different sk_bound_dev_if (otherwise there'd be
a routing loop). So for the purposes of routing the encapsulated packet,
the routing information as it pertains to the socket should come from
that socket's sk, rather than the packet's original skb->sk. For that
reason __ip_queue_xmit() and related functions all do the right thing.
One might argue that all tunnels should just call skb_orphan(skb) before
transmitting the encapsulated packet into the new socket. But tunnels do
*not* do this -- and this is wisely avoided in skb_scrub_packet() too --
because features like TSQ rely on skb->destructor() being called when
that buffer space is truely available again. Calling skb_orphan(skb) too
early would result in buffers filling up unnecessarily and accounting
info being all wrong. Instead, additional routing must take into account
the new sk, just as __ip_queue_xmit() notes.
So, this commit addresses the problem by fishing the correct sk out of
state->sk -- it's already set properly in the call to nf_hook() in
__ip_local_out(), which receives the sk as part of its normal
functionality. So we make sure to plumb state->sk through the various
route_me_harder functions, and then make correct use of it following the
example of __ip_queue_xmit().
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Reviewed-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 20149e9eb6 ]
The tunnel device such as vxlan, bareudp and geneve in the lwt mode set
the outer df only based TUNNEL_DONT_FRAGMENT.
And this was also the behavior for gre device before switching to use
ip_md_tunnel_xmit in commit 962924fa2b ("ip_gre: Refactor collect
metatdata mode tunnel xmit to ip_md_tunnel_xmit")
When the ip_gre in lwt mode xmit with ip_md_tunnel_xmi changed the rule and
make the discrepancy between handling of DF by different tunnels. So in the
ip_md_tunnel_xmit should follow the same rule like other tunnels.
Fixes: cfc7381b30 ("ip_tunnel: add collect_md mode to IPIP tunnel")
Signed-off-by: wenxu <wenxu@ucloud.cn>
Link: https://lore.kernel.org/r/1604028728-31100-1-git-send-email-wenxu@ucloud.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 435ccfa894 ]
With SO_RCVLOWAT, under memory pressure,
it is possible to enter a state where:
1. We have not received enough bytes to satisfy SO_RCVLOWAT.
2. We have not entered buffer pressure (see tcp_rmem_pressure()).
3. But, we do not have enough buffer space to accept more packets.
In this case, we advertise 0 rwnd (due to #3) but the application does
not drain the receive queue (no wakeup because of #1 and #2) so the
flow stalls.
Modify the heuristic for SO_RCVLOWAT so that, if we are advertising
rwnd<=rcv_mss, force a wakeup to prevent a stall.
Without this patch, setting tcp_rmem to 6143 and disabling TCP
autotune causes a stalled flow. With this patch, no stall occurs. This
is with RPC-style traffic with large messages.
Fixes: 03f45c883c ("tcp: avoid extra wakeups for SO_RCVLOWAT users")
Signed-off-by: Arjun Roy <arjunroy@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20201023184709.217614-1-arjunroy.kdev@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit fdafed4599 ]
GRE tunnel has its own header_ops, ipgre_header_ops, and sets it
conditionally. When it is set, it assumes the outer IP header is
already created before ipgre_xmit().
This is not true when we send packets through a raw packet socket,
where L2 headers are supposed to be constructed by user. Packet
socket calls dev_validate_header() to validate the header. But
GRE tunnel does not set dev->hard_header_len, so that check can
be simply bypassed, therefore uninit memory could be passed down
to ipgre_xmit(). Similar for dev->needed_headroom.
dev->hard_header_len is supposed to be the length of the header
created by dev->header_ops->create(), so it should be used whenever
header_ops is set, and dev->needed_headroom should be used when it
is not set.
Reported-and-tested-by: syzbot+4a2c52677a8a1aa283cb@syzkaller.appspotmail.com
Cc: William Tu <u9012063@gmail.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Xie He <xie.he.0141@gmail.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 0d9826bc18 ]
Dump vlan tag and proto for the usual vlan offload case if the
NF_LOG_MACDECODE flag is set on. Without this information the logging is
misleading as there is no reference to the VLAN header.
[12716.993704] test: IN=veth0 OUT= MACSRC=86:6c:92:ea:d6:73 MACDST=0e:3b:eb:86:73:76 VPROTO=8100 VID=10 MACPROTO=0800 SRC=192.168.10.2 DST=172.217.168.163 LEN=52 TOS=0x00 PREC=0x00 TTL=64 ID=2548 DF PROTO=TCP SPT=55848 DPT=80 WINDOW=501 RES=0x00 ACK FIN URGP=0
[12721.157643] test: IN=veth0 OUT= MACSRC=86:6c:92:ea:d6:73 MACDST=0e:3b:eb:86:73:76 VPROTO=8100 VID=10 MACPROTO=0806 ARP HTYPE=1 PTYPE=0x0800 OPCODE=2 MACSRC=86:6c:92:ea:d6:73 IPSRC=192.168.10.2 MACDST=0e:3b:eb:86:73:76 IPDST=192.168.10.1
Fixes: 83e96d443b ("netfilter: log: split family specific code to nf_log_{ip,ip6,common}.c files")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit b38e7819ca ]
Keyu Man reported that the ICMP rate limiter could be used
by attackers to get useful signal. Details will be provided
in an upcoming academic publication.
Our solution is to add some noise, so that the attackers
no longer can get help from the predictable token bucket limiter.
Fixes: 4cdf507d54 ("icmp: add a global rate limitation")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Keyu Man <kman001@ucr.edu>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 18ded910b5 ]
In the header prediction fast path for a bulk data receiver, if no
data is newly acknowledged then we do not call tcp_ack() and do not
call tcp_ack_update_window(). This means that a bulk receiver that
receives large amounts of data can have the incoming sequence numbers
wrap, so that the check in tcp_may_update_window fails:
after(ack_seq, tp->snd_wl1)
If the incoming receive windows are zero in this state, and then the
connection that was a bulk data receiver later wants to send data,
that connection can find itself persistently rejecting the window
updates in incoming ACKs. This means the connection can persistently
fail to discover that the receive window has opened, which in turn
means that the connection is unable to send anything, and the
connection's sending process can get permanently "stuck".
The fix is to update snd_wl1 in the header prediction fast path for a
bulk data receiver, so that it keeps up and does not see wrapping
problems.
This fix is based on a very nice and thorough analysis and diagnosis
by Apollon Oikonomopoulos (see link below).
This is a stable candidate but there is no Fixes tag here since the
bug predates current git history. Just for fun: looks like the bug
dates back to when header prediction was added in Linux v2.1.8 in Nov
1996. In that version tcp_rcv_established() was added, and the code
only updates snd_wl1 in tcp_ack(), and in the new "Bulk data transfer:
receiver" code path it does not call tcp_ack(). This fix seems to
apply cleanly at least as far back as v3.2.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reported-by: Apollon Oikonomopoulos <apoikos@dmesg.gr>
Tested-by: Apollon Oikonomopoulos <apoikos@dmesg.gr>
Link: https://www.spinics.net/lists/netdev/msg692430.html
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20201022143331.1887495-1-ncardwell.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit df6afe2f7c ]
While insertion of 16k nexthops all using the same netdev ('dummy10')
takes less than a second, deletion takes about 130 seconds:
# time -p ip -b nexthop.batch
real 0.29
user 0.01
sys 0.15
# time -p ip link set dev dummy10 down
real 131.03
user 0.06
sys 0.52
This is because of repeated calls to synchronize_rcu() whenever a
nexthop is removed from a nexthop group:
# /usr/share/bcc/tools/offcputime -p `pgrep -nx ip` -K
...
b'finish_task_switch'
b'schedule'
b'schedule_timeout'
b'wait_for_completion'
b'__wait_rcu_gp'
b'synchronize_rcu.part.0'
b'synchronize_rcu'
b'__remove_nexthop'
b'remove_nexthop'
b'nexthop_flush_dev'
b'nh_netdev_event'
b'raw_notifier_call_chain'
b'call_netdevice_notifiers_info'
b'__dev_notify_flags'
b'dev_change_flags'
b'do_setlink'
b'__rtnl_newlink'
b'rtnl_newlink'
b'rtnetlink_rcv_msg'
b'netlink_rcv_skb'
b'rtnetlink_rcv'
b'netlink_unicast'
b'netlink_sendmsg'
b'____sys_sendmsg'
b'___sys_sendmsg'
b'__sys_sendmsg'
b'__x64_sys_sendmsg'
b'do_syscall_64'
b'entry_SYSCALL_64_after_hwframe'
- ip (277)
126554955
Since nexthops are always deleted under RTNL, synchronize_net() can be
used instead. It will call synchronize_rcu_expedited() which only blocks
for several microseconds as opposed to multiple milliseconds like
synchronize_rcu().
With this patch deletion of 16k nexthops takes less than a second:
# time -p ip link set dev dummy10 down
real 0.12
user 0.00
sys 0.04
Tested with fib_nexthops.sh which includes torture tests that prompted
the initial change:
# ./fib_nexthops.sh
...
Tests passed: 134
Tests failed: 0
Fixes: 90f33bffa3 ("nexthops: don't modify published nexthop groups")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Acked-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Link: https://lore.kernel.org/r/20201016172914.643282-1-idosch@idosch.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 874fb9e2ca ]
Tobias reported regressions in IPsec tests following the patch
referenced by the Fixes tag below. The root cause is dropping the
reset of the flowi4_oif after the fib_lookup. Apparently it is
needed for xfrm cases, so restore the oif update to ip_route_output_flow
right before the call to xfrm_lookup_route.
Fixes: 2fbc6e89b2 ("ipv4: Update exception handling for multipath routes via same device")
Reported-by: Tobias Brunner <tobias@strongswan.org>
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 86bccd0367 upstream.
We got reports from GKE customers flows being reset by netfilter
conntrack unless nf_conntrack_tcp_be_liberal is set to 1.
Traces seemed to suggest ACK packet being dropped by the
packet capture, or more likely that ACK were received in the
wrong order.
wscale=7, SYN and SYNACK not shown here.
This ACK allows the sender to send 1871*128 bytes from seq 51359321 :
New right edge of the window -> 51359321+1871*128=51598809
09:17:23.389210 IP A > B: Flags [.], ack 51359321, win 1871, options [nop,nop,TS val 10 ecr 999], length 0
09:17:23.389212 IP B > A: Flags [.], seq 51422681:51424089, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 1408
09:17:23.389214 IP A > B: Flags [.], ack 51422681, win 1376, options [nop,nop,TS val 10 ecr 999], length 0
09:17:23.389253 IP B > A: Flags [.], seq 51424089:51488857, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 64768
09:17:23.389272 IP A > B: Flags [.], ack 51488857, win 859, options [nop,nop,TS val 10 ecr 999], length 0
09:17:23.389275 IP B > A: Flags [.], seq 51488857:51521241, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 32384
Receiver now allows to send 606*128=77568 from seq 51521241 :
New right edge of the window -> 51521241+606*128=51598809
09:17:23.389296 IP A > B: Flags [.], ack 51521241, win 606, options [nop,nop,TS val 10 ecr 999], length 0
09:17:23.389308 IP B > A: Flags [.], seq 51521241:51553625, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 32384
It seems the sender exceeds RWIN allowance, since 51611353 > 51598809
09:17:23.389346 IP B > A: Flags [.], seq 51553625:51611353, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 57728
09:17:23.389356 IP B > A: Flags [.], seq 51611353:51618393, ack 1577, win 268, options [nop,nop,TS val 999 ecr 10], length 7040
09:17:23.389367 IP A > B: Flags [.], ack 51611353, win 0, options [nop,nop,TS val 10 ecr 999], length 0
netfilter conntrack is not happy and sends RST
09:17:23.389389 IP A > B: Flags [R], seq 92176528, win 0, length 0
09:17:23.389488 IP B > A: Flags [R], seq 174478967, win 0, length 0
Now imagine ACK were delivered out of order and tcp_add_backlog() sets window based on wrong packet.
New right edge of the window -> 51521241+859*128=51631193
Normally TCP stack handles OOO packets just fine, but it
turns out tcp_add_backlog() does not. It can update the window
field of the aggregated packet even if the ACK sequence
of the last received packet is too old.
Many thanks to Alexandre Ferrieux for independently reporting the issue
and suggesting a fix.
Fixes: 4f693b55c3 ("tcp: implement coalescing on backlog queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Alexandre Ferrieux <alexandre.ferrieux@orange.com>
Acked-by: Soheil Hassas Yeganeh <soheil@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>
commit cf83a17ede upstream.
commit a10674bf24 ("tcp: detecting the misuse of .sendpage for Slab
objects") adds the checks for Slab pages, but the pages don't have
page_count are still missing from the check.
Network layer's sendpage method is not designed to send page_count 0
pages neither, therefore both PageSlab() and page_count() should be
both checked for the sending page. This is exactly what sendpage_ok()
does.
This patch uses sendpage_ok() in do_tcp_sendpages() to detect misused
.sendpage, to make the code more robust.
Fixes: a10674bf24 ("tcp: detecting the misuse of .sendpage for Slab objects")
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Coly Li <colyli@suse.de>
Cc: Vasily Averin <vvs@virtuozzo.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: stable@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit a3ea86739f ]
if seq_file .next fuction does not change position index,
read after some lseek can generate unexpected output.
https://bugzilla.kernel.org/show_bug.cgi?id=206283
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 2fbc6e89b2 ]
Kfir reported that pmtu exceptions are not created properly for
deployments where multipath routes use the same device.
After some digging I see 2 compounding problems:
1. ip_route_output_key_hash_rcu is updating the flowi4_oif *after*
the route lookup. This is the second use case where this has
been a problem (the first is related to use of vti devices with
VRF). I can not find any reason for the oif to be changed after the
lookup; the code goes back to the start of git. It does not seem
logical so remove it.
2. fib_lookups for exceptions do not call fib_select_path to handle
multipath route selection based on the hash.
The end result is that the fib_lookup used to add the exception
always creates it based using the first leg of the route.
An example topology showing the problem:
| host1
+------+
| eth0 | .209
+------+
|
+------+
switch | br0 |
+------+
|
+---------+---------+
| host2 | host3
+------+ +------+
| eth0 | .250 | eth0 | 192.168.252.252
+------+ +------+
+-----+ +-----+
| vti | .2 | vti | 192.168.247.3
+-----+ +-----+
\ /
=================================
tunnels
192.168.247.1/24
for h in host1 host2 host3; do
ip netns add ${h}
ip -netns ${h} link set lo up
ip netns exec ${h} sysctl -wq net.ipv4.ip_forward=1
done
ip netns add switch
ip -netns switch li set lo up
ip -netns switch link add br0 type bridge stp 0
ip -netns switch link set br0 up
for n in 1 2 3; do
ip -netns switch link add eth-sw type veth peer name eth-h${n}
ip -netns switch li set eth-h${n} master br0 up
ip -netns switch li set eth-sw netns host${n} name eth0
done
ip -netns host1 addr add 192.168.252.209/24 dev eth0
ip -netns host1 link set dev eth0 up
ip -netns host1 route add 192.168.247.0/24 \
nexthop via 192.168.252.250 dev eth0 nexthop via 192.168.252.252 dev eth0
ip -netns host2 addr add 192.168.252.250/24 dev eth0
ip -netns host2 link set dev eth0 up
ip -netns host2 addr add 192.168.252.252/24 dev eth0
ip -netns host3 link set dev eth0 up
ip netns add tunnel
ip -netns tunnel li set lo up
ip -netns tunnel li add br0 type bridge
ip -netns tunnel li set br0 up
for n in $(seq 11 20); do
ip -netns tunnel addr add dev br0 192.168.247.${n}/24
done
for n in 2 3
do
ip -netns tunnel link add vti${n} type veth peer name eth${n}
ip -netns tunnel link set eth${n} mtu 1360 master br0 up
ip -netns tunnel link set vti${n} netns host${n} mtu 1360 up
ip -netns host${n} addr add dev vti${n} 192.168.247.${n}/24
done
ip -netns tunnel ro add default nexthop via 192.168.247.2 nexthop via 192.168.247.3
ip netns exec host1 ping -M do -s 1400 -c3 -I 192.168.252.209 192.168.247.11
ip netns exec host1 ping -M do -s 1400 -c3 -I 192.168.252.209 192.168.247.15
ip -netns host1 ro ls cache
Before this patch the cache always shows exceptions against the first
leg in the multipath route; 192.168.252.250 per this example. Since the
hash has an initial random seed, you may need to vary the final octet
more than what is listed. In my tests, using addresses between 11 and 19
usually found 1 that used both legs.
With this patch, the cache will have exceptions for both legs.
Fixes: 4895c771c7 ("ipv4: Add FIB nexthop exceptions")
Reported-by: Kfir Itzhak <mastertheknife@gmail.com>
Signed-off-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 1869e226a7 ]
flowi4_multipath_hash was added by the commit referenced below for
tunnels. Unfortunately, the patch did not initialize the new field
for several fast path lookups that do not initialize the entire flow
struct to 0. Fix those locations. Currently, flowi4_multipath_hash
is random garbage and affects the hash value computed by
fib_multipath_hash for multipath selection.
Fixes: 24ba14406c ("route: Add multipath_hash in flowi_common to make user-define hash")
Signed-off-by: David Ahern <dsahern@gmail.com>
Cc: wenxu <wenxu@ucloud.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit ba9e04a7dd ]
Currently, in tcp_v4_reqsk_send_ack() and tcp_v4_send_reset(), we
echo the TOS value of the received packets in the response.
However, we do not want to echo the lower 2 ECN bits in accordance
with RFC 3168 6.1.5 robustness principles.
Fixes: 1da177e4c3 ("Linux-2.6.12-rc2")
Signed-off-by: Wei Wang <weiwan@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>
[ Upstream commit d76f3351ce ]
In the case of TPROXY, bind_conflict optimizations for SO_REUSEADDR or
SO_REUSEPORT are broken, possibly resulting in O(n) instead of O(1) bind
behaviour or in the incorrect reuse of a bind.
the kernel keeps track for each bind_bucket if all sockets in the
bind_bucket support SO_REUSEADDR or SO_REUSEPORT in two fastreuse flags.
These flags allow skipping the costly bind_conflict check when possible
(meaning when all sockets have the proper SO_REUSE option).
For every socket added to a bind_bucket, these flags need to be updated.
As soon as a socket that does not support reuse is added, the flag is
set to false and will never go back to true, unless the bind_bucket is
deleted.
Note that there is no mechanism to re-evaluate these flags when a socket
is removed (this might make sense when removing a socket that would not
allow reuse; this leaves room for a future patch).
For this optimization to work, it is mandatory that these flags are
properly initialized and updated.
When a child socket is created from a listen socket in
__inet_inherit_port, the TPROXY case could create a new bind bucket
without properly initializing these flags, thus preventing the
optimization to work. Alternatively, a socket not allowing reuse could
be added to an existing bind bucket without updating the flags, causing
bind_conflict to never be called as it should.
Call inet_csk_update_fastreuse when __inet_inherit_port decides to create
a new bind_bucket or use a different bind_bucket than the one of the
listen socket.
Fixes: 093d282321 ("tproxy: fix hash locking issue when using port redirection in __inet_inherit_port()")
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Tim Froidcoeur <tim.froidcoeur@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 62ffc589ab ]
Refactor the fastreuse update code in inet_csk_get_port into a small
helper function that can be called from other places.
Acked-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: Tim Froidcoeur <tim.froidcoeur@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit f19008e676 ]
When TFO keys are read back on big endian systems either via the global
sysctl interface or via getsockopt() using TCP_FASTOPEN_KEY, the values
don't match what was written.
For example, on s390x:
# echo "1-2-3-4" > /proc/sys/net/ipv4/tcp_fastopen_key
# cat /proc/sys/net/ipv4/tcp_fastopen_key
02000000-01000000-04000000-03000000
Instead of:
# cat /proc/sys/net/ipv4/tcp_fastopen_key
00000001-00000002-00000003-00000004
Fix this by converting to the correct endianness on read. This was
reported by Colin Ian King when running the 'tcp_fastopen_backup_key' net
selftest on s390x, which depends on the read value matching what was
written. I've confirmed that the test now passes on big and little endian
systems.
Signed-off-by: Jason Baron <jbaron@akamai.com>
Fixes: 438ac88009 ("net: fastopen: robustness and endianness fixes for SipHash")
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Eric Dumazet <edumazet@google.com>
Reported-and-tested-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 730e700e2c ]
For retransmitted packets, TCP needs to resort to using TCP timestamps
for computing RTT samples. In the common case where the data and ACK
fall in the same 1-millisecond interval, TCP senders with millisecond-
granularity TCP timestamps compute a ca_rtt_us of 0. This ca_rtt_us
of 0 propagates to rs->rtt_us.
This value of 0 can cause performance problems for congestion control
modules. For example, in BBR, the zero min_rtt sample can bring the
min_rtt and BDP estimate down to 0, reduce snd_cwnd and result in a
low throughput. It would be hard to mitigate this with filtering in
the congestion control module, because the proper floor to apply would
depend on the method of RTT sampling (using timestamp options or
internally-saved transmission timestamps).
This fix applies a floor of 1 for the RTT sample delta from TCP
timestamps, so that seq_rtt_us, ca_rtt_us, and rs->rtt_us will be at
least 1 * (USEC_PER_SEC / TCP_TS_HZ).
Note that the receiver RTT computation in tcp_rcv_rtt_measure() and
min_rtt computation in tcp_update_rtt_min() both already apply a floor
of 1 timestamp tick, so this commit makes the code more consistent in
avoiding this edge case of a value of 0.
Signed-off-by: Jianfeng Wang <jfwang@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Kevin Yang <yyd@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 622e32b7d4 ]
The GRE tunnel can be used to transport traffic that does not rely on a
Internet checksum (e.g. SCTP). The issue can be triggered creating a GRE
or GRETAP tunnel and transmitting SCTP traffic ontop of it where CRC
offload has been disabled. In order to fix the issue we need to
recompute the GRE csum in gre_gso_segment() not relying on the inner
checksum.
The issue is still present when we have the CRC offload enabled.
In this case we need to disable the CRC offload if we require GRE
checksum since otherwise skb_checksum() will report a wrong value.
Fixes: 90017accff ("sctp: Add GSO support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 83f3522860 ]
fib_trie_unmerge() is called with RTNL held, but not from an RCU
read-side critical section. This leads to the following warning [1] when
the FIB alias list in a leaf is traversed with
hlist_for_each_entry_rcu().
Since the function is always called with RTNL held and since
modification of the list is protected by RTNL, simply use
hlist_for_each_entry() and silence the warning.
[1]
WARNING: suspicious RCU usage
5.8.0-rc4-custom-01520-gc1f937f3f83b #30 Not tainted
-----------------------------
net/ipv4/fib_trie.c:1867 RCU-list traversed in non-reader section!!
other info that might help us debug this:
rcu_scheduler_active = 2, debug_locks = 1
1 lock held by ip/164:
#0: ffffffff85a27850 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x49a/0xbd0
stack backtrace:
CPU: 0 PID: 164 Comm: ip Not tainted 5.8.0-rc4-custom-01520-gc1f937f3f83b #30
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-2.fc32 04/01/2014
Call Trace:
dump_stack+0x100/0x184
lockdep_rcu_suspicious+0x153/0x15d
fib_trie_unmerge+0x608/0xdb0
fib_unmerge+0x44/0x360
fib4_rule_configure+0xc8/0xad0
fib_nl_newrule+0x37a/0x1dd0
rtnetlink_rcv_msg+0x4f7/0xbd0
netlink_rcv_skb+0x17a/0x480
rtnetlink_rcv+0x22/0x30
netlink_unicast+0x5ae/0x890
netlink_sendmsg+0x98a/0xf40
____sys_sendmsg+0x879/0xa00
___sys_sendmsg+0x122/0x190
__sys_sendmsg+0x103/0x1d0
__x64_sys_sendmsg+0x7d/0xb0
do_syscall_64+0x54/0xa0
entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7fc80a234e97
Code: Bad RIP value.
RSP: 002b:00007ffef8b66798 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fc80a234e97
RDX: 0000000000000000 RSI: 00007ffef8b66800 RDI: 0000000000000003
RBP: 000000005f141b1c R08: 0000000000000001 R09: 0000000000000000
R10: 00007fc80a2a8ac0 R11: 0000000000000246 R12: 0000000000000001
R13: 0000000000000000 R14: 00007ffef8b67008 R15: 0000556fccb10020
Fixes: 0ddcf43d5d ("ipv4: FIB Local/MAIN table collapse")
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit efc6b6f6c3 ]
Currently, SO_REUSEPORT does not work well if connected sockets are in a
UDP reuseport group.
Then reuseport_has_conns() returns true and the result of
reuseport_select_sock() is discarded. Also, unconnected sockets have the
same score, hence only does the first unconnected socket in udp_hslot
always receive all packets sent to unconnected sockets.
So, the result of reuseport_select_sock() should be used for load
balancing.
The noteworthy point is that the unconnected sockets placed after
connected sockets in sock_reuseport.socks will receive more packets than
others because of the algorithm in reuseport_select_sock().
index | connected | reciprocal_scale | result
---------------------------------------------
0 | no | 20% | 40%
1 | no | 20% | 20%
2 | yes | 20% | 0%
3 | no | 20% | 40%
4 | yes | 20% | 0%
If most of the sockets are connected, this can be a problem, but it still
works better than now.
Fixes: acdcecc612 ("udp: correct reuseport selection with connected sockets")
CC: Willem de Bruijn <willemb@google.com>
Reviewed-by: Benjamin Herrenschmidt <benh@amazon.com>
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.co.jp>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 76be93fc07 ]
Previously TLP may send multiple probes of new data in one
flight. This happens when the sender is cwnd limited. After the
initial TLP containing new data is sent, the sender receives another
ACK that acks partial inflight. It may re-arm another TLP timer
to send more, if no further ACK returns before the next TLP timeout
(PTO) expires. The sender may send in theory a large amount of TLP
until send queue is depleted. This only happens if the sender sees
such irregular uncommon ACK pattern. But it is generally undesirable
behavior during congestion especially.
The original TLP design restrict only one TLP probe per inflight as
published in "Reducing Web Latency: the Virtue of Gentle Aggression",
SIGCOMM 2013. This patch changes TLP to send at most one probe
per inflight.
Note that if the sender is app-limited, TLP retransmits old data
and did not have this issue.
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: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit b0a422772f ]
We can't use IS_UDPLITE to replace udp_sk->pcflag when UDPLITE_RECV_CC is
checked.
Fixes: b2bf1e2659 ("[UDP]: Clean up for IS_UDPLITE macro")
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 0da7536fb4 ]
When no full socket is available, skbs are sent over a per-netns
control socket. Its sk_mark is temporarily adjusted to match that
of the real (request or timewait) socket or to reflect an incoming
skb, so that the outgoing skb inherits this in __ip_make_skb.
Introduction of the socket cookie mark field broke this. Now the
skb is set through the cookie and cork:
<caller> # init sockc.mark from sk_mark or cmsg
ip_append_data
ip_setup_cork # convert sockc.mark to cork mark
ip_push_pending_frames
ip_finish_skb
__ip_make_skb # set skb->mark to cork mark
But I missed these special control sockets. Update all callers of
__ip(6)_make_skb that were originally missed.
For IPv6, the same two icmp(v6) paths are affected. The third
case is not, as commit 92e55f412c ("tcp: don't annotate
mark on control socket from tcp_v6_send_response()") replaced
the ctl_sk->sk_mark with passing the mark field directly as a
function argument. That commit predates the commit that
introduced the bug.
Fixes: c6af0c227a ("ip: support SO_MARK cmsg")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reported-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-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>
[ Upstream commit 1ca0fafd73 ]
This essentially reverts commit 7212303268 ("tcp: md5: reject TCP_MD5SIG
or TCP_MD5SIG_EXT on established sockets")
Mathieu reported that many vendors BGP implementations can
actually switch TCP MD5 on established flows.
Quoting Mathieu :
Here is a list of a few network vendors along with their behavior
with respect to TCP MD5:
- Cisco: Allows for password to be changed, but within the hold-down
timer (~180 seconds).
- Juniper: When password is initially set on active connection it will
reset, but after that any subsequent password changes no network
resets.
- Nokia: No notes on if they flap the tcp connection or not.
- Ericsson/RedBack: Allows for 2 password (old/new) to co-exist until
both sides are ok with new passwords.
- Meta-Switch: Expects the password to be set before a connection is
attempted, but no further info on whether they reset the TCP
connection on a change.
- Avaya: Disable the neighbor, then set password, then re-enable.
- Zebos: Would normally allow the change when socket connected.
We can revert my prior change because commit 9424e2e7ad ("tcp: md5: fix potential
overestimation of TCP option space") removed the leak of 4 kernel bytes to
the wire that was the main reason for my patch.
While doing my investigations, I found a bug when a MD5 key is changed, leading
to these commits that stable teams want to consider before backporting this revert :
Commit 6a2febec33 ("tcp: md5: add missing memory barriers in tcp_md5_do_add()/tcp_md5_hash_key()")
Commit e6ced831ef ("tcp: md5: refine tcp_md5_do_add()/tcp_md5_hash_key() barriers")
Fixes: 7212303268 "tcp: md5: reject TCP_MD5SIG or TCP_MD5SIG_EXT on established sockets"
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit e6ced831ef ]
My prior fix went a bit too far, according to Herbert and Mathieu.
Since we accept that concurrent TCP MD5 lookups might see inconsistent
keys, we can use READ_ONCE()/WRITE_ONCE() instead of smp_rmb()/smp_wmb()
Clearing all key->key[] is needed to avoid possible KMSAN reports,
if key->keylen is increased. Since tcp_md5_do_add() is not fast path,
using __GFP_ZERO to clear all struct tcp_md5sig_key is simpler.
data_race() was added in linux-5.8 and will prevent KCSAN reports,
this can safely be removed in stable backports, if data_race() is
not yet backported.
v2: use data_race() both in tcp_md5_hash_key() and tcp_md5_do_add()
Fixes: 6a2febec33 ("tcp: md5: add missing memory barriers in tcp_md5_do_add()/tcp_md5_hash_key()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Marco Elver <elver@google.com>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit e114e1e8ac ]
Whenever cookie_init_timestamp() has been used to encode
ECN,SACK,WSCALE options, we can not remove the TS option in the SYNACK.
Otherwise, tcp_synack_options() will still advertize options like WSCALE
that we can not deduce later when receiving the packet from the client
to complete 3WHS.
Note that modern linux TCP stacks wont use MD5+TS+SACK in a SYN packet,
but we can not know for sure that all TCP stacks have the same logic.
Before the fix a tcpdump would exhibit this wrong exchange :
10:12:15.464591 IP C > S: Flags [S], seq 4202415601, win 65535, options [nop,nop,md5 valid,mss 1400,sackOK,TS val 456965269 ecr 0,nop,wscale 8], length 0
10:12:15.464602 IP S > C: Flags [S.], seq 253516766, ack 4202415602, win 65535, options [nop,nop,md5 valid,mss 1400,nop,nop,sackOK,nop,wscale 8], length 0
10:12:15.464611 IP C > S: Flags [.], ack 1, win 256, options [nop,nop,md5 valid], length 0
10:12:15.464678 IP C > S: Flags [P.], seq 1:13, ack 1, win 256, options [nop,nop,md5 valid], length 12
10:12:15.464685 IP S > C: Flags [.], ack 13, win 65535, options [nop,nop,md5 valid], length 0
After this patch the exchange looks saner :
11:59:59.882990 IP C > S: Flags [S], seq 517075944, win 65535, options [nop,nop,md5 valid,mss 1400,sackOK,TS val 1751508483 ecr 0,nop,wscale 8], length 0
11:59:59.883002 IP S > C: Flags [S.], seq 1902939253, ack 517075945, win 65535, options [nop,nop,md5 valid,mss 1400,sackOK,TS val 1751508479 ecr 1751508483,nop,wscale 8], length 0
11:59:59.883012 IP C > S: Flags [.], ack 1, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508483 ecr 1751508479], length 0
11:59:59.883114 IP C > S: Flags [P.], seq 1:13, ack 1, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508483 ecr 1751508479], length 12
11:59:59.883122 IP S > C: Flags [.], ack 13, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508483 ecr 1751508483], length 0
11:59:59.883152 IP S > C: Flags [P.], seq 1:13, ack 13, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508484 ecr 1751508483], length 12
11:59:59.883170 IP C > S: Flags [.], ack 13, win 256, options [nop,nop,md5 valid,nop,nop,TS val 1751508484 ecr 1751508484], length 0
Of course, no SACK block will ever be added later, but nothing should break.
Technically, we could remove the 4 nops included in MD5+TS options,
but again some stacks could break seeing not conventional alignment.
Fixes: 4957faade1 ("TCPCT part 1g: Responder Cookie => Initiator")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 6a2febec33 ]
MD5 keys are read with RCU protection, and tcp_md5_do_add()
might update in-place a prior key.
Normally, typical RCU updates would allocate a new piece
of memory. In this case only key->key and key->keylen might
be updated, and we do not care if an incoming packet could
see the old key, the new one, or some intermediate value,
since changing the key on a live flow is known to be problematic
anyway.
We only want to make sure that in the case key->keylen
is changed, cpus in tcp_md5_hash_key() wont try to use
uninitialized data, or crash because key->keylen was
read twice to feed sg_init_one() and ahash_request_set_crypt()
Fixes: 9ea88a1530 ("tcp: md5: check md5 signature without socket lock")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit ba3bb0e76c ]
Whenever tcp_try_rmem_schedule() returns an error, we are under
trouble and should make sure to wakeup readers so that they
can drain socket queues and eventually make room.
Fixes: 03f45c883c ("tcp: avoid extra wakeups for SO_RCVLOWAT users")
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 5eff069023 ]
IPv4 ping sockets don't set fl4.fl4_icmp_{type,code}, which leads to
incomplete IPsec ACQUIRE messages being sent to userspace. Currently,
both raw sockets and IPv6 ping sockets set those fields.
Expected output of "ip xfrm monitor":
acquire proto esp
sel src 10.0.2.15/32 dst 8.8.8.8/32 proto icmp type 8 code 0 dev ens4
policy src 10.0.2.15/32 dst 8.8.8.8/32
<snip>
Currently with ping sockets:
acquire proto esp
sel src 10.0.2.15/32 dst 8.8.8.8/32 proto icmp type 0 code 0 dev ens4
policy src 10.0.2.15/32 dst 8.8.8.8/32
<snip>
The Libreswan test suite found this problem after Fedora changed the
value for the sysctl net.ipv4.ping_group_range.
Fixes: c319b4d76b ("net: ipv4: add IPPROTO_ICMP socket kind")
Reported-by: Paul Wouters <pwouters@redhat.com>
Tested-by: Paul Wouters <pwouters@redhat.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit b344579ca8 ]
Mirja Kuehlewind reported a bug in Linux TCP CUBIC Hystart, where
Hystart HYSTART_DELAY mechanism can exit Slow Start spuriously on an
ACK when the minimum rtt of a connection goes down. From inspection it
is clear from the existing code that this could happen in an example
like the following:
o The first 8 RTT samples in a round trip are 150ms, resulting in a
curr_rtt of 150ms and a delay_min of 150ms.
o The 9th RTT sample is 100ms. The curr_rtt does not change after the
first 8 samples, so curr_rtt remains 150ms. But delay_min can be
lowered at any time, so delay_min falls to 100ms. The code executes
the HYSTART_DELAY comparison between curr_rtt of 150ms and delay_min
of 100ms, and the curr_rtt is declared far enough above delay_min to
force a (spurious) exit of Slow start.
The fix here is simple: allow every RTT sample in a round trip to
lower the curr_rtt.
Fixes: ae27e98a51 ("[TCP] CUBIC v2.3")
Reported-by: Mirja Kuehlewind <mirja.kuehlewind@ericsson.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit ba61539c6a ]
In the datapath, the ip_tunnel_lookup() is used and it internally uses
fallback tunnel device pointer, which is fb_tunnel_dev.
This pointer variable should be set to NULL when a fb interface is deleted.
But there is no routine to set fb_tunnel_dev pointer to NULL.
So, this pointer will be still used after interface is deleted and
it eventually results in the use-after-free problem.
Test commands:
ip netns add A
ip netns add B
ip link add eth0 type veth peer name eth1
ip link set eth0 netns A
ip link set eth1 netns B
ip netns exec A ip link set lo up
ip netns exec A ip link set eth0 up
ip netns exec A ip link add gre1 type gre local 10.0.0.1 \
remote 10.0.0.2
ip netns exec A ip link set gre1 up
ip netns exec A ip a a 10.0.100.1/24 dev gre1
ip netns exec A ip a a 10.0.0.1/24 dev eth0
ip netns exec B ip link set lo up
ip netns exec B ip link set eth1 up
ip netns exec B ip link add gre1 type gre local 10.0.0.2 \
remote 10.0.0.1
ip netns exec B ip link set gre1 up
ip netns exec B ip a a 10.0.100.2/24 dev gre1
ip netns exec B ip a a 10.0.0.2/24 dev eth1
ip netns exec A hping3 10.0.100.2 -2 --flood -d 60000 &
ip netns del B
Splat looks like:
[ 77.793450][ C3] ==================================================================
[ 77.794702][ C3] BUG: KASAN: use-after-free in ip_tunnel_lookup+0xcc4/0xf30
[ 77.795573][ C3] Read of size 4 at addr ffff888060bd9c84 by task hping3/2905
[ 77.796398][ C3]
[ 77.796664][ C3] CPU: 3 PID: 2905 Comm: hping3 Not tainted 5.8.0-rc1+ #616
[ 77.797474][ C3] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
[ 77.798453][ C3] Call Trace:
[ 77.798815][ C3] <IRQ>
[ 77.799142][ C3] dump_stack+0x9d/0xdb
[ 77.799605][ C3] print_address_description.constprop.7+0x2cc/0x450
[ 77.800365][ C3] ? ip_tunnel_lookup+0xcc4/0xf30
[ 77.800908][ C3] ? ip_tunnel_lookup+0xcc4/0xf30
[ 77.801517][ C3] ? ip_tunnel_lookup+0xcc4/0xf30
[ 77.802145][ C3] kasan_report+0x154/0x190
[ 77.802821][ C3] ? ip_tunnel_lookup+0xcc4/0xf30
[ 77.803503][ C3] ip_tunnel_lookup+0xcc4/0xf30
[ 77.804165][ C3] __ipgre_rcv+0x1ab/0xaa0 [ip_gre]
[ 77.804862][ C3] ? rcu_read_lock_sched_held+0xc0/0xc0
[ 77.805621][ C3] gre_rcv+0x304/0x1910 [ip_gre]
[ 77.806293][ C3] ? lock_acquire+0x1a9/0x870
[ 77.806925][ C3] ? gre_rcv+0xfe/0x354 [gre]
[ 77.807559][ C3] ? erspan_xmit+0x2e60/0x2e60 [ip_gre]
[ 77.808305][ C3] ? rcu_read_lock_sched_held+0xc0/0xc0
[ 77.809032][ C3] ? rcu_read_lock_held+0x90/0xa0
[ 77.809713][ C3] gre_rcv+0x1b8/0x354 [gre]
[ ... ]
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Fixes: c544193214 ("GRE: Refactor GRE tunneling code.")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 662051215c ]
Back in 2013, we made a change that broke fast retransmit
for non SACK flows.
Indeed, for these flows, a sender needs to receive three duplicate
ACK before starting fast retransmit. Sending ACK with different
receive window do not count.
Even if enabling SACK is strongly recommended these days,
there still are some cases where it has to be disabled.
Not increasing the window seems better than having to
rely on RTO.
After the fix, following packetdrill test gives :
// Initialize connection
0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0 bind(3, ..., ...) = 0
+0 listen(3, 1) = 0
+0 < S 0:0(0) win 32792 <mss 1000,nop,wscale 7>
+0 > S. 0:0(0) ack 1 <mss 1460,nop,wscale 8>
+0 < . 1:1(0) ack 1 win 514
+0 accept(3, ..., ...) = 4
+0 < . 1:1001(1000) ack 1 win 514
// Quick ack
+0 > . 1:1(0) ack 1001 win 264
+0 < . 2001:3001(1000) ack 1 win 514
// DUPACK : Normally we should not change the window
+0 > . 1:1(0) ack 1001 win 264
+0 < . 3001:4001(1000) ack 1 win 514
// DUPACK : Normally we should not change the window
+0 > . 1:1(0) ack 1001 win 264
+0 < . 4001:5001(1000) ack 1 win 514
// DUPACK : Normally we should not change the window
+0 > . 1:1(0) ack 1001 win 264
+0 < . 1001:2001(1000) ack 1 win 514
// Hole is repaired.
+0 > . 1:1(0) ack 5001 win 272
Fixes: 4e4f1fc226 ("tcp: properly increase rcv_ssthresh for ofo packets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.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 2570284060 ]
there is a problem with the CWR flag set in an incoming ACK segment
and it leads to the situation when the ECE flag is latched forever
the following packetdrill script shows what happens:
// Stack receives incoming segments with CE set
+0.1 <[ect0] . 11001:12001(1000) ack 1001 win 65535
+0.0 <[ce] . 12001:13001(1000) ack 1001 win 65535
+0.0 <[ect0] P. 13001:14001(1000) ack 1001 win 65535
// Stack repsonds with ECN ECHO
+0.0 >[noecn] . 1001:1001(0) ack 12001
+0.0 >[noecn] E. 1001:1001(0) ack 13001
+0.0 >[noecn] E. 1001:1001(0) ack 14001
// Write a packet
+0.1 write(3, ..., 1000) = 1000
+0.0 >[ect0] PE. 1001:2001(1000) ack 14001
// Pure ACK received
+0.01 <[noecn] W. 14001:14001(0) ack 2001 win 65535
// Since CWR was sent, this packet should NOT have ECE set
+0.1 write(3, ..., 1000) = 1000
+0.0 >[ect0] P. 2001:3001(1000) ack 14001
// but Linux will still keep ECE latched here, with packetdrill
// flagging a missing ECE flag, expecting
// >[ect0] PE. 2001:3001(1000) ack 14001
// in the script
In the situation above we will continue to send ECN ECHO packets
and trigger the peer to reduce the congestion window. To avoid that
we can check CWR on pure ACKs received.
v3:
- Add a sequence check to avoid sending an ACK to an ACK
v2:
- Adjusted the comment
- move CWR check before checking for unacknowledged packets
Signed-off-by: Denis Kirjanov <denis.kirjanov@suse.com>
Acked-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: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 5eea3a63ff ]
ie.,
$ ifconfig eth0 6.6.6.6 netmask 255.255.255.0
$ ip rule add from 6.6.6.6 table 6666
$ ip route add 9.9.9.9 via 6.6.6.6
$ ping -I 6.6.6.6 9.9.9.9
PING 9.9.9.9 (9.9.9.9) from 6.6.6.6 : 56(84) bytes of data.
3 packets transmitted, 0 received, 100% packet loss, time 2079ms
$ arp
Address HWtype HWaddress Flags Mask Iface
6.6.6.6 (incomplete) eth0
The arp request address is error, this is because fib_table_lookup in
fib_check_nh lookup the destnation 9.9.9.9 nexthop, the scope of
the fib result is RT_SCOPE_LINK,the correct scope is RT_SCOPE_HOST.
Here I add a check of whether this is RT_TABLE_MAIN to solve this problem.
Fixes: 3bfd847203 ("net: Use passed in table for nexthop lookups")
Signed-off-by: guodeqing <geffrey.guo@huawei.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Guillaume Nault
Alexander Duyck
Florian Klink
John Fastabend
Ryan Sharpelletti
Wang Hai
Jeff Dike
Mao Wenan
Alexander Lobakin
Jason A. Donenfeld
wenxu
Arjun Roy
Cong Wang
Pablo Neira Ayuso
Eric Dumazet
Neal Cardwell
Ido Schimmel
David Ahern
Coly Li
Vasily Averin
David Ahern
Wei Wang
Nikolay Aleksandrov
Tim Froidcoeur
Jason Baron
Jianfeng Wang
Lorenzo Bianconi
Ido Schimmel
Kuniyuki Iwashima
Yuchung Cheng
Miaohe Lin
Willem de Bruijn
Christoph Paasch
Sabrina Dubroca
Taehee Yoo
Denis Kirjanov
guodeqing