commit 9d9b1ee0b2 upstream.
The TCP session does not terminate with TCP_USER_TIMEOUT when data
remain untransmitted due to zero window.
The number of unanswered zero-window probes (tcp_probes_out) is
reset to zero with incoming acks irrespective of the window size,
as described in tcp_probe_timer():
RFC 1122 4.2.2.17 requires the sender to stay open indefinitely
as long as the receiver continues to respond probes. We support
this by default and reset icsk_probes_out with incoming ACKs.
This counter, however, is the wrong one to be used in calculating the
duration that the window remains closed and data remain untransmitted.
Thanks to Jonathan Maxwell <jmaxwell37@gmail.com> for diagnosing the
actual issue.
In this patch a new timestamp is introduced for the socket in order to
track the elapsed time for the zero-window probes that have not been
answered with any non-zero window ack.
Fixes: 9721e709fa ("tcp: simplify window probe aborting on USER_TIMEOUT")
Reported-by: William McCall <william.mccall@gmail.com>
Co-developed-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Enke Chen <enchen@paloaltonetworks.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20210115223058.GA39267@localhost.localdomain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit b160c28548 upstream.
Heiner Kallweit reported that some skbs were sent with
the following invalid GSO properties :
- gso_size > 0
- gso_type == 0
This was triggerring a WARN_ON_ONCE() in rtl8169_tso_csum_v2.
Juerg Haefliger was able to reproduce a similar issue using
a lan78xx NIC and a workload mixing TCP incoming traffic
and forwarded packets.
The problem is that tcp_add_backlog() is writing
over gso_segs and gso_size even if the incoming packet will not
be coalesced to the backlog tail packet.
While skb_try_coalesce() would bail out if tail packet is cloned,
this overwriting would lead to corruptions of other packets
cooked by lan78xx, sharing a common super-packet.
The strategy used by lan78xx is to use a big skb, and split
it into all received packets using skb_clone() to avoid copies.
The drawback of this strategy is that all the small skb share a common
struct skb_shared_info.
This patch rewrites TCP gso_size/gso_segs handling to only
happen on the tail skb, since skb_try_coalesce() made sure
it was not cloned.
Fixes: 4f693b55c3 ("tcp: implement coalescing on backlog queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Bisected-by: Juerg Haefliger <juergh@canonical.com>
Tested-by: Juerg Haefliger <juergh@canonical.com>
Reported-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=209423
Link: https://lore.kernel.org/r/20210119164900.766957-1-eric.dumazet@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 8d2b51b008 upstream.
udp_v4_early_demux() is the only function that calls
ip_mc_validate_source() with a TOS that hasn't been masked with
IPTOS_RT_MASK.
This results in different behaviours for incoming multicast UDPv4
packets, depending on if ip_mc_validate_source() is called from the
early-demux path (udp_v4_early_demux) or from the regular input path
(ip_route_input_noref).
ECN would normally not be used with UDP multicast packets, so the
practical consequences should be limited on that side. However,
IPTOS_RT_MASK is used to also masks the TOS' high order bits, to align
with the non-early-demux path behaviour.
Reproducer:
Setup two netns, connected with veth:
$ ip netns add ns0
$ ip netns add ns1
$ ip -netns ns0 link set dev lo up
$ ip -netns ns1 link set dev lo up
$ ip link add name veth01 netns ns0 type veth peer name veth10 netns ns1
$ ip -netns ns0 link set dev veth01 up
$ ip -netns ns1 link set dev veth10 up
$ ip -netns ns0 address add 192.0.2.10 peer 192.0.2.11/32 dev veth01
$ ip -netns ns1 address add 192.0.2.11 peer 192.0.2.10/32 dev veth10
In ns0, add route to multicast address 224.0.2.0/24 using source
address 198.51.100.10:
$ ip -netns ns0 address add 198.51.100.10/32 dev lo
$ ip -netns ns0 route add 224.0.2.0/24 dev veth01 src 198.51.100.10
In ns1, define route to 198.51.100.10, only for packets with TOS 4:
$ ip -netns ns1 route add 198.51.100.10/32 tos 4 dev veth10
Also activate rp_filter in ns1, so that incoming packets not matching
the above route get dropped:
$ ip netns exec ns1 sysctl -wq net.ipv4.conf.veth10.rp_filter=1
Now try to receive packets on 224.0.2.11:
$ ip netns exec ns1 socat UDP-RECVFROM:1111,ip-add-membership=224.0.2.11:veth10,ignoreeof -
In ns0, send packet to 224.0.2.11 with TOS 4 and ECT(0) (that is,
tos 6 for socat):
$ echo test0 | ip netns exec ns0 socat - UDP-DATAGRAM:224.0.2.11:1111,bind=:1111,tos=6
The "test0" message is properly received by socat in ns1, because
early-demux has no cached dst to use, so source address validation
is done by ip_route_input_mc(), which receives a TOS that has the
ECN bits masked.
Now send another packet to 224.0.2.11, still with TOS 4 and ECT(0):
$ echo test1 | ip netns exec ns0 socat - UDP-DATAGRAM:224.0.2.11:1111,bind=:1111,tos=6
The "test1" message isn't received by socat in ns1, because, now,
early-demux has a cached dst to use and calls ip_mc_validate_source()
immediately, without masking the ECN bits.
Fixes: bc044e8db7 ("udp: perform source validation for mcast early demux")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
commit 2e5a6266fb upstream.
RT_TOS() only masks one of the two ECN bits. Therefore rpfilter_mt()
treats Not-ECT or ECT(1) packets in a different way than those with
ECT(0) or CE.
Reproducer:
Create two netns, connected with a veth:
$ ip netns add ns0
$ ip netns add ns1
$ ip link add name veth01 netns ns0 type veth peer name veth10 netns ns1
$ ip -netns ns0 link set dev veth01 up
$ ip -netns ns1 link set dev veth10 up
$ ip -netns ns0 address add 192.0.2.10/32 dev veth01
$ ip -netns ns1 address add 192.0.2.11/32 dev veth10
Add a route to ns1 in ns0:
$ ip -netns ns0 route add 192.0.2.11/32 dev veth01
In ns1, only packets with TOS 4 can be routed to ns0:
$ ip -netns ns1 route add 192.0.2.10/32 tos 4 dev veth10
Ping from ns0 to ns1 works regardless of the ECN bits, as long as TOS
is 4:
$ ip netns exec ns0 ping -Q 4 192.0.2.11 # TOS 4, Not-ECT
... 0% packet loss ...
$ ip netns exec ns0 ping -Q 5 192.0.2.11 # TOS 4, ECT(1)
... 0% packet loss ...
$ ip netns exec ns0 ping -Q 6 192.0.2.11 # TOS 4, ECT(0)
... 0% packet loss ...
$ ip netns exec ns0 ping -Q 7 192.0.2.11 # TOS 4, CE
... 0% packet loss ...
Now use iptable's rpfilter module in ns1:
$ ip netns exec ns1 iptables-legacy -t raw -A PREROUTING -m rpfilter --invert -j DROP
Not-ECT and ECT(1) packets still pass:
$ ip netns exec ns0 ping -Q 4 192.0.2.11 # TOS 4, Not-ECT
... 0% packet loss ...
$ ip netns exec ns0 ping -Q 5 192.0.2.11 # TOS 4, ECT(1)
... 0% packet loss ...
But ECT(0) and ECN packets are dropped:
$ ip netns exec ns0 ping -Q 6 192.0.2.11 # TOS 4, ECT(0)
... 100% packet loss ...
$ ip netns exec ns0 ping -Q 7 192.0.2.11 # TOS 4, CE
... 100% packet loss ...
After this patch, rpfilter doesn't drop ECT(0) and CE packets anymore.
Fixes: 8f97339d3f ("netfilter: add ipv4 reverse path filter match")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 9bd6b629c3 ]
esp(6)_output_head uses skb_page_frag_refill to allocate a buffer for
the esp trailer.
It accesses the page with kmap_atomic to handle highmem. But
skb_page_frag_refill can return compound pages, of which
kmap_atomic only maps the first underlying page.
skb_page_frag_refill does not return highmem, because flag
__GFP_HIGHMEM is not set. ESP uses it in the same manner as TCP.
That also does not call kmap_atomic, but directly uses page_address,
in skb_copy_to_page_nocache. Do the same for ESP.
This issue has become easier to trigger with recent kmap local
debugging feature CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP.
Fixes: cac2661c53 ("esp4: Avoid skb_cow_data whenever possible")
Fixes: 03e2a30f6a ("esp6: Avoid skb_cow_data whenever possible")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 7b01e53eee ]
In case of error, remove the nexthop group entry from the list to which
it was previously added.
Fixes: 430a049190 ("nexthop: Add support for nexthop groups")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 07e61a979c ]
A reference was not taken for the current nexthop entry, so do not try
to put it in the error path.
Fixes: 430a049190 ("nexthop: Add support for nexthop groups")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit bb4cc1a188 ]
Conntrack reassembly records the largest fragment size seen in IPCB.
However, when this gets forwarded/transmitted, fragmentation will only
be forced if one of the fragmented packets had the DF bit set.
In that case, a flag in IPCB will force fragmentation even if the
MTU is large enough.
This should work fine, but this breaks with ip tunnels.
Consider client that sends a UDP datagram of size X to another host.
The client fragments the datagram, so two packets, of size y and z, are
sent. DF bit is not set on any of these packets.
Middlebox netfilter reassembles those packets back to single size-X
packet, before routing decision.
packet-size-vs-mtu checks in ip_forward are irrelevant, because DF bit
isn't set. At output time, ip refragmentation is skipped as well
because x is still smaller than the mtu of the output device.
If ttransmit device is an ip tunnel, the packet size increases to
x+overhead.
Also, tunnel might be configured to force DF bit on outer header.
In this case, packet will be dropped (exceeds MTU) and an ICMP error is
generated back to sender.
But sender already respects the announced MTU, all the packets that
it sent did fit the announced mtu.
Force refragmentation as per original sizes unconditionally so ip tunnel
will encapsulate the fragments instead.
The only other solution I see is to place ip refragmentation in
the ip_tunnel code to handle this case.
Fixes: d6b915e29f ("ip_fragment: don't forward defragmented DF packet")
Reported-by: Christian Perle <christian.perle@secunet.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 50c661670f ]
For some reason ip_tunnel insist on setting the DF bit anyway when the
inner header has the DF bit set, EVEN if the tunnel was configured with
'nopmtudisc'.
This means that the script added in the previous commit
cannot be made to work by adding the 'nopmtudisc' flag to the
ip tunnel configuration. Doing so breaks connectivity even for the
without-conntrack/netfilter scenario.
When nopmtudisc is set, the tunnel will skip the mtu check, so no
icmp error is sent to client. Then, because inner header has DF set,
the outer header gets added with DF bit set as well.
IP stack then sends an error to itself because the packet exceeds
the device MTU.
Fixes: 23a3647bc4 ("ip_tunnels: Use skb-len to PMTU check.")
Cc: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 085c7c4e1c ]
Both version 0 and version 1 use ETH_P_ERSPAN, but version 0 does not
have an erspan header. So the check in gre_parse_header() is wrong,
we have to distinguish version 1 from version 0.
We can just check the gre header length like is_erspan_type1().
Fixes: cb73ee40b1 ("net: ip_gre: use erspan key field for tunnel lookup")
Reported-by: syzbot+f583ce3d4ddf9836b27a@syzkaller.appspotmail.com
Cc: William Tu <u9012063@gmail.com>
Cc: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Cong Wang <cong.wang@bytedance.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 21fdca22eb ]
RT_TOS() only clears one of the ECN bits. Therefore, when
fib_compute_spec_dst() resorts to a fib lookup, it can return
different results depending on the value of the second ECN bit.
For example, ECT(0) and ECT(1) packets could be treated differently.
$ ip netns add ns0
$ ip netns add ns1
$ ip link add name veth01 netns ns0 type veth peer name veth10 netns ns1
$ ip -netns ns0 link set dev lo up
$ ip -netns ns1 link set dev lo up
$ ip -netns ns0 link set dev veth01 up
$ ip -netns ns1 link set dev veth10 up
$ ip -netns ns0 address add 192.0.2.10/24 dev veth01
$ ip -netns ns1 address add 192.0.2.11/24 dev veth10
$ ip -netns ns1 address add 192.0.2.21/32 dev lo
$ ip -netns ns1 route add 192.0.2.10/32 tos 4 dev veth10 src 192.0.2.21
$ ip netns exec ns1 sysctl -wq net.ipv4.icmp_echo_ignore_broadcasts=0
With TOS 4 and ECT(1), ns1 replies using source address 192.0.2.21
(ping uses -Q to set all TOS and ECN bits):
$ ip netns exec ns0 ping -c 1 -b -Q 5 192.0.2.255
[...]
64 bytes from 192.0.2.21: icmp_seq=1 ttl=64 time=0.544 ms
But with TOS 4 and ECT(0), ns1 replies using source address 192.0.2.11
because the "tos 4" route isn't matched:
$ ip netns exec ns0 ping -c 1 -b -Q 6 192.0.2.255
[...]
64 bytes from 192.0.2.11: icmp_seq=1 ttl=64 time=0.597 ms
After this patch the ECN bits don't affect the result anymore:
$ ip netns exec ns0 ping -c 1 -b -Q 6 192.0.2.255
[...]
64 bytes from 192.0.2.21: icmp_seq=1 ttl=64 time=0.591 ms
Fixes: 35ebf65e85 ("ipv4: Create and use fib_compute_spec_dst() helper.")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit cc00bcaa58 ]
When running concurrent iptables rules replacement with data, the per CPU
sequence count is checked after the assignment of the new information.
The sequence count is used to synchronize with the packet path without the
use of any explicit locking. If there are any packets in the packet path using
the table information, the sequence count is incremented to an odd value and
is incremented to an even after the packet process completion.
The new table value assignment is followed by a write memory barrier so every
CPU should see the latest value. If the packet path has started with the old
table information, the sequence counter will be odd and the iptables
replacement will wait till the sequence count is even prior to freeing the
old table info.
However, this assumes that the new table information assignment and the memory
barrier is actually executed prior to the counter check in the replacement
thread. If CPU decides to execute the assignment later as there is no user of
the table information prior to the sequence check, the packet path in another
CPU may use the old table information. The replacement thread would then free
the table information under it leading to a use after free in the packet
processing context-
Unable to handle kernel NULL pointer dereference at virtual
address 000000000000008e
pc : ip6t_do_table+0x5d0/0x89c
lr : ip6t_do_table+0x5b8/0x89c
ip6t_do_table+0x5d0/0x89c
ip6table_filter_hook+0x24/0x30
nf_hook_slow+0x84/0x120
ip6_input+0x74/0xe0
ip6_rcv_finish+0x7c/0x128
ipv6_rcv+0xac/0xe4
__netif_receive_skb+0x84/0x17c
process_backlog+0x15c/0x1b8
napi_poll+0x88/0x284
net_rx_action+0xbc/0x23c
__do_softirq+0x20c/0x48c
This could be fixed by forcing instruction order after the new table
information assignment or by switching to RCU for the synchronization.
Fixes: 80055dab5d ("netfilter: x_tables: make xt_replace_table wait until old rules are not used anymore")
Reported-by: Sean Tranchetti <stranche@codeaurora.org>
Reported-by: kernel test robot <lkp@intel.com>
Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
[ Upstream commit 299bcb55ec ]
When cwnd is not a multiple of the TSO skb size of N*MSS, we can get
into persistent scenarios where we have the following sequence:
(1) ACK for full-sized skb of N*MSS arrives
-> tcp_write_xmit() transmit full-sized skb with N*MSS
-> move pacing release time forward
-> exit tcp_write_xmit() because pacing time is in the future
(2) TSQ callback or TCP internal pacing timer fires
-> try to transmit next skb, but TSO deferral finds remainder of
available cwnd is not big enough to trigger an immediate send
now, so we defer sending until the next ACK.
(3) repeat...
So we can get into a case where we never mark ourselves as
cwnd-limited for many seconds at a time, even with
bulk/infinite-backlog senders, because:
o In case (1) above, every time in tcp_write_xmit() we have enough
cwnd to send a full-sized skb, we are not fully using the cwnd
(because cwnd is not a multiple of the TSO skb size). So every time we
send data, we are not cwnd limited, and so in the cwnd-limited
tracking code in tcp_cwnd_validate() we mark ourselves as not
cwnd-limited.
o In case (2) above, every time in tcp_write_xmit() that we try to
transmit the "remainder" of the cwnd but defer, we set the local
variable is_cwnd_limited to true, but we do not send any packets, so
sent_pkts is zero, so we don't call the cwnd-limited logic to update
tp->is_cwnd_limited.
Fixes: ca8a226343 ("tcp: make cwnd-limited checks measurement-based, and gentler")
Reported-by: Ingemar Johansson <ingemar.s.johansson@ericsson.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20201209035759.1225145-1-ncardwell.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 72d05c00d7 ]
Before commit a337531b94 ("tcp: up initial rmem to 128KB and SYN rwin to around 64KB")
small tcp_rmem[1] values were overridden by tcp_fixup_rcvbuf() to accommodate various MSS.
This is no longer the case, and Hazem Mohamed Abuelfotoh reported
that DRS would not work for MTU 9000 endpoints receiving regular (1500 bytes) frames.
Root cause is that tcp_init_buffer_space() uses tp->rcv_wnd for upper limit
of rcvq_space.space computation, while it can select later a smaller
value for tp->rcv_ssthresh and tp->window_clamp.
ss -temoi on receiver would show :
skmem:(r0,rb131072,t0,tb46080,f0,w0,o0,bl0,d0) rcv_space:62496 rcv_ssthresh:56596
This means that TCP can not increase its window in tcp_grow_window(),
and that DRS can never kick.
Fix this by making sure that rcvq_space.space is not bigger than number of bytes
that can be held in TCP receive queue.
People unable/unwilling to change their kernel can work around this issue by
selecting a bigger tcp_rmem[1] value as in :
echo "4096 196608 6291456" >/proc/sys/net/ipv4/tcp_rmem
Based on an initial report and patch from Hazem Mohamed Abuelfotoh
https://lore.kernel.org/netdev/20201204180622.14285-1-abuehaze@amazon.com/
Fixes: a337531b94 ("tcp: up initial rmem to 128KB and SYN rwin to around 64KB")
Fixes: 041a14d267 ("tcp: start receiver buffer autotuning sooner")
Reported-by: Hazem Mohamed Abuelfotoh <abuehaze@amazon.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 10c678bd0a ]
Guillaume noticed that: for segments udp_queue_rcv_one_skb() returns the
proto, and it should pass "ret" unmodified to ip_protocol_deliver_rcu().
Otherwize, with a negtive value passed, it will underflow inet_protos.
This can be reproduced with IPIP FOU:
# ip fou add port 5555 ipproto 4
# ethtool -K eth1 rx-gro-list on
Fixes: cf329aa42b ("udp: cope with UDP GRO packet misdirection")
Reported-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit b410f04eb5 ]
Fix to return a negative error code from the error handling
case instead of 0, as done elsewhere in this function.
Fixes: d15662682d ("ipv4: Allow ipv6 gateway with ipv4 routes")
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/1607071695-33740-1-git-send-email-zhangchangzhong@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ 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>
Enke Chen