Age | Commit message (Collapse) | Author |
|
[ Upstream commit c95c07836fa4c1767ed11d8eca0769c652760e32 ]
We are changing expire_nodest_conn to work even for reused connections when
conn_reuse_mode=0, just as what was done with commit dc7b3eb900aa ("ipvs:
Fix reuse connection if real server is dead").
For controlled and persistent connections, the new connection will get the
needed real server depending on the rules in ip_vs_check_template().
Fixes: d752c3645717 ("ipvs: allow rescheduling of new connections when port reuse is detected")
Co-developed-by: Chuanqi Liu <legend050709@qq.com>
Signed-off-by: Chuanqi Liu <legend050709@qq.com>
Signed-off-by: yangxingwu <xingwu.yang@gmail.com>
Acked-by: Simon Horman <horms@verge.net.au>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
[ Upstream commit 46d6c5ae953cc0be38efd0e469284df7c4328cf8 ]
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: 1da177e4c3f4 ("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 f0a5e4d7a594e0fe237d3dfafb069bb82f80f42f ]
YangYuxi is reporting that connection reuse
is causing one-second delay when SYN hits
existing connection in TIME_WAIT state.
Such delay was added to give time to expire
both the IPVS connection and the corresponding
conntrack. This was considered a rare case
at that time but it is causing problem for
some environments such as Kubernetes.
As nf_conntrack_tcp_packet() can decide to
release the conntrack in TIME_WAIT state and
to replace it with a fresh NEW conntrack, we
can use this to allow rescheduling just by
tuning our check: if the conntrack is
confirmed we can not schedule it to different
real server and the one-second delay still
applies but if new conntrack was created,
we are free to select new real server without
any delays.
YangYuxi lists some of the problem reports:
- One second connection delay in masquerading mode:
https://marc.info/?t=151683118100004&r=1&w=2
- IPVS low throughput #70747
https://github.com/kubernetes/kubernetes/issues/70747
- Apache Bench can fill up ipvs service proxy in seconds #544
https://github.com/cloudnativelabs/kube-router/issues/544
- Additional 1s latency in `host -> service IP -> pod`
https://github.com/kubernetes/kubernetes/issues/90854
Fixes: f719e3754ee2 ("ipvs: drop first packet to redirect conntrack")
Co-developed-by: YangYuxi <yx.atom1@gmail.com>
Signed-off-by: YangYuxi <yx.atom1@gmail.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Reviewed-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
|
|
This patch removes extra spaces.
Signed-off-by: yangxingwu <xingwu.yang@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Two cases of overlapping changes, nothing fancy.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Recognize GRE tunnels in received ICMP errors and
properly strip the tunnel headers.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
syzkaller reports for memory leak when registering hooks [1]
As we moved the nf_unregister_net_hooks() call into
__ip_vs_dev_cleanup(), defer the nf_register_net_hooks()
call, so that hooks are allocated and freed from same
pernet_operations (ipvs_core_dev_ops).
[1]
BUG: memory leak
unreferenced object 0xffff88810acd8a80 (size 96):
comm "syz-executor073", pid 7254, jiffies 4294950560 (age 22.250s)
hex dump (first 32 bytes):
02 00 00 00 00 00 00 00 50 8b bb 82 ff ff ff ff ........P.......
00 00 00 00 00 00 00 00 00 77 bb 82 ff ff ff ff .........w......
backtrace:
[<0000000013db61f1>] kmemleak_alloc_recursive include/linux/kmemleak.h:55 [inline]
[<0000000013db61f1>] slab_post_alloc_hook mm/slab.h:439 [inline]
[<0000000013db61f1>] slab_alloc_node mm/slab.c:3269 [inline]
[<0000000013db61f1>] kmem_cache_alloc_node_trace+0x15b/0x2a0 mm/slab.c:3597
[<000000001a27307d>] __do_kmalloc_node mm/slab.c:3619 [inline]
[<000000001a27307d>] __kmalloc_node+0x38/0x50 mm/slab.c:3627
[<0000000025054add>] kmalloc_node include/linux/slab.h:590 [inline]
[<0000000025054add>] kvmalloc_node+0x4a/0xd0 mm/util.c:431
[<0000000050d1bc00>] kvmalloc include/linux/mm.h:637 [inline]
[<0000000050d1bc00>] kvzalloc include/linux/mm.h:645 [inline]
[<0000000050d1bc00>] allocate_hook_entries_size+0x3b/0x60 net/netfilter/core.c:61
[<00000000e8abe142>] nf_hook_entries_grow+0xae/0x270 net/netfilter/core.c:128
[<000000004b94797c>] __nf_register_net_hook+0x9a/0x170 net/netfilter/core.c:337
[<00000000d1545cbc>] nf_register_net_hook+0x34/0xc0 net/netfilter/core.c:464
[<00000000876c9b55>] nf_register_net_hooks+0x53/0xc0 net/netfilter/core.c:480
[<000000002ea868e0>] __ip_vs_init+0xe8/0x170 net/netfilter/ipvs/ip_vs_core.c:2280
[<000000002eb2d451>] ops_init+0x4c/0x140 net/core/net_namespace.c:130
[<000000000284ec48>] setup_net+0xde/0x230 net/core/net_namespace.c:316
[<00000000a70600fa>] copy_net_ns+0xf0/0x1e0 net/core/net_namespace.c:439
[<00000000ff26c15e>] create_new_namespaces+0x141/0x2a0 kernel/nsproxy.c:107
[<00000000b103dc79>] copy_namespaces+0xa1/0xe0 kernel/nsproxy.c:165
[<000000007cc008a2>] copy_process.part.0+0x11fd/0x2150 kernel/fork.c:2035
[<00000000c344af7c>] copy_process kernel/fork.c:1800 [inline]
[<00000000c344af7c>] _do_fork+0x121/0x4f0 kernel/fork.c:2369
Reported-by: syzbot+722da59ccb264bc19910@syzkaller.appspotmail.com
Fixes: 719c7d563c17 ("ipvs: Fix use-after-free in ip_vs_in")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Some ISDN files that got removed in net-next had some changes
done in mainline, take the removals.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Pablo Neira Ayuso says:
====================
Netfilter/IPVS updates for net-next
The following patchset container Netfilter/IPVS update for net-next:
1) Add UDP tunnel support for ICMP errors in IPVS.
Julian Anastasov says:
This patchset is a followup to the commit that adds UDP/GUE tunnel:
"ipvs: allow tunneling with gue encapsulation".
What we do is to put tunnel real servers in hash table (patch 1),
add function to lookup tunnels (patch 2) and use it to strip the
embedded tunnel headers from ICMP errors (patch 3).
2) Extend xt_owner to match for supplementary groups, from
Lukasz Pawelczyk.
3) Remove unused oif field in flow_offload_tuple object, from
Taehee Yoo.
4) Release basechain counters from workqueue to skip synchronize_rcu()
call. From Florian Westphal.
5) Replace skb_make_writable() by skb_ensure_writable(). Patchset
from Florian Westphal.
6) Checksum support for gue encapsulation in IPVS, from Jacky Hu.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
It does the same thing, use it instead so we can remove skb_make_writable.
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Recognize UDP tunnels in received ICMP errors and
properly strip the tunnel headers. GUE is what we
have for now.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Add ip_vs_find_tunnel() to match tunnel headers
by family, address and optional port. Use it to
properly find the tunnel real server used in
received ICMP errors.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core
Pull yet more SPDX updates from Greg KH:
"Here is another set of reviewed patches that adds SPDX tags to
different kernel files, based on a set of rules that are being used to
parse the comments to try to determine that the license of the file is
"GPL-2.0-or-later" or "GPL-2.0-only". Only the "obvious" versions of
these matches are included here, a number of "non-obvious" variants of
text have been found but those have been postponed for later review
and analysis.
There is also a patch in here to add the proper SPDX header to a bunch
of Kbuild files that we have missed in the past due to new files being
added and forgetting that Kbuild uses two different file names for
Makefiles. This issue was reported by the Kbuild maintainer.
These patches have been out for review on the linux-spdx@vger mailing
list, and while they were created by automatic tools, they were
hand-verified by a bunch of different people, all whom names are on
the patches are reviewers"
* tag 'spdx-5.2-rc3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (82 commits)
treewide: Add SPDX license identifier - Kbuild
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 225
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 224
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 223
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 222
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 221
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 220
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 218
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 217
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 216
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 215
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 214
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 213
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 211
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 210
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 209
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 207
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 206
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 203
treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 201
...
|
|
Based on 1 normalized pattern(s):
this program is free software you can redistribute it and or modify
it under the terms of the gnu general public license as published by
the free software foundation either version 2 of the license or at
your option any later version
extracted by the scancode license scanner the SPDX license identifier
GPL-2.0-or-later
has been chosen to replace the boilerplate/reference in 3029 file(s).
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Allison Randal <allison@lohutok.net>
Cc: linux-spdx@vger.kernel.org
Link: https://lkml.kernel.org/r/20190527070032.746973796@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
BUG: KASAN: use-after-free in ip_vs_in.part.29+0xe8/0xd20 [ip_vs]
Read of size 4 at addr ffff8881e9b26e2c by task sshd/5603
CPU: 0 PID: 5603 Comm: sshd Not tainted 4.19.39+ #30
Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011
Call Trace:
dump_stack+0x71/0xab
print_address_description+0x6a/0x270
kasan_report+0x179/0x2c0
ip_vs_in.part.29+0xe8/0xd20 [ip_vs]
ip_vs_in+0xd8/0x170 [ip_vs]
nf_hook_slow+0x5f/0xe0
__ip_local_out+0x1d5/0x250
ip_local_out+0x19/0x60
__tcp_transmit_skb+0xba1/0x14f0
tcp_write_xmit+0x41f/0x1ed0
? _copy_from_iter_full+0xca/0x340
__tcp_push_pending_frames+0x52/0x140
tcp_sendmsg_locked+0x787/0x1600
? tcp_sendpage+0x60/0x60
? inet_sk_set_state+0xb0/0xb0
tcp_sendmsg+0x27/0x40
sock_sendmsg+0x6d/0x80
sock_write_iter+0x121/0x1c0
? sock_sendmsg+0x80/0x80
__vfs_write+0x23e/0x370
vfs_write+0xe7/0x230
ksys_write+0xa1/0x120
? __ia32_sys_read+0x50/0x50
? __audit_syscall_exit+0x3ce/0x450
do_syscall_64+0x73/0x200
entry_SYSCALL_64_after_hwframe+0x44/0xa9
RIP: 0033:0x7ff6f6147c60
Code: 73 01 c3 48 8b 0d 28 12 2d 00 f7 d8 64 89 01 48 83 c8 ff c3 66 0f 1f 44 00 00 83 3d 5d 73 2d 00 00 75 10 b8 01 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83
RSP: 002b:00007ffd772ead18 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000000034 RCX: 00007ff6f6147c60
RDX: 0000000000000034 RSI: 000055df30a31270 RDI: 0000000000000003
RBP: 000055df30a31270 R08: 0000000000000000 R09: 0000000000000000
R10: 00007ffd772ead70 R11: 0000000000000246 R12: 00007ffd772ead74
R13: 00007ffd772eae20 R14: 00007ffd772eae24 R15: 000055df2f12ddc0
Allocated by task 6052:
kasan_kmalloc+0xa0/0xd0
__kmalloc+0x10a/0x220
ops_init+0x97/0x190
register_pernet_operations+0x1ac/0x360
register_pernet_subsys+0x24/0x40
0xffffffffc0ea016d
do_one_initcall+0x8b/0x253
do_init_module+0xe3/0x335
load_module+0x2fc0/0x3890
__do_sys_finit_module+0x192/0x1c0
do_syscall_64+0x73/0x200
entry_SYSCALL_64_after_hwframe+0x44/0xa9
Freed by task 6067:
__kasan_slab_free+0x130/0x180
kfree+0x90/0x1a0
ops_free_list.part.7+0xa6/0xc0
unregister_pernet_operations+0x18b/0x1f0
unregister_pernet_subsys+0x1d/0x30
ip_vs_cleanup+0x1d/0xd2f [ip_vs]
__x64_sys_delete_module+0x20c/0x300
do_syscall_64+0x73/0x200
entry_SYSCALL_64_after_hwframe+0x44/0xa9
The buggy address belongs to the object at ffff8881e9b26600 which belongs to the cache kmalloc-4096 of size 4096
The buggy address is located 2092 bytes inside of 4096-byte region [ffff8881e9b26600, ffff8881e9b27600)
The buggy address belongs to the page:
page:ffffea0007a6c800 count:1 mapcount:0 mapping:ffff888107c0e600 index:0x0 compound_mapcount: 0
flags: 0x17ffffc0008100(slab|head)
raw: 0017ffffc0008100 dead000000000100 dead000000000200 ffff888107c0e600
raw: 0000000000000000 0000000080070007 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected
while unregistering ipvs module, ops_free_list calls
__ip_vs_cleanup, then nf_unregister_net_hooks be called to
do remove nf hook entries. It need a RCU period to finish,
however net->ipvs is set to NULL immediately, which will
trigger NULL pointer dereference when a packet is hooked
and handled by ip_vs_in where net->ipvs is dereferenced.
Another scene is ops_free_list call ops_free to free the
net_generic directly while __ip_vs_cleanup finished, then
calling ip_vs_in will triggers use-after-free.
This patch moves nf_unregister_net_hooks from __ip_vs_cleanup()
to __ip_vs_dev_cleanup(), where rcu_barrier() is called by
unregister_pernet_device -> unregister_pernet_operations,
that will do the needed grace period.
Reported-by: Hulk Robot <hulkci@huawei.com>
Fixes: efe41606184e ("ipvs: convert to use pernet nf_hook api")
Suggested-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
We can receive ICMP errors from client or from
tunneling real server. While the former can be
scheduled to real server, the latter should
not be scheduled, they are decapsulated only when
existing connection is found.
Fixes: 6044eeffafbe ("ipvs: attempt to schedule icmp packets")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
The netfilter conflicts were rather simple overlapping
changes.
However, the cls_tcindex.c stuff was a bit more complex.
On the 'net' side, Cong is fixing several races and memory
leaks. Whilst on the 'net-next' side we have Vlad adding
the rtnl-ness support.
What I've decided to do, in order to resolve this, is revert the
conversion over to using a workqueue that Cong did, bringing us back
to pure RCU. I did it this way because I believe that either Cong's
races don't apply with have Vlad did things, or Cong will have to
implement the race fix slightly differently.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
ipvs relies on nf_defrag_ipv6 module to manage IPv6 fragmentation,
but lacks proper Kconfig dependencies and does not explicitly
request defrag features.
As a result, if netfilter hooks are not loaded, when IPv6 fragmented
packet are handled by ipvs only the first fragment makes through.
Fix it properly declaring the dependency on Kconfig and registering
netfilter hooks on ip_vs_add_service() and ip_vs_new_dest().
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Andrea Claudi <aclaudi@redhat.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Use the new indirect call wrappers in IPVS when calling the TCP or UDP
protocol specific functions.
This avoids an indirect calls in IPVS, and reduces the performance
impact of the Spectre mitigation.
Signed-off-by: Matteo Croce <mcroce@redhat.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
(the parameters in question are mark and flow_flags)
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
We came across infinite loop in ipvs when using ipvs in docker
env.
When ipvs receives new packets and cannot find an ipvs connection,
it will create a new connection, then if the dest is unavailable
(i.e. IP_VS_DEST_F_AVAILABLE), the packet will be dropped sliently.
But if the dropped packet is the first packet of this connection,
the connection control timer never has a chance to start and the
ipvs connection cannot be released. This will lead to memory leak, or
infinite loop in cleanup_net() when net namespace is released like
this:
ip_vs_conn_net_cleanup at ffffffffa0a9f31a [ip_vs]
__ip_vs_cleanup at ffffffffa0a9f60a [ip_vs]
ops_exit_list at ffffffff81567a49
cleanup_net at ffffffff81568b40
process_one_work at ffffffff810a851b
worker_thread at ffffffff810a9356
kthread at ffffffff810b0b6f
ret_from_fork at ffffffff81697a18
race condition:
CPU1 CPU2
ip_vs_in()
ip_vs_conn_new()
ip_vs_del_dest()
__ip_vs_unlink_dest()
~IP_VS_DEST_F_AVAILABLE
cp->dest && !IP_VS_DEST_F_AVAILABLE
__ip_vs_conn_put
...
cleanup_net ---> infinite looping
Fix this by checking whether the timer already started.
Signed-off-by: Tan Hu <tan.hu@zte.com.cn>
Reviewed-by: Jiang Biao <jiang.biao2@zte.com.cn>
Acked-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Local clients are not properly synchronized on 32-bit CPUs when
updating stats (3.10+). Now it is possible estimation_timer (timer),
a stats reader, to interrupt the local client in the middle of
write_seqcount_{begin,end} sequence leading to loop (DEADLOCK).
The same interrupt can happen from received packet (SoftIRQ)
which updates the same per-CPU stats.
Fix it by disabling BH while updating stats.
Found with debug:
WARNING: inconsistent lock state
4.17.0-rc2-00105-g35cb6d7-dirty #2 Not tainted
--------------------------------
inconsistent {IN-SOFTIRQ-R} -> {SOFTIRQ-ON-W} usage.
ftp/2545 [HC0[0]:SC0[0]:HE1:SE1] takes:
86845479 (&syncp->seq#6){+.+-}, at: ip_vs_schedule+0x1c5/0x59e [ip_vs]
{IN-SOFTIRQ-R} state was registered at:
lock_acquire+0x44/0x5b
estimation_timer+0x1b3/0x341 [ip_vs]
call_timer_fn+0x54/0xcd
run_timer_softirq+0x10c/0x12b
__do_softirq+0xc1/0x1a9
do_softirq_own_stack+0x1d/0x23
irq_exit+0x4a/0x64
smp_apic_timer_interrupt+0x63/0x71
apic_timer_interrupt+0x3a/0x40
default_idle+0xa/0xc
arch_cpu_idle+0x9/0xb
default_idle_call+0x21/0x23
do_idle+0xa0/0x167
cpu_startup_entry+0x19/0x1b
start_secondary+0x133/0x182
startup_32_smp+0x164/0x168
irq event stamp: 42213
other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock(&syncp->seq#6);
<Interrupt>
lock(&syncp->seq#6);
*** DEADLOCK ***
Fixes: ac69269a45e8 ("ipvs: do not disable bh for long time")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
The param of frag_safe_skb_hp, ipvsh, isn't used now. So remove it and
update the callers' codes too.
Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Acked-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
We no longer place these on a list so they can be const.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
This patch removes duplicate rcu_read_lock().
1. IPVS part:
According to Julian Anastasov's mention, contexts of ipvs are described
at: http://marc.info/?l=netfilter-devel&m=149562884514072&w=2, in summary:
- packet RX/TX: does not need locks because packets come from hooks.
- sync msg RX: backup server uses RCU locks while registering new
connections.
- ip_vs_ctl.c: configuration get/set, RCU locks needed.
- xt_ipvs.c: It is a netfilter match, running from hook context.
As result, rcu_read_lock and rcu_read_unlock can be removed from:
- ip_vs_core.c: all
- ip_vs_ctl.c:
- only from ip_vs_has_real_service
- ip_vs_ftp.c: all
- ip_vs_proto_sctp.c: all
- ip_vs_proto_tcp.c: all
- ip_vs_proto_udp.c: all
- ip_vs_xmit.c: all (contains only packet processing)
2. Netfilter part:
There are three types of functions that are guaranteed the rcu_read_lock().
First, as result, functions are only called by nf_hook():
- nf_conntrack_broadcast_help(), pptp_expectfn(), set_expected_rtp_rtcp().
- tcpmss_reverse_mtu(), tproxy_laddr4(), tproxy_laddr6().
- match_lookup_rt6(), check_hlist(), hashlimit_mt_common().
- xt_osf_match_packet().
Second, functions that caller already held the rcu_read_lock().
- destroy_conntrack(), ctnetlink_conntrack_event().
- ctnl_timeout_find_get(), nfqnl_nf_hook_drop().
Third, functions that are mixed with type1 and type2.
These functions are called by nf_hook() also these are called by
ordinary functions that already held the rcu_read_lock():
- __ctnetlink_glue_build(), ctnetlink_expect_event().
- ctnetlink_proto_size().
Applied files are below:
- nf_conntrack_broadcast.c, nf_conntrack_core.c, nf_conntrack_netlink.c.
- nf_conntrack_pptp.c, nf_conntrack_sip.c, nfnetlink_cttimeout.c.
- nfnetlink_queue.c, xt_TCPMSS.c, xt_TPROXY.c, xt_addrtype.c.
- xt_connlimit.c, xt_hashlimit.c, xt_osf.c
Detailed calltrace can be found at:
http://marc.info/?l=netfilter-devel&m=149667610710350&w=2
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
This patch is to remove the typedef sctp_chunkhdr_t, and replace
with struct sctp_chunkhdr in the places where it's using this
typedef.
It is also to fix some indents and use sizeof(variable) instead
of sizeof(type)., especially in sctp_new.
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This patch is to remove the typedef sctp_sctphdr_t, and replace
with struct sctphdr in the places where it's using this typedef.
It is also to fix some indents and use sizeof(variable) instead
of sizeof(type).
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
We do not check if packet from real server is for NAT
connection before performing SNAT. This causes problems
for setups that use DR/TUN and allow local clients to
access the real server directly, for example:
- local client in director creates IPVS-DR/TUN connection
CIP->VIP and the request packets are routed to RIP.
Talks are finished but IPVS connection is not expired yet.
- second local client creates non-IPVS connection CIP->RIP
with same reply tuple RIP->CIP and when replies are received
on LOCAL_IN we wrongly assign them for the first client
connection because RIP->CIP matches the reply direction.
As result, IPVS SNATs replies for non-IPVS connections.
The problem is more visible to local UDP clients but in rare
cases it can happen also for TCP or remote clients when the
real server sends the reply traffic via the director.
So, better to be more precise for the reply traffic.
As replies are not expected for DR/TUN connections, better
to not touch them.
Reported-by: Nick Moriarty <nick.moriarty@york.ac.uk>
Tested-by: Nick Moriarty <nick.moriarty@york.ac.uk>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
nf_(un)register_hooks has to maintain an internal hook list to add/remove
those hooks from net namespaces as they are added/deleted.
ipvs already uses pernet_ops, so we can switch to the (more recent)
pernet hook api instead.
Compile tested only.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
refcount_t type and corresponding API (see include/linux/refcount.h)
should be used instead of atomic_t when the variable is used as
a reference counter. This allows to avoid accidental
refcounter overflows that might lead to use-after-free
situations.
Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Signed-off-by: Hans Liljestrand <ishkamiel@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David Windsor <dwindsor@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
At most it is used for debugging purpose, but I don't think
it is even useful for debugging, just remove it.
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
Make struct pernet_operations::id unsigned.
There are 2 reasons to do so:
1)
This field is really an index into an zero based array and
thus is unsigned entity. Using negative value is out-of-bound
access by definition.
2)
On x86_64 unsigned 32-bit data which are mixed with pointers
via array indexing or offsets added or subtracted to pointers
are preffered to signed 32-bit data.
"int" being used as an array index needs to be sign-extended
to 64-bit before being used.
void f(long *p, int i)
{
g(p[i]);
}
roughly translates to
movsx rsi, esi
mov rdi, [rsi+...]
call g
MOVSX is 3 byte instruction which isn't necessary if the variable is
unsigned because x86_64 is zero extending by default.
Now, there is net_generic() function which, you guessed it right, uses
"int" as an array index:
static inline void *net_generic(const struct net *net, int id)
{
...
ptr = ng->ptr[id - 1];
...
}
And this function is used a lot, so those sign extensions add up.
Patch snipes ~1730 bytes on allyesconfig kernel (without all junk
messing with code generation):
add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730)
Unfortunately some functions actually grow bigger.
This is a semmingly random artefact of code generation with register
allocator being used differently. gcc decides that some variable
needs to live in new r8+ registers and every access now requires REX
prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be
used which is longer than [r8]
However, overall balance is in negative direction:
add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730)
function old new delta
nfsd4_lock 3886 3959 +73
tipc_link_build_proto_msg 1096 1140 +44
mac80211_hwsim_new_radio 2776 2808 +32
tipc_mon_rcv 1032 1058 +26
svcauth_gss_legacy_init 1413 1429 +16
tipc_bcbase_select_primary 379 392 +13
nfsd4_exchange_id 1247 1260 +13
nfsd4_setclientid_confirm 782 793 +11
...
put_client_renew_locked 494 480 -14
ip_set_sockfn_get 730 716 -14
geneve_sock_add 829 813 -16
nfsd4_sequence_done 721 703 -18
nlmclnt_lookup_host 708 686 -22
nfsd4_lockt 1085 1063 -22
nfs_get_client 1077 1050 -27
tcf_bpf_init 1106 1076 -30
nfsd4_encode_fattr 5997 5930 -67
Total: Before=154856051, After=154854321, chg -0.00%
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Previous patch that introduced handling of outgoing packets in SIP
persistent-engine did not call ip_vs_check_template() in case packet was
matching a connection template. Assumption was that real-server was
healthy, since it was sending a packet just in that moment.
There are however real-server fault conditions requiring that association
between call-id and real-server (represented by connection template)
gets updated. Here is an example of the sequence of events:
1) RS1 is a back2back user agent that handled call-id1 and call-id2
2) RS1 is down and was marked as unavailable
3) new message from outside comes to IPVS with call-id1
4) IPVS reschedules the message to RS2, which becomes new call handler
5) RS2 forwards the message outside, translating call-id1 to call-id2
6) inside pe->conn_out() IPVS matches call-id2 with existing template
7) IPVS does not change association call-id2 <-> RS1
8) new message comes from client with call-id2
9) IPVS reschedules the message to a real-server potentially different
from RS2, which is now the correct destination
This patch introduces ip_vs_check_template() call in the handling of
outgoing packets for SIP-pe. And also introduces a second optional
argument for ip_vs_check_template() that allows to check if dest
associated to a connection template is the same dest that was identified
as the source of the packet. This is to change the real-server bound to a
particular call-id independently from its availability status: the idea
is that it's more reliable, for in->out direction (where internal
network can be considered trusted), to always associate a call-id with
the last real-server that used it in one of its messages. Think about
above sequence of events where, just after step 5, RS1 returns instead
to be available.
Comparison of dests is done by simply comparing pointers to struct
ip_vs_dest; there should be no cases where struct ip_vs_dest keeps its
memory address, but represent a different real-server in terms of
ip-address / port.
Fixes: 39b972231536 ("ipvs: handle connections started by real-servers")
Signed-off-by: Marco Angaroni <marcoangaroni@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
DoS protection policy that deletes connections to avoid out of memory is
currently not effective for SIP-pe plus OPS-mode for two reasons:
1) connection templates (holding SIP call-id) are always skipped in
ip_vs_random_dropentry()
2) in_pkts counter (used by drop_entry algorithm) is not incremented
for connection templates
This patch addresses such problems with the following changes:
a) connection templates associated (via their dest) to virtual-services
configured in OPS mode are included in ip_vs_random_dropentry()
monitoring. This applies to SIP-pe over UDP (which requires OPS mode),
but is more general principle: when OPS is controlled by templates
memory can be used only by templates themselves, since OPS conns are
deleted after packet is forwarded.
b) OPS connections, if controlled by a template, cause increment of
in_pkts counter of their template. This is already happening but only
in case director is in master-slave mode (see ip_vs_sync_conn()).
Signed-off-by: Marco Angaroni <marcoangaroni@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
When using LVS-NAT and SIP persistence-egine over UDP, the following
limitations are present with current implementation:
1) To actually have load-balancing based on Call-ID header, you need to
use one-packet-scheduling mode. But with one-packet-scheduling the
connection is deleted just after packet is forwarded, so SIP responses
coming from real-servers do not match any connection and SNAT is
not applied.
2) If you do not use "-o" option, IPVS behaves as normal UDP load
balancer, so different SIP calls (each one identified by a different
Call-ID) coming from the same ip-address/port go to the same
real-server. So basically you don’t have load-balancing based on
Call-ID as intended.
3) Call-ID is not learned when a new SIP call is started by a real-server
(inside-to-outside direction), but only in the outside-to-inside
direction. This would be a general problem for all SIP servers acting
as Back2BackUserAgent.
This patch aims to solve problems 1) and 3) while keeping OPS mode
mandatory for SIP-UDP, so that 2) is not a problem anymore.
The basic mechanism implemented is to make packets, that do not match any
existent connection but come from real-servers, create new connections
instead of let them pass without any effect.
When such packets pass through ip_vs_out(), if their source ip address and
source port match a configured real-server, a new connection is
automatically created in the same way as it would have happened if the
packet had come from outside-to-inside direction. A new connection template
is created too if the virtual-service is persistent and there is no
matching connection template found. The new connection automatically
created, if the service had "-o" option, is an OPS connection that lasts
only the time to forward the packet, just like it happens on the
ingress side.
The main part of this mechanism is implemented inside a persistent-engine
specific callback (at the moment only SIP persistent engine exists) and
is triggered only for UDP packets, since connection oriented protocols, by
using different set of ports (typically ephemeral ports) to open new
outgoing connections, should not need this feature.
The following requisites are needed for automatic connection creation; if
any is missing the packet simply goes the same way as before.
a) virtual-service is not fwmark based (this is because fwmark services
do not store address and port of the virtual-service, required to
build the connection data).
b) virtual-service and real-servers must not have been configured with
omitted port (this is again to have all data to create the connection).
Signed-off-by: Marco Angaroni <marcoangaroni@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
"RFC 5961, 4.2. Mitigation" describes a mechanism to request
client to confirm with RST the restart of TCP connection
before resending its SYN. As result, IPVS can see SYNs for
existing connection in CLOSE state. Add check to allow
rescheduling in this state.
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
Jiri Bohac is reporting for a problem where the attempt
to reschedule existing connection to another real server
needs proper redirect for the conntrack used by the IPVS
connection. For example, when IPVS connection is created
to NAT-ed real server we alter the reply direction of
conntrack. If we later decide to select different real
server we can not alter again the conntrack. And if we
expire the old connection, the new connection is left
without conntrack.
So, the only way to redirect both the IPVS connection and
the Netfilter's conntrack is to drop the SYN packet that
hits existing connection, to wait for the next jiffie
to expire the old connection and its conntrack and to rely
on client's retransmission to create new connection as
usually.
Jiri Bohac provided a fix that drops all SYNs on rescheduling,
I extended his patch to do such drops only for connections
that use conntrack. Here is the original report from Jiri Bohac:
Since commit dc7b3eb900aa ("ipvs: Fix reuse connection if real server
is dead"), new connections to dead servers are redistributed
immediately to new servers. The old connection is expired using
ip_vs_conn_expire_now() which sets the connection timer to expire
immediately.
However, before the timer callback, ip_vs_conn_expire(), is run
to clean the connection's conntrack entry, the new redistributed
connection may already be established and its conntrack removed
instead.
Fix this by dropping the first packet of the new connection
instead, like we do when the destination server is not available.
The timer will have deleted the old conntrack entry long before
the first packet of the new connection is retransmitted.
Fixes: dc7b3eb900aa ("ipvs: Fix reuse connection if real server is dead")
Signed-off-by: Jiri Bohac <jbohac@suse.cz>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
SYNACK packets might be attached to request sockets.
Use skb_to_full_sk() helper to avoid illegal accesses to
inet_sk(skb->sk)
Fixes: ca6fb0651883 ("tcp: attach SYNACK messages to request sockets instead of listener")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Sander Eikelenboom <linux@eikelenboom.it>
Acked-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
This merge resolves conflicts with 75aec9df3a78 ("bridge: Remove
br_nf_push_frag_xmit_sk") as part of Eric Biederman's effort to improve
netns support in the network stack that reached upstream via David's
net-next tree.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Conflicts:
net/bridge/br_netfilter_hooks.c
|
|
since commit 8405a8fff3f8 ("netfilter: nf_qeueue: Drop queue entries on
nf_unregister_hook") all pending queued entries are discarded.
So we can simply remove all of the owner handling -- when module is
removed it also needs to unregister all its hooks.
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
The function ip_defrag is called on both the input and the output
paths of the networking stack. In particular conntrack when it is
tracking outbound packets from the local machine calls ip_defrag.
So add a struct net parameter and stop making ip_defrag guess which
network namespace it needs to defragment packets in.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Eric's net namespace changes in 1b75097dd7a26 leaves net unreferenced if
CONFIG_IP_VS_IPV6 is not enabled:
../net/netfilter/ipvs/ip_vs_core.c: In function ‘ip_vs_out’:
../net/netfilter/ipvs/ip_vs_core.c:1177:14: warning: unused variable ‘net’ [-Wunused-variable]
After the net refactoring there is only 1 user; push the reference to the
1 user. While the line length slightly exceeds 80 it seems to be the
best change.
Fixes: 1b75097dd7a26("ipvs: Pass ipvs into ip_vs_out")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
[horms: updated subject]
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
I arranged the code so that the compiler can remove the unecessary bits
in ip_vs_leave when CONFIG_SYSCTL is unset, and removed an explicit
CONFIG_SYSCTL.
Unfortunately when rebasing my work on top of that of Alex Gartrell I
missed the fact that the newly added function ip_vs_addr_is_unicast was
surrounded by CONFIG_SYSCTL.
So remove the now unnecessary CONFIG_SYSCTL guards around
ip_vs_addr_is_unicast. It is causing build failures today when
CONFIG_SYSCTL is not selected and any self respecting compiler will
notice that sysctl_cache_bypass is always false without CONFIG_SYSCTL
and not include the logic from the function ip_vs_addr_is_unicast in
the compiled code.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
Don't make ip6_route_me_harder guess which network namespace
it is routing in, pass the network namespace in.
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
Don't make ip_route_me_harder guess which network namespace
it is routing in, pass the network namespace in.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
|
|
This will be needed later when the network namespace guessing is
removed from ip_defrag.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
This removes the need to use the hack skb_net.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
This removes the need to compute ipvs with the hack "net_ipvs(skb_net(skb))"
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|
|
With ipvs passed into ip_vs_in_icmp and ip_vs_in_icmp_v6
they no longer need to call the hack that is skb_net.
Additionally ipvs_in_icmp no longer needs to call dev_net(skb->dev)
and can use the ipvs->net instead.
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
|