Commit graph

79 commits

Author SHA1 Message Date
Martin KaFai Lau
267cf9fa43 tcp: bpf: Optionally store mac header in TCP_SAVE_SYN
This patch is adapted from Eric's patch in an earlier discussion [1].

The TCP_SAVE_SYN currently only stores the network header and
tcp header.  This patch allows it to optionally store
the mac header also if the setsockopt's optval is 2.

It requires one more bit for the "save_syn" bit field in tcp_sock.
This patch achieves this by moving the syn_smc bit next to the is_mptcp.
The syn_smc is currently used with the TCP experimental option.  Since
syn_smc is only used when CONFIG_SMC is enabled, this patch also puts
the "IS_ENABLED(CONFIG_SMC)" around it like the is_mptcp did
with "IS_ENABLED(CONFIG_MPTCP)".

The mac_hdrlen is also stored in the "struct saved_syn"
to allow a quick offset from the bpf prog if it chooses to start
getting from the network header or the tcp header.

[1]: https://lore.kernel.org/netdev/CANn89iLJNWh6bkH7DNhy_kmcAexuUCccqERqe7z2QsvPhGrYPQ@mail.gmail.com/

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/bpf/20200820190123.2886935-1-kafai@fb.com
2020-08-24 14:35:00 -07:00
Martin KaFai Lau
70a217f197 tcp: Use a struct to represent a saved_syn
The TCP_SAVE_SYN has both the network header and tcp header.
The total length of the saved syn packet is currently stored in
the first 4 bytes (u32) of an array and the actual packet data is
stored after that.

A later patch will add a bpf helper that allows to get the tcp header
alone from the saved syn without the network header.  It will be more
convenient to have a direct offset to a specific header instead of
re-parsing it.  This requires to separately store the network hdrlen.
The total header length (i.e. network + tcp) is still needed for the
current usage in getsockopt.  Although this total length can be obtained
by looking into the tcphdr and then get the (th->doff << 2), this patch
chooses to directly store the tcp hdrlen in the second four bytes of
this newly created "struct saved_syn".  By using a new struct, it can
give a readable name to each individual header length.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20200820190014.2883694-1-kafai@fb.com
2020-08-24 14:34:59 -07:00
Florian Westphal
f8ace8d915 tcp: rename request_sock cookie_ts bit to syncookie
Nowadays output function has a 'synack_type' argument that tells us when
the syn/ack is emitted via syncookies.

The request already tells us when timestamps are supported, so check
both to detect special timestamp for tcp option encoding is needed.

We could remove cookie_ts altogether, but a followup patch would
otherwise need to adjust function signatures to pass 'want_cookie' to
mptcp core.

This way, the 'existing' bit can be used.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2020-07-31 16:55:32 -07:00
Eric Dumazet
60b173ca3d net: add {READ|WRITE}_ONCE() annotations on ->rskq_accept_head
reqsk_queue_empty() is called from inet_csk_listen_poll() while
other cpus might write ->rskq_accept_head value.

Use {READ|WRITE}_ONCE() to avoid compiler tricks
and potential KCSAN splats.

Fixes: fff1f3001c ("tcp: add a spinlock to protect struct request_sock_queue")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
2019-10-09 21:34:31 -07:00
Eric Dumazet
85f9aa7565 inet: clear num_timeout reqsk_alloc()
KMSAN caught uninit-value in tcp_create_openreq_child() [1]
This is caused by a recent change, combined by the fact
that TCP cleared num_timeout, num_retrans and sk fields only
when a request socket was about to be queued.

Under syncookie mode, a temporary request socket is used,
and req->num_timeout could contain garbage.

Lets clear these three fields sooner, there is really no
point trying to defer this and risk other bugs.

[1]

BUG: KMSAN: uninit-value in tcp_create_openreq_child+0x157f/0x1cc0 net/ipv4/tcp_minisocks.c:526
CPU: 1 PID: 13357 Comm: syz-executor591 Not tainted 5.2.0-rc4+ #3
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x191/0x1f0 lib/dump_stack.c:113
 kmsan_report+0x162/0x2d0 mm/kmsan/kmsan.c:611
 __msan_warning+0x75/0xe0 mm/kmsan/kmsan_instr.c:304
 tcp_create_openreq_child+0x157f/0x1cc0 net/ipv4/tcp_minisocks.c:526
 tcp_v6_syn_recv_sock+0x761/0x2d80 net/ipv6/tcp_ipv6.c:1152
 tcp_get_cookie_sock+0x16e/0x6b0 net/ipv4/syncookies.c:209
 cookie_v6_check+0x27e0/0x29a0 net/ipv6/syncookies.c:252
 tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:1039 [inline]
 tcp_v6_do_rcv+0xf1c/0x1ce0 net/ipv6/tcp_ipv6.c:1344
 tcp_v6_rcv+0x60b7/0x6a30 net/ipv6/tcp_ipv6.c:1554
 ip6_protocol_deliver_rcu+0x1433/0x22f0 net/ipv6/ip6_input.c:397
 ip6_input_finish net/ipv6/ip6_input.c:438 [inline]
 NF_HOOK include/linux/netfilter.h:305 [inline]
 ip6_input+0x2af/0x340 net/ipv6/ip6_input.c:447
 dst_input include/net/dst.h:439 [inline]
 ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline]
 NF_HOOK include/linux/netfilter.h:305 [inline]
 ipv6_rcv+0x683/0x710 net/ipv6/ip6_input.c:272
 __netif_receive_skb_one_core net/core/dev.c:4981 [inline]
 __netif_receive_skb net/core/dev.c:5095 [inline]
 process_backlog+0x721/0x1410 net/core/dev.c:5906
 napi_poll net/core/dev.c:6329 [inline]
 net_rx_action+0x738/0x1940 net/core/dev.c:6395
 __do_softirq+0x4ad/0x858 kernel/softirq.c:293
 do_softirq_own_stack+0x49/0x80 arch/x86/entry/entry_64.S:1052
 </IRQ>
 do_softirq kernel/softirq.c:338 [inline]
 __local_bh_enable_ip+0x199/0x1e0 kernel/softirq.c:190
 local_bh_enable+0x36/0x40 include/linux/bottom_half.h:32
 rcu_read_unlock_bh include/linux/rcupdate.h:682 [inline]
 ip6_finish_output2+0x213f/0x2670 net/ipv6/ip6_output.c:117
 ip6_finish_output+0xae4/0xbc0 net/ipv6/ip6_output.c:150
 NF_HOOK_COND include/linux/netfilter.h:294 [inline]
 ip6_output+0x5d3/0x720 net/ipv6/ip6_output.c:167
 dst_output include/net/dst.h:433 [inline]
 NF_HOOK include/linux/netfilter.h:305 [inline]
 ip6_xmit+0x1f53/0x2650 net/ipv6/ip6_output.c:271
 inet6_csk_xmit+0x3df/0x4f0 net/ipv6/inet6_connection_sock.c:135
 __tcp_transmit_skb+0x4076/0x5b40 net/ipv4/tcp_output.c:1156
 tcp_transmit_skb net/ipv4/tcp_output.c:1172 [inline]
 tcp_write_xmit+0x39a9/0xa730 net/ipv4/tcp_output.c:2397
 __tcp_push_pending_frames+0x124/0x4e0 net/ipv4/tcp_output.c:2573
 tcp_send_fin+0xd43/0x1540 net/ipv4/tcp_output.c:3118
 tcp_close+0x16ba/0x1860 net/ipv4/tcp.c:2403
 inet_release+0x1f7/0x270 net/ipv4/af_inet.c:427
 inet6_release+0xaf/0x100 net/ipv6/af_inet6.c:470
 __sock_release net/socket.c:601 [inline]
 sock_close+0x156/0x490 net/socket.c:1273
 __fput+0x4c9/0xba0 fs/file_table.c:280
 ____fput+0x37/0x40 fs/file_table.c:313
 task_work_run+0x22e/0x2a0 kernel/task_work.c:113
 tracehook_notify_resume include/linux/tracehook.h:185 [inline]
 exit_to_usermode_loop arch/x86/entry/common.c:168 [inline]
 prepare_exit_to_usermode+0x39d/0x4d0 arch/x86/entry/common.c:199
 syscall_return_slowpath+0x90/0x5c0 arch/x86/entry/common.c:279
 do_syscall_64+0xe2/0xf0 arch/x86/entry/common.c:305
 entry_SYSCALL_64_after_hwframe+0x63/0xe7
RIP: 0033:0x401d50
Code: 01 f0 ff ff 0f 83 40 0d 00 00 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 83 3d dd 8d 2d 00 00 75 14 b8 03 00 00 00 0f 05 <48> 3d 01 f0 ff ff 0f 83 14 0d 00 00 c3 48 83 ec 08 e8 7a 02 00 00
RSP: 002b:00007fff1cf58cf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000003
RAX: 0000000000000000 RBX: 0000000000000004 RCX: 0000000000401d50
RDX: 000000000000001c RSI: 0000000000000000 RDI: 0000000000000003
RBP: 00000000004a9050 R08: 0000000020000040 R09: 000000000000001c
R10: 0000000020004004 R11: 0000000000000246 R12: 0000000000402ef0
R13: 0000000000402f80 R14: 0000000000000000 R15: 0000000000000000

Uninit was created at:
 kmsan_save_stack_with_flags mm/kmsan/kmsan.c:201 [inline]
 kmsan_internal_poison_shadow+0x53/0xa0 mm/kmsan/kmsan.c:160
 kmsan_kmalloc+0xa4/0x130 mm/kmsan/kmsan_hooks.c:177
 kmem_cache_alloc+0x534/0xb00 mm/slub.c:2781
 reqsk_alloc include/net/request_sock.h:84 [inline]
 inet_reqsk_alloc+0xa8/0x600 net/ipv4/tcp_input.c:6384
 cookie_v6_check+0xadb/0x29a0 net/ipv6/syncookies.c:173
 tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:1039 [inline]
 tcp_v6_do_rcv+0xf1c/0x1ce0 net/ipv6/tcp_ipv6.c:1344
 tcp_v6_rcv+0x60b7/0x6a30 net/ipv6/tcp_ipv6.c:1554
 ip6_protocol_deliver_rcu+0x1433/0x22f0 net/ipv6/ip6_input.c:397
 ip6_input_finish net/ipv6/ip6_input.c:438 [inline]
 NF_HOOK include/linux/netfilter.h:305 [inline]
 ip6_input+0x2af/0x340 net/ipv6/ip6_input.c:447
 dst_input include/net/dst.h:439 [inline]
 ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline]
 NF_HOOK include/linux/netfilter.h:305 [inline]
 ipv6_rcv+0x683/0x710 net/ipv6/ip6_input.c:272
 __netif_receive_skb_one_core net/core/dev.c:4981 [inline]
 __netif_receive_skb net/core/dev.c:5095 [inline]
 process_backlog+0x721/0x1410 net/core/dev.c:5906
 napi_poll net/core/dev.c:6329 [inline]
 net_rx_action+0x738/0x1940 net/core/dev.c:6395
 __do_softirq+0x4ad/0x858 kernel/softirq.c:293
 do_softirq_own_stack+0x49/0x80 arch/x86/entry/entry_64.S:1052
 do_softirq kernel/softirq.c:338 [inline]
 __local_bh_enable_ip+0x199/0x1e0 kernel/softirq.c:190
 local_bh_enable+0x36/0x40 include/linux/bottom_half.h:32
 rcu_read_unlock_bh include/linux/rcupdate.h:682 [inline]
 ip6_finish_output2+0x213f/0x2670 net/ipv6/ip6_output.c:117
 ip6_finish_output+0xae4/0xbc0 net/ipv6/ip6_output.c:150
 NF_HOOK_COND include/linux/netfilter.h:294 [inline]
 ip6_output+0x5d3/0x720 net/ipv6/ip6_output.c:167
 dst_output include/net/dst.h:433 [inline]
 NF_HOOK include/linux/netfilter.h:305 [inline]
 ip6_xmit+0x1f53/0x2650 net/ipv6/ip6_output.c:271
 inet6_csk_xmit+0x3df/0x4f0 net/ipv6/inet6_connection_sock.c:135
 __tcp_transmit_skb+0x4076/0x5b40 net/ipv4/tcp_output.c:1156
 tcp_transmit_skb net/ipv4/tcp_output.c:1172 [inline]
 tcp_write_xmit+0x39a9/0xa730 net/ipv4/tcp_output.c:2397
 __tcp_push_pending_frames+0x124/0x4e0 net/ipv4/tcp_output.c:2573
 tcp_send_fin+0xd43/0x1540 net/ipv4/tcp_output.c:3118
 tcp_close+0x16ba/0x1860 net/ipv4/tcp.c:2403
 inet_release+0x1f7/0x270 net/ipv4/af_inet.c:427
 inet6_release+0xaf/0x100 net/ipv6/af_inet6.c:470
 __sock_release net/socket.c:601 [inline]
 sock_close+0x156/0x490 net/socket.c:1273
 __fput+0x4c9/0xba0 fs/file_table.c:280
 ____fput+0x37/0x40 fs/file_table.c:313
 task_work_run+0x22e/0x2a0 kernel/task_work.c:113
 tracehook_notify_resume include/linux/tracehook.h:185 [inline]
 exit_to_usermode_loop arch/x86/entry/common.c:168 [inline]
 prepare_exit_to_usermode+0x39d/0x4d0 arch/x86/entry/common.c:199
 syscall_return_slowpath+0x90/0x5c0 arch/x86/entry/common.c:279
 do_syscall_64+0xe2/0xf0 arch/x86/entry/common.c:305
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

Fixes: 336c39a031 ("tcp: undo init congestion window on false SYNACK timeout")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Soheil Hassas Yeganeh <soheil@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-06-19 17:46:57 -04:00
Thomas Gleixner
2874c5fd28 treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 152
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>
2019-05-30 11:26:32 -07:00
Guillaume Nault
9403cf2302 tcp: free request sock directly upon TFO or syncookies error
Since the request socket is created locally, it'd make more sense to
use reqsk_free() instead of reqsk_put() in TFO and syncookies' error
path.

However, tcp_get_cookie_sock() may set ->rsk_refcnt before freeing the
socket; tcp_conn_request() may also have non-null ->rsk_refcnt because
of tcp_try_fastopen(). In both cases 'req' hasn't been exposed
to the outside world and is safe to free immediately, but that'd
trigger the WARN_ON_ONCE in reqsk_free().

Define __reqsk_free() for these situations where we know nobody's
referencing the socket, even though ->rsk_refcnt might be non-null.
Now we can consolidate the error path of tcp_get_cookie_sock() and
tcp_conn_request().

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-19 14:13:01 -07:00
Guillaume Nault
1039c6e193 net: keep refcount warning in reqsk_free()
As Eric Dumazet said, "We do not have a way to tell if the req was ever
inserted in a hash table, so better play safe.".
Let's remove this comment, so that nobody will be tempted to drop the
WARN_ON_ONCE() line.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-03-09 19:51:44 -08:00
Yuchung Cheng
1fba70e5b6 tcp: socket option to set TCP fast open key
New socket option TCP_FASTOPEN_KEY to allow different keys per
listener.  The listener by default uses the global key until the
socket option is set.  The key is a 16 bytes long binary data. This
option has no effect on regular non-listener TCP sockets.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Christoph Paasch <cpaasch@apple.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-10-20 13:21:36 +01:00
Reshetova, Elena
41c6d650f6 net: convert sock.sk_refcnt from atomic_t to refcount_t
refcount_t type and corresponding API 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.

This patch uses refcount_inc_not_zero() instead of
atomic_inc_not_zero_hint() due to absense of a _hint()
version of refcount API. If the hint() version must
be used, we might need to revisit API.

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: David S. Miller <davem@davemloft.net>
2017-07-01 07:39:08 -07:00
Alexey Dobriyan
417ccf6b5b net: make struct request_sock_ops::obj_size unsigned
This field is sizeof of corresponding kmem_cache so it can't be negative.

Space will be saved after 32-bit kmem_cache_create() patch.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-23 11:13:19 -04:00
Haishuang Yan
fee83d097b ipv4: Namespaceify tcp_max_syn_backlog knob
Different namespace application might require different maximal
number of remembered connection requests.

Signed-off-by: Haishuang Yan <yanhaishuang@cmss.chinamobile.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-12-29 11:38:31 -05:00
Eric Dumazet
3a5d1c0e7c inet: reqsk_alloc() needs to take care of dead listeners
We'll soon no longer take a refcount on listeners,
so reqsk_alloc() can not assume a listener refcount is not
zero. We need to use atomic_inc_not_zero()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-04-04 22:11:19 -04:00
Florian Westphal
b1f0a0e99c net: add inet_sk_transparent() helper
Avoids cluttering tcp_v4_send_reset when followup patch extends
it to deal with timewait sockets.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-22 17:03:05 -05:00
Eric Dumazet
ebb516af60 tcp/dccp: fix race at listener dismantle phase
Under stress, a close() on a listener can trigger the
WARN_ON(sk->sk_ack_backlog) in inet_csk_listen_stop()

We need to test if listener is still active before queueing
a child in inet_csk_reqsk_queue_add()

Create a common inet_child_forget() helper, and use it
from inet_csk_reqsk_queue_add() and inet_csk_listen_stop()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-16 00:52:19 -07:00
Eric Dumazet
ed53d0ab76 net: shrink struct sock and request_sock by 8 bytes
One 32bit hole is following skc_refcnt, use it.
skc_incoming_cpu can also be an union for request_sock rcv_wnd.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-12 19:28:22 -07:00
Eric Dumazet
8e5eb54d30 net: align sk_refcnt on 128 bytes boundary
sk->sk_refcnt is dirtied for every TCP/UDP incoming packet.
This is a performance issue if multiple cpus hit a common socket,
or multiple sockets are chained due to SO_REUSEPORT.

By moving sk_refcnt 8 bytes further, first 128 bytes of sockets
are mostly read. As they contain the lookup keys, this has
a considerable performance impact, as cpus can cache them.

These 8 bytes are not wasted, we use them as a place holder
for various fields, depending on the socket type.

Tested:
 SYN flood hitting a 16 RX queues NIC.
 TCP listener using 16 sockets and SO_REUSEPORT
 and SO_INCOMING_CPU for proper siloing.

 Could process 6.0 Mpps SYN instead of 4.2 Mpps

 Kernel profile looked like :
    11.68%  [kernel]  [k] sha_transform
     6.51%  [kernel]  [k] __inet_lookup_listener
     5.07%  [kernel]  [k] __inet_lookup_established
     4.15%  [kernel]  [k] memcpy_erms
     3.46%  [kernel]  [k] ipt_do_table
     2.74%  [kernel]  [k] fib_table_lookup
     2.54%  [kernel]  [k] tcp_make_synack
     2.34%  [kernel]  [k] tcp_conn_request
     2.05%  [kernel]  [k] __netif_receive_skb_core
     2.03%  [kernel]  [k] kmem_cache_alloc

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-12 19:28:22 -07:00
Eric Dumazet
a1a5344ddb tcp: avoid two atomic ops for syncookies
inet_reqsk_alloc() is used to allocate a temporary request
in order to generate a SYNACK with a cookie. Then later,
syncookie validation also uses a temporary request.

These paths already took a reference on listener refcount,
we can avoid a couple of atomic operations.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-05 02:45:27 -07:00
Eric Dumazet
004a5d0140 net: use sk_fullsock() in __netdev_pick_tx()
SYN_RECV & TIMEWAIT sockets are not full blown, they do not have a
sk_dst_cache pointer.

Fixes: ca6fb06518 ("tcp: attach SYNACK messages to request sockets instead of listener")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-05 02:45:25 -07:00
Eric Dumazet
e96f78ab27 tcp/dccp: add SLAB_DESTROY_BY_RCU flag for request sockets
Before letting request sockets being put in TCP/DCCP regular
ehash table, we need to add either :

- SLAB_DESTROY_BY_RCU flag to their kmem_cache
- add RCU grace period before freeing them.

Since we carefully respected the SLAB_DESTROY_BY_RCU protocol
like ESTABLISH and TIMEWAIT sockets, use it here.

req_prot_init() being only used by TCP and DCCP, I did not add
a new slab_flags into their rsk_prot, but reuse prot->slab_flags

Since all reqsk_alloc() users are correctly dealing with a failure,
add the __GFP_NOWARN flag to avoid traces under pressure.

Fixes: 079096f103 ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-03 13:25:20 -07:00
Eric Dumazet
ef547f2ac1 tcp: remove max_qlen_log
This control variable was set at first listen(fd, backlog)
call, but not updated if application tried to increase or decrease
backlog. It made sense at the time listener had a non resizeable
hash table.

Also rounding to powers of two was not very friendly.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-03 04:32:44 -07:00
Eric Dumazet
10cbc8f179 tcp/dccp: remove struct listen_sock
It is enough to check listener sk_state, no need for an extra
condition.

max_qlen_log can be moved into struct request_sock_queue

We can remove syn_wait_lock and the alignment it enforced.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-03 04:32:43 -07:00
Eric Dumazet
81b496b31a tcp/dccp: shrink struct listen_sock
We no longer use hash_rnd, nr_table_entries and syn_table[]

For a listener with a backlog of 10 millions sockets, this
saves 80 MBytes of vmalloced memory.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-03 04:32:42 -07:00
Eric Dumazet
079096f103 tcp/dccp: install syn_recv requests into ehash table
In this patch, we insert request sockets into TCP/DCCP
regular ehash table (where ESTABLISHED and TIMEWAIT sockets
are) instead of using the per listener hash table.

ACK packets find SYN_RECV pseudo sockets without having
to find and lock the listener.

In nominal conditions, this halves pressure on listener lock.

Note that this will allow for SO_REUSEPORT refinements,
so that we can select a listener using cpu/numa affinities instead
of the prior 'consistent hash', since only SYN packets will
apply this selection logic.

We will shrink listen_sock in the following patch to ease
code review.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ying Cai <ycai@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-03 04:32:41 -07:00
Eric Dumazet
b267cdd107 tcp/dccp: init sk_prot and call sk_node_init() in reqsk_alloc()
We plan to use generic functions to insert request sockets
into ehash table.

sk_prot needs to be set (to retrieve sk_prot->h.hashinfo)
sk_node needs to be cleared.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-03 04:32:38 -07:00
Eric Dumazet
8d2675f1e4 tcp: move synflood_warned into struct request_sock_queue
long term plan is to remove struct listen_sock when its hash
table is no longer there.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-03 04:32:37 -07:00
Eric Dumazet
aac065c50a tcp: move qlen/young out of struct listen_sock
qlen_inc & young_inc were protected by listener lock,
while qlen_dec & young_dec were atomic fields.

Everything needs to be atomic for upcoming lockless listener.

Also move qlen/young in request_sock_queue as we'll get rid
of struct listen_sock eventually.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-03 04:32:36 -07:00
Eric Dumazet
fff1f3001c tcp: add a spinlock to protect struct request_sock_queue
struct request_sock_queue fields are currently protected
by the listener 'lock' (not a real spinlock)

We need to add a private spinlock instead, so that softirq handlers
creating children do not have to worry with backlog notion
that the listener 'lock' carries.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-10-03 04:32:36 -07:00
Eric Dumazet
0536fcc039 tcp: prepare fastopen code for upcoming listener changes
While auditing TCP stack for upcoming 'lockless' listener changes,
I found I had to change fastopen_init_queue() to properly init the object
before publishing it.

Otherwise an other cpu could try to lock the spinlock before it gets
properly initialized.

Instead of adding appropriate barriers, just remove dynamic memory
allocations :
- Structure is 28 bytes on 64bit arches. Using additional 8 bytes
  for holding a pointer seems overkill.
- Two listeners can share same cache line and performance would suffer.

If we really want to save few bytes, we would instead dynamically allocate
whole struct request_sock_queue in the future.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-29 16:53:10 -07:00
Eric Dumazet
2985aaac01 tcp: constify tcp_syn_flood_action() socket argument
tcp_syn_flood_action() will soon be called with unlocked socket.
In order to avoid SYN flood warning being emitted multiple times,
use xchg().
Extend max_qlen_log and synflood_warned fields in struct listen_sock
to u32

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-29 16:53:10 -07:00
Eric Dumazet
a00e74442b tcp/dccp: constify send_synack and send_reset socket argument
None of these functions need to change the socket, make it
const.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-29 16:53:07 -07:00
Eric Dumazet
1b70e977ce inet: constify inet_rtx_syn_ack() sock argument
SYNACK packets are sent on behalf on unlocked listeners
or fastopen sockets. Mark socket as const to catch future changes
that might break the assumption.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 13:00:39 -07:00
Eric Dumazet
ea3bea3a1d tcp/dccp: constify rtx_synack() and friends
This is done to make sure we do not change listener socket
while sending SYNACK packets while socket lock is not held.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-09-25 13:00:39 -07:00
Eric Dumazet
cd8ae85299 tcp: provide SYN headers for passive connections
This patch allows a server application to get the TCP SYN headers for
its passive connections.  This is useful if the server is doing
fingerprinting of clients based on SYN packet contents.

Two socket options are added: TCP_SAVE_SYN and TCP_SAVED_SYN.

The first is used on a socket to enable saving the SYN headers
for child connections. This can be set before or after the listen()
call.

The latter is used to retrieve the SYN headers for passive connections,
if the parent listener has enabled TCP_SAVE_SYN.

TCP_SAVED_SYN is read once, it frees the saved SYN headers.

The data returned in TCP_SAVED_SYN are network (IPv4/IPv6) and TCP
headers.

Original patch was written by Tom Herbert, I changed it to not hold
a full skb (and associated dst and conntracking reference).

We have used such patch for about 3 years at Google.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Tested-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-05 16:02:34 -04:00
Eric Dumazet
b357a364c5 inet: fix possible panic in reqsk_queue_unlink()
[ 3897.923145] BUG: unable to handle kernel NULL pointer dereference at
 0000000000000080
[ 3897.931025] IP: [<ffffffffa9f27686>] reqsk_timer_handler+0x1a6/0x243

There is a race when reqsk_timer_handler() and tcp_check_req() call
inet_csk_reqsk_queue_unlink() on the same req at the same time.

Before commit fa76ce7328 ("inet: get rid of central tcp/dccp listener
timer"), listener spinlock was held and race could not happen.

To solve this bug, we change reqsk_queue_unlink() to not assume req
must be found, and we return a status, to conditionally release a
refcount on the request sock.

This also means tcp_check_req() in non fastopen case might or not
consume req refcount, so tcp_v6_hnd_req() & tcp_v4_hnd_req() have
to properly handle this.

(Same remark for dccp_check_req() and its callers)

inet_csk_reqsk_queue_drop() is now too big to be inlined, as it is
called 4 times in tcp and 3 times in dccp.

Fixes: fa76ce7328 ("inet: get rid of central tcp/dccp listener timer")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-24 11:39:15 -04:00
Eric Dumazet
b282705336 net: convert syn_wait_lock to a spinlock
This is a low hanging fruit, as we'll get rid of syn_wait_lock eventually.

We hold syn_wait_lock for such small sections, that it makes no sense to use
a read/write lock. A spin lock is simply faster.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-23 16:52:26 -04:00
Eric Dumazet
42cb80a235 inet: remove sk_listener parameter from syn_ack_timeout()
It is not needed, and req->sk_listener points to the listener anyway.
request_sock argument can be const.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-23 16:52:25 -04:00
Eric Dumazet
fa76ce7328 inet: get rid of central tcp/dccp listener timer
One of the major issue for TCP is the SYNACK rtx handling,
done by inet_csk_reqsk_queue_prune(), fired by the keepalive
timer of a TCP_LISTEN socket.

This function runs for awful long times, with socket lock held,
meaning that other cpus needing this lock have to spin for hundred of ms.

SYNACK are sent in huge bursts, likely to cause severe drops anyway.

This model was OK 15 years ago when memory was very tight.

We now can afford to have a timer per request sock.

Timer invocations no longer need to lock the listener,
and can be run from all cpus in parallel.

With following patch increasing somaxconn width to 32 bits,
I tested a listener with more than 4 million active request sockets,
and a steady SYNFLOOD of ~200,000 SYN per second.
Host was sending ~830,000 SYNACK per second.

This is ~100 times more what we could achieve before this patch.

Later, we will get rid of the listener hash and use ehash instead.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-20 12:40:25 -04:00
Eric Dumazet
52452c5425 inet: drop prev pointer handling in request sock
When request sock are put in ehash table, the whole notion
of having a previous request to update dl_next is pointless.

Also, following patch will get rid of big purge timer,
so we want to delete a request sock without holding listener lock.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-20 12:40:25 -04:00
Eric Dumazet
08d2cc3b26 inet: request sock should init IPv6/IPv4 addresses
In order to be able to use sk_ehashfn() for request socks,
we need to initialize their IPv6/IPv4 addresses.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-18 22:00:35 -04:00
Eric Dumazet
0470c8ca1d inet: fix request sock refcounting
While testing last patch series, I found req sock refcounting was wrong.

We must set skc_refcnt to 1 for all request socks added in hashes,
but also on request sockets created by FastOpen or syncookies.

It is tricky because we need to defer this initialization so that
future RCU lookups do not try to take a refcount on a not yet
fully initialized request socket.

Also get rid of ireq_refcnt alias.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Fixes: 13854e5a60 ("inet: add proper refcounting to request sock")
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-17 22:02:29 -04:00
Eric Dumazet
4e9a578e5b inet: add rsk_listener field to struct request_sock
Once we'll be able to lookup request sockets in ehash table,
we'll need to get access to listener which created this request.

This avoid doing a lookup to find the listener, which benefits
for a more solid SO_REUSEPORT, and is needed once we no
longer queue request sock into a listener private queue.

Note that 'struct tcp_request_sock'->listener could be reduced
to a single bit, as TFO listener should match req->rsk_listener.
TFO will no longer need to hold a reference on the listener.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-17 22:01:56 -04:00
Eric Dumazet
13854e5a60 inet: add proper refcounting to request sock
reqsk_put() is the generic function that should be used
to release a refcount (and automatically call reqsk_free())

reqsk_free() might be called if refcount is known to be 0
or undefined.

refcnt is set to one in inet_csk_reqsk_queue_add()

As request socks are not yet in global ehash table,
I added temporary debugging checks in reqsk_put() and reqsk_free()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-16 15:55:29 -04:00
Eric Dumazet
41b822c59e inet: prepare sock_edemux() & sock_gen_put() for new SYN_RECV state
sock_edemux() & sock_gen_put() should be ready to cope with request socks.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-12 22:58:13 -04:00
Eric Dumazet
1e2e01172f inet: add rsk_refcnt/ireq_refcnt to request socks
When request socks will be in ehash, they'll need to be refcounted.

This patch adds rsk_refcnt/ireq_refcnt macros, and adds
reqsk_put() function, but nothing yet use them.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-03-12 22:58:13 -04:00
Eric Dumazet
634fb979e8 inet: includes a sock_common in request_sock
TCP listener refactoring, part 5 :

We want to be able to insert request sockets (SYN_RECV) into main
ehash table instead of the per listener hash table to allow RCU
lookups and remove listener lock contention.

This patch includes the needed struct sock_common in front
of struct request_sock

This means there is no more inet6_request_sock IPv6 specific
structure.

Following inet_request_sock fields were renamed as they became
macros to reference fields from struct sock_common.
Prefix ir_ was chosen to avoid name collisions.

loc_port   -> ir_loc_port
loc_addr   -> ir_loc_addr
rmt_addr   -> ir_rmt_addr
rmt_port   -> ir_rmt_port
iif        -> ir_iif

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-10 00:08:07 -04:00
Joe Perches
c0f4502a87 request_sock.h: Remove extern from function prototypes
There are a mix of function prototypes with and without extern
in the kernel sources.  Standardize on not using extern for
function prototypes.

Function prototypes don't need to be written with extern.
extern is assumed by the compiler.  Its use is as unnecessary as
using auto to declare automatic/local variables in a block.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-09-23 01:51:08 -04:00
Eric Dumazet
3fb62c5d3f net: remove a stale comment for dl_next
dl_next member in struct request_sock doesn't need to be first.

We expect to insert a "struct common_sock" or a subset of it,
so this claim had to be verified.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-04-22 15:55:48 -04:00
Christoph Paasch
1a2c6181c4 tcp: Remove TCPCT
TCPCT uses option-number 253, reserved for experimental use and should
not be used in production environments.
Further, TCPCT does not fully implement RFC 6013.

As a nice side-effect, removing TCPCT increases TCP's performance for
very short flows:

Doing an apache-benchmark with -c 100 -n 100000, sending HTTP-requests
for files of 1KB size.

before this patch:
	average (among 7 runs) of 20845.5 Requests/Second
after:
	average (among 7 runs) of 21403.6 Requests/Second

Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
2013-03-17 14:35:13 -04:00
Eric Dumazet
e6c022a4fa tcp: better retrans tracking for defer-accept
For passive TCP connections using TCP_DEFER_ACCEPT facility,
we incorrectly increment req->retrans each time timeout triggers
while no SYNACK is sent.

SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for
which we received the ACK from client). Only the last SYNACK is sent
so that we can receive again an ACK from client, to move the req into
accept queue. We plan to change this later to avoid the useless
retransmit (and potential problem as this SYNACK could be lost)

TCP_INFO later gives wrong information to user, claiming imaginary
retransmits.

Decouple req->retrans field into two independent fields :

num_retrans : number of retransmit
num_timeout : number of timeouts

num_timeout is the counter that is incremented at each timeout,
regardless of actual SYNACK being sent or not, and used to
compute the exponential timeout.

Introduce inet_rtx_syn_ack() helper to increment num_retrans
only if ->rtx_syn_ack() succeeded.

Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans
when we re-send a SYNACK in answer to a (retransmitted) SYN.
Prior to this patch, we were not counting these retransmits.

Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS
only if a synack packet was successfully queued.

Reported-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Elliott Hughes <enh@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-03 14:45:00 -04:00