Age | Commit message (Collapse) | Author |
|
[ Upstream commit 06f877d613be3621604c2520ec0351d9fbdca15f ]
In my first attempt to fix the lockdep splat, I forgot we could
enter inet_csk_route_req() with a freshly allocated request socket,
for which refcount has not yet been elevated, due to complex
SLAB_TYPESAFE_BY_RCU rules.
We either are in rcu_read_lock() section _or_ we own a refcount on the
request.
Correct RCU verb to use here is rcu_dereference_check(), although it is
not possible to prove we actually own a reference on a shared
refcount :/
In v2, I added ireq_opt_deref() helper and use in three places, to fix other
possible splats.
[ 49.844590] lockdep_rcu_suspicious+0xea/0xf3
[ 49.846487] inet_csk_route_req+0x53/0x14d
[ 49.848334] tcp_v4_route_req+0xe/0x10
[ 49.850174] tcp_conn_request+0x31c/0x6a0
[ 49.851992] ? __lock_acquire+0x614/0x822
[ 49.854015] tcp_v4_conn_request+0x5a/0x79
[ 49.855957] ? tcp_v4_conn_request+0x5a/0x79
[ 49.858052] tcp_rcv_state_process+0x98/0xdcc
[ 49.859990] ? sk_filter_trim_cap+0x2f6/0x307
[ 49.862085] tcp_v4_do_rcv+0xfc/0x145
[ 49.864055] ? tcp_v4_do_rcv+0xfc/0x145
[ 49.866173] tcp_v4_rcv+0x5ab/0xaf9
[ 49.868029] ip_local_deliver_finish+0x1af/0x2e7
[ 49.870064] ip_local_deliver+0x1b2/0x1c5
[ 49.871775] ? inet_del_offload+0x45/0x45
[ 49.873916] ip_rcv_finish+0x3f7/0x471
[ 49.875476] ip_rcv+0x3f1/0x42f
[ 49.876991] ? ip_local_deliver_finish+0x2e7/0x2e7
[ 49.878791] __netif_receive_skb_core+0x6d3/0x950
[ 49.880701] ? process_backlog+0x7e/0x216
[ 49.882589] __netif_receive_skb+0x1d/0x5e
[ 49.884122] process_backlog+0x10c/0x216
[ 49.885812] net_rx_action+0x147/0x3df
Fixes: a6ca7abe53633 ("tcp/dccp: fix lockdep splat in inet_csk_route_req()")
Fixes: c92e8c02fe66 ("tcp/dccp: fix ireq->opt races")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: kernel test robot <fengguang.wu@intel.com>
Reported-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit a6ca7abe53633d08eea1c6756cb49c9b2d4c90bf ]
This patch fixes the following lockdep splat in inet_csk_route_req()
lockdep_rcu_suspicious
inet_csk_route_req
tcp_v4_send_synack
tcp_rtx_synack
inet_rtx_syn_ack
tcp_fastopen_synack_time
tcp_retransmit_timer
tcp_write_timer_handler
tcp_write_timer
call_timer_fn
Thread running inet_csk_route_req() owns a reference on the request
socket, so we have the guarantee ireq->ireq_opt wont be changed or
freed.
lockdep can enforce this invariant for us.
Fixes: c92e8c02fe66 ("tcp/dccp: fix ireq->opt races")
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 c92e8c02fe664155ac4234516e32544bec0f113d ]
syzkaller found another bug in DCCP/TCP stacks [1]
For the reasons explained in commit ce1050089c96 ("tcp/dccp: fix
ireq->pktopts race"), we need to make sure we do not access
ireq->opt unless we own the request sock.
Note the opt field is renamed to ireq_opt to ease grep games.
[1]
BUG: KASAN: use-after-free in ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
Read of size 1 at addr ffff8801c951039c by task syz-executor5/3295
CPU: 1 PID: 3295 Comm: syz-executor5 Not tainted 4.14.0-rc4+ #80
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
__dump_stack lib/dump_stack.c:16 [inline]
dump_stack+0x194/0x257 lib/dump_stack.c:52
print_address_description+0x73/0x250 mm/kasan/report.c:252
kasan_report_error mm/kasan/report.c:351 [inline]
kasan_report+0x25b/0x340 mm/kasan/report.c:409
__asan_report_load1_noabort+0x14/0x20 mm/kasan/report.c:427
ip_queue_xmit+0x1687/0x18e0 net/ipv4/ip_output.c:474
tcp_transmit_skb+0x1ab7/0x3840 net/ipv4/tcp_output.c:1135
tcp_send_ack.part.37+0x3bb/0x650 net/ipv4/tcp_output.c:3587
tcp_send_ack+0x49/0x60 net/ipv4/tcp_output.c:3557
__tcp_ack_snd_check+0x2c6/0x4b0 net/ipv4/tcp_input.c:5072
tcp_ack_snd_check net/ipv4/tcp_input.c:5085 [inline]
tcp_rcv_state_process+0x2eff/0x4850 net/ipv4/tcp_input.c:6071
tcp_child_process+0x342/0x990 net/ipv4/tcp_minisocks.c:816
tcp_v4_rcv+0x1827/0x2f80 net/ipv4/tcp_ipv4.c:1682
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
RIP: 0033:0x40c341
RSP: 002b:00007f469523ec10 EFLAGS: 00000293 ORIG_RAX: 0000000000000001
RAX: ffffffffffffffda RBX: 0000000000718000 RCX: 000000000040c341
RDX: 0000000000000037 RSI: 0000000020004000 RDI: 0000000000000015
RBP: 0000000000000086 R08: 0000000000000000 R09: 0000000000000000
R10: 00000000000f4240 R11: 0000000000000293 R12: 00000000004b7fd1
R13: 00000000ffffffff R14: 0000000020000000 R15: 0000000000025000
Allocated by task 3295:
save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
kasan_kmalloc+0xad/0xe0 mm/kasan/kasan.c:551
__do_kmalloc mm/slab.c:3725 [inline]
__kmalloc+0x162/0x760 mm/slab.c:3734
kmalloc include/linux/slab.h:498 [inline]
tcp_v4_save_options include/net/tcp.h:1962 [inline]
tcp_v4_init_req+0x2d3/0x3e0 net/ipv4/tcp_ipv4.c:1271
tcp_conn_request+0xf6d/0x3410 net/ipv4/tcp_input.c:6283
tcp_v4_conn_request+0x157/0x210 net/ipv4/tcp_ipv4.c:1313
tcp_rcv_state_process+0x8ea/0x4850 net/ipv4/tcp_input.c:5857
tcp_v4_do_rcv+0x55c/0x7d0 net/ipv4/tcp_ipv4.c:1482
tcp_v4_rcv+0x2d10/0x2f80 net/ipv4/tcp_ipv4.c:1711
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
Freed by task 3306:
save_stack_trace+0x16/0x20 arch/x86/kernel/stacktrace.c:59
save_stack+0x43/0xd0 mm/kasan/kasan.c:447
set_track mm/kasan/kasan.c:459 [inline]
kasan_slab_free+0x71/0xc0 mm/kasan/kasan.c:524
__cache_free mm/slab.c:3503 [inline]
kfree+0xca/0x250 mm/slab.c:3820
inet_sock_destruct+0x59d/0x950 net/ipv4/af_inet.c:157
__sk_destruct+0xfd/0x910 net/core/sock.c:1560
sk_destruct+0x47/0x80 net/core/sock.c:1595
__sk_free+0x57/0x230 net/core/sock.c:1603
sk_free+0x2a/0x40 net/core/sock.c:1614
sock_put include/net/sock.h:1652 [inline]
inet_csk_complete_hashdance+0xd5/0xf0 net/ipv4/inet_connection_sock.c:959
tcp_check_req+0xf4d/0x1620 net/ipv4/tcp_minisocks.c:765
tcp_v4_rcv+0x17f6/0x2f80 net/ipv4/tcp_ipv4.c:1675
ip_local_deliver_finish+0x2e2/0xba0 net/ipv4/ip_input.c:216
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_local_deliver+0x1ce/0x6e0 net/ipv4/ip_input.c:257
dst_input include/net/dst.h:464 [inline]
ip_rcv_finish+0x887/0x19a0 net/ipv4/ip_input.c:397
NF_HOOK include/linux/netfilter.h:249 [inline]
ip_rcv+0xc3f/0x1820 net/ipv4/ip_input.c:493
__netif_receive_skb_core+0x1a3e/0x34b0 net/core/dev.c:4476
__netif_receive_skb+0x2c/0x1b0 net/core/dev.c:4514
netif_receive_skb_internal+0x10b/0x670 net/core/dev.c:4587
netif_receive_skb+0xae/0x390 net/core/dev.c:4611
tun_rx_batched.isra.50+0x5ed/0x860 drivers/net/tun.c:1372
tun_get_user+0x249c/0x36d0 drivers/net/tun.c:1766
tun_chr_write_iter+0xbf/0x160 drivers/net/tun.c:1792
call_write_iter include/linux/fs.h:1770 [inline]
new_sync_write fs/read_write.c:468 [inline]
__vfs_write+0x68a/0x970 fs/read_write.c:481
vfs_write+0x18f/0x510 fs/read_write.c:543
SYSC_write fs/read_write.c:588 [inline]
SyS_write+0xef/0x220 fs/read_write.c:580
entry_SYSCALL_64_fastpath+0x1f/0xbe
Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Fixes: 079096f103fa ("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>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
[ Upstream commit 657831ffc38e30092a2d5f03d385d710eb88b09a ]
syzkaller found a way to trigger double frees from ip_mc_drop_socket()
It turns out that leave a copy of parent mc_list at accept() time,
which is very bad.
Very similar to commit 8b485ce69876 ("tcp: do not inherit
fastopen_req from parent")
Initial report from Pray3r, completed by Andrey one.
Thanks a lot to them !
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Pray3r <pray3r.z@gmail.com>
Reported-by: Andrey Konovalov <andreyknvl@google.com>
Tested-by: Andrey Konovalov <andreyknvl@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
|
|
Pinned timers must carry the pinned attribute in the timer structure
itself, so convert the code to the new API.
No functional change.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Chris Mason <clm@fb.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: George Spelvin <linux@sciencehorizons.net>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Len Brown <lenb@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: rt@linutronix.de
Link: http://lkml.kernel.org/r/20160704094341.617891430@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
percpu_counter only have protection against preemption.
TCP stack uses them possibly from BH, so we need BH protection
in contexts that could be run in process context
Fixes: c10d9310edf5 ("tcp: do not assume TCP code is non preemptible")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Rename IP_INC_STATS_BH() to __IP_INC_STATS(), to
better express this is used in non preemptible context.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
David Ahern reported panics in __inet_hash() caused by my recent commit.
The reason is inet_reuseport_add_sock() was still using
sk_nulls_for_each_rcu() instead of sk_for_each_rcu().
SO_REUSEPORT enabled listeners were causing an instant crash.
While chasing this bug, I found that I forgot to clear SOCK_RCU_FREE
flag, as it is inherited from the parent at clone time.
Fixes: 3b24d854cb35 ("tcp/dccp: do not touch listener sk_refcnt under synflood")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: David Ahern <dsa@cumulusnetworks.com>
Tested-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
One of the validation checks for the new array-based TCP SO_REUSEPORT
validation was unintentionally dropped in ea8add2b1903. This adds it back.
Lack of this check allows the user to allocate multiple sock_reuseport
structures (leaking all but the first).
Fixes: ea8add2b1903 ("tcp/dccp: better use of ephemeral ports in bind()")
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Conflicts:
drivers/net/phy/bcm7xxx.c
drivers/net/phy/marvell.c
drivers/net/vxlan.c
All three conflicts were cases of simple overlapping changes.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Ilya reported following lockdep splat:
kernel: =========================
kernel: [ BUG: held lock freed! ]
kernel: 4.5.0-rc1-ceph-00026-g5e0a311 #1 Not tainted
kernel: -------------------------
kernel: swapper/5/0 is freeing memory
ffff880035c9d200-ffff880035c9dbff, with a lock still held there!
kernel: (&(&queue->rskq_lock)->rlock){+.-...}, at:
[<ffffffff816f6a88>] inet_csk_reqsk_queue_add+0x28/0xa0
kernel: 4 locks held by swapper/5/0:
kernel: #0: (rcu_read_lock){......}, at: [<ffffffff8169ef6b>]
netif_receive_skb_internal+0x4b/0x1f0
kernel: #1: (rcu_read_lock){......}, at: [<ffffffff816e977f>]
ip_local_deliver_finish+0x3f/0x380
kernel: #2: (slock-AF_INET){+.-...}, at: [<ffffffff81685ffb>]
sk_clone_lock+0x19b/0x440
kernel: #3: (&(&queue->rskq_lock)->rlock){+.-...}, at:
[<ffffffff816f6a88>] inet_csk_reqsk_queue_add+0x28/0xa0
To properly fix this issue, inet_csk_reqsk_queue_add() needs
to return to its callers if the child as been queued
into accept queue.
We also need to make sure listener is still there before
calling sk->sk_data_ready(), by holding a reference on it,
since the reference carried by the child can disappear as
soon as the child is put on accept queue.
Reported-by: Ilya Dryomov <idryomov@gmail.com>
Fixes: ebb516af60e1 ("tcp/dccp: fix race at listener dismantle phase")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Implement strategy used in __inet_hash_connect() in opposite way :
Try to find a candidate using odd ports, then fallback to even ports.
We no longer disable BH for whole traversal, but one bucket at a time.
We also use cond_resched() to yield cpu to other tasks if needed.
I removed one indentation level and tried to mirror the loop we have
in __inet_hash_connect() and variable names to ease code maintenance.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
This change extends the fast SO_REUSEPORT socket lookup implemented
for UDP to TCP. Listener sockets with SO_REUSEPORT and the same
receive address are additionally added to an array for faster
random access. This means that only a single socket from the group
must be found in the listener list before any socket in the group can
be used to receive a packet. Previously, every socket in the group
needed to be considered before handing off the incoming packet.
This feature also exposes the ability to use a BPF program when
selecting a socket from a reuseport group.
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
In order to support fast reuseport lookups in TCP, the hash function
defined in struct proto must be capable of returning an error code.
This patch changes the function signature of all related hash functions
to return an integer and handles or propagates this return value at
all call sites.
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Signed-off-by: Nikolay Borisov <kernel@kyup.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Some functions access TCP sockets without holding a lock and
might output non consistent data, depending on compiler and or
architecture.
tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ...
Introduce sk_state_load() and sk_state_store() to fix the issues,
and more clearly document where this lack of locking is happening.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Multiple cpus can process duplicates of incoming ACK messages
matching a SYN_RECV request socket. This is a rare event under
normal operations, but definitely can happen.
Only one must win the race, otherwise corruption would occur.
To fix this without adding new atomic ops, we use logic in
inet_ehash_nolisten() to detect the request was present in the same
ehash bucket where we try to insert the new child.
If request socket was not found, we have to undo the child creation.
This actually removes a spin_lock()/spin_unlock() pair in
reqsk_queue_unlink() for the fast path.
Fixes: e994b2f0fb92 ("tcp: do not lock listener to process SYN packets")
Fixes: 079096f103fa ("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>
|
|
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>
|
|
Let's reduce the confusion about inet_csk_reqsk_queue_drop() :
In many cases we also need to release reference on request socket,
so add a helper to do this, reducing code size and complexity.
Fixes: 4bdc3d66147b ("tcp/dccp: fix behavior of stale SYN_RECV request sockets")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
At listen() time, there is a small window where listener is visible with
a zero backlog, triggering a spurious "Possible SYN flooding on port"
message.
Nothing prevents us from setting the correct backlog.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Some applications use a listen() backlog of 1.
Prior kernels were silently enforcing a qlen_log of 4, so that we were
sending up to /proc/sys/net/ipv4/tcp_synack_retries SYNACK messages.
Fixes: ef547f2ac16b ("tcp: remove max_qlen_log")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
If a listener with thousands of children in accept queue
is dismantled, it can take a while to close all of them.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
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>
|
|
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>
|
|
If a listen backlog is very big (to avoid syncookies), then
the listener sk->sk_wmem_alloc is the main source of false
sharing, as we need to touch it twice per SYNACK re-transmit
and TX completion.
(One SYN packet takes listener lock once, but up to 6 SYNACK
are generated)
By attaching the skb to the request socket, we remove this
source of contention.
Tested:
listen(fd, 10485760); // single listener (no SO_REUSEPORT)
16 RX/TX queue NIC
Sustain a SYNFLOOD attack of ~320,000 SYN per second,
Sending ~1,400,000 SYNACK per second.
Perf profiles now show listener spinlock being next bottleneck.
20.29% [kernel] [k] queued_spin_lock_slowpath
10.06% [kernel] [k] __inet_lookup_established
5.12% [kernel] [k] reqsk_timer_handler
3.22% [kernel] [k] get_next_timer_interrupt
3.00% [kernel] [k] tcp_make_synack
2.77% [kernel] [k] ipt_do_table
2.70% [kernel] [k] run_timer_softirq
2.50% [kernel] [k] ip_finish_output
2.04% [kernel] [k] cascade
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
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>
|
|
This is no longer used.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
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>
|
|
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>
|
|
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>
|
|
The socket points to the (shared) listener.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Conflicts:
net/ipv4/arp.c
The net/ipv4/arp.c conflict was one commit adding a new
local variable while another commit was deleting one.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
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>
|
|
This is used by TCP listener core, and listener socket shall
not be modified by inet_csk_route_req().
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Before allowing lockless LISTEN processing, we need to make
sure to arm the SYN_RECV timer before the req socket is visible
in hash tables.
Also, req->rsk_hash should be written before we set rsk_refcnt
to a non zero value.
Fixes: fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ying Cai <ycai@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
When replacing del_timer() with del_timer_sync(), I introduced
a deadlock condition :
reqsk_queue_unlink() is called from inet_csk_reqsk_queue_drop()
inet_csk_reqsk_queue_drop() can be called from many contexts,
one being the timer handler itself (reqsk_timer_handler()).
In this case, del_timer_sync() loops forever.
Simple fix is to test if timer is pending.
Fixes: 2235f2ac75fd ("inet: fix races with reqsk timers")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
reqsk_queue_destroy() and reqsk_queue_unlink() should use
del_timer_sync() instead of del_timer() before calling reqsk_put(),
otherwise we could free a req still used by another cpu.
But before doing so, reqsk_queue_destroy() must release syn_wait_lock
spinlock or risk a dead lock, as reqsk_timer_handler() might
need to take this same spinlock from reqsk_queue_unlink() (called from
inet_csk_reqsk_queue_drop())
Fixes: fa76ce7328b2 ("inet: get rid of central tcp/dccp listener timer")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
inet_csk_get_port() randomization effort tends to spread
sockets on all the available range (ip_local_port_range)
This is unfortunate because SO_REUSEADDR sockets have
less requirements than non SO_REUSEADDR ones.
If an application uses SO_REUSEADDR hint, it is to try to
allow source ports being shared.
So instead of picking a random port number in ip_local_port_range,
lets try first in first half of the range.
This gives more chances to use upper half of the range for the
sockets with strong requirements (not using SO_REUSEADDR)
Note this patch does not add a new sysctl, and only changes
the way we try to pick port number.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Marcelo Ricardo Leitner <mleitner@redhat.com>
Cc: Flavio Leitner <fbl@redhat.com>
Acked-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
We no longer need bsocket atomic counter, as inet_csk_get_port()
calls bind_conflict() regardless of its value, after commit
2b05ad33e1e624e ("tcp: bind() fix autoselection to share ports")
This patch removes overhead of maintaining this counter and
double inet_csk_get_port() calls under pressure.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Marcelo Ricardo Leitner <mleitner@redhat.com>
Cc: Flavio Leitner <fbl@redhat.com>
Acked-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
[ 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 fa76ce7328b2 ("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: fa76ce7328b2 ("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>
|
|
The ipv4 code uses a mixture of coding styles. In some instances check
for non-NULL pointer is done as x != NULL and sometimes as x. x is
preferred according to checkpatch and this patch makes the code
consistent by adopting the latter form.
No changes detected by objdiff.
Signed-off-by: Ian Morris <ipm@chirality.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
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>
|
|
listener can be source of false sharing. request sock has some
useful information like : ireq->ir_iif, ireq->ir_num, ireq->ireq_net
This patch does not solve the major problem of having to read
sk->sk_protocol which is sharing a cache line with sk->sk_wmem_alloc.
(This same field is read later in ip_build_and_send_pkt())
One idea would be to move sk_protocol close to sk_family
(using 8 bits instead of 16 for sk_family seems enough)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
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>
|
|
Cache listen_sock_qlen() to limit false sharing, and read
rskq_defer_accept once as it might change under us.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Conflicts:
drivers/net/ethernet/emulex/benet/be_main.c
net/core/sysctl_net_core.c
net/ipv4/inet_diag.c
The be_main.c conflict resolution was really tricky. The conflict
hunks generated by GIT were very unhelpful, to say the least. It
split functions in half and moved them around, when the real actual
conflict only existed solely inside of one function, that being
be_map_pci_bars().
So instead, to resolve this, I checked out be_main.c from the top
of net-next, then I applied the be_main.c changes from 'net' since
the last time I merged. And this worked beautifully.
The inet_diag.c and sysctl_net_core.c conflicts were simple
overlapping changes, and were easily to resolve.
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
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>
|
|
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>
|
|
It is not because a TCP listener is FastOpen ready that
all incoming sockets actually used FastOpen.
Avoid taking queue->fastopenq->lock if not needed.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
The listener field in struct tcp_request_sock is a pointer
back to the listener. We now have req->rsk_listener, so TCP
only needs one boolean and not a full pointer.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|