linux/include/net/inet_timewait_sock.h

126 lines
3.6 KiB
C
Raw Permalink Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* Definitions for a generic INET TIMEWAIT sock
*
* From code originally in net/tcp.h
*/
#ifndef _INET_TIMEWAIT_SOCK_
#define _INET_TIMEWAIT_SOCK_
#include <linux/list.h>
#include <linux/timer.h>
#include <linux/types.h>
#include <linux/workqueue.h>
#include <net/inet_sock.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <net/timewait_sock.h>
#include <linux/atomic.h>
struct inet_bind_bucket;
/*
* This is a TIME_WAIT sock. It works around the memory consumption
* problems of sockets in such a state on heavily loaded servers, but
* without violating the protocol specification.
*/
struct inet_timewait_sock {
/*
* Now struct sock also uses sock_common, so please just
* don't add nothing before this first member (__tw_common) --acme
*/
struct sock_common __tw_common;
#define tw_family __tw_common.skc_family
#define tw_state __tw_common.skc_state
#define tw_reuse __tw_common.skc_reuse
soreuseport: initialise timewait reuseport field syzbot reported an uninit-value in inet_csk_bind_conflict() [1] It turns out we never propagated sk->sk_reuseport into timewait socket. [1] BUG: KMSAN: uninit-value in inet_csk_bind_conflict+0x5f9/0x990 net/ipv4/inet_connection_sock.c:151 CPU: 1 PID: 3589 Comm: syzkaller008242 Not tainted 4.16.0+ #82 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:17 [inline] dump_stack+0x185/0x1d0 lib/dump_stack.c:53 kmsan_report+0x142/0x240 mm/kmsan/kmsan.c:1067 __msan_warning_32+0x6c/0xb0 mm/kmsan/kmsan_instr.c:676 inet_csk_bind_conflict+0x5f9/0x990 net/ipv4/inet_connection_sock.c:151 inet_csk_get_port+0x1d28/0x1e40 net/ipv4/inet_connection_sock.c:320 inet6_bind+0x121c/0x1820 net/ipv6/af_inet6.c:399 SYSC_bind+0x3f2/0x4b0 net/socket.c:1474 SyS_bind+0x54/0x80 net/socket.c:1460 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x4416e9 RSP: 002b:00007ffce6d15c88 EFLAGS: 00000217 ORIG_RAX: 0000000000000031 RAX: ffffffffffffffda RBX: 0100000000000000 RCX: 00000000004416e9 RDX: 000000000000001c RSI: 0000000020402000 RDI: 0000000000000004 RBP: 0000000000000000 R08: 00000000e6d15e08 R09: 00000000e6d15e08 R10: 0000000000000004 R11: 0000000000000217 R12: 0000000000009478 R13: 00000000006cd448 R14: 0000000000000000 R15: 0000000000000000 Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_save_stack mm/kmsan/kmsan.c:293 [inline] kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:684 __msan_chain_origin+0x69/0xc0 mm/kmsan/kmsan_instr.c:521 tcp_time_wait+0xf17/0xf50 net/ipv4/tcp_minisocks.c:283 tcp_rcv_state_process+0xebe/0x6490 net/ipv4/tcp_input.c:6003 tcp_v6_do_rcv+0x11dd/0x1d90 net/ipv6/tcp_ipv6.c:1331 sk_backlog_rcv include/net/sock.h:908 [inline] __release_sock+0x2d6/0x680 net/core/sock.c:2271 release_sock+0x97/0x2a0 net/core/sock.c:2786 tcp_close+0x277/0x18f0 net/ipv4/tcp.c:2269 inet_release+0x240/0x2a0 net/ipv4/af_inet.c:427 inet6_release+0xaf/0x100 net/ipv6/af_inet6.c:435 sock_release net/socket.c:595 [inline] sock_close+0xe0/0x300 net/socket.c:1149 __fput+0x49e/0xa10 fs/file_table.c:209 ____fput+0x37/0x40 fs/file_table.c:243 task_work_run+0x243/0x2c0 kernel/task_work.c:113 exit_task_work include/linux/task_work.h:22 [inline] do_exit+0x10e1/0x38d0 kernel/exit.c:867 do_group_exit+0x1a0/0x360 kernel/exit.c:970 SYSC_exit_group+0x21/0x30 kernel/exit.c:981 SyS_exit_group+0x25/0x30 kernel/exit.c:979 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Uninit was stored to memory at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_save_stack mm/kmsan/kmsan.c:293 [inline] kmsan_internal_chain_origin+0x12b/0x210 mm/kmsan/kmsan.c:684 __msan_chain_origin+0x69/0xc0 mm/kmsan/kmsan_instr.c:521 inet_twsk_alloc+0xaef/0xc00 net/ipv4/inet_timewait_sock.c:182 tcp_time_wait+0xd9/0xf50 net/ipv4/tcp_minisocks.c:258 tcp_rcv_state_process+0xebe/0x6490 net/ipv4/tcp_input.c:6003 tcp_v6_do_rcv+0x11dd/0x1d90 net/ipv6/tcp_ipv6.c:1331 sk_backlog_rcv include/net/sock.h:908 [inline] __release_sock+0x2d6/0x680 net/core/sock.c:2271 release_sock+0x97/0x2a0 net/core/sock.c:2786 tcp_close+0x277/0x18f0 net/ipv4/tcp.c:2269 inet_release+0x240/0x2a0 net/ipv4/af_inet.c:427 inet6_release+0xaf/0x100 net/ipv6/af_inet6.c:435 sock_release net/socket.c:595 [inline] sock_close+0xe0/0x300 net/socket.c:1149 __fput+0x49e/0xa10 fs/file_table.c:209 ____fput+0x37/0x40 fs/file_table.c:243 task_work_run+0x243/0x2c0 kernel/task_work.c:113 exit_task_work include/linux/task_work.h:22 [inline] do_exit+0x10e1/0x38d0 kernel/exit.c:867 do_group_exit+0x1a0/0x360 kernel/exit.c:970 SYSC_exit_group+0x21/0x30 kernel/exit.c:981 SyS_exit_group+0x25/0x30 kernel/exit.c:979 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Uninit was created at: kmsan_save_stack_with_flags mm/kmsan/kmsan.c:278 [inline] kmsan_internal_poison_shadow+0xb8/0x1b0 mm/kmsan/kmsan.c:188 kmsan_kmalloc+0x94/0x100 mm/kmsan/kmsan.c:314 kmem_cache_alloc+0xaab/0xb90 mm/slub.c:2756 inet_twsk_alloc+0x13b/0xc00 net/ipv4/inet_timewait_sock.c:163 tcp_time_wait+0xd9/0xf50 net/ipv4/tcp_minisocks.c:258 tcp_rcv_state_process+0xebe/0x6490 net/ipv4/tcp_input.c:6003 tcp_v6_do_rcv+0x11dd/0x1d90 net/ipv6/tcp_ipv6.c:1331 sk_backlog_rcv include/net/sock.h:908 [inline] __release_sock+0x2d6/0x680 net/core/sock.c:2271 release_sock+0x97/0x2a0 net/core/sock.c:2786 tcp_close+0x277/0x18f0 net/ipv4/tcp.c:2269 inet_release+0x240/0x2a0 net/ipv4/af_inet.c:427 inet6_release+0xaf/0x100 net/ipv6/af_inet6.c:435 sock_release net/socket.c:595 [inline] sock_close+0xe0/0x300 net/socket.c:1149 __fput+0x49e/0xa10 fs/file_table.c:209 ____fput+0x37/0x40 fs/file_table.c:243 task_work_run+0x243/0x2c0 kernel/task_work.c:113 exit_task_work include/linux/task_work.h:22 [inline] do_exit+0x10e1/0x38d0 kernel/exit.c:867 do_group_exit+0x1a0/0x360 kernel/exit.c:970 SYSC_exit_group+0x21/0x30 kernel/exit.c:981 SyS_exit_group+0x25/0x30 kernel/exit.c:979 do_syscall_64+0x309/0x430 arch/x86/entry/common.c:287 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 Fixes: da5e36308d9f ("soreuseport: TCP/IPv4 implementation") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-04-07 20:42:43 +00:00
#define tw_reuseport __tw_common.skc_reuseport
#define tw_ipv6only __tw_common.skc_ipv6only
#define tw_bound_dev_if __tw_common.skc_bound_dev_if
#define tw_node __tw_common.skc_nulls_node
#define tw_bind_node __tw_common.skc_bind_node
#define tw_refcnt __tw_common.skc_refcnt
[INET]: speedup inet (tcp/dccp) lookups Arnaldo and I agreed it could be applied now, because I have other pending patches depending on this one (Thank you Arnaldo) (The other important patch moves skc_refcnt in a separate cache line, so that the SMP/NUMA performance doesnt suffer from cache line ping pongs) 1) First some performance data : -------------------------------- tcp_v4_rcv() wastes a *lot* of time in __inet_lookup_established() The most time critical code is : sk_for_each(sk, node, &head->chain) { if (INET_MATCH(sk, acookie, saddr, daddr, ports, dif)) goto hit; /* You sunk my battleship! */ } The sk_for_each() does use prefetch() hints but only the begining of "struct sock" is prefetched. As INET_MATCH first comparison uses inet_sk(__sk)->daddr, wich is far away from the begining of "struct sock", it has to bring into CPU cache cold cache line. Each iteration has to use at least 2 cache lines. This can be problematic if some chains are very long. 2) The goal ----------- The idea I had is to change things so that INET_MATCH() may return FALSE in 99% of cases only using the data already in the CPU cache, using one cache line per iteration. 3) Description of the patch --------------------------- Adds a new 'unsigned int skc_hash' field in 'struct sock_common', filling a 32 bits hole on 64 bits platform. struct sock_common { unsigned short skc_family; volatile unsigned char skc_state; unsigned char skc_reuse; int skc_bound_dev_if; struct hlist_node skc_node; struct hlist_node skc_bind_node; atomic_t skc_refcnt; + unsigned int skc_hash; struct proto *skc_prot; }; Store in this 32 bits field the full hash, not masked by (ehash_size - 1) Using this full hash as the first comparison done in INET_MATCH permits us immediatly skip the element without touching a second cache line in case of a miss. Suppress the sk_hashent/tw_hashent fields since skc_hash (aliased to sk_hash and tw_hash) already contains the slot number if we mask with (ehash_size - 1) File include/net/inet_hashtables.h 64 bits platforms : #define INET_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ (((__sk)->sk_hash == (__hash)) ((*((__u64 *)&(inet_sk(__sk)->daddr)))== (__cookie)) && \ ((*((__u32 *)&(inet_sk(__sk)->dport))) == (__ports)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) 32bits platforms: #define TCP_IPV4_MATCH(__sk, __hash, __cookie, __saddr, __daddr, __ports, __dif)\ (((__sk)->sk_hash == (__hash)) && \ (inet_sk(__sk)->daddr == (__saddr)) && \ (inet_sk(__sk)->rcv_saddr == (__daddr)) && \ (!((__sk)->sk_bound_dev_if) || ((__sk)->sk_bound_dev_if == (__dif)))) - Adds a prefetch(head->chain.first) in __inet_lookup_established()/__tcp_v4_check_established() and __inet6_lookup_established()/__tcp_v6_check_established() and __dccp_v4_check_established() to bring into cache the first element of the list, before the {read|write}_lock(&head->lock); Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Acked-by: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-03 21:13:38 +00:00
#define tw_hash __tw_common.skc_hash
#define tw_prot __tw_common.skc_prot
#define tw_net __tw_common.skc_net
#define tw_daddr __tw_common.skc_daddr
#define tw_v6_daddr __tw_common.skc_v6_daddr
#define tw_rcv_saddr __tw_common.skc_rcv_saddr
#define tw_v6_rcv_saddr __tw_common.skc_v6_rcv_saddr
net: move inet_dport/inet_num in sock_common commit 68835aba4d9b (net: optimize INET input path further) moved some fields used for tcp/udp sockets lookup in the first cache line of struct sock_common. This patch moves inet_dport/inet_num as well, filling a 32bit hole on 64 bit arches and reducing number of cache line misses in lookups. Also change INET_MATCH()/INET_TW_MATCH() to perform the ports match before addresses match, as this check is more discriminant. Remove the hash check from MATCH() macros because we dont need to re validate the hash value after taking a refcount on socket, and use likely/unlikely compiler hints, as the sk_hash/hash check makes the following conditional tests 100% predicted by cpu. Introduce skc_addrpair/skc_portpair pair values to better document the alignment requirements of the port/addr pairs used in the various MATCH() macros, and remove some casts. The namespace check can also be done at last. This slightly improves TCP/UDP lookup times. IP/TCP early demux needs inet->rx_dst_ifindex and TCP needs inet->min_ttl, lets group them together in same cache line. With help from Ben Hutchings & Joe Perches. Idea of this patch came after Ling Ma proposal to move skc_hash to the beginning of struct sock_common, and should allow him to submit a final version of his patch. My tests show an improvement doing so. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Joe Perches <joe@perches.com> Cc: Ling Ma <ling.ma.program@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-30 09:49:27 +00:00
#define tw_dport __tw_common.skc_dport
#define tw_num __tw_common.skc_num
#define tw_cookie __tw_common.skc_cookie
#define tw_dr __tw_common.skc_tw_dr
net: move inet_dport/inet_num in sock_common commit 68835aba4d9b (net: optimize INET input path further) moved some fields used for tcp/udp sockets lookup in the first cache line of struct sock_common. This patch moves inet_dport/inet_num as well, filling a 32bit hole on 64 bit arches and reducing number of cache line misses in lookups. Also change INET_MATCH()/INET_TW_MATCH() to perform the ports match before addresses match, as this check is more discriminant. Remove the hash check from MATCH() macros because we dont need to re validate the hash value after taking a refcount on socket, and use likely/unlikely compiler hints, as the sk_hash/hash check makes the following conditional tests 100% predicted by cpu. Introduce skc_addrpair/skc_portpair pair values to better document the alignment requirements of the port/addr pairs used in the various MATCH() macros, and remove some casts. The namespace check can also be done at last. This slightly improves TCP/UDP lookup times. IP/TCP early demux needs inet->rx_dst_ifindex and TCP needs inet->min_ttl, lets group them together in same cache line. With help from Ben Hutchings & Joe Perches. Idea of this patch came after Ling Ma proposal to move skc_hash to the beginning of struct sock_common, and should allow him to submit a final version of his patch. My tests show an improvement doing so. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ben Hutchings <bhutchings@solarflare.com> Cc: Joe Perches <joe@perches.com> Cc: Ling Ma <ling.ma.program@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-30 09:49:27 +00:00
__u32 tw_mark;
volatile unsigned char tw_substate;
unsigned char tw_rcv_wscale;
/* Socket demultiplex comparisons on incoming packets. */
/* these three are in inet_sock */
__be16 tw_sport;
/* And these are ours. */
unsigned int tw_transparent : 1,
tw_flowlabel : 20,
tw_pad : 3, /* 3 bits hole */
tw_tos : 8;
u32 tw_txhash;
u32 tw_priority;
tcp/dccp: get rid of central timewait timer Using a timer wheel for timewait sockets was nice ~15 years ago when memory was expensive and machines had a single processor. This does not scale, code is ugly and source of huge latencies (Typically 30 ms have been seen, cpus spinning on death_lock spinlock.) We can afford to use an extra 64 bytes per timewait sock and spread timewait load to all cpus to have better behavior. Tested: On following test, /proc/sys/net/ipv4/tcp_tw_recycle is set to 1 on the target (lpaa24) Before patch : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 419594 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 437171 While test is running, we can observe 25 or even 33 ms latencies. lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20601ms rtt min/avg/max/mdev = 0.020/0.217/25.771/1.535 ms, pipe 2 lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20702ms rtt min/avg/max/mdev = 0.019/0.183/33.761/1.441 ms, pipe 2 After patch : About 90% increase of throughput : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 810442 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 800992 And latencies are kept to minimal values during this load, even if network utilization is 90% higher : lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 19991ms rtt min/avg/max/mdev = 0.023/0.064/0.360/0.042 ms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-13 01:51:09 +00:00
struct timer_list tw_timer;
struct inet_bind_bucket *tw_tb;
};
#define tw_tclass tw_tos
static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
{
return (struct inet_timewait_sock *)sk;
}
tcp/dccp: remove twchain TCP listener refactoring, part 3 : Our goal is to hash SYN_RECV sockets into main ehash for fast lookup, and parallel SYN processing. Current inet_ehash_bucket contains two chains, one for ESTABLISH (and friend states) sockets, another for TIME_WAIT sockets only. As the hash table is sized to get at most one socket per bucket, it makes little sense to have separate twchain, as it makes the lookup slightly more complicated, and doubles hash table memory usage. If we make sure all socket types have the lookup keys at the same offsets, we can use a generic and faster lookup. It turns out TIME_WAIT and ESTABLISHED sockets already have common lookup fields for IPv4. [ INET_TW_MATCH() is no longer needed ] I'll provide a follow-up to factorize IPv6 lookup as well, to remove INET6_TW_MATCH() This way, SYN_RECV pseudo sockets will be supported the same. A new sock_gen_put() helper is added, doing either a sock_put() or inet_twsk_put() [ and will support SYN_RECV later ]. Note this helper should only be called in real slow path, when rcu lookup found a socket that was moved to another identity (freed/reused immediately), but could eventually be used in other contexts, like sock_edemux() Before patch : dmesg | grep "TCP established" TCP established hash table entries: 524288 (order: 11, 8388608 bytes) After patch : TCP established hash table entries: 524288 (order: 10, 4194304 bytes) Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-03 07:22:02 +00:00
void inet_twsk_free(struct inet_timewait_sock *tw);
void inet_twsk_put(struct inet_timewait_sock *tw);
void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
struct inet_hashinfo *hashinfo);
struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
tcp/dccp: get rid of central timewait timer Using a timer wheel for timewait sockets was nice ~15 years ago when memory was expensive and machines had a single processor. This does not scale, code is ugly and source of huge latencies (Typically 30 ms have been seen, cpus spinning on death_lock spinlock.) We can afford to use an extra 64 bytes per timewait sock and spread timewait load to all cpus to have better behavior. Tested: On following test, /proc/sys/net/ipv4/tcp_tw_recycle is set to 1 on the target (lpaa24) Before patch : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 419594 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 437171 While test is running, we can observe 25 or even 33 ms latencies. lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20601ms rtt min/avg/max/mdev = 0.020/0.217/25.771/1.535 ms, pipe 2 lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 20702ms rtt min/avg/max/mdev = 0.019/0.183/33.761/1.441 ms, pipe 2 After patch : About 90% increase of throughput : lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 810442 lpaa23:~# ./super_netperf 200 -H lpaa24 -t TCP_CC -l 60 -- -p0,0 800992 And latencies are kept to minimal values during this load, even if network utilization is 90% higher : lpaa24:~# ping -c 1000 -i 0.02 -qn lpaa23 ... 1000 packets transmitted, 1000 received, 0% packet loss, time 19991ms rtt min/avg/max/mdev = 0.023/0.064/0.360/0.042 ms Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-04-13 01:51:09 +00:00
struct inet_timewait_death_row *dr,
const int state);
void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
struct inet_hashinfo *hashinfo);
void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
bool rearm);
static inline void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo)
{
__inet_twsk_schedule(tw, timeo, false);
}
static inline void inet_twsk_reschedule(struct inet_timewait_sock *tw, int timeo)
{
__inet_twsk_schedule(tw, timeo, true);
}
void inet_twsk_deschedule_put(struct inet_timewait_sock *tw);
void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family);
static inline
struct net *twsk_net(const struct inet_timewait_sock *twsk)
{
return read_pnet(&twsk->tw_net);
}
static inline
void twsk_net_set(struct inet_timewait_sock *twsk, struct net *net)
{
write_pnet(&twsk->tw_net, net);
}
#endif /* _INET_TIMEWAIT_SOCK_ */