mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-24 11:25:43 +00:00
936a192f97
Jiri Slaby reported regression of bind() with a simple repro. [0] The repro creates a TIME_WAIT socket and tries to bind() a new socket with the same local address and port. Before commit28044fc1d4("net: Add a bhash2 table hashed by port and address"), the bind() failed with -EADDRINUSE, but now it succeeds. The cited commit should have put TIME_WAIT sockets into bhash2; otherwise, inet_bhash2_conflict() misses TIME_WAIT sockets when validating bind() requests if the address is not a wildcard one. The straight option is to move sk_bind2_node from struct sock to struct sock_common to add twsk to bhash2 as implemented as RFC. [1] However, the binary layout change in the struct sock could affect performances moving hot fields on different cachelines. To avoid that, we add another TIME_WAIT list in inet_bind2_bucket and check it while validating bind(). [0]: https://lore.kernel.org/netdev/6b971a4e-c7d8-411e-1f92-fda29b5b2fb9@kernel.org/ [1]: https://lore.kernel.org/netdev/20221221151258.25748-2-kuniyu@amazon.com/ Fixes:28044fc1d4("net: Add a bhash2 table hashed by port and address") Reported-by: Jiri Slaby <jirislaby@kernel.org> Suggested-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com> Acked-by: Joanne Koong <joannelkoong@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
130 lines
3.8 KiB
C
130 lines
3.8 KiB
C
/* 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
|
|
#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
|
|
#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
|
|
#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
|
|
|
|
__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;
|
|
struct timer_list tw_timer;
|
|
struct inet_bind_bucket *tw_tb;
|
|
struct inet_bind2_bucket *tw_tb2;
|
|
struct hlist_node tw_bind2_node;
|
|
};
|
|
#define tw_tclass tw_tos
|
|
|
|
#define twsk_for_each_bound_bhash2(__tw, list) \
|
|
hlist_for_each_entry(__tw, list, tw_bind2_node)
|
|
|
|
static inline struct inet_timewait_sock *inet_twsk(const struct sock *sk)
|
|
{
|
|
return (struct inet_timewait_sock *)sk;
|
|
}
|
|
|
|
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,
|
|
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_ */
|