mirror of
https://github.com/torvalds/linux.git
synced 2024-12-30 14:52:05 +00:00
7170a97774
This socket field can be read and written by concurrent cpus. Use READ_ONCE() and WRITE_ONCE() annotations to document this, and avoid some compiler 'optimizations'. KCSAN reported : BUG: KCSAN: data-race in tcp_v4_rcv / tcp_v4_rcv write to 0xffff88812220763c of 4 bytes by interrupt on cpu 0: sk_incoming_cpu_update include/net/sock.h:953 [inline] tcp_v4_rcv+0x1b3c/0x1bb0 net/ipv4/tcp_ipv4.c:1934 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5010 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5124 process_backlog+0x1d3/0x420 net/core/dev.c:5955 napi_poll net/core/dev.c:6392 [inline] net_rx_action+0x3ae/0xa90 net/core/dev.c:6460 __do_softirq+0x115/0x33f kernel/softirq.c:292 do_softirq_own_stack+0x2a/0x40 arch/x86/entry/entry_64.S:1082 do_softirq.part.0+0x6b/0x80 kernel/softirq.c:337 do_softirq kernel/softirq.c:329 [inline] __local_bh_enable_ip+0x76/0x80 kernel/softirq.c:189 read to 0xffff88812220763c of 4 bytes by interrupt on cpu 1: sk_incoming_cpu_update include/net/sock.h:952 [inline] tcp_v4_rcv+0x181a/0x1bb0 net/ipv4/tcp_ipv4.c:1934 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5010 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5124 process_backlog+0x1d3/0x420 net/core/dev.c:5955 napi_poll net/core/dev.c:6392 [inline] net_rx_action+0x3ae/0xa90 net/core/dev.c:6460 __do_softirq+0x115/0x33f kernel/softirq.c:292 run_ksoftirqd+0x46/0x60 kernel/softirq.c:603 smpboot_thread_fn+0x37d/0x4a0 kernel/smpboot.c:165 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.4.0-rc3+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Signed-off-by: David S. Miller <davem@davemloft.net>
299 lines
8.0 KiB
C
299 lines
8.0 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.
|
|
*
|
|
* Generic INET6 transport hashtables
|
|
*
|
|
* Authors: Lotsa people, from code originally in tcp, generalised here
|
|
* by Arnaldo Carvalho de Melo <acme@mandriva.com>
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/random.h>
|
|
|
|
#include <net/addrconf.h>
|
|
#include <net/inet_connection_sock.h>
|
|
#include <net/inet_hashtables.h>
|
|
#include <net/inet6_hashtables.h>
|
|
#include <net/secure_seq.h>
|
|
#include <net/ip.h>
|
|
#include <net/sock_reuseport.h>
|
|
|
|
u32 inet6_ehashfn(const struct net *net,
|
|
const struct in6_addr *laddr, const u16 lport,
|
|
const struct in6_addr *faddr, const __be16 fport)
|
|
{
|
|
static u32 inet6_ehash_secret __read_mostly;
|
|
static u32 ipv6_hash_secret __read_mostly;
|
|
|
|
u32 lhash, fhash;
|
|
|
|
net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret));
|
|
net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
|
|
|
|
lhash = (__force u32)laddr->s6_addr32[3];
|
|
fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret);
|
|
|
|
return __inet6_ehashfn(lhash, lport, fhash, fport,
|
|
inet6_ehash_secret + net_hash_mix(net));
|
|
}
|
|
|
|
/*
|
|
* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
|
|
* we need not check it for TCP lookups anymore, thanks Alexey. -DaveM
|
|
*
|
|
* The sockhash lock must be held as a reader here.
|
|
*/
|
|
struct sock *__inet6_lookup_established(struct net *net,
|
|
struct inet_hashinfo *hashinfo,
|
|
const struct in6_addr *saddr,
|
|
const __be16 sport,
|
|
const struct in6_addr *daddr,
|
|
const u16 hnum,
|
|
const int dif, const int sdif)
|
|
{
|
|
struct sock *sk;
|
|
const struct hlist_nulls_node *node;
|
|
const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
|
|
/* Optimize here for direct hit, only listening connections can
|
|
* have wildcards anyways.
|
|
*/
|
|
unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport);
|
|
unsigned int slot = hash & hashinfo->ehash_mask;
|
|
struct inet_ehash_bucket *head = &hashinfo->ehash[slot];
|
|
|
|
|
|
begin:
|
|
sk_nulls_for_each_rcu(sk, node, &head->chain) {
|
|
if (sk->sk_hash != hash)
|
|
continue;
|
|
if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif))
|
|
continue;
|
|
if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
|
|
goto out;
|
|
|
|
if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif))) {
|
|
sock_gen_put(sk);
|
|
goto begin;
|
|
}
|
|
goto found;
|
|
}
|
|
if (get_nulls_value(node) != slot)
|
|
goto begin;
|
|
out:
|
|
sk = NULL;
|
|
found:
|
|
return sk;
|
|
}
|
|
EXPORT_SYMBOL(__inet6_lookup_established);
|
|
|
|
static inline int compute_score(struct sock *sk, struct net *net,
|
|
const unsigned short hnum,
|
|
const struct in6_addr *daddr,
|
|
const int dif, const int sdif, bool exact_dif)
|
|
{
|
|
int score = -1;
|
|
|
|
if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum &&
|
|
sk->sk_family == PF_INET6) {
|
|
if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
|
|
return -1;
|
|
|
|
if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
|
|
return -1;
|
|
|
|
score = 1;
|
|
if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
|
|
score++;
|
|
}
|
|
return score;
|
|
}
|
|
|
|
/* called with rcu_read_lock() */
|
|
static struct sock *inet6_lhash2_lookup(struct net *net,
|
|
struct inet_listen_hashbucket *ilb2,
|
|
struct sk_buff *skb, int doff,
|
|
const struct in6_addr *saddr,
|
|
const __be16 sport, const struct in6_addr *daddr,
|
|
const unsigned short hnum, const int dif, const int sdif)
|
|
{
|
|
bool exact_dif = inet6_exact_dif_match(net, skb);
|
|
struct inet_connection_sock *icsk;
|
|
struct sock *sk, *result = NULL;
|
|
int score, hiscore = 0;
|
|
u32 phash = 0;
|
|
|
|
inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
|
|
sk = (struct sock *)icsk;
|
|
score = compute_score(sk, net, hnum, daddr, dif, sdif,
|
|
exact_dif);
|
|
if (score > hiscore) {
|
|
if (sk->sk_reuseport) {
|
|
phash = inet6_ehashfn(net, daddr, hnum,
|
|
saddr, sport);
|
|
result = reuseport_select_sock(sk, phash,
|
|
skb, doff);
|
|
if (result)
|
|
return result;
|
|
}
|
|
result = sk;
|
|
hiscore = score;
|
|
}
|
|
}
|
|
|
|
return result;
|
|
}
|
|
|
|
struct sock *inet6_lookup_listener(struct net *net,
|
|
struct inet_hashinfo *hashinfo,
|
|
struct sk_buff *skb, int doff,
|
|
const struct in6_addr *saddr,
|
|
const __be16 sport, const struct in6_addr *daddr,
|
|
const unsigned short hnum, const int dif, const int sdif)
|
|
{
|
|
struct inet_listen_hashbucket *ilb2;
|
|
struct sock *result = NULL;
|
|
unsigned int hash2;
|
|
|
|
hash2 = ipv6_portaddr_hash(net, daddr, hnum);
|
|
ilb2 = inet_lhash2_bucket(hashinfo, hash2);
|
|
|
|
result = inet6_lhash2_lookup(net, ilb2, skb, doff,
|
|
saddr, sport, daddr, hnum,
|
|
dif, sdif);
|
|
if (result)
|
|
goto done;
|
|
|
|
/* Lookup lhash2 with in6addr_any */
|
|
hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
|
|
ilb2 = inet_lhash2_bucket(hashinfo, hash2);
|
|
|
|
result = inet6_lhash2_lookup(net, ilb2, skb, doff,
|
|
saddr, sport, &in6addr_any, hnum,
|
|
dif, sdif);
|
|
done:
|
|
if (IS_ERR(result))
|
|
return NULL;
|
|
return result;
|
|
}
|
|
EXPORT_SYMBOL_GPL(inet6_lookup_listener);
|
|
|
|
struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo,
|
|
struct sk_buff *skb, int doff,
|
|
const struct in6_addr *saddr, const __be16 sport,
|
|
const struct in6_addr *daddr, const __be16 dport,
|
|
const int dif)
|
|
{
|
|
struct sock *sk;
|
|
bool refcounted;
|
|
|
|
sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr,
|
|
ntohs(dport), dif, 0, &refcounted);
|
|
if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt))
|
|
sk = NULL;
|
|
return sk;
|
|
}
|
|
EXPORT_SYMBOL_GPL(inet6_lookup);
|
|
|
|
static int __inet6_check_established(struct inet_timewait_death_row *death_row,
|
|
struct sock *sk, const __u16 lport,
|
|
struct inet_timewait_sock **twp)
|
|
{
|
|
struct inet_hashinfo *hinfo = death_row->hashinfo;
|
|
struct inet_sock *inet = inet_sk(sk);
|
|
const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
|
|
const struct in6_addr *saddr = &sk->sk_v6_daddr;
|
|
const int dif = sk->sk_bound_dev_if;
|
|
struct net *net = sock_net(sk);
|
|
const int sdif = l3mdev_master_ifindex_by_index(net, dif);
|
|
const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
|
|
const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr,
|
|
inet->inet_dport);
|
|
struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
|
|
spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
|
|
struct sock *sk2;
|
|
const struct hlist_nulls_node *node;
|
|
struct inet_timewait_sock *tw = NULL;
|
|
|
|
spin_lock(lock);
|
|
|
|
sk_nulls_for_each(sk2, node, &head->chain) {
|
|
if (sk2->sk_hash != hash)
|
|
continue;
|
|
|
|
if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports,
|
|
dif, sdif))) {
|
|
if (sk2->sk_state == TCP_TIME_WAIT) {
|
|
tw = inet_twsk(sk2);
|
|
if (twsk_unique(sk, sk2, twp))
|
|
break;
|
|
}
|
|
goto not_unique;
|
|
}
|
|
}
|
|
|
|
/* Must record num and sport now. Otherwise we will see
|
|
* in hash table socket with a funny identity.
|
|
*/
|
|
inet->inet_num = lport;
|
|
inet->inet_sport = htons(lport);
|
|
sk->sk_hash = hash;
|
|
WARN_ON(!sk_unhashed(sk));
|
|
__sk_nulls_add_node_rcu(sk, &head->chain);
|
|
if (tw) {
|
|
sk_nulls_del_node_init_rcu((struct sock *)tw);
|
|
__NET_INC_STATS(net, LINUX_MIB_TIMEWAITRECYCLED);
|
|
}
|
|
spin_unlock(lock);
|
|
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
|
|
|
|
if (twp) {
|
|
*twp = tw;
|
|
} else if (tw) {
|
|
/* Silly. Should hash-dance instead... */
|
|
inet_twsk_deschedule_put(tw);
|
|
}
|
|
return 0;
|
|
|
|
not_unique:
|
|
spin_unlock(lock);
|
|
return -EADDRNOTAVAIL;
|
|
}
|
|
|
|
static u32 inet6_sk_port_offset(const struct sock *sk)
|
|
{
|
|
const struct inet_sock *inet = inet_sk(sk);
|
|
|
|
return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32,
|
|
sk->sk_v6_daddr.s6_addr32,
|
|
inet->inet_dport);
|
|
}
|
|
|
|
int inet6_hash_connect(struct inet_timewait_death_row *death_row,
|
|
struct sock *sk)
|
|
{
|
|
u32 port_offset = 0;
|
|
|
|
if (!inet_sk(sk)->inet_num)
|
|
port_offset = inet6_sk_port_offset(sk);
|
|
return __inet_hash_connect(death_row, sk, port_offset,
|
|
__inet6_check_established);
|
|
}
|
|
EXPORT_SYMBOL_GPL(inet6_hash_connect);
|
|
|
|
int inet6_hash(struct sock *sk)
|
|
{
|
|
int err = 0;
|
|
|
|
if (sk->sk_state != TCP_CLOSE) {
|
|
local_bh_disable();
|
|
err = __inet_hash(sk, NULL);
|
|
local_bh_enable();
|
|
}
|
|
|
|
return err;
|
|
}
|
|
EXPORT_SYMBOL_GPL(inet6_hash);
|