iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'net-ipv4-sysctl-races-part-3'

Browse Source 
Kuniyuki Iwashima says:

====================
sysctl: Fix data-races around ipv4_net_table (Round 3).

This series fixes data-races around 21 knobs after
igmp_link_local_mcast_reports in ipv4_net_table.

These 4 knobs are skipped because they are safe.

  - tcp_congestion_control: Safe with RCU and xchg().
  - tcp_available_congestion_control: Read only.
  - tcp_allowed_congestion_control: Safe with RCU and spinlock().
  - tcp_fastopen_key: Safe with RCU and xchg()

So, round 4 will start with fib_multipath_use_neigh.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2022-07-18 12:21:54 +01:00
commit c9f21106d9
18 changed files with 106 additions and 73 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/net/amt.c
View File

@ -563,7 +563,7 @@ static struct sk_buff *amt_build_igmp_gq(struct amt_dev *amt)
ihv3->nsrcs = 0;
ihv3->resv = 0;
ihv3->suppress = false;
ihv3->qrv = amt->net->ipv4.sysctl_igmp_qrv;
ihv3->qrv = READ_ONCE(amt->net->ipv4.sysctl_igmp_qrv);
ihv3->csum = 0;
csum = &ihv3->csum;
csum_start = (void *)ihv3;
@ -3095,7 +3095,7 @@ static int amt_newlink(struct net *net, struct net_device *dev,
goto err;
}
if (amt->mode == AMT_MODE_RELAY) {
amt->qrv = amt->net->ipv4.sysctl_igmp_qrv;
amt->qrv = READ_ONCE(amt->net->ipv4.sysctl_igmp_qrv);
amt->qri = 10;
dev->needed_headroom = amt->stream_dev->needed_headroom +
AMT_RELAY_HLEN;

14
include/net/tcp.h
View File

@ -1493,21 +1493,24 @@ static inline int keepalive_intvl_when(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
return tp->keepalive_intvl ? : net->ipv4.sysctl_tcp_keepalive_intvl;
return tp->keepalive_intvl ? :
READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl);
}
static inline int keepalive_time_when(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
return tp->keepalive_time ? : net->ipv4.sysctl_tcp_keepalive_time;
return tp->keepalive_time ? :
READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time);
}
static inline int keepalive_probes(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
return tp->keepalive_probes ? : net->ipv4.sysctl_tcp_keepalive_probes;
return tp->keepalive_probes ? :
READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes);
}
static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)
@ -1520,7 +1523,8 @@ static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp)
static inline int tcp_fin_time(const struct sock *sk)
{
int fin_timeout = tcp_sk(sk)->linger2 ? : sock_net(sk)->ipv4.sysctl_tcp_fin_timeout;
int fin_timeout = tcp_sk(sk)->linger2 ? :
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fin_timeout);
const int rto = inet_csk(sk)->icsk_rto;
if (fin_timeout < (rto << 2) - (rto >> 1))
@ -2023,7 +2027,7 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp)
{
struct net *net = sock_net((struct sock *)tp);
return tp->notsent_lowat ?: net->ipv4.sysctl_tcp_notsent_lowat;
return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat);
}
bool tcp_stream_memory_free(const struct sock *sk, int wake);

4
net/core/filter.c
View File

@ -7041,7 +7041,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
return -EINVAL;
if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies))
return -EINVAL;
if (!th->ack || th->rst || th->syn)
@ -7116,7 +7116,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
return -EINVAL;
if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies))
return -ENOENT;
if (!th->syn || th->ack || th->fin || th->rst)

4
net/core/sock_reuseport.c
View File

@ -387,7 +387,7 @@ void reuseport_stop_listen_sock(struct sock *sk)
prog = rcu_dereference_protected(reuse->prog,
lockdep_is_held(&reuseport_lock));
if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req ||
if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req) ||
(prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) {
/* Migration capable, move sk from the listening section
* to the closed section.
@ -545,7 +545,7 @@ struct sock *reuseport_migrate_sock(struct sock *sk,
hash = migrating_sk->sk_hash;
prog = rcu_dereference(reuse->prog);
if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) {
if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req)
if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req))
goto select_by_hash;
goto failure;
}

2
net/ipv4/af_inet.c
View File

@ -217,7 +217,7 @@ int inet_listen(struct socket *sock, int backlog)
* because the socket was in TCP_LISTEN state previously but
* was shutdown() rather than close().
*/
tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen);
if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
(tcp_fastopen & TFO_SERVER_ENABLE) &&
!inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {

49
net/ipv4/igmp.c
View File

@ -467,7 +467,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
if (pmc->multiaddr == IGMP_ALL_HOSTS)
return skb;
if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
if (ipv4_is_local_multicast(pmc->multiaddr) &&
!READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return skb;
mtu = READ_ONCE(dev->mtu);
@ -593,7 +594,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc)
if (pmc->multiaddr == IGMP_ALL_HOSTS)
continue;
if (ipv4_is_local_multicast(pmc->multiaddr) &&
!net->ipv4.sysctl_igmp_llm_reports)
!READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
continue;
spin_lock_bh(&pmc->lock);
if (pmc->sfcount[MCAST_EXCLUDE])
@ -736,7 +737,8 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
if (type == IGMPV3_HOST_MEMBERSHIP_REPORT)
return igmpv3_send_report(in_dev, pmc);
if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports)
if (ipv4_is_local_multicast(group) &&
!READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return 0;
if (type == IGMP_HOST_LEAVE_MESSAGE)
@ -825,7 +827,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
struct net *net = dev_net(in_dev->dev);
if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
return;
WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv);
WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv));
igmp_ifc_start_timer(in_dev, 1);
}
@ -920,7 +922,8 @@ static bool igmp_heard_report(struct in_device *in_dev, __be32 group)
if (group == IGMP_ALL_HOSTS)
return false;
if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports)
if (ipv4_is_local_multicast(group) &&
!READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return false;
rcu_read_lock();
@ -1006,7 +1009,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
* received value was zero, use the default or statically
* configured value.
*/
in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv;
in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL;
/* RFC3376, 8.3. Query Response Interval:
@ -1045,7 +1048,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
if (im->multiaddr == IGMP_ALL_HOSTS)
continue;
if (ipv4_is_local_multicast(im->multiaddr) &&
!net->ipv4.sysctl_igmp_llm_reports)
!READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
continue;
spin_lock_bh(&im->lock);
if (im->tm_running)
@ -1186,7 +1189,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im,
pmc->interface = im->interface;
in_dev_hold(in_dev);
pmc->multiaddr = im->multiaddr;
pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
pmc->sfmode = im->sfmode;
if (pmc->sfmode == MCAST_INCLUDE) {
struct ip_sf_list *psf;
@ -1237,9 +1240,11 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
swap(im->tomb, pmc->tomb);
swap(im->sources, pmc->sources);
for (psf = im->sources; psf; psf = psf->sf_next)
psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
psf->sf_crcount = in_dev->mr_qrv ?:
READ_ONCE(net->ipv4.sysctl_igmp_qrv);
} else {
im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
im->crcount = in_dev->mr_qrv ?:
READ_ONCE(net->ipv4.sysctl_igmp_qrv);
}
in_dev_put(pmc->interface);
kfree_pmc(pmc);
@ -1296,7 +1301,8 @@ static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp)
#ifdef CONFIG_IP_MULTICAST
if (im->multiaddr == IGMP_ALL_HOSTS)
return;
if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
if (ipv4_is_local_multicast(im->multiaddr) &&
!READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return;
reporter = im->reporter;
@ -1338,13 +1344,14 @@ static void igmp_group_added(struct ip_mc_list *im)
#ifdef CONFIG_IP_MULTICAST
if (im->multiaddr == IGMP_ALL_HOSTS)
return;
if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
if (ipv4_is_local_multicast(im->multiaddr) &&
!READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return;
if (in_dev->dead)
return;
im->unsolicit_count = net->ipv4.sysctl_igmp_qrv;
im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv);
if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) {
spin_lock_bh(&im->lock);
igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY);
@ -1358,7 +1365,7 @@ static void igmp_group_added(struct ip_mc_list *im)
* IN() to IN(A).
*/
if (im->sfmode == MCAST_EXCLUDE)
im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
igmp_ifc_event(in_dev);
#endif
@ -1642,7 +1649,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev)
if (im->multiaddr == IGMP_ALL_HOSTS)
continue;
if (ipv4_is_local_multicast(im->multiaddr) &&
!net->ipv4.sysctl_igmp_llm_reports)
!READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
continue;
/* a failover is happening and switches
@ -1749,7 +1756,7 @@ static void ip_mc_reset(struct in_device *in_dev)
in_dev->mr_qi = IGMP_QUERY_INTERVAL;
in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL;
in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv);
}
#else
static void ip_mc_reset(struct in_device *in_dev)
@ -1883,7 +1890,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode,
#ifdef CONFIG_IP_MULTICAST
if (psf->sf_oldin &&
!IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) {
psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
psf->sf_next = pmc->tomb;
pmc->tomb = psf;
rv = 1;
@ -1947,7 +1954,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
/* filter mode change */
pmc->sfmode = MCAST_INCLUDE;
#ifdef CONFIG_IP_MULTICAST
pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
@ -2126,7 +2133,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
#ifdef CONFIG_IP_MULTICAST
/* else no filters; keep old mode for reports */
pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
@ -2192,7 +2199,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr,
count++;
}
err = -ENOBUFS;
if (count >= net->ipv4.sysctl_igmp_max_memberships)
if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships))
goto done;
iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL);
if (!iml)
@ -2379,7 +2386,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
}
/* else, add a new source to the filter */
if (psl && psl->sl_count >= net->ipv4.sysctl_igmp_max_msf) {
if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) {
err = -ENOBUFS;
goto done;
}

3
net/ipv4/inet_connection_sock.c
View File

@ -833,7 +833,8 @@ static void reqsk_timer_handler(struct timer_list *t)
icsk = inet_csk(sk_listener);
net = sock_net(sk_listener);
max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
max_syn_ack_retries = icsk->icsk_syn_retries ? :
READ_ONCE(net->ipv4.sysctl_tcp_synack_retries);
/* Normally all the openreqs are young and become mature
* (i.e. converted to established socket) for first timeout.
* If synack was not acknowledged for 1 second, it means

6
net/ipv4/ip_sockglue.c
View File

@ -782,7 +782,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
/* numsrc >= (4G-140)/128 overflow in 32 bits */
err = -ENOBUFS;
if (gsf->gf_numsrc >= 0x1ffffff ||
gsf->gf_numsrc > sock_net(sk)->ipv4.sysctl_igmp_max_msf)
gsf->gf_numsrc > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf))
goto out_free_gsf;
err = -EINVAL;
@ -832,7 +832,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
/* numsrc >= (4G-140)/128 overflow in 32 bits */
err = -ENOBUFS;
if (n > sock_net(sk)->ipv4.sysctl_igmp_max_msf)
if (n > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf))
goto out_free_gsf;
err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode,
&gf32->gf_group, gf32->gf_slist_flex);
@ -1244,7 +1244,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
}
/* numsrc >= (1G-4) overflow in 32 bits */
if (msf->imsf_numsrc >= 0x3ffffffcU ||
msf->imsf_numsrc > net->ipv4.sysctl_igmp_max_msf) {
msf->imsf_numsrc > READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) {
kfree(msf);
err = -ENOBUFS;
break;

3
net/ipv4/syncookies.c
View File

@ -340,7 +340,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
struct flowi4 fl4;
u32 tsoff = 0;
if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) ||
!th->ack || th->rst)
goto out;
if (tcp_synq_no_recent_overflow(sk))

13
net/ipv4/tcp.c
View File

@ -441,7 +441,7 @@ void tcp_init_sock(struct sock *sk)
tp->snd_cwnd_clamp = ~0;
tp->mss_cache = TCP_MSS_DEFAULT;
tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering);
tcp_assign_congestion_control(sk);
tp->tsoffset = 0;
@ -1150,7 +1150,8 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
struct sockaddr *uaddr = msg->msg_name;
int err, flags;
if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) &
TFO_CLIENT_ENABLE) ||
(uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
uaddr->sa_family == AF_UNSPEC))
return -EOPNOTSUPP;
@ -3617,7 +3618,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
case TCP_FASTOPEN_CONNECT:
if (val > 1 || val < 0) {
err = -EINVAL;
} else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
} else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) &
TFO_CLIENT_ENABLE) {
if (sk->sk_state == TCP_CLOSE)
tp->fastopen_connect = val;
else
@ -3967,12 +3969,13 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
val = keepalive_probes(tp);
break;
case TCP_SYNCNT:
val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
val = icsk->icsk_syn_retries ? :
READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
break;
case TCP_LINGER2:
val = tp->linger2;
if (val >= 0)
val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ;
val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ;
break;
case TCP_DEFER_ACCEPT:
val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,

9
net/ipv4/tcp_fastopen.c
View File

@ -332,7 +332,7 @@ static bool tcp_fastopen_no_cookie(const struct sock *sk,
const struct dst_entry *dst,
int flag)
{
return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) ||
return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) ||
tcp_sk(sk)->fastopen_no_cookie ||
(dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE));
}
@ -347,7 +347,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
const struct dst_entry *dst)
{
bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen);
struct tcp_fastopen_cookie valid_foc = { .len = -1 };
struct sock *child;
int ret = 0;
@ -489,7 +489,7 @@ void tcp_fastopen_active_disable(struct sock *sk)
{
struct net *net = sock_net(sk);
if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)
if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout))
return;
/* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */
@ -510,7 +510,8 @@ void tcp_fastopen_active_disable(struct sock *sk)
*/
bool tcp_fastopen_active_should_disable(struct sock *sk)
{
unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
unsigned int tfo_bh_timeout =
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout);
unsigned long timeout;
int tfo_da_times;
int multiplier;

36
net/ipv4/tcp_input.c
View File

@ -2139,6 +2139,7 @@ void tcp_enter_loss(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
u8 reordering;
tcp_timeout_mark_lost(sk);
@ -2159,10 +2160,12 @@ void tcp_enter_loss(struct sock *sk)
/* Timeout in disordered state after receiving substantial DUPACKs
* suggests that the degree of reordering is over-estimated.
*/
reordering = READ_ONCE(net->ipv4.sysctl_tcp_reordering);
if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
tp->sacked_out >= net->ipv4.sysctl_tcp_reordering)
tp->sacked_out >= reordering)
tp->reordering = min_t(unsigned int, tp->reordering,
net->ipv4.sysctl_tcp_reordering);
reordering);
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
tcp_ecn_queue_cwr(tp);
@ -3464,7 +3467,8 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
* new SACK or ECE mark may first advance cwnd here and later reduce
* cwnd in tcp_fastretrans_alert() based on more states.
*/
if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering)
if (tcp_sk(sk)->reordering >
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering))
return flag & FLAG_FORWARD_PROGRESS;
return flag & FLAG_DATA_ACKED;
@ -6797,11 +6801,14 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto)
{
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
const char *msg = "Dropping request";
bool want_cookie = false;
struct net *net = sock_net(sk);
bool want_cookie = false;
u8 syncookies;
syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies);
#ifdef CONFIG_SYN_COOKIES
if (net->ipv4.sysctl_tcp_syncookies) {
if (syncookies) {
msg = "Sending cookies";
want_cookie = true;
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES);
@ -6809,8 +6816,7 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto)
#endif
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
if (!queue->synflood_warned &&
net->ipv4.sysctl_tcp_syncookies != 2 &&
if (!queue->synflood_warned && syncookies != 2 &&
xchg(&queue->synflood_warned, 1) == 0)
net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n",
proto, sk->sk_num, msg);
@ -6859,7 +6865,7 @@ u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
struct tcp_sock *tp = tcp_sk(sk);
u16 mss;
if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 &&
if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) != 2 &&
!inet_csk_reqsk_queue_is_full(sk))
return 0;
@ -6893,13 +6899,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
bool want_cookie = false;
struct dst_entry *dst;
struct flowi fl;
u8 syncookies;
syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies);
/* TW buckets are converted to open requests without
* limitations, they conserve resources and peer is
* evidently real one.
*/
if ((net->ipv4.sysctl_tcp_syncookies == 2 ||
inet_csk_reqsk_queue_is_full(sk)) && !isn) {
if ((syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) {
want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name);
if (!want_cookie)
goto drop;
@ -6948,10 +6956,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
if (!want_cookie && !isn) {
int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog);
/* Kill the following clause, if you dislike this way. */
if (!net->ipv4.sysctl_tcp_syncookies &&
(net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
(net->ipv4.sysctl_max_syn_backlog >> 2)) &&
if (!syncookies &&
(max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
(max_syn_backlog >> 2)) &&
!tcp_peer_is_proven(req, dst)) {
/* Without syncookies last quarter of
* backlog is filled with destinations,

2
net/ipv4/tcp_ipv4.c
View File

@ -108,10 +108,10 @@ static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb)
int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
{
int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse);
const struct inet_timewait_sock *tw = inet_twsk(sktw);
const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
struct tcp_sock *tp = tcp_sk(sk);
int reuse = sock_net(sk)->ipv4.sysctl_tcp_tw_reuse;
if (reuse == 2) {
/* Still does not detect *everything* that goes through

3
net/ipv4/tcp_metrics.c
View File

@ -428,7 +428,8 @@ void tcp_update_metrics(struct sock *sk)
if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) {
val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
if (val < tp->reordering &&
tp->reordering != net->ipv4.sysctl_tcp_reordering)
tp->reordering !=
READ_ONCE(net->ipv4.sysctl_tcp_reordering))
tcp_metric_set(tm, TCP_METRIC_REORDERING,
tp->reordering);
}

2
net/ipv4/tcp_output.c
View File

@ -4090,7 +4090,7 @@ void tcp_send_probe0(struct sock *sk)
icsk->icsk_probes_out++;
if (err <= 0) {
if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2)
if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2))
icsk->icsk_backoff++;
timeout = tcp_probe0_when(sk, TCP_RTO_MAX);
} else {

20
net/ipv4/tcp_timer.c
View File

@ -143,7 +143,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
*/
static int tcp_orphan_retries(struct sock *sk, bool alive)
{
int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */
int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */
/* We know from an ICMP that something is wrong. */
if (sk->sk_err_soft && !alive)
@ -239,17 +239,18 @@ static int tcp_write_timeout(struct sock *sk)
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
if (icsk->icsk_retransmits)
__dst_negative_advice(sk);
retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
retry_until = icsk->icsk_syn_retries ? :
READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
expired = icsk->icsk_retransmits >= retry_until;
} else {
if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) {
if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) {
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
__dst_negative_advice(sk);
}
retry_until = net->ipv4.sysctl_tcp_retries2;
retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2);
if (sock_flag(sk, SOCK_DEAD)) {
const bool alive = icsk->icsk_rto < TCP_RTO_MAX;
@ -380,7 +381,7 @@ static void tcp_probe_timer(struct sock *sk)
msecs_to_jiffies(icsk->icsk_user_timeout))
goto abort;
max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2);
if (sock_flag(sk, SOCK_DEAD)) {
const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
@ -406,12 +407,15 @@ abort: tcp_write_err(sk);
static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
{
struct inet_connection_sock *icsk = inet_csk(sk);
int max_retries = icsk->icsk_syn_retries ? :
sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
struct tcp_sock *tp = tcp_sk(sk);
int max_retries;
req->rsk_ops->syn_ack_timeout(req);
/* add one more retry for fastopen */
max_retries = icsk->icsk_syn_retries ? :
READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1;
if (req->num_timeout >= max_retries) {
tcp_write_err(sk);
return;
@ -585,7 +589,7 @@ out_reset_timer:
}
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX);
if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0))
if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0))
__sk_dst_reset(sk);
out:;

3
net/ipv6/syncookies.c
View File

@ -141,7 +141,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
__u8 rcv_wscale;
u32 tsoff = 0;
if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) ||
!th->ack || th->rst)
goto out;
if (tcp_synq_no_recent_overflow(sk))

2
net/smc/smc_llc.c
View File

@ -2122,7 +2122,7 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc)
init_waitqueue_head(&lgr->llc_flow_waiter);
init_waitqueue_head(&lgr->llc_msg_waiter);
mutex_init(&lgr->llc_conf_mutex);
lgr->llc_testlink_time = net->ipv4.sysctl_tcp_keepalive_time;
lgr->llc_testlink_time = READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time);
}
/* called after lgr was removed from lgr_list */