[PATCH 4.9 01/36] ipvs: fix rtnl_lock lockups caused by start_sync_thread

From: Greg Kroah-Hartman
Date: Mon May 14 2018 - 03:36:05 EST


4.9-stable review patch. If anyone has any objections, please let me know.

------------------

From: Julian Anastasov <ja@xxxxxx>

commit 5c64576a77894a50be80be0024bed27171b55989 upstream.

syzkaller reports for wrong rtnl_lock usage in sync code [1] and [2]

We have 2 problems in start_sync_thread if error path is
taken, eg. on memory allocation error or failure to configure
sockets for mcast group or addr/port binding:

1. recursive locking: holding rtnl_lock while calling sock_release
which in turn calls again rtnl_lock in ip_mc_drop_socket to leave
the mcast group, as noticed by Florian Westphal. Additionally,
sock_release can not be called while holding sync_mutex (ABBA
deadlock).

2. task hung: holding rtnl_lock while calling kthread_stop to
stop the running kthreads. As the kthreads do the same to leave
the mcast group (sock_release -> ip_mc_drop_socket -> rtnl_lock)
they hang.

Fix the problems by calling rtnl_unlock early in the error path,
now sock_release is called after unlocking both mutexes.

Problem 3 (task hung reported by syzkaller [2]) is variant of
problem 2: use _trylock to prevent one user to call rtnl_lock and
then while waiting for sync_mutex to block kthreads that execute
sock_release when they are stopped by stop_sync_thread.

[1]
IPVS: stopping backup sync thread 4500 ...
WARNING: possible recursive locking detected
4.16.0-rc7+ #3 Not tainted
--------------------------------------------
syzkaller688027/4497 is trying to acquire lock:
(rtnl_mutex){+.+.}, at: [<00000000bb14d7fb>] rtnl_lock+0x17/0x20
net/core/rtnetlink.c:74

but task is already holding lock:
IPVS: stopping backup sync thread 4495 ...
(rtnl_mutex){+.+.}, at: [<00000000bb14d7fb>] rtnl_lock+0x17/0x20
net/core/rtnetlink.c:74

other info that might help us debug this:
Possible unsafe locking scenario:

CPU0
----
lock(rtnl_mutex);
lock(rtnl_mutex);

*** DEADLOCK ***

May be due to missing lock nesting notation

2 locks held by syzkaller688027/4497:
#0: (rtnl_mutex){+.+.}, at: [<00000000bb14d7fb>] rtnl_lock+0x17/0x20
net/core/rtnetlink.c:74
#1: (ipvs->sync_mutex){+.+.}, at: [<00000000703f78e3>]
do_ip_vs_set_ctl+0x10f8/0x1cc0 net/netfilter/ipvs/ip_vs_ctl.c:2388

stack backtrace:
CPU: 1 PID: 4497 Comm: syzkaller688027 Not tainted 4.16.0-rc7+ #3
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+0x194/0x24d lib/dump_stack.c:53
print_deadlock_bug kernel/locking/lockdep.c:1761 [inline]
check_deadlock kernel/locking/lockdep.c:1805 [inline]
validate_chain kernel/locking/lockdep.c:2401 [inline]
__lock_acquire+0xe8f/0x3e00 kernel/locking/lockdep.c:3431
lock_acquire+0x1d5/0x580 kernel/locking/lockdep.c:3920
__mutex_lock_common kernel/locking/mutex.c:756 [inline]
__mutex_lock+0x16f/0x1a80 kernel/locking/mutex.c:893
mutex_lock_nested+0x16/0x20 kernel/locking/mutex.c:908
rtnl_lock+0x17/0x20 net/core/rtnetlink.c:74
ip_mc_drop_socket+0x88/0x230 net/ipv4/igmp.c:2643
inet_release+0x4e/0x1c0 net/ipv4/af_inet.c:413
sock_release+0x8d/0x1e0 net/socket.c:595
start_sync_thread+0x2213/0x2b70 net/netfilter/ipvs/ip_vs_sync.c:1924
do_ip_vs_set_ctl+0x1139/0x1cc0 net/netfilter/ipvs/ip_vs_ctl.c:2389
nf_sockopt net/netfilter/nf_sockopt.c:106 [inline]
nf_setsockopt+0x67/0xc0 net/netfilter/nf_sockopt.c:115
ip_setsockopt+0x97/0xa0 net/ipv4/ip_sockglue.c:1261
udp_setsockopt+0x45/0x80 net/ipv4/udp.c:2406
sock_common_setsockopt+0x95/0xd0 net/core/sock.c:2975
SYSC_setsockopt net/socket.c:1849 [inline]
SyS_setsockopt+0x189/0x360 net/socket.c:1828
do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x446a69
RSP: 002b:00007fa1c3a64da8 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 0000000000446a69
RDX: 000000000000048b RSI: 0000000000000000 RDI: 0000000000000003
RBP: 00000000006e29fc R08: 0000000000000018 R09: 0000000000000000
R10: 00000000200000c0 R11: 0000000000000246 R12: 00000000006e29f8
R13: 00676e697279656b R14: 00007fa1c3a659c0 R15: 00000000006e2b60

[2]
IPVS: sync thread started: state = BACKUP, mcast_ifn = syz_tun, syncid = 4,
id = 0
IPVS: stopping backup sync thread 25415 ...
INFO: task syz-executor7:25421 blocked for more than 120 seconds.
Not tainted 4.16.0-rc6+ #284
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
syz-executor7 D23688 25421 4408 0x00000004
Call Trace:
context_switch kernel/sched/core.c:2862 [inline]
__schedule+0x8fb/0x1ec0 kernel/sched/core.c:3440
schedule+0xf5/0x430 kernel/sched/core.c:3499
schedule_timeout+0x1a3/0x230 kernel/time/timer.c:1777
do_wait_for_common kernel/sched/completion.c:86 [inline]
__wait_for_common kernel/sched/completion.c:107 [inline]
wait_for_common kernel/sched/completion.c:118 [inline]
wait_for_completion+0x415/0x770 kernel/sched/completion.c:139
kthread_stop+0x14a/0x7a0 kernel/kthread.c:530
stop_sync_thread+0x3d9/0x740 net/netfilter/ipvs/ip_vs_sync.c:1996
do_ip_vs_set_ctl+0x2b1/0x1cc0 net/netfilter/ipvs/ip_vs_ctl.c:2394
nf_sockopt net/netfilter/nf_sockopt.c:106 [inline]
nf_setsockopt+0x67/0xc0 net/netfilter/nf_sockopt.c:115
ip_setsockopt+0x97/0xa0 net/ipv4/ip_sockglue.c:1253
sctp_setsockopt+0x2ca/0x63e0 net/sctp/socket.c:4154
sock_common_setsockopt+0x95/0xd0 net/core/sock.c:3039
SYSC_setsockopt net/socket.c:1850 [inline]
SyS_setsockopt+0x189/0x360 net/socket.c:1829
do_syscall_64+0x281/0x940 arch/x86/entry/common.c:287
entry_SYSCALL_64_after_hwframe+0x42/0xb7
RIP: 0033:0x454889
RSP: 002b:00007fc927626c68 EFLAGS: 00000246 ORIG_RAX: 0000000000000036
RAX: ffffffffffffffda RBX: 00007fc9276276d4 RCX: 0000000000454889
RDX: 000000000000048c RSI: 0000000000000000 RDI: 0000000000000017
RBP: 000000000072bf58 R08: 0000000000000018 R09: 0000000000000000
R10: 0000000020000000 R11: 0000000000000246 R12: 00000000ffffffff
R13: 000000000000051c R14: 00000000006f9b40 R15: 0000000000000001

Showing all locks held in the system:
2 locks held by khungtaskd/868:
#0: (rcu_read_lock){....}, at: [<00000000a1a8f002>]
check_hung_uninterruptible_tasks kernel/hung_task.c:175 [inline]
#0: (rcu_read_lock){....}, at: [<00000000a1a8f002>] watchdog+0x1c5/0xd60
kernel/hung_task.c:249
#1: (tasklist_lock){.+.+}, at: [<0000000037c2f8f9>]
debug_show_all_locks+0xd3/0x3d0 kernel/locking/lockdep.c:4470
1 lock held by rsyslogd/4247:
#0: (&f->f_pos_lock){+.+.}, at: [<000000000d8d6983>]
__fdget_pos+0x12b/0x190 fs/file.c:765
2 locks held by getty/4338:
#0: (&tty->ldisc_sem){++++}, at: [<00000000bee98654>]
ldsem_down_read+0x37/0x40 drivers/tty/tty_ldsem.c:365
#1: (&ldata->atomic_read_lock){+.+.}, at: [<00000000c1d180aa>]
n_tty_read+0x2ef/0x1a40 drivers/tty/n_tty.c:2131
2 locks held by getty/4339:
#0: (&tty->ldisc_sem){++++}, at: [<00000000bee98654>]
ldsem_down_read+0x37/0x40 drivers/tty/tty_ldsem.c:365
#1: (&ldata->atomic_read_lock){+.+.}, at: [<00000000c1d180aa>]
n_tty_read+0x2ef/0x1a40 drivers/tty/n_tty.c:2131
2 locks held by getty/4340:
#0: (&tty->ldisc_sem){++++}, at: [<00000000bee98654>]
ldsem_down_read+0x37/0x40 drivers/tty/tty_ldsem.c:365
#1: (&ldata->atomic_read_lock){+.+.}, at: [<00000000c1d180aa>]
n_tty_read+0x2ef/0x1a40 drivers/tty/n_tty.c:2131
2 locks held by getty/4341:
#0: (&tty->ldisc_sem){++++}, at: [<00000000bee98654>]
ldsem_down_read+0x37/0x40 drivers/tty/tty_ldsem.c:365
#1: (&ldata->atomic_read_lock){+.+.}, at: [<00000000c1d180aa>]
n_tty_read+0x2ef/0x1a40 drivers/tty/n_tty.c:2131
2 locks held by getty/4342:
#0: (&tty->ldisc_sem){++++}, at: [<00000000bee98654>]
ldsem_down_read+0x37/0x40 drivers/tty/tty_ldsem.c:365
#1: (&ldata->atomic_read_lock){+.+.}, at: [<00000000c1d180aa>]
n_tty_read+0x2ef/0x1a40 drivers/tty/n_tty.c:2131
2 locks held by getty/4343:
#0: (&tty->ldisc_sem){++++}, at: [<00000000bee98654>]
ldsem_down_read+0x37/0x40 drivers/tty/tty_ldsem.c:365
#1: (&ldata->atomic_read_lock){+.+.}, at: [<00000000c1d180aa>]
n_tty_read+0x2ef/0x1a40 drivers/tty/n_tty.c:2131
2 locks held by getty/4344:
#0: (&tty->ldisc_sem){++++}, at: [<00000000bee98654>]
ldsem_down_read+0x37/0x40 drivers/tty/tty_ldsem.c:365
#1: (&ldata->atomic_read_lock){+.+.}, at: [<00000000c1d180aa>]
n_tty_read+0x2ef/0x1a40 drivers/tty/n_tty.c:2131
3 locks held by kworker/0:5/6494:
#0: ((wq_completion)"%s"("ipv6_addrconf")){+.+.}, at:
[<00000000a062b18e>] work_static include/linux/workqueue.h:198 [inline]
#0: ((wq_completion)"%s"("ipv6_addrconf")){+.+.}, at:
[<00000000a062b18e>] set_work_data kernel/workqueue.c:619 [inline]
#0: ((wq_completion)"%s"("ipv6_addrconf")){+.+.}, at:
[<00000000a062b18e>] set_work_pool_and_clear_pending kernel/workqueue.c:646
[inline]
#0: ((wq_completion)"%s"("ipv6_addrconf")){+.+.}, at:
[<00000000a062b18e>] process_one_work+0xb12/0x1bb0 kernel/workqueue.c:2084
#1: ((addr_chk_work).work){+.+.}, at: [<00000000278427d5>]
process_one_work+0xb89/0x1bb0 kernel/workqueue.c:2088
#2: (rtnl_mutex){+.+.}, at: [<00000000066e35ac>] rtnl_lock+0x17/0x20
net/core/rtnetlink.c:74
1 lock held by syz-executor7/25421:
#0: (ipvs->sync_mutex){+.+.}, at: [<00000000d414a689>]
do_ip_vs_set_ctl+0x277/0x1cc0 net/netfilter/ipvs/ip_vs_ctl.c:2393
2 locks held by syz-executor7/25427:
#0: (rtnl_mutex){+.+.}, at: [<00000000066e35ac>] rtnl_lock+0x17/0x20
net/core/rtnetlink.c:74
#1: (ipvs->sync_mutex){+.+.}, at: [<00000000e6d48489>]
do_ip_vs_set_ctl+0x10f8/0x1cc0 net/netfilter/ipvs/ip_vs_ctl.c:2388
1 lock held by syz-executor7/25435:
#0: (rtnl_mutex){+.+.}, at: [<00000000066e35ac>] rtnl_lock+0x17/0x20
net/core/rtnetlink.c:74
1 lock held by ipvs-b:2:0/25415:
#0: (rtnl_mutex){+.+.}, at: [<00000000066e35ac>] rtnl_lock+0x17/0x20
net/core/rtnetlink.c:74

Reported-and-tested-by: syzbot+a46d6abf9d56b1365a72@xxxxxxxxxxxxxxxxxxxxxxxxx
Reported-and-tested-by: syzbot+5fe074c01b2032ce9618@xxxxxxxxxxxxxxxxxxxxxxxxx
Fixes: e0b26cc997d5 ("ipvs: call rtnl_lock early")
Signed-off-by: Julian Anastasov <ja@xxxxxx>
Signed-off-by: Simon Horman <horms@xxxxxxxxxxxx>
Signed-off-by: Pablo Neira Ayuso <pablo@xxxxxxxxxxxxx>
Cc: Zubin Mithra <zsm@xxxxxxxxxxxx>
Cc: Guenter Roeck <groeck@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
net/netfilter/ipvs/ip_vs_ctl.c | 8 --
net/netfilter/ipvs/ip_vs_sync.c | 155 ++++++++++++++++++++--------------------
2 files changed, 80 insertions(+), 83 deletions(-)

--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2393,11 +2393,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cm
strlcpy(cfg.mcast_ifn, dm->mcast_ifn,
sizeof(cfg.mcast_ifn));
cfg.syncid = dm->syncid;
- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &cfg, dm->state);
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
} else {
mutex_lock(&ipvs->sync_mutex);
ret = stop_sync_thread(ipvs, dm->state);
@@ -3495,12 +3491,8 @@ static int ip_vs_genl_new_daemon(struct
if (ipvs->mixed_address_family_dests > 0)
return -EINVAL;

- rtnl_lock();
- mutex_lock(&ipvs->sync_mutex);
ret = start_sync_thread(ipvs, &c,
nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
- mutex_unlock(&ipvs->sync_mutex);
- rtnl_unlock();
return ret;
}

--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -48,6 +48,7 @@
#include <linux/kthread.h>
#include <linux/wait.h>
#include <linux/kernel.h>
+#include <linux/sched.h>

#include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */

@@ -1359,15 +1360,9 @@ static void set_mcast_pmtudisc(struct so
/*
* Specifiy default interface for outgoing multicasts
*/
-static int set_mcast_if(struct sock *sk, char *ifname)
+static int set_mcast_if(struct sock *sk, struct net_device *dev)
{
- struct net_device *dev;
struct inet_sock *inet = inet_sk(sk);
- struct net *net = sock_net(sk);
-
- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;

if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;
@@ -1395,19 +1390,14 @@ static int set_mcast_if(struct sock *sk,
* in the in_addr structure passed in as a parameter.
*/
static int
-join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname)
+join_mcast_group(struct sock *sk, struct in_addr *addr, struct net_device *dev)
{
- struct net *net = sock_net(sk);
struct ip_mreqn mreq;
- struct net_device *dev;
int ret;

memset(&mreq, 0, sizeof(mreq));
memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr));

- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;

@@ -1422,15 +1412,10 @@ join_mcast_group(struct sock *sk, struct

#ifdef CONFIG_IP_VS_IPV6
static int join_mcast_group6(struct sock *sk, struct in6_addr *addr,
- char *ifname)
+ struct net_device *dev)
{
- struct net *net = sock_net(sk);
- struct net_device *dev;
int ret;

- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if)
return -EINVAL;

@@ -1442,24 +1427,18 @@ static int join_mcast_group6(struct sock
}
#endif

-static int bind_mcastif_addr(struct socket *sock, char *ifname)
+static int bind_mcastif_addr(struct socket *sock, struct net_device *dev)
{
- struct net *net = sock_net(sock->sk);
- struct net_device *dev;
__be32 addr;
struct sockaddr_in sin;

- dev = __dev_get_by_name(net, ifname);
- if (!dev)
- return -ENODEV;
-
addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
if (!addr)
pr_err("You probably need to specify IP address on "
"multicast interface.\n");

IP_VS_DBG(7, "binding socket with (%s) %pI4\n",
- ifname, &addr);
+ dev->name, &addr);

/* Now bind the socket with the address of multicast interface */
sin.sin_family = AF_INET;
@@ -1492,7 +1471,8 @@ static void get_mcast_sockaddr(union ipv
/*
* Set up sending multicast socket over UDP
*/
-static struct socket *make_send_sock(struct netns_ipvs *ipvs, int id)
+static int make_send_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
@@ -1504,9 +1484,10 @@ static struct socket *make_send_sock(str
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
- result = set_mcast_if(sock->sk, ipvs->mcfg.mcast_ifn);
+ *sock_ret = sock;
+ result = set_mcast_if(sock->sk, dev);
if (result < 0) {
pr_err("Error setting outbound mcast interface\n");
goto error;
@@ -1521,7 +1502,7 @@ static struct socket *make_send_sock(str
set_sock_size(sock->sk, 1, result);

if (AF_INET == ipvs->mcfg.mcast_af)
- result = bind_mcastif_addr(sock, ipvs->mcfg.mcast_ifn);
+ result = bind_mcastif_addr(sock, dev);
else
result = 0;
if (result < 0) {
@@ -1537,19 +1518,18 @@ static struct socket *make_send_sock(str
goto error;
}

- return sock;
+ return 0;

error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}


/*
* Set up receiving multicast socket over UDP
*/
-static struct socket *make_receive_sock(struct netns_ipvs *ipvs, int id,
- int ifindex)
+static int make_receive_sock(struct netns_ipvs *ipvs, int id,
+ struct net_device *dev, struct socket **sock_ret)
{
/* multicast addr */
union ipvs_sockaddr mcast_addr;
@@ -1561,8 +1541,9 @@ static struct socket *make_receive_sock(
IPPROTO_UDP, &sock);
if (result < 0) {
pr_err("Error during creation of socket; terminating\n");
- return ERR_PTR(result);
+ goto error;
}
+ *sock_ret = sock;
/* it is equivalent to the REUSEADDR option in user-space */
sock->sk->sk_reuse = SK_CAN_REUSE;
result = sysctl_sync_sock_size(ipvs);
@@ -1570,7 +1551,7 @@ static struct socket *make_receive_sock(
set_sock_size(sock->sk, 0, result);

get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id);
- sock->sk->sk_bound_dev_if = ifindex;
+ sock->sk->sk_bound_dev_if = dev->ifindex;
result = sock->ops->bind(sock, (struct sockaddr *)&mcast_addr, salen);
if (result < 0) {
pr_err("Error binding to the multicast addr\n");
@@ -1581,21 +1562,20 @@ static struct socket *make_receive_sock(
#ifdef CONFIG_IP_VS_IPV6
if (ipvs->bcfg.mcast_af == AF_INET6)
result = join_mcast_group6(sock->sk, &mcast_addr.in6.sin6_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
else
#endif
result = join_mcast_group(sock->sk, &mcast_addr.in.sin_addr,
- ipvs->bcfg.mcast_ifn);
+ dev);
if (result < 0) {
pr_err("Error joining to the multicast group\n");
goto error;
}

- return sock;
+ return 0;

error:
- sock_release(sock);
- return ERR_PTR(result);
+ return result;
}


@@ -1780,13 +1760,12 @@ static int sync_thread_backup(void *data
int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
int state)
{
- struct ip_vs_sync_thread_data *tinfo;
+ struct ip_vs_sync_thread_data *tinfo = NULL;
struct task_struct **array = NULL, *task;
- struct socket *sock;
struct net_device *dev;
char *name;
int (*threadfn)(void *data);
- int id, count, hlen;
+ int id = 0, count, hlen;
int result = -ENOMEM;
u16 mtu, min_mtu;

@@ -1794,6 +1773,18 @@ int start_sync_thread(struct netns_ipvs
IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n",
sizeof(struct ip_vs_sync_conn_v0));

+ /* Do not hold one mutex and then to block on another */
+ for (;;) {
+ rtnl_lock();
+ if (mutex_trylock(&ipvs->sync_mutex))
+ break;
+ rtnl_unlock();
+ mutex_lock(&ipvs->sync_mutex);
+ if (rtnl_trylock())
+ break;
+ mutex_unlock(&ipvs->sync_mutex);
+ }
+
if (!ipvs->sync_state) {
count = clamp(sysctl_sync_ports(ipvs), 1, IPVS_SYNC_PORTS_MAX);
ipvs->threads_mask = count - 1;
@@ -1812,7 +1803,8 @@ int start_sync_thread(struct netns_ipvs
dev = __dev_get_by_name(ipvs->net, c->mcast_ifn);
if (!dev) {
pr_err("Unknown mcast interface: %s\n", c->mcast_ifn);
- return -ENODEV;
+ result = -ENODEV;
+ goto out_early;
}
hlen = (AF_INET6 == c->mcast_af) ?
sizeof(struct ipv6hdr) + sizeof(struct udphdr) :
@@ -1829,26 +1821,30 @@ int start_sync_thread(struct netns_ipvs
c->sync_maxlen = mtu - hlen;

if (state == IP_VS_STATE_MASTER) {
+ result = -EEXIST;
if (ipvs->ms)
- return -EEXIST;
+ goto out_early;

ipvs->mcfg = *c;
name = "ipvs-m:%d:%d";
threadfn = sync_thread_master;
} else if (state == IP_VS_STATE_BACKUP) {
+ result = -EEXIST;
if (ipvs->backup_threads)
- return -EEXIST;
+ goto out_early;

ipvs->bcfg = *c;
name = "ipvs-b:%d:%d";
threadfn = sync_thread_backup;
} else {
- return -EINVAL;
+ result = -EINVAL;
+ goto out_early;
}

if (state == IP_VS_STATE_MASTER) {
struct ipvs_master_sync_state *ms;

+ result = -ENOMEM;
ipvs->ms = kzalloc(count * sizeof(ipvs->ms[0]), GFP_KERNEL);
if (!ipvs->ms)
goto out;
@@ -1864,39 +1860,38 @@ int start_sync_thread(struct netns_ipvs
} else {
array = kzalloc(count * sizeof(struct task_struct *),
GFP_KERNEL);
+ result = -ENOMEM;
if (!array)
goto out;
}

- tinfo = NULL;
for (id = 0; id < count; id++) {
- if (state == IP_VS_STATE_MASTER)
- sock = make_send_sock(ipvs, id);
- else
- sock = make_receive_sock(ipvs, id, dev->ifindex);
- if (IS_ERR(sock)) {
- result = PTR_ERR(sock);
- goto outtinfo;
- }
+ result = -ENOMEM;
tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
if (!tinfo)
- goto outsocket;
+ goto out;
tinfo->ipvs = ipvs;
- tinfo->sock = sock;
+ tinfo->sock = NULL;
if (state == IP_VS_STATE_BACKUP) {
tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
GFP_KERNEL);
if (!tinfo->buf)
- goto outtinfo;
+ goto out;
} else {
tinfo->buf = NULL;
}
tinfo->id = id;
+ if (state == IP_VS_STATE_MASTER)
+ result = make_send_sock(ipvs, id, dev, &tinfo->sock);
+ else
+ result = make_receive_sock(ipvs, id, dev, &tinfo->sock);
+ if (result < 0)
+ goto out;

task = kthread_run(threadfn, tinfo, name, ipvs->gen, id);
if (IS_ERR(task)) {
result = PTR_ERR(task);
- goto outtinfo;
+ goto out;
}
tinfo = NULL;
if (state == IP_VS_STATE_MASTER)
@@ -1913,20 +1908,20 @@ int start_sync_thread(struct netns_ipvs
ipvs->sync_state |= state;
spin_unlock_bh(&ipvs->sync_buff_lock);

+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
+
/* increase the module use count */
ip_vs_use_count_inc();

return 0;

-outsocket:
- sock_release(sock);
-
-outtinfo:
- if (tinfo) {
- sock_release(tinfo->sock);
- kfree(tinfo->buf);
- kfree(tinfo);
- }
+out:
+ /* We do not need RTNL lock anymore, release it here so that
+ * sock_release below and in the kthreads can use rtnl_lock
+ * to leave the mcast group.
+ */
+ rtnl_unlock();
count = id;
while (count-- > 0) {
if (state == IP_VS_STATE_MASTER)
@@ -1934,13 +1929,23 @@ outtinfo:
else
kthread_stop(array[count]);
}
- kfree(array);
-
-out:
if (!(ipvs->sync_state & IP_VS_STATE_MASTER)) {
kfree(ipvs->ms);
ipvs->ms = NULL;
}
+ mutex_unlock(&ipvs->sync_mutex);
+ if (tinfo) {
+ if (tinfo->sock)
+ sock_release(tinfo->sock);
+ kfree(tinfo->buf);
+ kfree(tinfo);
+ }
+ kfree(array);
+ return result;
+
+out_early:
+ mutex_unlock(&ipvs->sync_mutex);
+ rtnl_unlock();
return result;
}