[PATCH AUTOSEL 5.1 070/219] ipset: Fix memory accounting for hash types on resize

[PATCH AUTOSEL 5.1 070/219] ipset: Fix memory accounting for hash types on resize

[Sasha Levin]

From: Stefano Brivio <sbrivio@redhat.com>

[ Upstream commit 11921796f4799ca9c61c4b22cc54d84aa69f8a35 ]

If a fresh array block is allocated during resize, the current in-memory
set size should be increased by the size of the block, not replaced by it.

Before the fix, adding entries to a hash set type, leading to a table
resize, caused an inconsistent memory size to be reported. This becomes
more obvious when swapping sets with similar sizes:

  # cat hash_ip_size.sh
  #!/bin/sh
  FAIL_RETRIES=10

  tries=0
  while [ ${tries} -lt ${FAIL_RETRIES} ]; do
  	ipset create t1 hash:ip
  	for i in `seq 1 4345`; do
  		ipset add t1 1.2.$((i / 255)).$((i % 255))
  	done
  	t1_init="$(ipset list t1|sed -n 's/Size in memory: \(.*\)/\1/p')"

  	ipset create t2 hash:ip
  	for i in `seq 1 4360`; do
  		ipset add t2 1.2.$((i / 255)).$((i % 255))
  	done
  	t2_init="$(ipset list t2|sed -n 's/Size in memory: \(.*\)/\1/p')"

  	ipset swap t1 t2
  	t1_swap="$(ipset list t1|sed -n 's/Size in memory: \(.*\)/\1/p')"
  	t2_swap="$(ipset list t2|sed -n 's/Size in memory: \(.*\)/\1/p')"

  	ipset destroy t1
  	ipset destroy t2
  	tries=$((tries + 1))

  	if [ ${t1_init} -lt 10000 ] || [ ${t2_init} -lt 10000 ]; then
  		echo "FAIL after ${tries} tries:"
  		echo "T1 size ${t1_init}, after swap ${t1_swap}"
  		echo "T2 size ${t2_init}, after swap ${t2_swap}"
  		exit 1
  	fi
  done
  echo "PASS"
  # echo -n 'func hash_ip4_resize +p' > /sys/kernel/debug/dynamic_debug/control
  # ./hash_ip_size.sh
  [ 2035.018673] attempt to resize set t1 from 10 to 11, t 00000000fe6551fa
  [ 2035.078583] set t1 resized from 10 (00000000fe6551fa) to 11 (00000000172a0163)
  [ 2035.080353] Table destroy by resize 00000000fe6551fa
  FAIL after 4 tries:
  T1 size 9064, after swap 71128
  T2 size 71128, after swap 9064

Reported-by: NOYB <JunkYardMail1@Frontier.com>
Fixes: 9e41f26a505c ("netfilter: ipset: Count non-static extension memory for userspace")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/ipset/ip_set_hash_gen.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 2c9609929c71..455804456008 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -625,7 +625,7 @@ mtype_resize(struct ip_set *set, bool retried)
 					goto cleanup;
 				}
 				m->size = AHASH_INIT_SIZE;
-				extsize = ext_size(AHASH_INIT_SIZE, dsize);
+				extsize += ext_size(AHASH_INIT_SIZE, dsize);
 				RCU_INIT_POINTER(hbucket(t, key), m);
 			} else if (m->pos >= m->size) {
 				struct hbucket *ht;
-- 
2.20.1

[PATCH AUTOSEL 5.1 125/219] ipvs: defer hook registration to avoid leaks

[Sasha Levin]

From: Julian Anastasov <ja@ssi.bg>

[ Upstream commit cf47a0b882a4e5f6b34c7949d7b293e9287f1972 ]

syzkaller reports for memory leak when registering hooks [1]

As we moved the nf_unregister_net_hooks() call into
__ip_vs_dev_cleanup(), defer the nf_register_net_hooks()
call, so that hooks are allocated and freed from same
pernet_operations (ipvs_core_dev_ops).

[1]
BUG: memory leak
unreferenced object 0xffff88810acd8a80 (size 96):
 comm "syz-executor073", pid 7254, jiffies 4294950560 (age 22.250s)
 hex dump (first 32 bytes):
   02 00 00 00 00 00 00 00 50 8b bb 82 ff ff ff ff  ........P.......
   00 00 00 00 00 00 00 00 00 77 bb 82 ff ff ff ff  .........w......
 backtrace:
   [<0000000013db61f1>] kmemleak_alloc_recursive include/linux/kmemleak.h:55 [inline]
   [<0000000013db61f1>] slab_post_alloc_hook mm/slab.h:439 [inline]
   [<0000000013db61f1>] slab_alloc_node mm/slab.c:3269 [inline]
   [<0000000013db61f1>] kmem_cache_alloc_node_trace+0x15b/0x2a0 mm/slab.c:3597
   [<000000001a27307d>] __do_kmalloc_node mm/slab.c:3619 [inline]
   [<000000001a27307d>] __kmalloc_node+0x38/0x50 mm/slab.c:3627
   [<0000000025054add>] kmalloc_node include/linux/slab.h:590 [inline]
   [<0000000025054add>] kvmalloc_node+0x4a/0xd0 mm/util.c:431
   [<0000000050d1bc00>] kvmalloc include/linux/mm.h:637 [inline]
   [<0000000050d1bc00>] kvzalloc include/linux/mm.h:645 [inline]
   [<0000000050d1bc00>] allocate_hook_entries_size+0x3b/0x60 net/netfilter/core.c:61
   [<00000000e8abe142>] nf_hook_entries_grow+0xae/0x270 net/netfilter/core.c:128
   [<000000004b94797c>] __nf_register_net_hook+0x9a/0x170 net/netfilter/core.c:337
   [<00000000d1545cbc>] nf_register_net_hook+0x34/0xc0 net/netfilter/core.c:464
   [<00000000876c9b55>] nf_register_net_hooks+0x53/0xc0 net/netfilter/core.c:480
   [<000000002ea868e0>] __ip_vs_init+0xe8/0x170 net/netfilter/ipvs/ip_vs_core.c:2280
   [<000000002eb2d451>] ops_init+0x4c/0x140 net/core/net_namespace.c:130
   [<000000000284ec48>] setup_net+0xde/0x230 net/core/net_namespace.c:316
   [<00000000a70600fa>] copy_net_ns+0xf0/0x1e0 net/core/net_namespace.c:439
   [<00000000ff26c15e>] create_new_namespaces+0x141/0x2a0 kernel/nsproxy.c:107
   [<00000000b103dc79>] copy_namespaces+0xa1/0xe0 kernel/nsproxy.c:165
   [<000000007cc008a2>] copy_process.part.0+0x11fd/0x2150 kernel/fork.c:2035
   [<00000000c344af7c>] copy_process kernel/fork.c:1800 [inline]
   [<00000000c344af7c>] _do_fork+0x121/0x4f0 kernel/fork.c:2369

Reported-by: syzbot+722da59ccb264bc19910@syzkaller.appspotmail.com
Fixes: 719c7d563c17 ("ipvs: Fix use-after-free in ip_vs_in")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/ipvs/ip_vs_core.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 8ebf21149ec3..e72b51157cbb 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -2250,7 +2250,6 @@ static const struct nf_hook_ops ip_vs_ops[] = {
 static int __net_init __ip_vs_init(struct net *net)
 {
 	struct netns_ipvs *ipvs;
-	int ret;
 
 	ipvs = net_generic(net, ip_vs_net_id);
 	if (ipvs == NULL)
@@ -2282,17 +2281,11 @@ static int __net_init __ip_vs_init(struct net *net)
 	if (ip_vs_sync_net_init(ipvs) < 0)
 		goto sync_fail;
 
-	ret = nf_register_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
-	if (ret < 0)
-		goto hook_fail;
-
 	return 0;
 /*
  * Error handling
  */
 
-hook_fail:
-	ip_vs_sync_net_cleanup(ipvs);
 sync_fail:
 	ip_vs_conn_net_cleanup(ipvs);
 conn_fail:
@@ -2322,6 +2315,19 @@ static void __net_exit __ip_vs_cleanup(struct net *net)
 	net->ipvs = NULL;
 }
 
+static int __net_init __ip_vs_dev_init(struct net *net)
+{
+	int ret;
+
+	ret = nf_register_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops));
+	if (ret < 0)
+		goto hook_fail;
+	return 0;
+
+hook_fail:
+	return ret;
+}
+
 static void __net_exit __ip_vs_dev_cleanup(struct net *net)
 {
 	struct netns_ipvs *ipvs = net_ipvs(net);
@@ -2341,6 +2347,7 @@ static struct pernet_operations ipvs_core_ops = {
 };
 
 static struct pernet_operations ipvs_core_dev_ops = {
+	.init = __ip_vs_dev_init,
 	.exit = __ip_vs_dev_cleanup,
 };
 
-- 
2.20.1

[PATCH AUTOSEL 5.1 143/219] ipvs: fix tinfo memory leak in start_sync_thread

[Sasha Levin]

From: Julian Anastasov <ja@ssi.bg>

[ Upstream commit 5db7c8b9f9fc2aeec671ae3ca6375752c162e0e7 ]

syzkaller reports for memory leak in start_sync_thread [1]

As Eric points out, kthread may start and stop before the
threadfn function is called, so there is no chance the
data (tinfo in our case) to be released in thread.

Fix this by releasing tinfo in the controlling code instead.

[1]
BUG: memory leak
unreferenced object 0xffff8881206bf700 (size 32):
 comm "syz-executor761", pid 7268, jiffies 4294943441 (age 20.470s)
 hex dump (first 32 bytes):
   00 40 7c 09 81 88 ff ff 80 45 b8 21 81 88 ff ff  .@|......E.!....
   00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
 backtrace:
   [<0000000057619e23>] kmemleak_alloc_recursive include/linux/kmemleak.h:55 [inline]
   [<0000000057619e23>] slab_post_alloc_hook mm/slab.h:439 [inline]
   [<0000000057619e23>] slab_alloc mm/slab.c:3326 [inline]
   [<0000000057619e23>] kmem_cache_alloc_trace+0x13d/0x280 mm/slab.c:3553
   [<0000000086ce5479>] kmalloc include/linux/slab.h:547 [inline]
   [<0000000086ce5479>] start_sync_thread+0x5d2/0xe10 net/netfilter/ipvs/ip_vs_sync.c:1862
   [<000000001a9229cc>] do_ip_vs_set_ctl+0x4c5/0x780 net/netfilter/ipvs/ip_vs_ctl.c:2402
   [<00000000ece457c8>] nf_sockopt net/netfilter/nf_sockopt.c:106 [inline]
   [<00000000ece457c8>] nf_setsockopt+0x4c/0x80 net/netfilter/nf_sockopt.c:115
   [<00000000942f62d4>] ip_setsockopt net/ipv4/ip_sockglue.c:1258 [inline]
   [<00000000942f62d4>] ip_setsockopt+0x9b/0xb0 net/ipv4/ip_sockglue.c:1238
   [<00000000a56a8ffd>] udp_setsockopt+0x4e/0x90 net/ipv4/udp.c:2616
   [<00000000fa895401>] sock_common_setsockopt+0x38/0x50 net/core/sock.c:3130
   [<0000000095eef4cf>] __sys_setsockopt+0x98/0x120 net/socket.c:2078
   [<000000009747cf88>] __do_sys_setsockopt net/socket.c:2089 [inline]
   [<000000009747cf88>] __se_sys_setsockopt net/socket.c:2086 [inline]
   [<000000009747cf88>] __x64_sys_setsockopt+0x26/0x30 net/socket.c:2086
   [<00000000ded8ba80>] do_syscall_64+0x76/0x1a0 arch/x86/entry/common.c:301
   [<00000000893b4ac8>] entry_SYSCALL_64_after_hwframe+0x44/0xa9

Reported-by: syzbot+7e2e50c8adfccd2e5041@syzkaller.appspotmail.com
Suggested-by: Eric Biggers <ebiggers@kernel.org>
Fixes: 998e7a76804b ("ipvs: Use kthread_run() instead of doing a double-fork via kernel_thread()")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/ip_vs.h             |   6 +-
 net/netfilter/ipvs/ip_vs_ctl.c  |   4 -
 net/netfilter/ipvs/ip_vs_sync.c | 134 +++++++++++++++++---------------
 3 files changed, 76 insertions(+), 68 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 047f9a5ccaad..1790bb41c964 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -803,11 +803,12 @@ struct ipvs_master_sync_state {
 	struct ip_vs_sync_buff	*sync_buff;
 	unsigned long		sync_queue_len;
 	unsigned int		sync_queue_delay;
-	struct task_struct	*master_thread;
 	struct delayed_work	master_wakeup_work;
 	struct netns_ipvs	*ipvs;
 };
 
+struct ip_vs_sync_thread_data;
+
 /* How much time to keep dests in trash */
 #define IP_VS_DEST_TRASH_PERIOD		(120 * HZ)
 
@@ -938,7 +939,8 @@ struct netns_ipvs {
 	spinlock_t		sync_lock;
 	struct ipvs_master_sync_state *ms;
 	spinlock_t		sync_buff_lock;
-	struct task_struct	**backup_threads;
+	struct ip_vs_sync_thread_data *master_tinfo;
+	struct ip_vs_sync_thread_data *backup_tinfo;
 	int			threads_mask;
 	volatile int		sync_state;
 	struct mutex		sync_mutex;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 053cd96b9c76..179e9d11e41b 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2382,9 +2382,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
 			cfg.syncid = dm->syncid;
 			ret = start_sync_thread(ipvs, &cfg, dm->state);
 		} else {
-			mutex_lock(&ipvs->sync_mutex);
 			ret = stop_sync_thread(ipvs, dm->state);
-			mutex_unlock(&ipvs->sync_mutex);
 		}
 		goto out_dec;
 	}
@@ -3490,10 +3488,8 @@ static int ip_vs_genl_del_daemon(struct netns_ipvs *ipvs, struct nlattr **attrs)
 	if (!attrs[IPVS_DAEMON_ATTR_STATE])
 		return -EINVAL;
 
-	mutex_lock(&ipvs->sync_mutex);
 	ret = stop_sync_thread(ipvs,
 			       nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]));
-	mutex_unlock(&ipvs->sync_mutex);
 	return ret;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 2526be6b3d90..a4a78c4b06de 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -195,6 +195,7 @@ union ip_vs_sync_conn {
 #define IPVS_OPT_F_PARAM	(1 << (IPVS_OPT_PARAM-1))
 
 struct ip_vs_sync_thread_data {
+	struct task_struct *task;
 	struct netns_ipvs *ipvs;
 	struct socket *sock;
 	char *buf;
@@ -374,8 +375,11 @@ static inline void sb_queue_tail(struct netns_ipvs *ipvs,
 					      max(IPVS_SYNC_SEND_DELAY, 1));
 		ms->sync_queue_len++;
 		list_add_tail(&sb->list, &ms->sync_queue);
-		if ((++ms->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE)
-			wake_up_process(ms->master_thread);
+		if ((++ms->sync_queue_delay) == IPVS_SYNC_WAKEUP_RATE) {
+			int id = (int)(ms - ipvs->ms);
+
+			wake_up_process(ipvs->master_tinfo[id].task);
+		}
 	} else
 		ip_vs_sync_buff_release(sb);
 	spin_unlock(&ipvs->sync_lock);
@@ -1636,8 +1640,10 @@ static void master_wakeup_work_handler(struct work_struct *work)
 	spin_lock_bh(&ipvs->sync_lock);
 	if (ms->sync_queue_len &&
 	    ms->sync_queue_delay < IPVS_SYNC_WAKEUP_RATE) {
+		int id = (int)(ms - ipvs->ms);
+
 		ms->sync_queue_delay = IPVS_SYNC_WAKEUP_RATE;
-		wake_up_process(ms->master_thread);
+		wake_up_process(ipvs->master_tinfo[id].task);
 	}
 	spin_unlock_bh(&ipvs->sync_lock);
 }
@@ -1703,10 +1709,6 @@ static int sync_thread_master(void *data)
 	if (sb)
 		ip_vs_sync_buff_release(sb);
 
-	/* release the sending multicast socket */
-	sock_release(tinfo->sock);
-	kfree(tinfo);
-
 	return 0;
 }
 
@@ -1740,11 +1742,6 @@ static int sync_thread_backup(void *data)
 		}
 	}
 
-	/* release the sending multicast socket */
-	sock_release(tinfo->sock);
-	kfree(tinfo->buf);
-	kfree(tinfo);
-
 	return 0;
 }
 
@@ -1752,8 +1749,8 @@ 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 = NULL;
-	struct task_struct **array = NULL, *task;
+	struct ip_vs_sync_thread_data *ti = NULL, *tinfo;
+	struct task_struct *task;
 	struct net_device *dev;
 	char *name;
 	int (*threadfn)(void *data);
@@ -1822,7 +1819,7 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 		threadfn = sync_thread_master;
 	} else if (state == IP_VS_STATE_BACKUP) {
 		result = -EEXIST;
-		if (ipvs->backup_threads)
+		if (ipvs->backup_tinfo)
 			goto out_early;
 
 		ipvs->bcfg = *c;
@@ -1849,28 +1846,22 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 					  master_wakeup_work_handler);
 			ms->ipvs = ipvs;
 		}
-	} else {
-		array = kcalloc(count, sizeof(struct task_struct *),
-				GFP_KERNEL);
-		result = -ENOMEM;
-		if (!array)
-			goto out;
 	}
+	result = -ENOMEM;
+	ti = kcalloc(count, sizeof(struct ip_vs_sync_thread_data),
+		     GFP_KERNEL);
+	if (!ti)
+		goto out;
 
 	for (id = 0; id < count; id++) {
-		result = -ENOMEM;
-		tinfo = kmalloc(sizeof(*tinfo), GFP_KERNEL);
-		if (!tinfo)
-			goto out;
+		tinfo = &ti[id];
 		tinfo->ipvs = ipvs;
-		tinfo->sock = NULL;
 		if (state == IP_VS_STATE_BACKUP) {
+			result = -ENOMEM;
 			tinfo->buf = kmalloc(ipvs->bcfg.sync_maxlen,
 					     GFP_KERNEL);
 			if (!tinfo->buf)
 				goto out;
-		} else {
-			tinfo->buf = NULL;
 		}
 		tinfo->id = id;
 		if (state == IP_VS_STATE_MASTER)
@@ -1885,17 +1876,15 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 			result = PTR_ERR(task);
 			goto out;
 		}
-		tinfo = NULL;
-		if (state == IP_VS_STATE_MASTER)
-			ipvs->ms[id].master_thread = task;
-		else
-			array[id] = task;
+		tinfo->task = task;
 	}
 
 	/* mark as active */
 
-	if (state == IP_VS_STATE_BACKUP)
-		ipvs->backup_threads = array;
+	if (state == IP_VS_STATE_MASTER)
+		ipvs->master_tinfo = ti;
+	else
+		ipvs->backup_tinfo = ti;
 	spin_lock_bh(&ipvs->sync_buff_lock);
 	ipvs->sync_state |= state;
 	spin_unlock_bh(&ipvs->sync_buff_lock);
@@ -1910,29 +1899,31 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 
 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.
+	 * sock_release below can use rtnl_lock to leave the mcast group.
 	 */
 	rtnl_unlock();
-	count = id;
-	while (count-- > 0) {
-		if (state == IP_VS_STATE_MASTER)
-			kthread_stop(ipvs->ms[count].master_thread);
-		else
-			kthread_stop(array[count]);
+	id = min(id, count - 1);
+	if (ti) {
+		for (tinfo = ti + id; tinfo >= ti; tinfo--) {
+			if (tinfo->task)
+				kthread_stop(tinfo->task);
+		}
 	}
 	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);
+
+	/* No more mutexes, release socks */
+	if (ti) {
+		for (tinfo = ti + id; tinfo >= ti; tinfo--) {
+			if (tinfo->sock)
+				sock_release(tinfo->sock);
+			kfree(tinfo->buf);
+		}
+		kfree(ti);
 	}
-	kfree(array);
 	return result;
 
 out_early:
@@ -1944,15 +1935,18 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c,
 
 int stop_sync_thread(struct netns_ipvs *ipvs, int state)
 {
-	struct task_struct **array;
+	struct ip_vs_sync_thread_data *ti, *tinfo;
 	int id;
 	int retc = -EINVAL;
 
 	IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current));
 
+	mutex_lock(&ipvs->sync_mutex);
 	if (state == IP_VS_STATE_MASTER) {
+		retc = -ESRCH;
 		if (!ipvs->ms)
-			return -ESRCH;
+			goto err;
+		ti = ipvs->master_tinfo;
 
 		/*
 		 * The lock synchronizes with sb_queue_tail(), so that we don't
@@ -1971,38 +1965,56 @@ int stop_sync_thread(struct netns_ipvs *ipvs, int state)
 			struct ipvs_master_sync_state *ms = &ipvs->ms[id];
 			int ret;
 
+			tinfo = &ti[id];
 			pr_info("stopping master sync thread %d ...\n",
-				task_pid_nr(ms->master_thread));
+				task_pid_nr(tinfo->task));
 			cancel_delayed_work_sync(&ms->master_wakeup_work);
-			ret = kthread_stop(ms->master_thread);
+			ret = kthread_stop(tinfo->task);
 			if (retc >= 0)
 				retc = ret;
 		}
 		kfree(ipvs->ms);
 		ipvs->ms = NULL;
+		ipvs->master_tinfo = NULL;
 	} else if (state == IP_VS_STATE_BACKUP) {
-		if (!ipvs->backup_threads)
-			return -ESRCH;
+		retc = -ESRCH;
+		if (!ipvs->backup_tinfo)
+			goto err;
+		ti = ipvs->backup_tinfo;
 
 		ipvs->sync_state &= ~IP_VS_STATE_BACKUP;
-		array = ipvs->backup_threads;
 		retc = 0;
 		for (id = ipvs->threads_mask; id >= 0; id--) {
 			int ret;
 
+			tinfo = &ti[id];
 			pr_info("stopping backup sync thread %d ...\n",
-				task_pid_nr(array[id]));
-			ret = kthread_stop(array[id]);
+				task_pid_nr(tinfo->task));
+			ret = kthread_stop(tinfo->task);
 			if (retc >= 0)
 				retc = ret;
 		}
-		kfree(array);
-		ipvs->backup_threads = NULL;
+		ipvs->backup_tinfo = NULL;
+	} else {
+		goto err;
 	}
+	id = ipvs->threads_mask;
+	mutex_unlock(&ipvs->sync_mutex);
+
+	/* No more mutexes, release socks */
+	for (tinfo = ti + id; tinfo >= ti; tinfo--) {
+		if (tinfo->sock)
+			sock_release(tinfo->sock);
+		kfree(tinfo->buf);
+	}
+	kfree(ti);
 
 	/* decrease the module use count */
 	ip_vs_use_count_dec();
+	return retc;
 
+err:
+	mutex_unlock(&ipvs->sync_mutex);
 	return retc;
 }
 
@@ -2021,7 +2033,6 @@ void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs)
 {
 	int retc;
 
-	mutex_lock(&ipvs->sync_mutex);
 	retc = stop_sync_thread(ipvs, IP_VS_STATE_MASTER);
 	if (retc && retc != -ESRCH)
 		pr_err("Failed to stop Master Daemon\n");
@@ -2029,5 +2040,4 @@ void ip_vs_sync_net_cleanup(struct netns_ipvs *ipvs)
 	retc = stop_sync_thread(ipvs, IP_VS_STATE_BACKUP);
 	if (retc && retc != -ESRCH)
 		pr_err("Failed to stop Backup Daemon\n");
-	mutex_unlock(&ipvs->sync_mutex);
 }
-- 
2.20.1

[PATCH AUTOSEL 5.1 153/219] netfilter: ctnetlink: Fix regression in conntrack entry deletion

[Sasha Levin]

From: Felix Kaechele <felix@kaechele.ca>

[ Upstream commit e7600865db32b69deb0109b8254244dca592adcf ]

Commit f8e608982022 ("netfilter: ctnetlink: Resolve conntrack
L3-protocol flush regression") introduced a regression in which deletion
of conntrack entries would fail because the L3 protocol information
is replaced by AF_UNSPEC. As a result the search for the entry to be
deleted would turn up empty due to the tuple used to perform the search
is now different from the tuple used to initially set up the entry.

For flushing the conntrack table we do however want to keep the option
for nfgenmsg->version to have a non-zero value to allow for newer
user-space tools to request treatment under the new behavior. With that
it is possible to independently flush tables for a defined L3 protocol.
This was introduced with the enhancements in in commit 59c08c69c278
("netfilter: ctnetlink: Support L3 protocol-filter on flush").

Older user-space tools will retain the behavior of flushing all tables
regardless of defined L3 protocol.

Fixes: f8e608982022 ("netfilter: ctnetlink: Resolve conntrack L3-protocol flush regression")
Suggested-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Felix Kaechele <felix@kaechele.ca>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nf_conntrack_netlink.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index d2715b4d2e72..061bdab37b1a 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1254,7 +1254,6 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl,
 	struct nf_conntrack_tuple tuple;
 	struct nf_conn *ct;
 	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
-	u_int8_t u3 = nfmsg->version ? nfmsg->nfgen_family : AF_UNSPEC;
 	struct nf_conntrack_zone zone;
 	int err;
 
@@ -1264,11 +1263,13 @@ static int ctnetlink_del_conntrack(struct net *net, struct sock *ctnl,
 
 	if (cda[CTA_TUPLE_ORIG])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_ORIG,
-					    u3, &zone);
+					    nfmsg->nfgen_family, &zone);
 	else if (cda[CTA_TUPLE_REPLY])
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY,
-					    u3, &zone);
+					    nfmsg->nfgen_family, &zone);
 	else {
+		u_int8_t u3 = nfmsg->version ? nfmsg->nfgen_family : AF_UNSPEC;
+
 		return ctnetlink_flush_conntrack(net, cda,
 						 NETLINK_CB(skb).portid,
 						 nlmsg_report(nlh), u3);
-- 
2.20.1

[PATCH AUTOSEL 5.1 183/219] netfilter: Fix remainder of pseudo-header protocol 0

[Sasha Levin]

From: He Zhe <zhe.he@windriver.com>

[ Upstream commit 5d1549847c76b1ffcf8e388ef4d0f229bdd1d7e8 ]

Since v5.1-rc1, some types of packets do not get unreachable reply with the
following iptables setting. Fox example,

$ iptables -A INPUT -p icmp --icmp-type 8 -j REJECT
$ ping 127.0.0.1 -c 1
PING 127.0.0.1 (127.0.0.1) 56(84) bytes of data.
— 127.0.0.1 ping statistics —
1 packets transmitted, 0 received, 100% packet loss, time 0ms

We should have got the following reply from command line, but we did not.
From 127.0.0.1 icmp_seq=1 Destination Port Unreachable

Yi Zhao reported it and narrowed it down to:
7fc38225363d ("netfilter: reject: skip csum verification for protocols that don't support it"),

This is because nf_ip_checksum still expects pseudo-header protocol type 0 for
packets that are of neither TCP or UDP, and thus ICMP packets are mistakenly
treated as TCP/UDP.

This patch corrects the conditions in nf_ip_checksum and all other places that
still call it with protocol 0.

Fixes: 7fc38225363d ("netfilter: reject: skip csum verification for protocols that don't support it")
Reported-by: Yi Zhao <yi.zhao@windriver.com>
Signed-off-by: He Zhe <zhe.he@windriver.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nf_conntrack_proto_icmp.c | 2 +-
 net/netfilter/nf_nat_proto.c            | 2 +-
 net/netfilter/utils.c                   | 5 +++--
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c
index 9becac953587..71a84a0517f3 100644
--- a/net/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/netfilter/nf_conntrack_proto_icmp.c
@@ -221,7 +221,7 @@ int nf_conntrack_icmpv4_error(struct nf_conn *tmpl,
 	/* See ip_conntrack_proto_tcp.c */
 	if (state->net->ct.sysctl_checksum &&
 	    state->hook == NF_INET_PRE_ROUTING &&
-	    nf_ip_checksum(skb, state->hook, dataoff, 0)) {
+	    nf_ip_checksum(skb, state->hook, dataoff, IPPROTO_ICMP)) {
 		icmp_error_log(skb, state, "bad hw icmp checksum");
 		return -NF_ACCEPT;
 	}
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 62743da3004f..0b0efbb953bf 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -567,7 +567,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 
 	if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
 		return 0;
-	if (nf_ip_checksum(skb, hooknum, hdrlen, 0))
+	if (nf_ip_checksum(skb, hooknum, hdrlen, IPPROTO_ICMP))
 		return 0;
 
 	inside = (void *)skb->data + hdrlen;
diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c
index 06dc55590441..51b454d8fa9c 100644
--- a/net/netfilter/utils.c
+++ b/net/netfilter/utils.c
@@ -17,7 +17,8 @@ __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
 	case CHECKSUM_COMPLETE:
 		if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
 			break;
-		if ((protocol == 0 && !csum_fold(skb->csum)) ||
+		if ((protocol != IPPROTO_TCP && protocol != IPPROTO_UDP &&
+		    !csum_fold(skb->csum)) ||
 		    !csum_tcpudp_magic(iph->saddr, iph->daddr,
 				       skb->len - dataoff, protocol,
 				       skb->csum)) {
@@ -26,7 +27,7 @@ __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
 		}
 		/* fall through */
 	case CHECKSUM_NONE:
-		if (protocol == 0)
+		if (protocol != IPPROTO_TCP && protocol != IPPROTO_UDP)
 			skb->csum = 0;
 		else
 			skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
-- 
2.20.1