Skip to contentSkip to conversation

Netfilter/IPVS fixes for net

PATCH In review Pablo Neira Ayuso 2 participants 6 messages Jun 28, 2019

Subsystems (5)
lore
Share & tools
lore

Pablo Neira Ayuso

author maintainer
#0 lore raw

cover Netfilter/IPVS fixes for net

Hi,

The following patchset contains Netfilter fixes for net:

1) Fix memleak reported by syzkaller when registering IPVS hooks, patch from Julian Anastasov.

2) Fix memory leak in start_sync_thread, also from Julian.

3) Fix conntrack deletion via ctnetlink, from Felix Kaechele.

4) Fix reject for ICMP due to incorrect checksum handling, from He Zhe.

You can pull these changes from:

git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf.git

Thanks.

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

The following changes since commit 85f9aa7565bd79b039325f2c01af7ffa717924df:

inet: clear num_timeout reqsk_alloc() (2019-06-19 17:46:57 -0400)

are available in the git repository at:

git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf.git HEAD

for you to fetch changes up to 5d1549847c76b1ffcf8e388ef4d0f229bdd1d7e8:

netfilter: Fix remainder of pseudo-header protocol 0 (2019-06-28 19:30:50 +0200)

----------------------------------------------------------------
Felix Kaechele (1):
netfilter: ctnetlink: Fix regression in conntrack entry deletion

He Zhe (1):
netfilter: Fix remainder of pseudo-header protocol 0

Julian Anastasov (2):
ipvs: defer hook registration to avoid leaks
ipvs: fix tinfo memory leak in start_sync_thread

 include/net/ip_vs.h                     |   6 +-
 net/netfilter/ipvs/ip_vs_core.c         |  21 +++--
 net/netfilter/ipvs/ip_vs_ctl.c          |   4 -
 net/netfilter/ipvs/ip_vs_sync.c         | 134 +++++++++++++++++---------------
 net/netfilter/nf_conntrack_netlink.c    |   7 +-
 net/netfilter/nf_conntrack_proto_icmp.c |   2 +-
 net/netfilter/nf_nat_proto.c            |   2 +-
 net/netfilter/utils.c                   |   5 +-
 8 files changed, 99 insertions(+), 82 deletions(-)
author maintainer
#1 lore raw

PATCH 1/4 ipvs: defer hook registration to avoid leaks

From: Julian Anastasov <[email protected]>

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 [email protected]
Fixes 719c7d563c17 ("ipvs: Fix use-after-free in ip_vs_in")
---
 net/netfilter/ipvs/ip_vs_core.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)
net/netfilter/ipvs/ip_vs_core.c +14 -7
index 7138556b206b..d5103a9eb302 100644
@@ -2245,7 +2245,6 @@ 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)
@@ -2277,17 +2276,11 @@ 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:
@@ -2317,6 +2310,19 @@ 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);
@@ -2336,6 +2342,7 @@ 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,
 };
 
Signature · 1 line
2.11.0
author maintainer
#2 lore raw

PATCH 2/4 ipvs: fix tinfo memory leak in start_sync_thread

In reply to Pablo Neira Ayuso

From: Julian Anastasov <[email protected]>

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 [email protected]
Fixes 998e7a76804b ("ipvs: Use kthread_run() instead of doing a double-fork via kernel_thread()")
---
 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(-)
include/net/ip_vs.h +4 -2
index 2ac40135b576..b36a1df93e7c 100644
@@ -808,11 +808,12 @@ 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)
 
@@ -943,7 +944,8 @@ 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;
net/netfilter/ipvs/ip_vs_ctl.c +0 -4
index 776c87ed4813..741d91aa4a8d 100644
@@ -2396,9 +2396,7 @@ 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;
 	}
@@ -3515,10 +3513,8 @@ 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;
 }
 
net/netfilter/ipvs/ip_vs_sync.c +72 -62

269 lines not on this page · raw message

Signature · 1 line
2.11.0
author maintainer
#3 lore raw

PATCH 3/4 netfilter: ctnetlink: Fix regression in conntrack entry deletion

In reply to Pablo Neira Ayuso

From: Felix Kaechele <[email protected]>

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")
---
 net/netfilter/nf_conntrack_netlink.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)
net/netfilter/nf_conntrack_netlink.c +4 -3
index 7db79c1b8084..1b77444d5b52 100644
@@ -1256,7 +1256,6 @@ 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;
 
@@ -1266,11 +1265,13 @@ 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);
Signature · 1 line
2.11.0
author maintainer
#4 lore raw

PATCH 4/4 netfilter: Fix remainder of pseudo-header protocol 0

In reply to Pablo Neira Ayuso

From: He Zhe <[email protected]>

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")
---
 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(-)
net/netfilter/nf_conntrack_proto_icmp.c +1 -1
index 9becac953587..71a84a0517f3 100644
@@ -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;
 	}
net/netfilter/nf_nat_proto.c +1 -1
index 84f5c90a7f21..9f3e52ebd3b8 100644
@@ -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;
net/netfilter/utils.c +3 -2
index 06dc55590441..51b454d8fa9c 100644
@@ -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,
Signature · 1 line
2.11.0
maintainer
#5 lore raw
In reply to Pablo Neira Ayuso

From: Pablo Neira Ayuso <[email protected]>
Date: Fri, 28 Jun 2019 19:41:21 +0200

Quoted 7 lines

The following patchset contains Netfilter fixes for net:

1) Fix memleak reported by syzkaller when registering IPVS hooks, patch from Julian Anastasov.

2) Fix memory leak in start_sync_thread, also from Julian.

Quoted 8 lines

3) Fix conntrack deletion via ctnetlink, from Felix Kaechele.

4) Fix reject for ICMP due to incorrect checksum handling, from He Zhe.

You can pull these changes from:

git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf.git

Pulled, thanks.