From 902c0b1887522a099aa4e1e6b4b476c2fe5dd13e Mon Sep 17 00:00:00 2001
From: Juhee Kang <claudiajkang@gmail.com>
Date: Mon, 4 Oct 2021 21:14:38 +0900
Subject: netfilter: xt_IDLETIMER: fix panic that occurs when timer_type has
 garbage value

Currently, when the rule related to IDLETIMER is added, idletimer_tg timer
structure is initialized by kmalloc on executing idletimer_tg_create
function. However, in this process timer->timer_type is not defined to
a specific value. Thus, timer->timer_type has garbage value and it occurs
kernel panic. So, this commit fixes the panic by initializing
timer->timer_type using kzalloc instead of kmalloc.

Test commands:
    # iptables -A OUTPUT -j IDLETIMER --timeout 1 --label test
    $ cat /sys/class/xt_idletimer/timers/test
      Killed

Splat looks like:
    BUG: KASAN: user-memory-access in alarm_expires_remaining+0x49/0x70
    Read of size 8 at addr 0000002e8c7bc4c8 by task cat/917
    CPU: 12 PID: 917 Comm: cat Not tainted 5.14.0+ #3 79940a339f71eb14fc81aee1757a20d5bf13eb0e
    Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.13.0-1ubuntu1.1 04/01/2014
    Call Trace:
     dump_stack_lvl+0x6e/0x9c
     kasan_report.cold+0x112/0x117
     ? alarm_expires_remaining+0x49/0x70
     __asan_load8+0x86/0xb0
     alarm_expires_remaining+0x49/0x70
     idletimer_tg_show+0xe5/0x19b [xt_IDLETIMER 11219304af9316a21bee5ba9d58f76a6b9bccc6d]
     dev_attr_show+0x3c/0x60
     sysfs_kf_seq_show+0x11d/0x1f0
     ? device_remove_bin_file+0x20/0x20
     kernfs_seq_show+0xa4/0xb0
     seq_read_iter+0x29c/0x750
     kernfs_fop_read_iter+0x25a/0x2c0
     ? __fsnotify_parent+0x3d1/0x570
     ? iov_iter_init+0x70/0x90
     new_sync_read+0x2a7/0x3d0
     ? __x64_sys_llseek+0x230/0x230
     ? rw_verify_area+0x81/0x150
     vfs_read+0x17b/0x240
     ksys_read+0xd9/0x180
     ? vfs_write+0x460/0x460
     ? do_syscall_64+0x16/0xc0
     ? lockdep_hardirqs_on+0x79/0x120
     __x64_sys_read+0x43/0x50
     do_syscall_64+0x3b/0xc0
     entry_SYSCALL_64_after_hwframe+0x44/0xae
    RIP: 0033:0x7f0cdc819142
    Code: c0 e9 c2 fe ff ff 50 48 8d 3d 3a ca 0a 00 e8 f5 19 02 00 0f 1f 44 00 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 0f 05 <48> 3d 00 f0 ff ff 77 56 c3 0f 1f 44 00 00 48 83 ec 28 48 89 54 24
    RSP: 002b:00007fff28eee5b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
    RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007f0cdc819142
    RDX: 0000000000020000 RSI: 00007f0cdc032000 RDI: 0000000000000003
    RBP: 00007f0cdc032000 R08: 00007f0cdc031010 R09: 0000000000000000
    R10: 0000000000000022 R11: 0000000000000246 R12: 00005607e9ee31f0
    R13: 0000000000000003 R14: 0000000000020000 R15: 0000000000020000

Fixes: 68983a354a65 ("netfilter: xtables: Add snapshot of hardidletimer target")
Signed-off-by: Juhee Kang <claudiajkang@gmail.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/xt_IDLETIMER.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net')

diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index 7b2f359bfce4..2f7cf5ecebf4 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -137,7 +137,7 @@ static int idletimer_tg_create(struct idletimer_tg_info *info)
 {
 	int ret;
 
-	info->timer = kmalloc(sizeof(*info->timer), GFP_KERNEL);
+	info->timer = kzalloc(sizeof(*info->timer), GFP_KERNEL);
 	if (!info->timer) {
 		ret = -ENOMEM;
 		goto out;
-- 
cgit v1.2.3


From 77076934afdcd46516caf18ed88b2f88025c9ddb Mon Sep 17 00:00:00 2001
From: Vegard Nossum <vegard.nossum@gmail.com>
Date: Tue, 5 Oct 2021 22:54:54 +0200
Subject: netfilter: Kconfig: use 'default y' instead of 'm' for bool config
 option

This option, NF_CONNTRACK_SECMARK, is a bool, so it can never be 'm'.

Fixes: 33b8e77605620 ("[NETFILTER]: Add CONFIG_NETFILTER_ADVANCED option")
Signed-off-by: Vegard Nossum <vegard.nossum@oracle.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net')

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 54395266339d..92a747896f80 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -109,7 +109,7 @@ config NF_CONNTRACK_MARK
 config NF_CONNTRACK_SECMARK
 	bool  'Connection tracking security mark support'
 	depends on NETWORK_SECMARK
-	default m if NETFILTER_ADVANCED=n
+	default y if NETFILTER_ADVANCED=n
 	help
 	  This option enables security markings to be applied to
 	  connections.  Typically they are copied to connections from
-- 
cgit v1.2.3


From 68a3765c659f809dcaac20030853a054646eb739 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 6 Oct 2021 16:20:34 +0200
Subject: netfilter: nf_tables: skip netdev events generated on netns removal

syzbot reported following (harmless) WARN:

 WARNING: CPU: 1 PID: 2648 at net/netfilter/core.c:468
  nft_netdev_unregister_hooks net/netfilter/nf_tables_api.c:230 [inline]
  nf_tables_unregister_hook include/net/netfilter/nf_tables.h:1090 [inline]
  __nft_release_basechain+0x138/0x640 net/netfilter/nf_tables_api.c:9524
  nft_netdev_event net/netfilter/nft_chain_filter.c:351 [inline]
  nf_tables_netdev_event+0x521/0x8a0 net/netfilter/nft_chain_filter.c:382

reproducer:
unshare -n bash -c 'ip link add br0 type bridge; nft add table netdev t ; \
 nft add chain netdev t ingress \{ type filter hook ingress device "br0" \
 priority 0\; policy drop\; \}'

Problem is that when netns device exit hooks create the UNREGISTER
event, the .pre_exit hook for nf_tables core has already removed the
base hook.  Notifier attempts to do this again.

The need to do base hook unregister unconditionally was needed in the past,
because notifier was last stage where reg->dev dereference was safe.

Now that nf_tables does the hook removal in .pre_exit, this isn't
needed anymore.

Reported-and-tested-by: syzbot+154bd5be532a63aa778b@syzkaller.appspotmail.com
Fixes: 767d1216bff825 ("netfilter: nftables: fix possible UAF over chains from packet path in netns")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_chain_filter.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

(limited to 'net')

diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index 5b02408a920b..3ced0eb6b7c3 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -342,12 +342,6 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev,
 		return;
 	}
 
-	/* UNREGISTER events are also happening on netns exit.
-	 *
-	 * Although nf_tables core releases all tables/chains, only this event
-	 * handler provides guarantee that hook->ops.dev is still accessible,
-	 * so we cannot skip exiting net namespaces.
-	 */
 	__nft_release_basechain(ctx);
 }
 
@@ -366,6 +360,9 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 	    event != NETDEV_CHANGENAME)
 		return NOTIFY_DONE;
 
+	if (!check_net(ctx.net))
+		return NOTIFY_DONE;
+
 	nft_net = nft_pernet(ctx.net);
 	mutex_lock(&nft_net->commit_mutex);
 	list_for_each_entry(table, &nft_net->tables, list) {
-- 
cgit v1.2.3


From a482c5e00a9b5a194085bcd372ac36141028becb Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Tue, 12 Oct 2021 08:18:13 -0400
Subject: netfilter: ip6t_rt: fix rt0_hdr parsing in rt_mt6

In rt_mt6(), when it's a nonlinear skb, the 1st skb_header_pointer()
only copies sizeof(struct ipv6_rt_hdr) to _route that rh points to.
The access by ((const struct rt0_hdr *)rh)->reserved will overflow
the buffer. So this access should be moved below the 2nd call to
skb_header_pointer().

Besides, after the 2nd skb_header_pointer(), its return value should
also be checked, othersize, *rp may cause null-pointer-ref.

v1->v2:
  - clean up some old debugging log.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv6/netfilter/ip6t_rt.c | 48 ++++++--------------------------------------
 1 file changed, 6 insertions(+), 42 deletions(-)

(limited to 'net')

diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c
index 733c83d38b30..4ad8b2032f1f 100644
--- a/net/ipv6/netfilter/ip6t_rt.c
+++ b/net/ipv6/netfilter/ip6t_rt.c
@@ -25,12 +25,7 @@ MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
 static inline bool
 segsleft_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert)
 {
-	bool r;
-	pr_debug("segsleft_match:%c 0x%x <= 0x%x <= 0x%x\n",
-		 invert ? '!' : ' ', min, id, max);
-	r = (id >= min && id <= max) ^ invert;
-	pr_debug(" result %s\n", r ? "PASS" : "FAILED");
-	return r;
+	return (id >= min && id <= max) ^ invert;
 }
 
 static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
@@ -65,30 +60,6 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 		return false;
 	}
 
-	pr_debug("IPv6 RT LEN %u %u ", hdrlen, rh->hdrlen);
-	pr_debug("TYPE %04X ", rh->type);
-	pr_debug("SGS_LEFT %u %02X\n", rh->segments_left, rh->segments_left);
-
-	pr_debug("IPv6 RT segsleft %02X ",
-		 segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1],
-				rh->segments_left,
-				!!(rtinfo->invflags & IP6T_RT_INV_SGS)));
-	pr_debug("type %02X %02X %02X ",
-		 rtinfo->rt_type, rh->type,
-		 (!(rtinfo->flags & IP6T_RT_TYP) ||
-		  ((rtinfo->rt_type == rh->type) ^
-		   !!(rtinfo->invflags & IP6T_RT_INV_TYP))));
-	pr_debug("len %02X %04X %02X ",
-		 rtinfo->hdrlen, hdrlen,
-		 !(rtinfo->flags & IP6T_RT_LEN) ||
-		  ((rtinfo->hdrlen == hdrlen) ^
-		   !!(rtinfo->invflags & IP6T_RT_INV_LEN)));
-	pr_debug("res %02X %02X %02X ",
-		 rtinfo->flags & IP6T_RT_RES,
-		 ((const struct rt0_hdr *)rh)->reserved,
-		 !((rtinfo->flags & IP6T_RT_RES) &&
-		   (((const struct rt0_hdr *)rh)->reserved)));
-
 	ret = (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1],
 			      rh->segments_left,
 			      !!(rtinfo->invflags & IP6T_RT_INV_SGS))) &&
@@ -107,22 +78,22 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 						       reserved),
 					sizeof(_reserved),
 					&_reserved);
+		if (!rp) {
+			par->hotdrop = true;
+			return false;
+		}
 
 		ret = (*rp == 0);
 	}
 
-	pr_debug("#%d ", rtinfo->addrnr);
 	if (!(rtinfo->flags & IP6T_RT_FST)) {
 		return ret;
 	} else if (rtinfo->flags & IP6T_RT_FST_NSTRICT) {
-		pr_debug("Not strict ");
 		if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) {
-			pr_debug("There isn't enough space\n");
 			return false;
 		} else {
 			unsigned int i = 0;
 
-			pr_debug("#%d ", rtinfo->addrnr);
 			for (temp = 0;
 			     temp < (unsigned int)((hdrlen - 8) / 16);
 			     temp++) {
@@ -138,26 +109,20 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 					return false;
 				}
 
-				if (ipv6_addr_equal(ap, &rtinfo->addrs[i])) {
-					pr_debug("i=%d temp=%d;\n", i, temp);
+				if (ipv6_addr_equal(ap, &rtinfo->addrs[i]))
 					i++;
-				}
 				if (i == rtinfo->addrnr)
 					break;
 			}
-			pr_debug("i=%d #%d\n", i, rtinfo->addrnr);
 			if (i == rtinfo->addrnr)
 				return ret;
 			else
 				return false;
 		}
 	} else {
-		pr_debug("Strict ");
 		if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) {
-			pr_debug("There isn't enough space\n");
 			return false;
 		} else {
-			pr_debug("#%d ", rtinfo->addrnr);
 			for (temp = 0; temp < rtinfo->addrnr; temp++) {
 				ap = skb_header_pointer(skb,
 							ptr
@@ -173,7 +138,6 @@ static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
 				if (!ipv6_addr_equal(ap, &rtinfo->addrs[temp]))
 					break;
 			}
-			pr_debug("temp=%d #%d\n", temp, rtinfo->addrnr);
 			if (temp == rtinfo->addrnr &&
 			    temp == (unsigned int)((hdrlen - 8) / 16))
 				return ret;
-- 
cgit v1.2.3


From 174c376278949c44aad89c514a6b5db6cee8db59 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Tue, 12 Oct 2021 16:54:37 +0200
Subject: netfilter: ipvs: make global sysctl readonly in non-init netns

Because the data pointer of net/ipv4/vs/debug_level is not updated per
netns, it must be marked as read-only in non-init netns.

Fixes: c6d2d445d8de ("IPVS: netns, final patch enabling network name space.")
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'net')

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c25097092a06..29ec3ef63edc 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -4090,6 +4090,11 @@ static int __net_init ip_vs_control_net_init_sysctl(struct netns_ipvs *ipvs)
 	tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode;
 	tbl[idx++].data = &ipvs->sysctl_schedule_icmp;
 	tbl[idx++].data = &ipvs->sysctl_ignore_tunneled;
+#ifdef CONFIG_IP_VS_DEBUG
+	/* Global sysctls must be ro in non-init netns */
+	if (!net_eq(net, &init_net))
+		tbl[idx++].mode = 0444;
+#endif
 
 	ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
 	if (ipvs->sysctl_hdr == NULL) {
-- 
cgit v1.2.3


From 86f1e3a8489f6a0232c1f3bc2bdb379f5ccdecec Mon Sep 17 00:00:00 2001
From: Leonard Crestez <cdleonard@gmail.com>
Date: Fri, 15 Oct 2021 10:26:04 +0300
Subject: tcp: md5: Fix overlap between vrf and non-vrf keys

With net.ipv4.tcp_l3mdev_accept=1 it is possible for a listen socket to
accept connection from the same client address in different VRFs. It is
also possible to set different MD5 keys for these clients which differ
only in the tcpm_l3index field.

This appears to work when distinguishing between different VRFs but not
between non-VRF and VRF connections. In particular:

 * tcp_md5_do_lookup_exact will match a non-vrf key against a vrf key.
This means that adding a key with l3index != 0 after a key with l3index
== 0 will cause the earlier key to be deleted. Both keys can be present
if the non-vrf key is added later.
 * _tcp_md5_do_lookup can match a non-vrf key before a vrf key. This
casues failures if the passwords differ.

Fix this by making tcp_md5_do_lookup_exact perform an actual exact
comparison on l3index and by making  __tcp_md5_do_lookup perfer
vrf-bound keys above other considerations like prefixlen.

Fixes: dea53bb80e07 ("tcp: Add l3index to tcp_md5sig_key and md5 functions")
Signed-off-by: Leonard Crestez <cdleonard@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

(limited to 'net')

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2e62e0d6373a..f64b6c8380e8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1037,6 +1037,20 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req)
 DEFINE_STATIC_KEY_FALSE(tcp_md5_needed);
 EXPORT_SYMBOL(tcp_md5_needed);
 
+static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new)
+{
+	if (!old)
+		return true;
+
+	/* l3index always overrides non-l3index */
+	if (old->l3index && new->l3index == 0)
+		return false;
+	if (old->l3index == 0 && new->l3index)
+		return true;
+
+	return old->prefixlen < new->prefixlen;
+}
+
 /* Find the Key structure for an address.  */
 struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
 					   const union tcp_md5_addr *addr,
@@ -1074,8 +1088,7 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
 			match = false;
 		}
 
-		if (match && (!best_match ||
-			      key->prefixlen > best_match->prefixlen))
+		if (match && better_md5_match(best_match, key))
 			best_match = key;
 	}
 	return best_match;
@@ -1105,7 +1118,7 @@ static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk,
 				 lockdep_sock_is_held(sk)) {
 		if (key->family != family)
 			continue;
-		if (key->l3index && key->l3index != l3index)
+		if (key->l3index != l3index)
 			continue;
 		if (!memcmp(&key->addr, addr, size) &&
 		    key->prefixlen == prefixlen)
-- 
cgit v1.2.3


From a76c2315bec7afeb9bafe776fe532106fa0a8b05 Mon Sep 17 00:00:00 2001
From: Leonard Crestez <cdleonard@gmail.com>
Date: Fri, 15 Oct 2021 10:26:05 +0300
Subject: tcp: md5: Allow MD5SIG_FLAG_IFINDEX with ifindex=0

Multiple VRFs are generally meant to be "separate" but right now md5
keys for the default VRF also affect connections inside VRFs if the IP
addresses happen to overlap.

So far the combination of TCP_MD5SIG_FLAG_IFINDEX with tcpm_ifindex == 0
was an error, accept this to mean "key only applies to default VRF".
This is what applications using VRFs for traffic separation want.

Signed-off-by: Leonard Crestez <cdleonard@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h   |  5 +++--
 net/ipv4/tcp_ipv4.c | 26 ++++++++++++++++----------
 net/ipv6/tcp_ipv6.c | 15 +++++++++------
 3 files changed, 28 insertions(+), 18 deletions(-)

(limited to 'net')

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 3166dc15d7d6..60c384569e9c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1576,6 +1576,7 @@ struct tcp_md5sig_key {
 	u8			keylen;
 	u8			family; /* AF_INET or AF_INET6 */
 	u8			prefixlen;
+	u8			flags;
 	union tcp_md5_addr	addr;
 	int			l3index; /* set if key added with L3 scope */
 	u8			key[TCP_MD5SIG_MAXKEYLEN];
@@ -1621,10 +1622,10 @@ struct tcp_md5sig_pool {
 int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
 			const struct sock *sk, const struct sk_buff *skb);
 int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
-		   int family, u8 prefixlen, int l3index,
+		   int family, u8 prefixlen, int l3index, u8 flags,
 		   const u8 *newkey, u8 newkeylen, gfp_t gfp);
 int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr,
-		   int family, u8 prefixlen, int l3index);
+		   int family, u8 prefixlen, int l3index, u8 flags);
 struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
 					 const struct sock *addr_sk);
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f64b6c8380e8..5b8ce65dfc06 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1073,7 +1073,7 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
 				 lockdep_sock_is_held(sk)) {
 		if (key->family != family)
 			continue;
-		if (key->l3index && key->l3index != l3index)
+		if (key->flags & TCP_MD5SIG_FLAG_IFINDEX && key->l3index != l3index)
 			continue;
 		if (family == AF_INET) {
 			mask = inet_make_mask(key->prefixlen);
@@ -1098,7 +1098,7 @@ EXPORT_SYMBOL(__tcp_md5_do_lookup);
 static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk,
 						      const union tcp_md5_addr *addr,
 						      int family, u8 prefixlen,
-						      int l3index)
+						      int l3index, u8 flags)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_key *key;
@@ -1118,6 +1118,8 @@ static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk,
 				 lockdep_sock_is_held(sk)) {
 		if (key->family != family)
 			continue;
+		if ((key->flags & TCP_MD5SIG_FLAG_IFINDEX) != (flags & TCP_MD5SIG_FLAG_IFINDEX))
+			continue;
 		if (key->l3index != l3index)
 			continue;
 		if (!memcmp(&key->addr, addr, size) &&
@@ -1142,7 +1144,7 @@ EXPORT_SYMBOL(tcp_v4_md5_lookup);
 
 /* This can be called on a newly created socket, from other files */
 int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
-		   int family, u8 prefixlen, int l3index,
+		   int family, u8 prefixlen, int l3index, u8 flags,
 		   const u8 *newkey, u8 newkeylen, gfp_t gfp)
 {
 	/* Add Key to the list */
@@ -1150,7 +1152,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct tcp_md5sig_info *md5sig;
 
-	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index);
+	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index, flags);
 	if (key) {
 		/* Pre-existing entry - just update that one.
 		 * Note that the key might be used concurrently.
@@ -1195,6 +1197,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	key->family = family;
 	key->prefixlen = prefixlen;
 	key->l3index = l3index;
+	key->flags = flags;
 	memcpy(&key->addr, addr,
 	       (family == AF_INET6) ? sizeof(struct in6_addr) :
 				      sizeof(struct in_addr));
@@ -1204,11 +1207,11 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 EXPORT_SYMBOL(tcp_md5_do_add);
 
 int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family,
-		   u8 prefixlen, int l3index)
+		   u8 prefixlen, int l3index, u8 flags)
 {
 	struct tcp_md5sig_key *key;
 
-	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index);
+	key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen, l3index, flags);
 	if (!key)
 		return -ENOENT;
 	hlist_del_rcu(&key->node);
@@ -1242,6 +1245,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname,
 	const union tcp_md5_addr *addr;
 	u8 prefixlen = 32;
 	int l3index = 0;
+	u8 flags;
 
 	if (optlen < sizeof(cmd))
 		return -EINVAL;
@@ -1252,6 +1256,8 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname,
 	if (sin->sin_family != AF_INET)
 		return -EINVAL;
 
+	flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX;
+
 	if (optname == TCP_MD5SIG_EXT &&
 	    cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) {
 		prefixlen = cmd.tcpm_prefixlen;
@@ -1259,7 +1265,7 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname,
 			return -EINVAL;
 	}
 
-	if (optname == TCP_MD5SIG_EXT &&
+	if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex &&
 	    cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) {
 		struct net_device *dev;
 
@@ -1280,12 +1286,12 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname,
 	addr = (union tcp_md5_addr *)&sin->sin_addr.s_addr;
 
 	if (!cmd.tcpm_keylen)
-		return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index);
+		return tcp_md5_do_del(sk, addr, AF_INET, prefixlen, l3index, flags);
 
 	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
 		return -EINVAL;
 
-	return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index,
+	return tcp_md5_do_add(sk, addr, AF_INET, prefixlen, l3index, flags,
 			      cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
 }
 
@@ -1609,7 +1615,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 		 * memory, then we end up not copying the key
 		 * across. Shucks.
 		 */
-		tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index,
+		tcp_md5_do_add(newsk, addr, AF_INET, 32, l3index, key->flags,
 			       key->key, key->keylen, GFP_ATOMIC);
 		sk_nocaps_add(newsk, NETIF_F_GSO_MASK);
 	}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 0ce52d46e4f8..b03dd02c9f13 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -599,6 +599,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
 	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&cmd.tcpm_addr;
 	int l3index = 0;
 	u8 prefixlen;
+	u8 flags;
 
 	if (optlen < sizeof(cmd))
 		return -EINVAL;
@@ -609,6 +610,8 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
 	if (sin6->sin6_family != AF_INET6)
 		return -EINVAL;
 
+	flags = cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX;
+
 	if (optname == TCP_MD5SIG_EXT &&
 	    cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) {
 		prefixlen = cmd.tcpm_prefixlen;
@@ -619,7 +622,7 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
 		prefixlen = ipv6_addr_v4mapped(&sin6->sin6_addr) ? 32 : 128;
 	}
 
-	if (optname == TCP_MD5SIG_EXT &&
+	if (optname == TCP_MD5SIG_EXT && cmd.tcpm_ifindex &&
 	    cmd.tcpm_flags & TCP_MD5SIG_FLAG_IFINDEX) {
 		struct net_device *dev;
 
@@ -640,9 +643,9 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
 		if (ipv6_addr_v4mapped(&sin6->sin6_addr))
 			return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
 					      AF_INET, prefixlen,
-					      l3index);
+					      l3index, flags);
 		return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
-				      AF_INET6, prefixlen, l3index);
+				      AF_INET6, prefixlen, l3index, flags);
 	}
 
 	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
@@ -650,12 +653,12 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname,
 
 	if (ipv6_addr_v4mapped(&sin6->sin6_addr))
 		return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr.s6_addr32[3],
-				      AF_INET, prefixlen, l3index,
+				      AF_INET, prefixlen, l3index, flags,
 				      cmd.tcpm_key, cmd.tcpm_keylen,
 				      GFP_KERNEL);
 
 	return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin6->sin6_addr,
-			      AF_INET6, prefixlen, l3index,
+			      AF_INET6, prefixlen, l3index, flags,
 			      cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL);
 }
 
@@ -1404,7 +1407,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 		 * across. Shucks.
 		 */
 		tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr,
-			       AF_INET6, 128, l3index, key->key, key->keylen,
+			       AF_INET6, 128, l3index, key->flags, key->key, key->keylen,
 			       sk_gfp_mask(sk, GFP_ATOMIC));
 	}
 #endif
-- 
cgit v1.2.3


From 0857d6f8c759d95f89d0436f86cdfd189ef99f20 Mon Sep 17 00:00:00 2001
From: Stephen Suryaputra <ssuryaextr@gmail.com>
Date: Thu, 14 Oct 2021 09:08:45 -0400
Subject: ipv6: When forwarding count rx stats on the orig netdev

Commit bdb7cc643fc9 ("ipv6: Count interface receive statistics on the
ingress netdev") does not work when ip6_forward() executes on the skbs
with vrf-enslaved netdev. Use IP6CB(skb)->iif to get to the right one.

Add a selftest script to verify.

Fixes: bdb7cc643fc9 ("ipv6: Count interface receive statistics on the ingress netdev")
Signed-off-by: Stephen Suryaputra <ssuryaextr@gmail.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://lore.kernel.org/r/20211014130845.410602-1-ssuryaextr@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_output.c                              |   3 +-
 tools/testing/selftests/net/forwarding/Makefile    |   1 +
 .../net/forwarding/forwarding.config.sample        |   2 +
 .../net/forwarding/ip6_forward_instats_vrf.sh      | 172 +++++++++++++++++++++
 tools/testing/selftests/net/forwarding/lib.sh      |   8 +
 5 files changed, 185 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh

(limited to 'net')

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 12f985f43bcc..2f044a49afa8 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -464,13 +464,14 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
 
 int ip6_forward(struct sk_buff *skb)
 {
-	struct inet6_dev *idev = __in6_dev_get_safely(skb->dev);
 	struct dst_entry *dst = skb_dst(skb);
 	struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct inet6_skb_parm *opt = IP6CB(skb);
 	struct net *net = dev_net(dst->dev);
+	struct inet6_dev *idev;
 	u32 mtu;
 
+	idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
 	if (net->ipv6.devconf_all->forwarding == 0)
 		goto error;
 
diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index d97bd6889446..72ee644d47bf 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -9,6 +9,7 @@ TEST_PROGS = bridge_igmp.sh \
 	gre_inner_v4_multipath.sh \
 	gre_inner_v6_multipath.sh \
 	gre_multipath.sh \
+	ip6_forward_instats_vrf.sh \
 	ip6gre_inner_v4_multipath.sh \
 	ip6gre_inner_v6_multipath.sh \
 	ipip_flat_gre_key.sh \
diff --git a/tools/testing/selftests/net/forwarding/forwarding.config.sample b/tools/testing/selftests/net/forwarding/forwarding.config.sample
index b802c14d2950..e5e2fbeca22e 100644
--- a/tools/testing/selftests/net/forwarding/forwarding.config.sample
+++ b/tools/testing/selftests/net/forwarding/forwarding.config.sample
@@ -39,3 +39,5 @@ NETIF_CREATE=yes
 # Timeout (in seconds) before ping exits regardless of how many packets have
 # been sent or received
 PING_TIMEOUT=5
+# IPv6 traceroute utility name.
+TROUTE6=traceroute6
diff --git a/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh
new file mode 100755
index 000000000000..9f5b3e2e5e95
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ip6_forward_instats_vrf.sh
@@ -0,0 +1,172 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test ipv6 stats on the incoming if when forwarding with VRF
+
+ALL_TESTS="
+	ipv6_ping
+	ipv6_in_too_big_err
+	ipv6_in_hdr_err
+	ipv6_in_addr_err
+	ipv6_in_discard
+"
+
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 2001:1:1::2/64
+	ip -6 route add vrf v$h1 2001:1:2::/64 via 2001:1:1::1
+}
+
+h1_destroy()
+{
+	ip -6 route del vrf v$h1 2001:1:2::/64 via 2001:1:1::1
+	simple_if_fini $h1 2001:1:1::2/64
+}
+
+router_create()
+{
+	vrf_create router
+	__simple_if_init $rtr1 router 2001:1:1::1/64
+	__simple_if_init $rtr2 router 2001:1:2::1/64
+	mtu_set $rtr2 1280
+}
+
+router_destroy()
+{
+	mtu_restore $rtr2
+	__simple_if_fini $rtr2 2001:1:2::1/64
+	__simple_if_fini $rtr1 2001:1:1::1/64
+	vrf_destroy router
+}
+
+h2_create()
+{
+	simple_if_init $h2 2001:1:2::2/64
+	ip -6 route add vrf v$h2 2001:1:1::/64 via 2001:1:2::1
+	mtu_set $h2 1280
+}
+
+h2_destroy()
+{
+	mtu_restore $h2
+	ip -6 route del vrf v$h2 2001:1:1::/64 via 2001:1:2::1
+	simple_if_fini $h2 2001:1:2::2/64
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rtr1=${NETIFS[p2]}
+
+	rtr2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+	h1_create
+	router_create
+	h2_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	h2_destroy
+	router_destroy
+	h1_destroy
+	vrf_cleanup
+}
+
+ipv6_in_too_big_err()
+{
+	RET=0
+
+	local t0=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors)
+	local vrf_name=$(master_name_get $h1)
+
+	# Send too big packets
+	ip vrf exec $vrf_name \
+		$PING6 -s 1300 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+
+	local t1=$(ipv6_stats_get $rtr1 Ip6InTooBigErrors)
+	test "$((t1 - t0))" -ne 0
+	check_err $?
+	log_test "Ip6InTooBigErrors"
+}
+
+ipv6_in_hdr_err()
+{
+	RET=0
+
+	local t0=$(ipv6_stats_get $rtr1 Ip6InHdrErrors)
+	local vrf_name=$(master_name_get $h1)
+
+	# Send packets with hop limit 1, easiest with traceroute6 as some ping6
+	# doesn't allow hop limit to be specified
+	ip vrf exec $vrf_name \
+		$TROUTE6 2001:1:2::2 &> /dev/null
+
+	local t1=$(ipv6_stats_get $rtr1 Ip6InHdrErrors)
+	test "$((t1 - t0))" -ne 0
+	check_err $?
+	log_test "Ip6InHdrErrors"
+}
+
+ipv6_in_addr_err()
+{
+	RET=0
+
+	local t0=$(ipv6_stats_get $rtr1 Ip6InAddrErrors)
+	local vrf_name=$(master_name_get $h1)
+
+	# Disable forwarding temporary while sending the packet
+	sysctl -qw net.ipv6.conf.all.forwarding=0
+	ip vrf exec $vrf_name \
+		$PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+	sysctl -qw net.ipv6.conf.all.forwarding=1
+
+	local t1=$(ipv6_stats_get $rtr1 Ip6InAddrErrors)
+	test "$((t1 - t0))" -ne 0
+	check_err $?
+	log_test "Ip6InAddrErrors"
+}
+
+ipv6_in_discard()
+{
+	RET=0
+
+	local t0=$(ipv6_stats_get $rtr1 Ip6InDiscards)
+	local vrf_name=$(master_name_get $h1)
+
+	# Add a policy to discard
+	ip xfrm policy add dst 2001:1:2::2/128 dir fwd action block
+	ip vrf exec $vrf_name \
+		$PING6 2001:1:2::2 -c 1 -w $PING_TIMEOUT &> /dev/null
+	ip xfrm policy del dst 2001:1:2::2/128 dir fwd
+
+	local t1=$(ipv6_stats_get $rtr1 Ip6InDiscards)
+	test "$((t1 - t0))" -ne 0
+	check_err $?
+	log_test "Ip6InDiscards"
+}
+ipv6_ping()
+{
+	RET=0
+
+	ping6_test $h1 2001:1:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index e7fc5c35b569..92087d423bcf 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -751,6 +751,14 @@ qdisc_parent_stats_get()
 	    | jq '.[] | select(.parent == "'"$parent"'") | '"$selector"
 }
 
+ipv6_stats_get()
+{
+	local dev=$1; shift
+	local stat=$1; shift
+
+	cat /proc/net/dev_snmp6/$dev | grep "^$stat" | cut -f2
+}
+
 humanize()
 {
 	local speed=$1; shift
-- 
cgit v1.2.3


From fac3cb82a54a4b7c49c932f96ef196cf5774344c Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@nvidia.com>
Date: Fri, 15 Oct 2021 12:05:46 +0300
Subject: net: bridge: mcast: use multicast_membership_interval for IGMPv3

When I added IGMPv3 support I decided to follow the RFC for computing
the GMI dynamically:
" 8.4. Group Membership Interval

   The Group Membership Interval is the amount of time that must pass
   before a multicast router decides there are no more members of a
   group or a particular source on a network.

   This value MUST be ((the Robustness Variable) times (the Query
   Interval)) plus (one Query Response Interval)."

But that actually is inconsistent with how the bridge used to compute it
for IGMPv2, where it was user-configurable that has a correct default value
but it is up to user-space to maintain it. This would make it consistent
with the other timer values which are also maintained correct by the user
instead of being dynamically computed. It also changes back to the previous
user-expected GMI behaviour for IGMPv3 queries which were supported before
IGMPv3 was added. Note that to properly compute it dynamically we would
need to add support for "Robustness Variable" which is currently missing.

Reported-by: Hangbin Liu <liuhangbin@gmail.com>
Fixes: 0436862e417e ("net: bridge: mcast: support for IGMPv3/MLDv2 ALLOW_NEW_SOURCES report")
Signed-off-by: Nikolay Aleksandrov <nikolay@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_private.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'net')

diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e8136db44462..37ca76406f1e 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -1125,9 +1125,7 @@ static inline unsigned long br_multicast_lmqt(const struct net_bridge_mcast *brm
 
 static inline unsigned long br_multicast_gmi(const struct net_bridge_mcast *brmctx)
 {
-	/* use the RFC default of 2 for QRV */
-	return 2 * brmctx->multicast_query_interval +
-	       brmctx->multicast_query_response_interval;
+	return brmctx->multicast_membership_interval;
 }
 
 static inline bool
-- 
cgit v1.2.3


From b504a884f6b5a77dac7d580ffa08e482f70d1a30 Mon Sep 17 00:00:00 2001
From: Ziyang Xuan <william.xuanziyang@huawei.com>
Date: Mon, 6 Sep 2021 17:42:19 +0800
Subject: can: j1939: j1939_tp_rxtimer(): fix errant alert in j1939_tp_rxtimer

When the session state is J1939_SESSION_DONE, j1939_tp_rxtimer() will
give an alert "rx timeout, send abort", but do nothing actually. Move
the alert into session active judgment condition, it is more
reasonable.

One of the scenarios is that j1939_tp_rxtimer() execute followed by
j1939_xtp_rx_abort_one(). After j1939_xtp_rx_abort_one(), the session
state is J1939_SESSION_DONE, then j1939_tp_rxtimer() give an alert.

Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/all/20210906094219.95924-1-william.xuanziyang@huawei.com
Cc: stable@vger.kernel.org
Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/j1939/transport.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'net')

diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index bb5c4b8979be..bfb0718d4587 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1237,12 +1237,11 @@ static enum hrtimer_restart j1939_tp_rxtimer(struct hrtimer *hrtimer)
 		session->err = -ETIME;
 		j1939_session_deactivate(session);
 	} else {
-		netdev_alert(priv->ndev, "%s: 0x%p: rx timeout, send abort\n",
-			     __func__, session);
-
 		j1939_session_list_lock(session->priv);
 		if (session->state >= J1939_SESSION_ACTIVE &&
 		    session->state < J1939_SESSION_ACTIVE_MAX) {
+			netdev_alert(priv->ndev, "%s: 0x%p: rx timeout, send abort\n",
+				     __func__, session);
 			j1939_session_get(session);
 			hrtimer_start(&session->rxtimer,
 				      ms_to_ktime(J1939_XTP_ABORT_TIMEOUT_MS),
-- 
cgit v1.2.3


From d9d52a3ebd284882f5562c88e55991add5d01586 Mon Sep 17 00:00:00 2001
From: Ziyang Xuan <william.xuanziyang@huawei.com>
Date: Sun, 26 Sep 2021 18:47:57 +0800
Subject: can: j1939: j1939_netdev_start(): fix UAF for rx_kref of j1939_priv

It will trigger UAF for rx_kref of j1939_priv as following.

        cpu0                                    cpu1
j1939_sk_bind(socket0, ndev0, ...)
j1939_netdev_start
                                        j1939_sk_bind(socket1, ndev0, ...)
                                        j1939_netdev_start
j1939_priv_set
                                        j1939_priv_get_by_ndev_locked
j1939_jsk_add
.....
j1939_netdev_stop
kref_put_lock(&priv->rx_kref, ...)
                                        kref_get(&priv->rx_kref, ...)
                                        REFCOUNT_WARN("addition on 0;...")

====================================================
refcount_t: addition on 0; use-after-free.
WARNING: CPU: 1 PID: 20874 at lib/refcount.c:25 refcount_warn_saturate+0x169/0x1e0
RIP: 0010:refcount_warn_saturate+0x169/0x1e0
Call Trace:
 j1939_netdev_start+0x68b/0x920
 j1939_sk_bind+0x426/0xeb0
 ? security_socket_bind+0x83/0xb0

The rx_kref's kref_get() and kref_put() should use j1939_netdev_lock to
protect.

Fixes: 9d71dd0c70099 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/all/20210926104757.2021540-1-william.xuanziyang@huawei.com
Cc: stable@vger.kernel.org
Reported-by: syzbot+85d9878b19c94f9019ad@syzkaller.appspotmail.com
Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/j1939/main.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'net')

diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index 08c8606cfd9c..9bc55ecb37f9 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -249,11 +249,14 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev)
 	struct j1939_priv *priv, *priv_new;
 	int ret;
 
-	priv = j1939_priv_get_by_ndev(ndev);
+	spin_lock(&j1939_netdev_lock);
+	priv = j1939_priv_get_by_ndev_locked(ndev);
 	if (priv) {
 		kref_get(&priv->rx_kref);
+		spin_unlock(&j1939_netdev_lock);
 		return priv;
 	}
+	spin_unlock(&j1939_netdev_lock);
 
 	priv = j1939_priv_create(ndev);
 	if (!priv)
@@ -269,10 +272,10 @@ struct j1939_priv *j1939_netdev_start(struct net_device *ndev)
 		/* Someone was faster than us, use their priv and roll
 		 * back our's.
 		 */
+		kref_get(&priv_new->rx_kref);
 		spin_unlock(&j1939_netdev_lock);
 		dev_put(ndev);
 		kfree(priv);
-		kref_get(&priv_new->rx_kref);
 		return priv_new;
 	}
 	j1939_priv_set(ndev, priv);
-- 
cgit v1.2.3


From 379743985ab6cfe2cbd32067cf4ed497baca6d06 Mon Sep 17 00:00:00 2001
From: Zhang Changzhong <zhangchangzhong@huawei.com>
Date: Thu, 30 Sep 2021 11:33:20 +0800
Subject: can: j1939: j1939_xtp_rx_dat_one(): cancel session if receive TP.DT
 with error length

According to SAE-J1939-21, the data length of TP.DT must be 8 bytes, so
cancel session when receive unexpected TP.DT message.

Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/all/1632972800-45091-1-git-send-email-zhangchangzhong@huawei.com
Cc: stable@vger.kernel.org
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/j1939/transport.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

(limited to 'net')

diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index bfb0718d4587..1ea6fee3d986 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1788,6 +1788,7 @@ static void j1939_xtp_rx_dpo(struct j1939_priv *priv, struct sk_buff *skb,
 static void j1939_xtp_rx_dat_one(struct j1939_session *session,
 				 struct sk_buff *skb)
 {
+	enum j1939_xtp_abort abort = J1939_XTP_ABORT_FAULT;
 	struct j1939_priv *priv = session->priv;
 	struct j1939_sk_buff_cb *skcb, *se_skcb;
 	struct sk_buff *se_skb = NULL;
@@ -1802,9 +1803,11 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
 
 	skcb = j1939_skb_to_cb(skb);
 	dat = skb->data;
-	if (skb->len <= 1)
+	if (skb->len != 8) {
 		/* makes no sense */
+		abort = J1939_XTP_ABORT_UNEXPECTED_DATA;
 		goto out_session_cancel;
+	}
 
 	switch (session->last_cmd) {
 	case 0xff:
@@ -1903,7 +1906,7 @@ static void j1939_xtp_rx_dat_one(struct j1939_session *session,
  out_session_cancel:
 	kfree_skb(se_skb);
 	j1939_session_timers_cancel(session);
-	j1939_session_cancel(session, J1939_XTP_ABORT_FAULT);
+	j1939_session_cancel(session, abort);
 	j1939_session_put(session);
 }
 
-- 
cgit v1.2.3


From a4fbe70c5cb746441d56b28cf88161d9e0e25378 Mon Sep 17 00:00:00 2001
From: Zhang Changzhong <zhangchangzhong@huawei.com>
Date: Thu, 14 Oct 2021 17:26:40 +0800
Subject: can: j1939: j1939_xtp_rx_rts_session_new(): abort TP less than 9
 bytes

The receiver should abort TP if 'total message size' in TP.CM_RTS and
TP.CM_BAM is less than 9 or greater than 1785 [1], but currently the
j1939 stack only checks the upper bound and the receiver will accept
the following broadcast message:

  vcan1  18ECFF00   [8]  20 08 00 02 FF 00 23 01
  vcan1  18EBFF00   [8]  01 00 00 00 00 00 00 00
  vcan1  18EBFF00   [8]  02 00 FF FF FF FF FF FF

This patch adds check for the lower bound and abort illegal TP.

[1] SAE-J1939-82 A.3.4 Row 2 and A.3.6 Row 6.

Fixes: 9d71dd0c7009 ("can: add support of SAE J1939 protocol")
Link: https://lore.kernel.org/all/1634203601-3460-1-git-send-email-zhangchangzhong@huawei.com
Cc: stable@vger.kernel.org
Signed-off-by: Zhang Changzhong <zhangchangzhong@huawei.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/j1939/j1939-priv.h | 1 +
 net/can/j1939/transport.c  | 2 ++
 2 files changed, 3 insertions(+)

(limited to 'net')

diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h
index f6df20808f5e..16af1a7f80f6 100644
--- a/net/can/j1939/j1939-priv.h
+++ b/net/can/j1939/j1939-priv.h
@@ -330,6 +330,7 @@ int j1939_session_activate(struct j1939_session *session);
 void j1939_tp_schedule_txtimer(struct j1939_session *session, int msec);
 void j1939_session_timers_cancel(struct j1939_session *session);
 
+#define J1939_MIN_TP_PACKET_SIZE 9
 #define J1939_MAX_TP_PACKET_SIZE (7 * 0xff)
 #define J1939_MAX_ETP_PACKET_SIZE (7 * 0x00ffffff)
 
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index 1ea6fee3d986..6c0a0ebdd024 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -1608,6 +1608,8 @@ j1939_session *j1939_xtp_rx_rts_session_new(struct j1939_priv *priv,
 			abort = J1939_XTP_ABORT_FAULT;
 		else if (len > priv->tp_max_packet_size)
 			abort = J1939_XTP_ABORT_RESOURCE;
+		else if (len < J1939_MIN_TP_PACKET_SIZE)
+			abort = J1939_XTP_ABORT_FAULT;
 	}
 
 	if (abort != J1939_XTP_NO_ABORT) {
-- 
cgit v1.2.3


From 9acf636215a6ce9362fe618e7da4913b8bfe84c8 Mon Sep 17 00:00:00 2001
From: Ziyang Xuan <william.xuanziyang@huawei.com>
Date: Sat, 9 Oct 2021 15:40:18 +0800
Subject: can: isotp: isotp_sendmsg(): add result check for
 wait_event_interruptible()

Using wait_event_interruptible() to wait for complete transmission,
but do not check the result of wait_event_interruptible() which can be
interrupted. It will result in TX buffer has multiple accessors and
the later process interferes with the previous process.

Following is one of the problems reported by syzbot.

=============================================================
WARNING: CPU: 0 PID: 0 at net/can/isotp.c:840 isotp_tx_timer_handler+0x2e0/0x4c0
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.13.0-rc7+ #68
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1 04/01/2014
RIP: 0010:isotp_tx_timer_handler+0x2e0/0x4c0
Call Trace:
 <IRQ>
 ? isotp_setsockopt+0x390/0x390
 __hrtimer_run_queues+0xb8/0x610
 hrtimer_run_softirq+0x91/0xd0
 ? rcu_read_lock_sched_held+0x4d/0x80
 __do_softirq+0xe8/0x553
 irq_exit_rcu+0xf8/0x100
 sysvec_apic_timer_interrupt+0x9e/0xc0
 </IRQ>
 asm_sysvec_apic_timer_interrupt+0x12/0x20

Add result check for wait_event_interruptible() in isotp_sendmsg()
to avoid multiple accessers for tx buffer.

Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol")
Link: https://lore.kernel.org/all/10ca695732c9dd267c76a3c30f37aefe1ff7e32f.1633764159.git.william.xuanziyang@huawei.com
Cc: stable@vger.kernel.org
Reported-by: syzbot+78bab6958a614b0c80b9@syzkaller.appspotmail.com
Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/isotp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'net')

diff --git a/net/can/isotp.c b/net/can/isotp.c
index caaa532ece94..2ac29c2b2ca6 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -865,7 +865,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 			return -EAGAIN;
 
 		/* wait for complete transmission of current pdu */
-		wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+		err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+		if (err)
+			return err;
 	}
 
 	if (!size || size > MAX_MSG_LENGTH)
-- 
cgit v1.2.3


From 43a08c3bdac4cb42eff8fe5e2278bffe0c5c3daa Mon Sep 17 00:00:00 2001
From: Ziyang Xuan <william.xuanziyang@huawei.com>
Date: Sat, 9 Oct 2021 15:40:30 +0800
Subject: can: isotp: isotp_sendmsg(): fix TX buffer concurrent access in
 isotp_sendmsg()

When isotp_sendmsg() concurrent, tx.state of all TX processes can be
ISOTP_IDLE. The conditions so->tx.state != ISOTP_IDLE and
wq_has_sleeper(&so->wait) can not protect TX buffer from being
accessed by multiple TX processes.

We can use cmpxchg() to try to modify tx.state to ISOTP_SENDING firstly.
If the modification of the previous process succeed, the later process
must wait tx.state to ISOTP_IDLE firstly. Thus, we can ensure TX buffer
is accessed by only one process at the same time. And we should also
restore the original tx.state at the subsequent error processes.

Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol")
Link: https://lore.kernel.org/all/c2517874fbdf4188585cf9ddf67a8fa74d5dbde5.1633764159.git.william.xuanziyang@huawei.com
Cc: stable@vger.kernel.org
Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com>
Acked-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/isotp.c | 46 +++++++++++++++++++++++++++++++---------------
 1 file changed, 31 insertions(+), 15 deletions(-)

(limited to 'net')

diff --git a/net/can/isotp.c b/net/can/isotp.c
index 2ac29c2b2ca6..d1f54273c0bb 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -121,7 +121,7 @@ enum {
 struct tpcon {
 	int idx;
 	int len;
-	u8 state;
+	u32 state;
 	u8 bs;
 	u8 sn;
 	u8 ll_dl;
@@ -848,6 +848,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 {
 	struct sock *sk = sock->sk;
 	struct isotp_sock *so = isotp_sk(sk);
+	u32 old_state = so->tx.state;
 	struct sk_buff *skb;
 	struct net_device *dev;
 	struct canfd_frame *cf;
@@ -860,47 +861,55 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 		return -EADDRNOTAVAIL;
 
 	/* we do not support multiple buffers - for now */
-	if (so->tx.state != ISOTP_IDLE || wq_has_sleeper(&so->wait)) {
-		if (msg->msg_flags & MSG_DONTWAIT)
-			return -EAGAIN;
+	if (cmpxchg(&so->tx.state, ISOTP_IDLE, ISOTP_SENDING) != ISOTP_IDLE ||
+	    wq_has_sleeper(&so->wait)) {
+		if (msg->msg_flags & MSG_DONTWAIT) {
+			err = -EAGAIN;
+			goto err_out;
+		}
 
 		/* wait for complete transmission of current pdu */
 		err = wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
 		if (err)
-			return err;
+			goto err_out;
 	}
 
-	if (!size || size > MAX_MSG_LENGTH)
-		return -EINVAL;
+	if (!size || size > MAX_MSG_LENGTH) {
+		err = -EINVAL;
+		goto err_out;
+	}
 
 	/* take care of a potential SF_DL ESC offset for TX_DL > 8 */
 	off = (so->tx.ll_dl > CAN_MAX_DLEN) ? 1 : 0;
 
 	/* does the given data fit into a single frame for SF_BROADCAST? */
 	if ((so->opt.flags & CAN_ISOTP_SF_BROADCAST) &&
-	    (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off))
-		return -EINVAL;
+	    (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off)) {
+		err = -EINVAL;
+		goto err_out;
+	}
 
 	err = memcpy_from_msg(so->tx.buf, msg, size);
 	if (err < 0)
-		return err;
+		goto err_out;
 
 	dev = dev_get_by_index(sock_net(sk), so->ifindex);
-	if (!dev)
-		return -ENXIO;
+	if (!dev) {
+		err = -ENXIO;
+		goto err_out;
+	}
 
 	skb = sock_alloc_send_skb(sk, so->ll.mtu + sizeof(struct can_skb_priv),
 				  msg->msg_flags & MSG_DONTWAIT, &err);
 	if (!skb) {
 		dev_put(dev);
-		return err;
+		goto err_out;
 	}
 
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 	can_skb_prv(skb)->skbcnt = 0;
 
-	so->tx.state = ISOTP_SENDING;
 	so->tx.len = size;
 	so->tx.idx = 0;
 
@@ -956,7 +965,7 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	if (err) {
 		pr_notice_once("can-isotp: %s: can_send_ret %pe\n",
 			       __func__, ERR_PTR(err));
-		return err;
+		goto err_out;
 	}
 
 	if (wait_tx_done) {
@@ -965,6 +974,13 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	}
 
 	return size;
+
+err_out:
+	so->tx.state = old_state;
+	if (so->tx.state == ISOTP_IDLE)
+		wake_up_interruptible(&so->wait);
+
+	return err;
 }
 
 static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
-- 
cgit v1.2.3


From d9aaaf223297f6146d9d7f36caca927c92ab855a Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Sun, 10 Oct 2021 11:24:39 -0700
Subject: netfilter: ebtables: allocate chainstack on CPU local nodes

Keep the per-CPU memory allocated for chainstacks local.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/bridge/netfilter/ebtables.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'net')

diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 83d1798dfbb4..ba045f35114d 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -926,7 +926,9 @@ static int translate_table(struct net *net, const char *name,
 			return -ENOMEM;
 		for_each_possible_cpu(i) {
 			newinfo->chainstack[i] =
-			  vmalloc(array_size(udc_cnt, sizeof(*(newinfo->chainstack[0]))));
+			  vmalloc_node(array_size(udc_cnt,
+					  sizeof(*(newinfo->chainstack[0]))),
+				       cpu_to_node(i));
 			if (!newinfo->chainstack[i]) {
 				while (i)
 					vfree(newinfo->chainstack[--i]);
-- 
cgit v1.2.3


From 2dc4e9e88cfcc38454d52b01ed3422238c134003 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@nvidia.com>
Date: Sun, 17 Oct 2021 14:58:51 +0300
Subject: net/sched: act_ct: Fix byte count on fragmented packets

First fragmented packets (frag offset = 0) byte len is zeroed
when stolen by ip_defrag(). And since act_ct update the stats
only afterwards (at end of execute), bytes aren't correctly
accounted for such packets.

To fix this, move stats update to start of action execute.

Fixes: b57dc7c13ea9 ("net/sched: Introduce action ct")
Signed-off-by: Paul Blakey <paulb@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ct.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'net')

diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index ad9df0cb4b98..90866ae45573 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -960,6 +960,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a,
 	tmpl = p->tmpl;
 
 	tcf_lastuse_update(&c->tcf_tm);
+	tcf_action_update_bstats(&c->common, skb);
 
 	if (clear) {
 		qdisc_skb_cb(skb)->post_ct = false;
@@ -1049,7 +1050,6 @@ out_push:
 
 	qdisc_skb_cb(skb)->post_ct = true;
 out_clear:
-	tcf_action_update_bstats(&c->common, skb);
 	if (defrag)
 		qdisc_skb_cb(skb)->pkt_len = skb->len;
 	return retval;
-- 
cgit v1.2.3


From d674a8f123b4096d85955c7eaabec688f29724c9 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Fri, 7 May 2021 11:18:39 +0200
Subject: can: isotp: isotp_sendmsg(): fix return error on FC timeout on TX
 path

When the a large chunk of data send and the receiver does not send a
Flow Control frame back in time, the sendmsg() does not return a error
code, but the number of bytes sent corresponding to the size of the
packet.

If a timeout occurs the isotp_tx_timer_handler() is fired, sets
sk->sk_err and calls the sk->sk_error_report() function. It was
wrongly expected that the error would be propagated to user space in
every case. For isotp_sendmsg() blocking on wait_event_interruptible()
this is not the case.

This patch fixes the problem by checking if sk->sk_err is set and
returning the error to user space.

Fixes: e057dd3fc20f ("can: add ISO 15765-2:2016 transport protocol")
Link: https://github.com/hartkopp/can-isotp/issues/42
Link: https://github.com/hartkopp/can-isotp/pull/43
Link: https://lore.kernel.org/all/20210507091839.1366379-1-mkl@pengutronix.de
Cc: stable@vger.kernel.org
Reported-by: Sottas Guillaume (LMB) <Guillaume.Sottas@liebherr.com>
Tested-by: Oliver Hartkopp <socketcan@hartkopp.net>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/isotp.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'net')

diff --git a/net/can/isotp.c b/net/can/isotp.c
index d1f54273c0bb..df6968b28bf4 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -971,6 +971,9 @@ static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	if (wait_tx_done) {
 		/* wait for complete transmission of current pdu */
 		wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+
+		if (sk->sk_err)
+			return -sk->sk_err;
 	}
 
 	return size;
-- 
cgit v1.2.3


From ba69fd9101f20a6d05a96ab743341d4e7b1a2178 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 18 Oct 2021 21:59:00 +0200
Subject: net: dsa: Fix an error handling path in 'dsa_switch_parse_ports_of()'

If we return before the end of the 'for_each_child_of_node()' iterator, the
reference taken on 'port' must be released.

Add the missing 'of_node_put()' calls.

Fixes: 83c0afaec7b7 ("net: dsa: Add new binding implementation")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/15d5310d1d55ad51c1af80775865306d92432e03.1634587046.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/dsa/dsa2.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'net')

diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index da18094b5a04..e9911b18bdbf 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -1374,12 +1374,15 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds,
 
 	for_each_available_child_of_node(ports, port) {
 		err = of_property_read_u32(port, "reg", &reg);
-		if (err)
+		if (err) {
+			of_node_put(port);
 			goto out_put_node;
+		}
 
 		if (reg >= ds->num_ports) {
 			dev_err(ds->dev, "port %pOF index %u exceeds num_ports (%zu)\n",
 				port, reg, ds->num_ports);
+			of_node_put(port);
 			err = -EINVAL;
 			goto out_put_node;
 		}
@@ -1387,8 +1390,10 @@ static int dsa_switch_parse_ports_of(struct dsa_switch *ds,
 		dp = dsa_to_port(ds, reg);
 
 		err = dsa_port_parse_of(dp, port);
-		if (err)
+		if (err) {
+			of_node_put(port);
 			goto out_put_node;
+		}
 	}
 
 out_put_node:
-- 
cgit v1.2.3