[PATCH AUTOSEL 5.4 01/14] net/802/mrp: fix memleak in mrp_request_join()

[PATCH AUTOSEL 5.4 01/14] net/802/mrp: fix memleak in mrp_request_join()

[Sasha Levin]

From: Yang Yingliang <yangyingliang@huawei.com>

[ Upstream commit 996af62167d0e0ec69b938a3561e96f84ffff1aa ]

I got kmemleak report when doing fuzz test:

BUG: memory leak
unreferenced object 0xffff88810c239500 (size 64):
comm "syz-executor940", pid 882, jiffies 4294712870 (age 14.631s)
hex dump (first 32 bytes):
01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................
00 00 00 00 00 00 00 00 01 00 00 00 01 02 00 04 ................
backtrace:
[<00000000a323afa4>] slab_alloc_node mm/slub.c:2972 [inline]
[<00000000a323afa4>] slab_alloc mm/slub.c:2980 [inline]
[<00000000a323afa4>] __kmalloc+0x167/0x340 mm/slub.c:4130
[<000000005034ca11>] kmalloc include/linux/slab.h:595 [inline]
[<000000005034ca11>] mrp_attr_create net/802/mrp.c:276 [inline]
[<000000005034ca11>] mrp_request_join+0x265/0x550 net/802/mrp.c:530
[<00000000fcfd81f3>] vlan_mvrp_request_join+0x145/0x170 net/8021q/vlan_mvrp.c:40
[<000000009258546e>] vlan_dev_open+0x477/0x890 net/8021q/vlan_dev.c:292
[<0000000059acd82b>] __dev_open+0x281/0x410 net/core/dev.c:1609
[<000000004e6dc695>] __dev_change_flags+0x424/0x560 net/core/dev.c:8767
[<00000000471a09af>] rtnl_configure_link+0xd9/0x210 net/core/rtnetlink.c:3122
[<0000000037a4672b>] __rtnl_newlink+0xe08/0x13e0 net/core/rtnetlink.c:3448
[<000000008d5d0fda>] rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3488
[<000000004882fe39>] rtnetlink_rcv_msg+0x369/0xa10 net/core/rtnetlink.c:5552
[<00000000907e6c54>] netlink_rcv_skb+0x134/0x3d0 net/netlink/af_netlink.c:2504
[<00000000e7d7a8c4>] netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline]
[<00000000e7d7a8c4>] netlink_unicast+0x4a0/0x6a0 net/netlink/af_netlink.c:1340
[<00000000e0645d50>] netlink_sendmsg+0x78e/0xc90 net/netlink/af_netlink.c:1929
[<00000000c24559b7>] sock_sendmsg_nosec net/socket.c:654 [inline]
[<00000000c24559b7>] sock_sendmsg+0x139/0x170 net/socket.c:674
[<00000000fc210bc2>] ____sys_sendmsg+0x658/0x7d0 net/socket.c:2350
[<00000000be4577b5>] ___sys_sendmsg+0xf8/0x170 net/socket.c:2404

Calling mrp_request_leave() after mrp_request_join(), the attr->state
is set to MRP_APPLICANT_VO, mrp_attr_destroy() won't be called in last
TX event in mrp_uninit_applicant(), the attr of applicant will be leaked.
To fix this leak, iterate and free each attr of applicant before rerturning
from mrp_uninit_applicant().

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/802/mrp.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/net/802/mrp.c b/net/802/mrp.c
index 2cfdfbfbb2ed..5b804dbe2d08 100644
--- a/net/802/mrp.c
+++ b/net/802/mrp.c
@@ -292,6 +292,19 @@ static void mrp_attr_destroy(struct mrp_applicant *app, struct mrp_attr *attr)
 	kfree(attr);
 }
 
+static void mrp_attr_destroy_all(struct mrp_applicant *app)
+{
+	struct rb_node *node, *next;
+	struct mrp_attr *attr;
+
+	for (node = rb_first(&app->mad);
+	     next = node ? rb_next(node) : NULL, node != NULL;
+	     node = next) {
+		attr = rb_entry(node, struct mrp_attr, node);
+		mrp_attr_destroy(app, attr);
+	}
+}
+
 static int mrp_pdu_init(struct mrp_applicant *app)
 {
 	struct sk_buff *skb;
@@ -895,6 +908,7 @@ void mrp_uninit_applicant(struct net_device *dev, struct mrp_application *appl)
 
 	spin_lock_bh(&app->lock);
 	mrp_mad_event(app, MRP_EVENT_TX);
+	mrp_attr_destroy_all(app);
 	mrp_pdu_queue(app);
 	spin_unlock_bh(&app->lock);
 
-- 
2.30.2

[PATCH AUTOSEL 5.4 02/14] net/802/garp: fix memleak in garp_request_join()

[Sasha Levin]

From: Yang Yingliang <yangyingliang@huawei.com>

[ Upstream commit 42ca63f980842918560b25f0244307fd83b4777c ]

I got kmemleak report when doing fuzz test:

BUG: memory leak
unreferenced object 0xffff88810c909b80 (size 64):
  comm "syz", pid 957, jiffies 4295220394 (age 399.090s)
  hex dump (first 32 bytes):
    01 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 08 00 00 00 01 02 00 04  ................
  backtrace:
    [<00000000ca1f2e2e>] garp_request_join+0x285/0x3d0
    [<00000000bf153351>] vlan_gvrp_request_join+0x15b/0x190
    [<0000000024005e72>] vlan_dev_open+0x706/0x980
    [<00000000dc20c4d4>] __dev_open+0x2bb/0x460
    [<0000000066573004>] __dev_change_flags+0x501/0x650
    [<0000000035b42f83>] rtnl_configure_link+0xee/0x280
    [<00000000a5e69de0>] __rtnl_newlink+0xed5/0x1550
    [<00000000a5258f4a>] rtnl_newlink+0x66/0x90
    [<00000000506568ee>] rtnetlink_rcv_msg+0x439/0xbd0
    [<00000000b7eaeae1>] netlink_rcv_skb+0x14d/0x420
    [<00000000c373ce66>] netlink_unicast+0x550/0x750
    [<00000000ec74ce74>] netlink_sendmsg+0x88b/0xda0
    [<00000000381ff246>] sock_sendmsg+0xc9/0x120
    [<000000008f6a2db3>] ____sys_sendmsg+0x6e8/0x820
    [<000000008d9c1735>] ___sys_sendmsg+0x145/0x1c0
    [<00000000aa39dd8b>] __sys_sendmsg+0xfe/0x1d0

Calling garp_request_leave() after garp_request_join(), the attr->state
is set to GARP_APPLICANT_VO, garp_attr_destroy() won't be called in last
transmit event in garp_uninit_applicant(), the attr of applicant will be
leaked. To fix this leak, iterate and free each attr of applicant before
rerturning from garp_uninit_applicant().

Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/802/garp.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/net/802/garp.c b/net/802/garp.c
index 400bd857e5f5..f6012f8e59f0 100644
--- a/net/802/garp.c
+++ b/net/802/garp.c
@@ -203,6 +203,19 @@ static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr
 	kfree(attr);
 }
 
+static void garp_attr_destroy_all(struct garp_applicant *app)
+{
+	struct rb_node *node, *next;
+	struct garp_attr *attr;
+
+	for (node = rb_first(&app->gid);
+	     next = node ? rb_next(node) : NULL, node != NULL;
+	     node = next) {
+		attr = rb_entry(node, struct garp_attr, node);
+		garp_attr_destroy(app, attr);
+	}
+}
+
 static int garp_pdu_init(struct garp_applicant *app)
 {
 	struct sk_buff *skb;
@@ -609,6 +622,7 @@ void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl
 
 	spin_lock_bh(&app->lock);
 	garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU);
+	garp_attr_destroy_all(app);
 	garp_pdu_queue(app);
 	spin_unlock_bh(&app->lock);
 
-- 
2.30.2

[PATCH AUTOSEL 5.4 03/14] net: annotate data race around sk_ll_usec

[Sasha Levin]

From: Eric Dumazet <edumazet@google.com>

[ Upstream commit 0dbffbb5335a1e3aa6855e4ee317e25e669dd302 ]

sk_ll_usec is read locklessly from sk_can_busy_loop()
while another thread can change its value in sock_setsockopt()

This is correct but needs annotations.

BUG: KCSAN: data-race in __skb_try_recv_datagram / sock_setsockopt

write to 0xffff88814eb5f904 of 4 bytes by task 14011 on cpu 0:
 sock_setsockopt+0x1287/0x2090 net/core/sock.c:1175
 __sys_setsockopt+0x14f/0x200 net/socket.c:2100
 __do_sys_setsockopt net/socket.c:2115 [inline]
 __se_sys_setsockopt net/socket.c:2112 [inline]
 __x64_sys_setsockopt+0x62/0x70 net/socket.c:2112
 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47
 entry_SYSCALL_64_after_hwframe+0x44/0xae

read to 0xffff88814eb5f904 of 4 bytes by task 14001 on cpu 1:
 sk_can_busy_loop include/net/busy_poll.h:41 [inline]
 __skb_try_recv_datagram+0x14f/0x320 net/core/datagram.c:273
 unix_dgram_recvmsg+0x14c/0x870 net/unix/af_unix.c:2101
 unix_seqpacket_recvmsg+0x5a/0x70 net/unix/af_unix.c:2067
 ____sys_recvmsg+0x15d/0x310 include/linux/uio.h:244
 ___sys_recvmsg net/socket.c:2598 [inline]
 do_recvmmsg+0x35c/0x9f0 net/socket.c:2692
 __sys_recvmmsg net/socket.c:2771 [inline]
 __do_sys_recvmmsg net/socket.c:2794 [inline]
 __se_sys_recvmmsg net/socket.c:2787 [inline]
 __x64_sys_recvmmsg+0xcf/0x150 net/socket.c:2787
 do_syscall_64+0x4a/0x90 arch/x86/entry/common.c:47
 entry_SYSCALL_64_after_hwframe+0x44/0xae

value changed: 0x00000000 -> 0x00000101

Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 14001 Comm: syz-executor.3 Not tainted 5.13.0-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/busy_poll.h | 2 +-
 net/core/sock.c         | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 86e028388bad..9899b9af7f22 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -36,7 +36,7 @@ static inline bool net_busy_loop_on(void)
 
 static inline bool sk_can_busy_loop(const struct sock *sk)
 {
-	return sk->sk_ll_usec && !signal_pending(current);
+	return READ_ONCE(sk->sk_ll_usec) && !signal_pending(current);
 }
 
 bool sk_busy_loop_end(void *p, unsigned long start_time);
diff --git a/net/core/sock.c b/net/core/sock.c
index 68f84fac63e0..452883b28aba 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1098,7 +1098,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 			if (val < 0)
 				ret = -EINVAL;
 			else
-				sk->sk_ll_usec = val;
+				WRITE_ONCE(sk->sk_ll_usec, val);
 		}
 		break;
 #endif
-- 
2.30.2

[PATCH AUTOSEL 5.4 04/14] sctp: move 198 addresses from unusable to private scope

[Sasha Levin]

From: Xin Long <lucien.xin@gmail.com>

[ Upstream commit 1d11fa231cabeae09a95cb3e4cf1d9dd34e00f08 ]

The doc draft-stewart-tsvwg-sctp-ipv4-00 that restricts 198 addresses
was never published. These addresses as private addresses should be
allowed to use in SCTP.

As Michael Tuexen suggested, this patch is to move 198 addresses from
unusable to private scope.

Reported-by: Sérgio <surkamp@gmail.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/net/sctp/constants.h | 4 +---
 net/sctp/protocol.c          | 3 ++-
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h
index 06e1deeef464..8c6b04f9f6cb 100644
--- a/include/net/sctp/constants.h
+++ b/include/net/sctp/constants.h
@@ -328,8 +328,7 @@ enum {
 #define SCTP_SCOPE_POLICY_MAX	SCTP_SCOPE_POLICY_LINK
 
 /* Based on IPv4 scoping <draft-stewart-tsvwg-sctp-ipv4-00.txt>,
- * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 198.18.0.0/24,
- * 192.88.99.0/24.
+ * SCTP IPv4 unusable addresses: 0.0.0.0/8, 224.0.0.0/4, 192.88.99.0/24.
  * Also, RFC 8.4, non-unicast addresses are not considered valid SCTP
  * addresses.
  */
@@ -337,7 +336,6 @@ enum {
 	((htonl(INADDR_BROADCAST) == a) ||  \
 	 ipv4_is_multicast(a) ||	    \
 	 ipv4_is_zeronet(a) ||		    \
-	 ipv4_is_test_198(a) ||		    \
 	 ipv4_is_anycast_6to4(a))
 
 /* Flags used for the bind address copy functions.  */
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 981c7cbca46a..2661a453a1c2 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -392,7 +392,8 @@ static enum sctp_scope sctp_v4_scope(union sctp_addr *addr)
 		retval = SCTP_SCOPE_LINK;
 	} else if (ipv4_is_private_10(addr->v4.sin_addr.s_addr) ||
 		   ipv4_is_private_172(addr->v4.sin_addr.s_addr) ||
-		   ipv4_is_private_192(addr->v4.sin_addr.s_addr)) {
+		   ipv4_is_private_192(addr->v4.sin_addr.s_addr) ||
+		   ipv4_is_test_198(addr->v4.sin_addr.s_addr)) {
 		retval = SCTP_SCOPE_PRIVATE;
 	} else {
 		retval = SCTP_SCOPE_GLOBAL;
-- 
2.30.2

[PATCH AUTOSEL 5.4 05/14] ipv6: allocate enough headroom in ip6_finish_output2()

[Sasha Levin]

From: Vasily Averin <vvs@virtuozzo.com>

[ Upstream commit 5796015fa968a3349027a27dcd04c71d95c53ba5 ]

When TEE target mirrors traffic to another interface, sk_buff may
not have enough headroom to be processed correctly.
ip_finish_output2() detect this situation for ipv4 and allocates
new skb with enogh headroom. However ipv6 lacks this logic in
ip_finish_output2 and it leads to skb_under_panic:

 skbuff: skb_under_panic: text:ffffffffc0866ad4 len:96 put:24
 head:ffff97be85e31800 data:ffff97be85e317f8 tail:0x58 end:0xc0 dev:gre0
 ------------[ cut here ]------------
 kernel BUG at net/core/skbuff.c:110!
 invalid opcode: 0000 [#1] SMP PTI
 CPU: 2 PID: 393 Comm: kworker/2:2 Tainted: G           OE     5.13.0 #13
 Hardware name: Virtuozzo KVM, BIOS 1.11.0-2.vz7.4 04/01/2014
 Workqueue: ipv6_addrconf addrconf_dad_work
 RIP: 0010:skb_panic+0x48/0x4a
 Call Trace:
  skb_push.cold.111+0x10/0x10
  ipgre_header+0x24/0xf0 [ip_gre]
  neigh_connected_output+0xae/0xf0
  ip6_finish_output2+0x1a8/0x5a0
  ip6_output+0x5c/0x110
  nf_dup_ipv6+0x158/0x1000 [nf_dup_ipv6]
  tee_tg6+0x2e/0x40 [xt_TEE]
  ip6t_do_table+0x294/0x470 [ip6_tables]
  nf_hook_slow+0x44/0xc0
  nf_hook.constprop.34+0x72/0xe0
  ndisc_send_skb+0x20d/0x2e0
  ndisc_send_ns+0xd1/0x210
  addrconf_dad_work+0x3c8/0x540
  process_one_work+0x1d1/0x370
  worker_thread+0x30/0x390
  kthread+0x116/0x130
  ret_from_fork+0x22/0x30

Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ipv6/ip6_output.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 7a80c42fcce2..004ead8af5e9 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -59,10 +59,38 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device *dev = dst->dev;
+	unsigned int hh_len = LL_RESERVED_SPACE(dev);
+	int delta = hh_len - skb_headroom(skb);
 	const struct in6_addr *nexthop;
 	struct neighbour *neigh;
 	int ret;
 
+	/* Be paranoid, rather than too clever. */
+	if (unlikely(delta > 0) && dev->header_ops) {
+		/* pskb_expand_head() might crash, if skb is shared */
+		if (skb_shared(skb)) {
+			struct sk_buff *nskb = skb_clone(skb, GFP_ATOMIC);
+
+			if (likely(nskb)) {
+				if (skb->sk)
+					skb_set_owner_w(skb, skb->sk);
+				consume_skb(skb);
+			} else {
+				kfree_skb(skb);
+			}
+			skb = nskb;
+		}
+		if (skb &&
+		    pskb_expand_head(skb, SKB_DATA_ALIGN(delta), 0, GFP_ATOMIC)) {
+			kfree_skb(skb);
+			skb = NULL;
+		}
+		if (!skb) {
+			IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTDISCARDS);
+			return -ENOMEM;
+		}
+	}
+
 	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
 		struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
 
-- 
2.30.2