From 02b2faaf0af1d85585f6d6980e286d53612acfc2 Mon Sep 17 00:00:00 2001
From: Eric Dumazet
Date: Fri, 3 Mar 2017 14:08:21 -0800
Subject: tcp: fix various issues for sockets morphing to listen state

Dmitry Vyukov reported a divide by 0 triggered by syzkaller, exploiting
tcp_disconnect() path that was never really considered and/or used
before syzkaller ;)

I was not able to reproduce the bug, but it seems issues here are the
three possible actions that assumed they would never trigger on a
listener.

1) tcp_write_timer_handler
2) tcp_delack_timer_handler
3) MTU reduction

Only IPv6 MTU reduction was properly testing TCP_CLOSE and TCP_LISTEN
 states from tcp_v6_mtu_reduced()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c  | 7 +++++--
 net/ipv4/tcp_timer.c | 6 ++++--
 2 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'net/ipv4')

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 9a89b8deafae..8f3ec1365497 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -279,10 +279,13 @@ EXPORT_SYMBOL(tcp_v4_connect);
  */
 void tcp_v4_mtu_reduced(struct sock *sk)
 {
-	struct dst_entry *dst;
 	struct inet_sock *inet = inet_sk(sk);
-	u32 mtu = tcp_sk(sk)->mtu_info;
+	struct dst_entry *dst;
+	u32 mtu;
 
+	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
+		return;
+	mtu = tcp_sk(sk)->mtu_info;
 	dst = inet_csk_update_pmtu(sk, mtu);
 	if (!dst)
 		return;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 40d893556e67..b2ab411c6d37 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -249,7 +249,8 @@ void tcp_delack_timer_handler(struct sock *sk)
 
 	sk_mem_reclaim_partial(sk);
 
-	if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
 		goto out;
 
 	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
@@ -552,7 +553,8 @@ void tcp_write_timer_handler(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	int event;
 
-	if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending)
+	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
+	    !icsk->icsk_pending)
 		goto out;
 
 	if (time_after(icsk->icsk_timeout, jiffies)) {
-- 
cgit v1.2.3-55-g7522


From 294acf1c01bace5cea5d30b510504238bf5f7c25 Mon Sep 17 00:00:00 2001
From: Paolo Abeni
Date: Tue, 7 Mar 2017 18:33:31 +0100
Subject: net/tunnel: set inner protocol in network gro hooks

The gso code of several tunnels type (gre and udp tunnels)
takes for granted that the skb->inner_protocol is properly
initialized and drops the packet elsewhere.

On the forwarding path no one is initializing such field,
so gro encapsulated packets are dropped on forward.

Since commit 38720352412a ("gre: Use inner_proto to obtain
inner header protocol"), this can be reproduced when the
encapsulated packets use gre as the tunneling protocol.

The issue happens also with vxlan and geneve tunnels since
commit 8bce6d7d0d1e ("udp: Generalize skb_udp_segment"), if the
forwarding host's ingress nic has h/w offload for such tunnel
and a vxlan/geneve device is configured on top of it, regardless
of the configured peer address and vni.

To address the issue, this change initialize the inner_protocol
field for encapsulated packets in both ipv4 and ipv6 gro complete
callbacks.

Fixes: 38720352412a ("gre: Use inner_proto to obtain inner header protocol")
Fixes: 8bce6d7d0d1e ("udp: Generalize skb_udp_segment")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/af_inet.c     | 4 +++-
 net/ipv6/ip6_offload.c | 4 +++-
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'net/ipv4')

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 602d40f43687..5091f46826fa 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1487,8 +1487,10 @@ int inet_gro_complete(struct sk_buff *skb, int nhoff)
 	int proto = iph->protocol;
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IP));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	csum_replace2(&iph->check, iph->tot_len, newlen);
 	iph->tot_len = newlen;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 0838e6d01d2e..93e58a5e1837 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -294,8 +294,10 @@ static int ipv6_gro_complete(struct sk_buff *skb, int nhoff)
 	struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + nhoff);
 	int err = -ENOSYS;
 
-	if (skb->encapsulation)
+	if (skb->encapsulation) {
+		skb_set_inner_protocol(skb, cpu_to_be16(ETH_P_IPV6));
 		skb_set_inner_network_header(skb, nhoff);
+	}
 
 	iph->payload_len = htons(skb->len - nhoff - sizeof(*iph));
 
-- 
cgit v1.2.3-55-g7522


From cdfbabfb2f0ce983fdaa42f20e5f7842178fc01e Mon Sep 17 00:00:00 2001
From: David Howells
Date: Thu, 9 Mar 2017 08:09:05 +0000
Subject: net: Work around lockdep limitation in sockets that use sockets

Lockdep issues a circular dependency warning when AFS issues an operation
through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem.

The theory lockdep comes up with is as follows:

 (1) If the pagefault handler decides it needs to read pages from AFS, it
     calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but
     creating a call requires the socket lock:

	mmap_sem must be taken before sk_lock-AF_RXRPC

 (2) afs_open_socket() opens an AF_RXRPC socket and binds it.  rxrpc_bind()
     binds the underlying UDP socket whilst holding its socket lock.
     inet_bind() takes its own socket lock:

	sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET

 (3) Reading from a TCP socket into a userspace buffer might cause a fault
     and thus cause the kernel to take the mmap_sem, but the TCP socket is
     locked whilst doing this:

	sk_lock-AF_INET must be taken before mmap_sem

However, lockdep's theory is wrong in this instance because it deals only
with lock classes and not individual locks.  The AF_INET lock in (2) isn't
really equivalent to the AF_INET lock in (3) as the former deals with a
socket entirely internal to the kernel that never sees userspace.  This is
a limitation in the design of lockdep.

Fix the general case by:

 (1) Double up all the locking keys used in sockets so that one set are
     used if the socket is created by userspace and the other set is used
     if the socket is created by the kernel.

 (2) Store the kern parameter passed to sk_alloc() in a variable in the
     sock struct (sk_kern_sock).  This informs sock_lock_init(),
     sock_init_data() and sk_clone_lock() as to the lock keys to be used.

     Note that the child created by sk_clone_lock() inherits the parent's
     kern setting.

 (3) Add a 'kern' parameter to ->accept() that is analogous to the one
     passed in to ->create() that distinguishes whether kernel_accept() or
     sys_accept4() was the caller and can be passed to sk_alloc().

     Note that a lot of accept functions merely dequeue an already
     allocated socket.  I haven't touched these as the new socket already
     exists before we get the parameter.

     Note also that there are a couple of places where I've made the accepted
     socket unconditionally kernel-based:

	irda_accept()
	rds_rcp_accept_one()
	tcp_accept_from_sock()

     because they follow a sock_create_kern() and accept off of that.

Whilst creating this, I noticed that lustre and ocfs don't create sockets
through sock_create_kern() and thus they aren't marked as for-kernel,
though they appear to be internal.  I wonder if these should do that so
that they use the new set of lock keys.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 crypto/af_alg.c                               |   9 ++-
 crypto/algif_hash.c                           |   9 ++-
 drivers/staging/lustre/lnet/lnet/lib-socket.c |   4 +-
 fs/dlm/lowcomms.c                             |   2 +-
 fs/ocfs2/cluster/tcp.c                        |   2 +-
 include/crypto/if_alg.h                       |   2 +-
 include/linux/net.h                           |   2 +-
 include/net/inet_common.h                     |   3 +-
 include/net/inet_connection_sock.h            |   2 +-
 include/net/sctp/structs.h                    |   3 +-
 include/net/sock.h                            |   9 ++-
 net/atm/svc.c                                 |   5 +-
 net/ax25/af_ax25.c                            |   3 +-
 net/bluetooth/l2cap_sock.c                    |   2 +-
 net/bluetooth/rfcomm/sock.c                   |   3 +-
 net/bluetooth/sco.c                           |   2 +-
 net/core/sock.c                               | 106 ++++++++++++++------------
 net/decnet/af_decnet.c                        |   5 +-
 net/ipv4/af_inet.c                            |   5 +-
 net/ipv4/inet_connection_sock.c               |   2 +-
 net/irda/af_irda.c                            |   5 +-
 net/iucv/af_iucv.c                            |   2 +-
 net/llc/af_llc.c                              |   4 +-
 net/netrom/af_netrom.c                        |   3 +-
 net/nfc/llcp_sock.c                           |   2 +-
 net/phonet/pep.c                              |   6 +-
 net/phonet/socket.c                           |   4 +-
 net/rds/tcp_listen.c                          |   2 +-
 net/rose/af_rose.c                            |   3 +-
 net/sctp/ipv6.c                               |   5 +-
 net/sctp/protocol.c                           |   5 +-
 net/sctp/socket.c                             |   4 +-
 net/smc/af_smc.c                              |   2 +-
 net/socket.c                                  |   4 +-
 net/tipc/socket.c                             |   8 +-
 net/unix/af_unix.c                            |   5 +-
 net/vmw_vsock/af_vsock.c                      |   3 +-
 net/x25/af_x25.c                              |   3 +-
 38 files changed, 142 insertions(+), 108 deletions(-)

(limited to 'net/ipv4')

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index f5e18c2a4852..690deca17c35 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -266,7 +266,7 @@ unlock:
 	return err;
 }
 
-int af_alg_accept(struct sock *sk, struct socket *newsock)
+int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern)
 {
 	struct alg_sock *ask = alg_sk(sk);
 	const struct af_alg_type *type;
@@ -281,7 +281,7 @@ int af_alg_accept(struct sock *sk, struct socket *newsock)
 	if (!type)
 		goto unlock;
 
-	sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, 0);
+	sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, kern);
 	err = -ENOMEM;
 	if (!sk2)
 		goto unlock;
@@ -323,9 +323,10 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(af_alg_accept);
 
-static int alg_accept(struct socket *sock, struct socket *newsock, int flags)
+static int alg_accept(struct socket *sock, struct socket *newsock, int flags,
+		      bool kern)
 {
-	return af_alg_accept(sock->sk, newsock);
+	return af_alg_accept(sock->sk, newsock, kern);
 }
 
 static const struct proto_ops alg_proto_ops = {
diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c
index 54fc90e8339c..5e92bd275ef3 100644
--- a/crypto/algif_hash.c
+++ b/crypto/algif_hash.c
@@ -239,7 +239,8 @@ unlock:
 	return err ?: len;
 }
 
-static int hash_accept(struct socket *sock, struct socket *newsock, int flags)
+static int hash_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct alg_sock *ask = alg_sk(sk);
@@ -260,7 +261,7 @@ static int hash_accept(struct socket *sock, struct socket *newsock, int flags)
 	if (err)
 		return err;
 
-	err = af_alg_accept(ask->parent, newsock);
+	err = af_alg_accept(ask->parent, newsock, kern);
 	if (err)
 		return err;
 
@@ -378,7 +379,7 @@ static int hash_recvmsg_nokey(struct socket *sock, struct msghdr *msg,
 }
 
 static int hash_accept_nokey(struct socket *sock, struct socket *newsock,
-			     int flags)
+			     int flags, bool kern)
 {
 	int err;
 
@@ -386,7 +387,7 @@ static int hash_accept_nokey(struct socket *sock, struct socket *newsock,
 	if (err)
 		return err;
 
-	return hash_accept(sock, newsock, flags);
+	return hash_accept(sock, newsock, flags, kern);
 }
 
 static struct proto_ops algif_hash_ops_nokey = {
diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c
index b7b87ecefcdf..9fca8d225ee0 100644
--- a/drivers/staging/lustre/lnet/lnet/lib-socket.c
+++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c
@@ -532,7 +532,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock)
 
 	newsock->ops = sock->ops;
 
-	rc = sock->ops->accept(sock, newsock, O_NONBLOCK);
+	rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false);
 	if (rc == -EAGAIN) {
 		/* Nothing ready, so wait for activity */
 		init_waitqueue_entry(&wait, current);
@@ -540,7 +540,7 @@ lnet_sock_accept(struct socket **newsockp, struct socket *sock)
 		set_current_state(TASK_INTERRUPTIBLE);
 		schedule();
 		remove_wait_queue(sk_sleep(sock->sk), &wait);
-		rc = sock->ops->accept(sock, newsock, O_NONBLOCK);
+		rc = sock->ops->accept(sock, newsock, O_NONBLOCK, false);
 	}
 
 	if (rc)
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 7d398d300e97..9382db998ec9 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -743,7 +743,7 @@ static int tcp_accept_from_sock(struct connection *con)
 	newsock->type = con->sock->type;
 	newsock->ops = con->sock->ops;
 
-	result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK);
+	result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK, true);
 	if (result < 0)
 		goto accept_err;
 
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 4348027384f5..d0ab7e56d0b4 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1863,7 +1863,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
 
 	new_sock->type = sock->type;
 	new_sock->ops = sock->ops;
-	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK);
+	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, false);
 	if (ret < 0)
 		goto out;
 
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index a2bfd7843f18..e2b9c6fe2714 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -73,7 +73,7 @@ int af_alg_unregister_type(const struct af_alg_type *type);
 
 int af_alg_release(struct socket *sock);
 void af_alg_release_parent(struct sock *sk);
-int af_alg_accept(struct sock *sk, struct socket *newsock);
+int af_alg_accept(struct sock *sk, struct socket *newsock, bool kern);
 
 int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len);
 void af_alg_free_sg(struct af_alg_sgl *sgl);
diff --git a/include/linux/net.h b/include/linux/net.h
index cd0c8bd0a1de..0620f5e18c96 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -146,7 +146,7 @@ struct proto_ops {
 	int		(*socketpair)(struct socket *sock1,
 				      struct socket *sock2);
 	int		(*accept)    (struct socket *sock,
-				      struct socket *newsock, int flags);
+				      struct socket *newsock, int flags, bool kern);
 	int		(*getname)   (struct socket *sock,
 				      struct sockaddr *addr,
 				      int *sockaddr_len, int peer);
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index b7952d55b9c0..f39ae697347f 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -20,7 +20,8 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 			  int addr_len, int flags, int is_sendmsg);
 int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
 		       int addr_len, int flags);
-int inet_accept(struct socket *sock, struct socket *newsock, int flags);
+int inet_accept(struct socket *sock, struct socket *newsock, int flags,
+		bool kern);
 int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size);
 ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset,
 		      size_t size, int flags);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 826f198374f8..c7a577976bec 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -258,7 +258,7 @@ inet_csk_rto_backoff(const struct inet_connection_sock *icsk,
         return (unsigned long)min_t(u64, when, max_when);
 }
 
-struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern);
 
 int inet_csk_get_port(struct sock *sk, unsigned short snum);
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index a244db5e5ff7..07a0b128625a 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -476,7 +476,8 @@ struct sctp_pf {
 	int  (*send_verify) (struct sctp_sock *, union sctp_addr *);
 	int  (*supported_addrs)(const struct sctp_sock *, __be16 *);
 	struct sock *(*create_accept_sk) (struct sock *sk,
-					  struct sctp_association *asoc);
+					  struct sctp_association *asoc,
+					  bool kern);
 	int (*addr_to_user)(struct sctp_sock *sk, union sctp_addr *addr);
 	void (*to_sk_saddr)(union sctp_addr *, struct sock *sk);
 	void (*to_sk_daddr)(union sctp_addr *, struct sock *sk);
diff --git a/include/net/sock.h b/include/net/sock.h
index 5e5997654db6..03252d53975d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -236,6 +236,7 @@ struct sock_common {
   *	@sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
   *	@sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
   *	@sk_lock:	synchronizer
+  *	@sk_kern_sock: True if sock is using kernel lock classes
   *	@sk_rcvbuf: size of receive buffer in bytes
   *	@sk_wq: sock wait queue and async head
   *	@sk_rx_dst: receive input route used by early demux
@@ -430,7 +431,8 @@ struct sock {
 #endif
 
 	kmemcheck_bitfield_begin(flags);
-	unsigned int		sk_padding : 2,
+	unsigned int		sk_padding : 1,
+				sk_kern_sock : 1,
 				sk_no_check_tx : 1,
 				sk_no_check_rx : 1,
 				sk_userlocks : 4,
@@ -1015,7 +1017,8 @@ struct proto {
 					int addr_len);
 	int			(*disconnect)(struct sock *sk, int flags);
 
-	struct sock *		(*accept)(struct sock *sk, int flags, int *err);
+	struct sock *		(*accept)(struct sock *sk, int flags, int *err,
+					  bool kern);
 
 	int			(*ioctl)(struct sock *sk, int cmd,
 					 unsigned long arg);
@@ -1573,7 +1576,7 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
 int sock_no_bind(struct socket *, struct sockaddr *, int);
 int sock_no_connect(struct socket *, struct sockaddr *, int, int);
 int sock_no_socketpair(struct socket *, struct socket *);
-int sock_no_accept(struct socket *, struct socket *, int);
+int sock_no_accept(struct socket *, struct socket *, int, bool);
 int sock_no_getname(struct socket *, struct sockaddr *, int *, int);
 unsigned int sock_no_poll(struct file *, struct socket *,
 			  struct poll_table_struct *);
diff --git a/net/atm/svc.c b/net/atm/svc.c
index db9794ec61d8..5589de7086af 100644
--- a/net/atm/svc.c
+++ b/net/atm/svc.c
@@ -318,7 +318,8 @@ out:
 	return error;
 }
 
-static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
+static int svc_accept(struct socket *sock, struct socket *newsock, int flags,
+		      bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
@@ -329,7 +330,7 @@ static int svc_accept(struct socket *sock, struct socket *newsock, int flags)
 
 	lock_sock(sk);
 
-	error = svc_create(sock_net(sk), newsock, 0, 0);
+	error = svc_create(sock_net(sk), newsock, 0, kern);
 	if (error)
 		goto out;
 
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index a8e42cedf1db..b7c486752b3a 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1320,7 +1320,8 @@ out_release:
 	return err;
 }
 
-static int ax25_accept(struct socket *sock, struct socket *newsock, int flags)
+static int ax25_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sk_buff *skb;
 	struct sock *newsk;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index f307b145ea54..507b80d59dec 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -301,7 +301,7 @@ done:
 }
 
 static int l2cap_sock_accept(struct socket *sock, struct socket *newsock,
-			     int flags)
+			     int flags, bool kern)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *nsk;
diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c
index aa1a814ceddc..ac3c650cb234 100644
--- a/net/bluetooth/rfcomm/sock.c
+++ b/net/bluetooth/rfcomm/sock.c
@@ -471,7 +471,8 @@ done:
 	return err;
 }
 
-static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags)
+static int rfcomm_sock_accept(struct socket *sock, struct socket *newsock, int flags,
+			      bool kern)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *nsk;
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index e4e9a2da1e7e..728e0c8dc8e7 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -627,7 +627,7 @@ done:
 }
 
 static int sco_sock_accept(struct socket *sock, struct socket *newsock,
-			   int flags)
+			   int flags, bool kern)
 {
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 	struct sock *sk = sock->sk, *ch;
diff --git a/net/core/sock.c b/net/core/sock.c
index f6fd79f33097..a96d5f7a5734 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -197,66 +197,55 @@ EXPORT_SYMBOL(sk_net_capable);
 
 /*
  * Each address family might have different locking rules, so we have
- * one slock key per address family:
+ * one slock key per address family and separate keys for internal and
+ * userspace sockets.
  */
 static struct lock_class_key af_family_keys[AF_MAX];
+static struct lock_class_key af_family_kern_keys[AF_MAX];
 static struct lock_class_key af_family_slock_keys[AF_MAX];
+static struct lock_class_key af_family_kern_slock_keys[AF_MAX];
 
 /*
  * Make lock validator output more readable. (we pre-construct these
  * strings build-time, so that runtime initialization of socket
  * locks is fast):
  */
+
+#define _sock_locks(x)						  \
+  x "AF_UNSPEC",	x "AF_UNIX"     ,	x "AF_INET"     , \
+  x "AF_AX25"  ,	x "AF_IPX"      ,	x "AF_APPLETALK", \
+  x "AF_NETROM",	x "AF_BRIDGE"   ,	x "AF_ATMPVC"   , \
+  x "AF_X25"   ,	x "AF_INET6"    ,	x "AF_ROSE"     , \
+  x "AF_DECnet",	x "AF_NETBEUI"  ,	x "AF_SECURITY" , \
+  x "AF_KEY"   ,	x "AF_NETLINK"  ,	x "AF_PACKET"   , \
+  x "AF_ASH"   ,	x "AF_ECONET"   ,	x "AF_ATMSVC"   , \
+  x "AF_RDS"   ,	x "AF_SNA"      ,	x "AF_IRDA"     , \
+  x "AF_PPPOX" ,	x "AF_WANPIPE"  ,	x "AF_LLC"      , \
+  x "27"       ,	x "28"          ,	x "AF_CAN"      , \
+  x "AF_TIPC"  ,	x "AF_BLUETOOTH",	x "IUCV"        , \
+  x "AF_RXRPC" ,	x "AF_ISDN"     ,	x "AF_PHONET"   , \
+  x "AF_IEEE802154",	x "AF_CAIF"	,	x "AF_ALG"      , \
+  x "AF_NFC"   ,	x "AF_VSOCK"    ,	x "AF_KCM"      , \
+  x "AF_QIPCRTR",	x "AF_SMC"	,	x "AF_MAX"
+
 static const char *const af_family_key_strings[AF_MAX+1] = {
-  "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX"     , "sk_lock-AF_INET"     ,
-  "sk_lock-AF_AX25"  , "sk_lock-AF_IPX"      , "sk_lock-AF_APPLETALK",
-  "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE"   , "sk_lock-AF_ATMPVC"   ,
-  "sk_lock-AF_X25"   , "sk_lock-AF_INET6"    , "sk_lock-AF_ROSE"     ,
-  "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI"  , "sk_lock-AF_SECURITY" ,
-  "sk_lock-AF_KEY"   , "sk_lock-AF_NETLINK"  , "sk_lock-AF_PACKET"   ,
-  "sk_lock-AF_ASH"   , "sk_lock-AF_ECONET"   , "sk_lock-AF_ATMSVC"   ,
-  "sk_lock-AF_RDS"   , "sk_lock-AF_SNA"      , "sk_lock-AF_IRDA"     ,
-  "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE"  , "sk_lock-AF_LLC"      ,
-  "sk_lock-27"       , "sk_lock-28"          , "sk_lock-AF_CAN"      ,
-  "sk_lock-AF_TIPC"  , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV"        ,
-  "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN"     , "sk_lock-AF_PHONET"   ,
-  "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG"      ,
-  "sk_lock-AF_NFC"   , "sk_lock-AF_VSOCK"    , "sk_lock-AF_KCM"      ,
-  "sk_lock-AF_QIPCRTR", "sk_lock-AF_SMC"     , "sk_lock-AF_MAX"
+	_sock_locks("sk_lock-")
 };
 static const char *const af_family_slock_key_strings[AF_MAX+1] = {
-  "slock-AF_UNSPEC", "slock-AF_UNIX"     , "slock-AF_INET"     ,
-  "slock-AF_AX25"  , "slock-AF_IPX"      , "slock-AF_APPLETALK",
-  "slock-AF_NETROM", "slock-AF_BRIDGE"   , "slock-AF_ATMPVC"   ,
-  "slock-AF_X25"   , "slock-AF_INET6"    , "slock-AF_ROSE"     ,
-  "slock-AF_DECnet", "slock-AF_NETBEUI"  , "slock-AF_SECURITY" ,
-  "slock-AF_KEY"   , "slock-AF_NETLINK"  , "slock-AF_PACKET"   ,
-  "slock-AF_ASH"   , "slock-AF_ECONET"   , "slock-AF_ATMSVC"   ,
-  "slock-AF_RDS"   , "slock-AF_SNA"      , "slock-AF_IRDA"     ,
-  "slock-AF_PPPOX" , "slock-AF_WANPIPE"  , "slock-AF_LLC"      ,
-  "slock-27"       , "slock-28"          , "slock-AF_CAN"      ,
-  "slock-AF_TIPC"  , "slock-AF_BLUETOOTH", "slock-AF_IUCV"     ,
-  "slock-AF_RXRPC" , "slock-AF_ISDN"     , "slock-AF_PHONET"   ,
-  "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG"      ,
-  "slock-AF_NFC"   , "slock-AF_VSOCK"    ,"slock-AF_KCM"       ,
-  "slock-AF_QIPCRTR", "slock-AF_SMC"     , "slock-AF_MAX"
+	_sock_locks("slock-")
 };
 static const char *const af_family_clock_key_strings[AF_MAX+1] = {
-  "clock-AF_UNSPEC", "clock-AF_UNIX"     , "clock-AF_INET"     ,
-  "clock-AF_AX25"  , "clock-AF_IPX"      , "clock-AF_APPLETALK",
-  "clock-AF_NETROM", "clock-AF_BRIDGE"   , "clock-AF_ATMPVC"   ,
-  "clock-AF_X25"   , "clock-AF_INET6"    , "clock-AF_ROSE"     ,
-  "clock-AF_DECnet", "clock-AF_NETBEUI"  , "clock-AF_SECURITY" ,
-  "clock-AF_KEY"   , "clock-AF_NETLINK"  , "clock-AF_PACKET"   ,
-  "clock-AF_ASH"   , "clock-AF_ECONET"   , "clock-AF_ATMSVC"   ,
-  "clock-AF_RDS"   , "clock-AF_SNA"      , "clock-AF_IRDA"     ,
-  "clock-AF_PPPOX" , "clock-AF_WANPIPE"  , "clock-AF_LLC"      ,
-  "clock-27"       , "clock-28"          , "clock-AF_CAN"      ,
-  "clock-AF_TIPC"  , "clock-AF_BLUETOOTH", "clock-AF_IUCV"     ,
-  "clock-AF_RXRPC" , "clock-AF_ISDN"     , "clock-AF_PHONET"   ,
-  "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG"      ,
-  "clock-AF_NFC"   , "clock-AF_VSOCK"    , "clock-AF_KCM"      ,
-  "clock-AF_QIPCRTR", "clock-AF_SMC"     , "clock-AF_MAX"
+	_sock_locks("clock-")
+};
+
+static const char *const af_family_kern_key_strings[AF_MAX+1] = {
+	_sock_locks("k-sk_lock-")
+};
+static const char *const af_family_kern_slock_key_strings[AF_MAX+1] = {
+	_sock_locks("k-slock-")
+};
+static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = {
+	_sock_locks("k-clock-")
 };
 
 /*
@@ -264,6 +253,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = {
  * so split the lock classes by using a per-AF key:
  */
 static struct lock_class_key af_callback_keys[AF_MAX];
+static struct lock_class_key af_kern_callback_keys[AF_MAX];
 
 /* Take into consideration the size of the struct sk_buff overhead in the
  * determination of these values, since that is non-constant across
@@ -1293,7 +1283,16 @@ lenout:
  */
 static inline void sock_lock_init(struct sock *sk)
 {
-	sock_lock_init_class_and_name(sk,
+	if (sk->sk_kern_sock)
+		sock_lock_init_class_and_name(
+			sk,
+			af_family_kern_slock_key_strings[sk->sk_family],
+			af_family_kern_slock_keys + sk->sk_family,
+			af_family_kern_key_strings[sk->sk_family],
+			af_family_kern_keys + sk->sk_family);
+	else
+		sock_lock_init_class_and_name(
+			sk,
 			af_family_slock_key_strings[sk->sk_family],
 			af_family_slock_keys + sk->sk_family,
 			af_family_key_strings[sk->sk_family],
@@ -1399,6 +1398,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		 * why we need sk_prot_creator -acme
 		 */
 		sk->sk_prot = sk->sk_prot_creator = prot;
+		sk->sk_kern_sock = kern;
 		sock_lock_init(sk);
 		sk->sk_net_refcnt = kern ? 0 : 1;
 		if (likely(sk->sk_net_refcnt))
@@ -2277,7 +2277,8 @@ int sock_no_socketpair(struct socket *sock1, struct socket *sock2)
 }
 EXPORT_SYMBOL(sock_no_socketpair);
 
-int sock_no_accept(struct socket *sock, struct socket *newsock, int flags)
+int sock_no_accept(struct socket *sock, struct socket *newsock, int flags,
+		   bool kern)
 {
 	return -EOPNOTSUPP;
 }
@@ -2481,7 +2482,14 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	}
 
 	rwlock_init(&sk->sk_callback_lock);
-	lockdep_set_class_and_name(&sk->sk_callback_lock,
+	if (sk->sk_kern_sock)
+		lockdep_set_class_and_name(
+			&sk->sk_callback_lock,
+			af_kern_callback_keys + sk->sk_family,
+			af_family_kern_clock_key_strings[sk->sk_family]);
+	else
+		lockdep_set_class_and_name(
+			&sk->sk_callback_lock,
 			af_callback_keys + sk->sk_family,
 			af_family_clock_key_strings[sk->sk_family]);
 
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index e6e79eda9763..7de5b40a5d0d 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -1070,7 +1070,8 @@ static struct sk_buff *dn_wait_for_connect(struct sock *sk, long *timeo)
 	return skb == NULL ? ERR_PTR(err) : skb;
 }
 
-static int dn_accept(struct socket *sock, struct socket *newsock, int flags)
+static int dn_accept(struct socket *sock, struct socket *newsock, int flags,
+		     bool kern)
 {
 	struct sock *sk = sock->sk, *newsk;
 	struct sk_buff *skb = NULL;
@@ -1099,7 +1100,7 @@ static int dn_accept(struct socket *sock, struct socket *newsock, int flags)
 
 	cb = DN_SKB_CB(skb);
 	sk->sk_ack_backlog--;
-	newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, 0);
+	newsk = dn_alloc_sock(sock_net(sk), newsock, sk->sk_allocation, kern);
 	if (newsk == NULL) {
 		release_sock(sk);
 		kfree_skb(skb);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 5091f46826fa..6b1fc6e4278e 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -689,11 +689,12 @@ EXPORT_SYMBOL(inet_stream_connect);
  *	Accept a pending connection. The TCP layer now gives BSD semantics.
  */
 
-int inet_accept(struct socket *sock, struct socket *newsock, int flags)
+int inet_accept(struct socket *sock, struct socket *newsock, int flags,
+		bool kern)
 {
 	struct sock *sk1 = sock->sk;
 	int err = -EINVAL;
-	struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err);
+	struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err, kern);
 
 	if (!sk2)
 		goto do_err;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b4d5980ade3b..5e313c1ac94f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -424,7 +424,7 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
 /*
  * This will accept the next outstanding connection.
  */
-struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c
index 81adc29a448d..8d77ad5cadaf 100644
--- a/net/irda/af_irda.c
+++ b/net/irda/af_irda.c
@@ -828,7 +828,8 @@ out:
  *    Wait for incoming connection
  *
  */
-static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
+static int irda_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct irda_sock *new, *self = irda_sk(sk);
@@ -836,7 +837,7 @@ static int irda_accept(struct socket *sock, struct socket *newsock, int flags)
 	struct sk_buff *skb = NULL;
 	int err;
 
-	err = irda_create(sock_net(sk), newsock, sk->sk_protocol, 0);
+	err = irda_create(sock_net(sk), newsock, sk->sk_protocol, kern);
 	if (err)
 		return err;
 
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 89bbde1081ce..84de7b6326dc 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -938,7 +938,7 @@ done:
 
 /* Accept a pending connection */
 static int iucv_sock_accept(struct socket *sock, struct socket *newsock,
-			    int flags)
+			    int flags, bool kern)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct sock *sk = sock->sk, *nsk;
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 06186d608a27..cb4fff785cbf 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -641,11 +641,13 @@ static void llc_cmsg_rcv(struct msghdr *msg, struct sk_buff *skb)
  *	@sock: Socket which connections arrive on.
  *	@newsock: Socket to move incoming connection to.
  *	@flags: User specified operational flags.
+ *	@kern: If the socket is kernel internal
  *
  *	Accept a new incoming connection.
  *	Returns 0 upon success, negative otherwise.
  */
-static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags)
+static int llc_ui_accept(struct socket *sock, struct socket *newsock, int flags,
+			 bool kern)
 {
 	struct sock *sk = sock->sk, *newsk;
 	struct llc_sock *llc, *newllc;
diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c
index 4bbf4526b885..ebf16f7f9089 100644
--- a/net/netrom/af_netrom.c
+++ b/net/netrom/af_netrom.c
@@ -765,7 +765,8 @@ out_release:
 	return err;
 }
 
-static int nr_accept(struct socket *sock, struct socket *newsock, int flags)
+static int nr_accept(struct socket *sock, struct socket *newsock, int flags,
+		     bool kern)
 {
 	struct sk_buff *skb;
 	struct sock *newsk;
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index 879885b31cce..2ffb18e73df6 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -441,7 +441,7 @@ struct sock *nfc_llcp_accept_dequeue(struct sock *parent,
 }
 
 static int llcp_sock_accept(struct socket *sock, struct socket *newsock,
-			    int flags)
+			    int flags, bool kern)
 {
 	DECLARE_WAITQUEUE(wait, current);
 	struct sock *sk = sock->sk, *new_sk;
diff --git a/net/phonet/pep.c b/net/phonet/pep.c
index 222bedcd9575..e81537991ddf 100644
--- a/net/phonet/pep.c
+++ b/net/phonet/pep.c
@@ -772,7 +772,8 @@ static void pep_sock_close(struct sock *sk, long timeout)
 	sock_put(sk);
 }
 
-static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
+static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp,
+				    bool kern)
 {
 	struct pep_sock *pn = pep_sk(sk), *newpn;
 	struct sock *newsk = NULL;
@@ -846,7 +847,8 @@ static struct sock *pep_sock_accept(struct sock *sk, int flags, int *errp)
 	}
 
 	/* Create a new to-be-accepted sock */
-	newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot, 0);
+	newsk = sk_alloc(sock_net(sk), PF_PHONET, GFP_KERNEL, sk->sk_prot,
+			 kern);
 	if (!newsk) {
 		pep_reject_conn(sk, skb, PN_PIPE_ERR_OVERLOAD, GFP_KERNEL);
 		err = -ENOBUFS;
diff --git a/net/phonet/socket.c b/net/phonet/socket.c
index a6c8da3ee893..64634e3ec2fc 100644
--- a/net/phonet/socket.c
+++ b/net/phonet/socket.c
@@ -305,7 +305,7 @@ out:
 }
 
 static int pn_socket_accept(struct socket *sock, struct socket *newsock,
-				int flags)
+			    int flags, bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sock *newsk;
@@ -314,7 +314,7 @@ static int pn_socket_accept(struct socket *sock, struct socket *newsock,
 	if (unlikely(sk->sk_state != TCP_LISTEN))
 		return -EINVAL;
 
-	newsk = sk->sk_prot->accept(sk, flags, &err);
+	newsk = sk->sk_prot->accept(sk, flags, &err, kern);
 	if (!newsk)
 		return err;
 
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 2c69a508a693..507678853e6c 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -133,7 +133,7 @@ int rds_tcp_accept_one(struct socket *sock)
 
 	new_sock->type = sock->type;
 	new_sock->ops = sock->ops;
-	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK);
+	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, true);
 	if (ret < 0)
 		goto out;
 
diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c
index b8a1df2c9785..4a9729257023 100644
--- a/net/rose/af_rose.c
+++ b/net/rose/af_rose.c
@@ -871,7 +871,8 @@ out_release:
 	return err;
 }
 
-static int rose_accept(struct socket *sock, struct socket *newsock, int flags)
+static int rose_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sk_buff *skb;
 	struct sock *newsk;
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 063baac5b9fe..961ee59f696a 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -640,14 +640,15 @@ static sctp_scope_t sctp_v6_scope(union sctp_addr *addr)
 
 /* Create and initialize a new sk for the socket to be returned by accept(). */
 static struct sock *sctp_v6_create_accept_sk(struct sock *sk,
-					     struct sctp_association *asoc)
+					     struct sctp_association *asoc,
+					     bool kern)
 {
 	struct sock *newsk;
 	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
 	struct sctp6_sock *newsctp6sk;
 	struct ipv6_txoptions *opt;
 
-	newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, 0);
+	newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern);
 	if (!newsk)
 		goto out;
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 1b6d4574d2b0..989a900383b5 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -575,10 +575,11 @@ static int sctp_v4_is_ce(const struct sk_buff *skb)
 
 /* Create and initialize a new sk for the socket returned by accept(). */
 static struct sock *sctp_v4_create_accept_sk(struct sock *sk,
-					     struct sctp_association *asoc)
+					     struct sctp_association *asoc,
+					     bool kern)
 {
 	struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL,
-			sk->sk_prot, 0);
+			sk->sk_prot, kern);
 	struct inet_sock *newinet;
 
 	if (!newsk)
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 6f0a9be50f50..0f378ea2ae38 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4116,7 +4116,7 @@ static int sctp_disconnect(struct sock *sk, int flags)
  * descriptor will be returned from accept() to represent the newly
  * formed association.
  */
-static struct sock *sctp_accept(struct sock *sk, int flags, int *err)
+static struct sock *sctp_accept(struct sock *sk, int flags, int *err, bool kern)
 {
 	struct sctp_sock *sp;
 	struct sctp_endpoint *ep;
@@ -4151,7 +4151,7 @@ static struct sock *sctp_accept(struct sock *sk, int flags, int *err)
 	 */
 	asoc = list_entry(ep->asocs.next, struct sctp_association, asocs);
 
-	newsk = sp->pf->create_accept_sk(sk, asoc);
+	newsk = sp->pf->create_accept_sk(sk, asoc, kern);
 	if (!newsk) {
 		error = -ENOMEM;
 		goto out;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 85837ab90e89..093803786eac 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -944,7 +944,7 @@ out:
 }
 
 static int smc_accept(struct socket *sock, struct socket *new_sock,
-		      int flags)
+		      int flags, bool kern)
 {
 	struct sock *sk = sock->sk, *nsk;
 	DECLARE_WAITQUEUE(wait, current);
diff --git a/net/socket.c b/net/socket.c
index e0757e648c0c..e034fe4164be 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1506,7 +1506,7 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
 	if (err)
 		goto out_fd;
 
-	err = sock->ops->accept(sock, newsock, sock->file->f_flags);
+	err = sock->ops->accept(sock, newsock, sock->file->f_flags, false);
 	if (err < 0)
 		goto out_fd;
 
@@ -3239,7 +3239,7 @@ int kernel_accept(struct socket *sock, struct socket **newsock, int flags)
 	if (err < 0)
 		goto done;
 
-	err = sock->ops->accept(sock, *newsock, flags);
+	err = sock->ops->accept(sock, *newsock, flags, true);
 	if (err < 0) {
 		sock_release(*newsock);
 		*newsock = NULL;
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 43e4045e72bc..7130e73bd42c 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -115,7 +115,8 @@ static void tipc_data_ready(struct sock *sk);
 static void tipc_write_space(struct sock *sk);
 static void tipc_sock_destruct(struct sock *sk);
 static int tipc_release(struct socket *sock);
-static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags);
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
+		       bool kern);
 static void tipc_sk_timeout(unsigned long data);
 static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
 			   struct tipc_name_seq const *seq);
@@ -2029,7 +2030,8 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
  *
  * Returns 0 on success, errno otherwise
  */
-static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
+static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
+		       bool kern)
 {
 	struct sock *new_sk, *sk = sock->sk;
 	struct sk_buff *buf;
@@ -2051,7 +2053,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags)
 
 	buf = skb_peek(&sk->sk_receive_queue);
 
-	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 0);
+	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, kern);
 	if (res)
 		goto exit;
 	security_sk_clone(sock->sk, new_sock->sk);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index ee37b390260a..928691c43408 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -636,7 +636,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int);
 static int unix_stream_connect(struct socket *, struct sockaddr *,
 			       int addr_len, int flags);
 static int unix_socketpair(struct socket *, struct socket *);
-static int unix_accept(struct socket *, struct socket *, int);
+static int unix_accept(struct socket *, struct socket *, int, bool);
 static int unix_getname(struct socket *, struct sockaddr *, int *, int);
 static unsigned int unix_poll(struct file *, struct socket *, poll_table *);
 static unsigned int unix_dgram_poll(struct file *, struct socket *,
@@ -1402,7 +1402,8 @@ static void unix_sock_inherit_flags(const struct socket *old,
 		set_bit(SOCK_PASSSEC, &new->flags);
 }
 
-static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
+static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
+		       bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sock *tsk;
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9192ead66751..9f770f33c100 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1250,7 +1250,8 @@ out:
 	return err;
 }
 
-static int vsock_accept(struct socket *sock, struct socket *newsock, int flags)
+static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
+			bool kern)
 {
 	struct sock *listener;
 	int err;
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index fd28a49dbe8f..8b911c29860e 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -852,7 +852,8 @@ static int x25_wait_for_data(struct sock *sk, long timeout)
 	return rc;
 }
 
-static int x25_accept(struct socket *sock, struct socket *newsock, int flags)
+static int x25_accept(struct socket *sock, struct socket *newsock, int flags,
+		      bool kern)
 {
 	struct sock *sk = sock->sk;
 	struct sock *newsk;
-- 
cgit v1.2.3-55-g7522


From 4b3b45edba9222e518a1ec72df841eba3609fe34 Mon Sep 17 00:00:00 2001
From: Alexey Kodanev
Date: Thu, 9 Mar 2017 13:56:46 +0300
Subject: udp: avoid ufo handling on IP payload compression packets

commit c146066ab802 ("ipv4: Don't use ufo handling on later transformed
packets") and commit f89c56ce710a ("ipv6: Don't use ufo handling on
later transformed packets") added a check that 'rt->dst.header_len' isn't
zero in order to skip UFO, but it doesn't include IPcomp in transport mode
where it equals zero.

Packets, after payload compression, may not require further fragmentation,
and if original length exceeds MTU, later compressed packets will be
transmitted incorrectly. This can be reproduced with LTP udp_ipsec.sh test
on veth device with enabled UFO, MTU is 1500 and UDP payload is 2000:

* IPv4 case, offset is wrong + unnecessary fragmentation
    udp_ipsec.sh -p comp -m transport -s 2000 &
    tcpdump -ni ltp_ns_veth2
    ...
    IP (tos 0x0, ttl 64, id 45203, offset 0, flags [+],
      proto Compressed IP (108), length 49)
      10.0.0.2 > 10.0.0.1: IPComp(cpi=0x1000)
    IP (tos 0x0, ttl 64, id 45203, offset 1480, flags [none],
      proto UDP (17), length 21) 10.0.0.2 > 10.0.0.1: ip-proto-17

* IPv6 case, sending small fragments
    udp_ipsec.sh -6 -p comp -m transport -s 2000 &
    tcpdump -ni ltp_ns_veth2
    ...
    IP6 (flowlabel 0x6b9ba, hlim 64, next-header Compressed IP (108)
      payload length: 37) fd00::2 > fd00::1: IPComp(cpi=0x1000)
    IP6 (flowlabel 0x6b9ba, hlim 64, next-header Compressed IP (108)
      payload length: 21) fd00::2 > fd00::1: IPComp(cpi=0x1000)

Fix it by checking 'rt->dst.xfrm' pointer to 'xfrm_state' struct, skip UFO
if xfrm is set. So the new check will include both cases: IPcomp and IPsec.

Fixes: c146066ab802 ("ipv4: Don't use ufo handling on later transformed packets")
Fixes: f89c56ce710a ("ipv6: Don't use ufo handling on later transformed packets")
Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 2 +-
 net/ipv6/ip6_output.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'net/ipv4')

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 737ce826d7ec..7a3fd25e8913 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -966,7 +966,7 @@ static int __ip_append_data(struct sock *sk,
 	cork->length += length;
 	if ((((length + fragheaderlen) > mtu) || (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
 	    (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 528b3c1f3fde..df42096e1f04 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1385,7 +1385,7 @@ emsgsize:
 	if ((((length + fragheaderlen) > mtu) ||
 	     (skb && skb_is_gso(skb))) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
-	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
+	    (rt->dst.dev->features & NETIF_F_UFO) && !dst_xfrm(&rt->dst) &&
 	    (sk->sk_type == SOCK_DGRAM) && !udp_get_no_check6_tx(sk)) {
 		err = ip6_ufo_append_data(sk, queue, getfrag, from, length,
 					  hh_len, fragheaderlen, exthdrlen,
-- 
cgit v1.2.3-55-g7522


From 45caeaa5ac0b4b11784ac6f932c0ad4c6b67cda0 Mon Sep 17 00:00:00 2001
From: Jon Maxwell
Date: Fri, 10 Mar 2017 16:40:33 +1100
Subject: dccp/tcp: fix routing redirect race

As Eric Dumazet pointed out this also needs to be fixed in IPv6.
v2: Contains the IPv6 tcp/Ipv6 dccp patches as well.

We have seen a few incidents lately where a dst_enty has been freed
with a dangling TCP socket reference (sk->sk_dst_cache) pointing to that
dst_entry. If the conditions/timings are right a crash then ensues when the
freed dst_entry is referenced later on. A Common crashing back trace is:

 #8 [] page_fault at ffffffff8163e648
    [exception RIP: __tcp_ack_snd_check+74]
.
.
 #9 [] tcp_rcv_established at ffffffff81580b64
#10 [] tcp_v4_do_rcv at ffffffff8158b54a
#11 [] tcp_v4_rcv at ffffffff8158cd02
#12 [] ip_local_deliver_finish at ffffffff815668f4
#13 [] ip_local_deliver at ffffffff81566bd9
#14 [] ip_rcv_finish at ffffffff8156656d
#15 [] ip_rcv at ffffffff81566f06
#16 [] __netif_receive_skb_core at ffffffff8152b3a2
#17 [] __netif_receive_skb at ffffffff8152b608
#18 [] netif_receive_skb at ffffffff8152b690
#19 [] vmxnet3_rq_rx_complete at ffffffffa015eeaf [vmxnet3]
#20 [] vmxnet3_poll_rx_only at ffffffffa015f32a [vmxnet3]
#21 [] net_rx_action at ffffffff8152bac2
#22 [] __do_softirq at ffffffff81084b4f
#23 [] call_softirq at ffffffff8164845c
#24 [] do_softirq at ffffffff81016fc5
#25 [] irq_exit at ffffffff81084ee5
#26 [] do_IRQ at ffffffff81648ff8

Of course it may happen with other NIC drivers as well.

It's found the freed dst_entry here:

 224 static bool tcp_in_quickack_mode(struct sock *sk)↩
 225 {↩
 226 ▹       const struct inet_connection_sock *icsk = inet_csk(sk);↩
 227 ▹       const struct dst_entry *dst = __sk_dst_get(sk);↩
 228 ↩
 229 ▹       return (dst && dst_metric(dst, RTAX_QUICKACK)) ||↩
 230 ▹       ▹       (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong);↩
 231 }↩

But there are other backtraces attributed to the same freed dst_entry in
netfilter code as well.

All the vmcores showed 2 significant clues:

- Remote hosts behind the default gateway had always been redirected to a
different gateway. A rtable/dst_entry will be added for that host. Making
more dst_entrys with lower reference counts. Making this more probable.

- All vmcores showed a postitive LockDroppedIcmps value, e.g:

LockDroppedIcmps                  267

A closer look at the tcp_v4_err() handler revealed that do_redirect() will run
regardless of whether user space has the socket locked. This can result in a
race condition where the same dst_entry cached in sk->sk_dst_entry can be
decremented twice for the same socket via:

do_redirect()->__sk_dst_check()-> dst_release().

Which leads to the dst_entry being prematurely freed with another socket
pointing to it via sk->sk_dst_cache and a subsequent crash.

To fix this skip do_redirect() if usespace has the socket locked. Instead let
the redirect take place later when user space does not have the socket
locked.

The dccp/IPv6 code is very similar in this respect, so fixing it there too.

As Eric Garver pointed out the following commit now invalidates routes. Which
can set the dst->obsolete flag so that ipv4_dst_check() returns null and
triggers the dst_release().

Fixes: ceb3320610d6 ("ipv4: Kill routes during PMTU/redirect updates.")
Cc: Eric Garver <egarver@redhat.com>
Cc: Hannes Sowa <hsowa@redhat.com>
Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dccp/ipv4.c     | 3 ++-
 net/dccp/ipv6.c     | 8 +++++---
 net/ipv4/tcp_ipv4.c | 3 ++-
 net/ipv6/tcp_ipv6.c | 8 +++++---
 4 files changed, 14 insertions(+), 8 deletions(-)

(limited to 'net/ipv4')

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 409d0cfd3447..b99168b0fabf 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -289,7 +289,8 @@ static void dccp_v4_err(struct sk_buff *skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		dccp_do_redirect(skb, sk);
+		if (!sock_owned_by_user(sk))
+			dccp_do_redirect(skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 233b57367758..d9b6a4e403e7 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -122,10 +122,12 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8f3ec1365497..575e19dcc017 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -431,7 +431,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 
 	switch (type) {
 	case ICMP_REDIRECT:
-		do_redirect(icmp_skb, sk);
+		if (!sock_owned_by_user(sk))
+			do_redirect(icmp_skb, sk);
 		goto out;
 	case ICMP_SOURCE_QUENCH:
 		/* Just silently ignore these. */
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 60a5295a7de6..49fa2e8c3fa9 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -391,10 +391,12 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	np = inet6_sk(sk);
 
 	if (type == NDISC_REDIRECT) {
-		struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
+		if (!sock_owned_by_user(sk)) {
+			struct dst_entry *dst = __sk_dst_check(sk, np->dst_cookie);
 
-		if (dst)
-			dst->ops->redirect(dst, sk, skb);
+			if (dst)
+				dst->ops->redirect(dst, sk, skb);
+		}
 		goto out;
 	}
 
-- 
cgit v1.2.3-55-g7522