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>

4 files changed, 11 insertions, 6 deletions

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 *);