path: root/crypto
diff options
authorDavid Howells <dhowells@redhat.com>2017-03-09 08:09:05 +0000
committerDavid S. Miller <davem@davemloft.net>2017-03-09 18:23:27 -0800
commitcdfbabfb2f0ce983fdaa42f20e5f7842178fc01e (patch)
tree30aae04d074592571b8cb36d001d5d10c7181652 /crypto
parent81dca07b3be974e81cff250a19282473d67a870b (diff)
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>
Diffstat (limited to 'crypto')
2 files changed, 10 insertions, 8 deletions
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:
-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 = {

Privacy Policy