cdfbabfb2f
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>
98 lines
2.5 KiB
C
98 lines
2.5 KiB
C
/*
|
|
* if_alg: User-space algorithm interface
|
|
*
|
|
* Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms of the GNU General Public License as published by the Free
|
|
* Software Foundation; either version 2 of the License, or (at your option)
|
|
* any later version.
|
|
*
|
|
*/
|
|
|
|
#ifndef _CRYPTO_IF_ALG_H
|
|
#define _CRYPTO_IF_ALG_H
|
|
|
|
#include <linux/compiler.h>
|
|
#include <linux/completion.h>
|
|
#include <linux/if_alg.h>
|
|
#include <linux/scatterlist.h>
|
|
#include <linux/types.h>
|
|
#include <net/sock.h>
|
|
|
|
#define ALG_MAX_PAGES 16
|
|
|
|
struct crypto_async_request;
|
|
|
|
struct alg_sock {
|
|
/* struct sock must be the first member of struct alg_sock */
|
|
struct sock sk;
|
|
|
|
struct sock *parent;
|
|
|
|
unsigned int refcnt;
|
|
unsigned int nokey_refcnt;
|
|
|
|
const struct af_alg_type *type;
|
|
void *private;
|
|
};
|
|
|
|
struct af_alg_completion {
|
|
struct completion completion;
|
|
int err;
|
|
};
|
|
|
|
struct af_alg_control {
|
|
struct af_alg_iv *iv;
|
|
int op;
|
|
unsigned int aead_assoclen;
|
|
};
|
|
|
|
struct af_alg_type {
|
|
void *(*bind)(const char *name, u32 type, u32 mask);
|
|
void (*release)(void *private);
|
|
int (*setkey)(void *private, const u8 *key, unsigned int keylen);
|
|
int (*accept)(void *private, struct sock *sk);
|
|
int (*accept_nokey)(void *private, struct sock *sk);
|
|
int (*setauthsize)(void *private, unsigned int authsize);
|
|
|
|
struct proto_ops *ops;
|
|
struct proto_ops *ops_nokey;
|
|
struct module *owner;
|
|
char name[14];
|
|
};
|
|
|
|
struct af_alg_sgl {
|
|
struct scatterlist sg[ALG_MAX_PAGES + 1];
|
|
struct page *pages[ALG_MAX_PAGES];
|
|
unsigned int npages;
|
|
};
|
|
|
|
int af_alg_register_type(const struct af_alg_type *type);
|
|
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, 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);
|
|
void af_alg_link_sg(struct af_alg_sgl *sgl_prev, struct af_alg_sgl *sgl_new);
|
|
|
|
int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con);
|
|
|
|
int af_alg_wait_for_completion(int err, struct af_alg_completion *completion);
|
|
void af_alg_complete(struct crypto_async_request *req, int err);
|
|
|
|
static inline struct alg_sock *alg_sk(struct sock *sk)
|
|
{
|
|
return (struct alg_sock *)sk;
|
|
}
|
|
|
|
static inline void af_alg_init_completion(struct af_alg_completion *completion)
|
|
{
|
|
init_completion(&completion->completion);
|
|
}
|
|
|
|
#endif /* _CRYPTO_IF_ALG_H */
|