android_kernel_sony_sdm845/crypto/af_alg.c

540 lines
11 KiB
C
Raw Permalink Normal View History

/*
* af_alg: User-space algorithm interface
*
* This file provides the user-space API for algorithms.
*
* 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.
*
*/
#include <linux/atomic.h>
#include <crypto/if_alg.h>
#include <linux/crypto.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/net.h>
#include <linux/rwsem.h>
#include <linux/security.h>
struct alg_type_list {
const struct af_alg_type *type;
struct list_head list;
};
static atomic_long_t alg_memory_allocated;
static struct proto alg_proto = {
.name = "ALG",
.owner = THIS_MODULE,
.memory_allocated = &alg_memory_allocated,
.obj_size = sizeof(struct alg_sock),
};
static LIST_HEAD(alg_types);
static DECLARE_RWSEM(alg_types_sem);
static const struct af_alg_type *alg_get_type(const char *name)
{
const struct af_alg_type *type = ERR_PTR(-ENOENT);
struct alg_type_list *node;
down_read(&alg_types_sem);
list_for_each_entry(node, &alg_types, list) {
if (strcmp(node->type->name, name))
continue;
if (try_module_get(node->type->owner))
type = node->type;
break;
}
up_read(&alg_types_sem);
return type;
}
int af_alg_register_type(const struct af_alg_type *type)
{
struct alg_type_list *node;
int err = -EEXIST;
down_write(&alg_types_sem);
list_for_each_entry(node, &alg_types, list) {
if (!strcmp(node->type->name, type->name))
goto unlock;
}
node = kmalloc(sizeof(*node), GFP_KERNEL);
err = -ENOMEM;
if (!node)
goto unlock;
type->ops->owner = THIS_MODULE;
if (type->ops_nokey)
type->ops_nokey->owner = THIS_MODULE;
node->type = type;
list_add(&node->list, &alg_types);
err = 0;
unlock:
up_write(&alg_types_sem);
return err;
}
EXPORT_SYMBOL_GPL(af_alg_register_type);
int af_alg_unregister_type(const struct af_alg_type *type)
{
struct alg_type_list *node;
int err = -ENOENT;
down_write(&alg_types_sem);
list_for_each_entry(node, &alg_types, list) {
if (strcmp(node->type->name, type->name))
continue;
list_del(&node->list);
kfree(node);
err = 0;
break;
}
up_write(&alg_types_sem);
return err;
}
EXPORT_SYMBOL_GPL(af_alg_unregister_type);
static void alg_do_release(const struct af_alg_type *type, void *private)
{
if (!type)
return;
type->release(private);
module_put(type->owner);
}
int af_alg_release(struct socket *sock)
{
UPSTREAM: net: crypto set sk to NULL when af_alg_release. KASAN has found use-after-free in sockfs_setattr. The existed commit 6d8c50dcb029 ("socket: close race condition between sock_close() and sockfs_setattr()") is to fix this simillar issue, but it seems to ignore that crypto module forgets to set the sk to NULL after af_alg_release. KASAN report details as below: BUG: KASAN: use-after-free in sockfs_setattr+0x120/0x150 Write of size 4 at addr ffff88837b956128 by task syz-executor0/4186 CPU: 2 PID: 4186 Comm: syz-executor0 Not tainted xxx + #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 Call Trace: dump_stack+0xca/0x13e print_address_description+0x79/0x330 ? vprintk_func+0x5e/0xf0 kasan_report+0x18a/0x2e0 ? sockfs_setattr+0x120/0x150 sockfs_setattr+0x120/0x150 ? sock_register+0x2d0/0x2d0 notify_change+0x90c/0xd40 ? chown_common+0x2ef/0x510 chown_common+0x2ef/0x510 ? chmod_common+0x3b0/0x3b0 ? __lock_is_held+0xbc/0x160 ? __sb_start_write+0x13d/0x2b0 ? __mnt_want_write+0x19a/0x250 do_fchownat+0x15c/0x190 ? __ia32_sys_chmod+0x80/0x80 ? trace_hardirqs_on_thunk+0x1a/0x1c __x64_sys_fchownat+0xbf/0x160 ? lockdep_hardirqs_on+0x39a/0x5e0 do_syscall_64+0xc8/0x580 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x462589 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fb4b2c83c58 EFLAGS: 00000246 ORIG_RAX: 0000000000000104 RAX: ffffffffffffffda RBX: 000000000072bfa0 RCX: 0000000000462589 RDX: 0000000000000000 RSI: 00000000200000c0 RDI: 0000000000000007 RBP: 0000000000000005 R08: 0000000000001000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fb4b2c846bc R13: 00000000004bc733 R14: 00000000006f5138 R15: 00000000ffffffff Allocated by task 4185: kasan_kmalloc+0xa0/0xd0 __kmalloc+0x14a/0x350 sk_prot_alloc+0xf6/0x290 sk_alloc+0x3d/0xc00 af_alg_accept+0x9e/0x670 hash_accept+0x4a3/0x650 __sys_accept4+0x306/0x5c0 __x64_sys_accept4+0x98/0x100 do_syscall_64+0xc8/0x580 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 4184: __kasan_slab_free+0x12e/0x180 kfree+0xeb/0x2f0 __sk_destruct+0x4e6/0x6a0 sk_destruct+0x48/0x70 __sk_free+0xa9/0x270 sk_free+0x2a/0x30 af_alg_release+0x5c/0x70 __sock_release+0xd3/0x280 sock_close+0x1a/0x20 __fput+0x27f/0x7f0 task_work_run+0x136/0x1b0 exit_to_usermode_loop+0x1a7/0x1d0 do_syscall_64+0x461/0x580 entry_SYSCALL_64_after_hwframe+0x49/0xbe Syzkaller reproducer: r0 = perf_event_open(&(0x7f0000000000)={0x0, 0x70, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, @perf_config_ext}, 0x0, 0x0, 0xffffffffffffffff, 0x0) r1 = socket$alg(0x26, 0x5, 0x0) getrusage(0x0, 0x0) bind(r1, &(0x7f00000001c0)=@alg={0x26, 'hash\x00', 0x0, 0x0, 'sha256-ssse3\x00'}, 0x80) r2 = accept(r1, 0x0, 0x0) r3 = accept4$unix(r2, 0x0, 0x0, 0x0) r4 = dup3(r3, r0, 0x0) fchownat(r4, &(0x7f00000000c0)='\x00', 0x0, 0x0, 0x1000) Fixes: 6d8c50dcb029 ("socket: close race condition between sock_close() and sockfs_setattr()") Signed-off-by: Mao Wenan <maowenan@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net> (cherry picked from commit 9060cb719e61b685ec0102574e10337fa5f445ea) Signed-off-by: Greg Kroah-Hartman <gregkh@google.com> Change-Id: Ia63c10f857d4f1081edd2d8df26b18829b9ec691 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2019-02-18 10:44:44 +08:00
if (sock->sk) {
sock_put(sock->sk);
UPSTREAM: net: crypto set sk to NULL when af_alg_release. KASAN has found use-after-free in sockfs_setattr. The existed commit 6d8c50dcb029 ("socket: close race condition between sock_close() and sockfs_setattr()") is to fix this simillar issue, but it seems to ignore that crypto module forgets to set the sk to NULL after af_alg_release. KASAN report details as below: BUG: KASAN: use-after-free in sockfs_setattr+0x120/0x150 Write of size 4 at addr ffff88837b956128 by task syz-executor0/4186 CPU: 2 PID: 4186 Comm: syz-executor0 Not tainted xxx + #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1ubuntu1 04/01/2014 Call Trace: dump_stack+0xca/0x13e print_address_description+0x79/0x330 ? vprintk_func+0x5e/0xf0 kasan_report+0x18a/0x2e0 ? sockfs_setattr+0x120/0x150 sockfs_setattr+0x120/0x150 ? sock_register+0x2d0/0x2d0 notify_change+0x90c/0xd40 ? chown_common+0x2ef/0x510 chown_common+0x2ef/0x510 ? chmod_common+0x3b0/0x3b0 ? __lock_is_held+0xbc/0x160 ? __sb_start_write+0x13d/0x2b0 ? __mnt_want_write+0x19a/0x250 do_fchownat+0x15c/0x190 ? __ia32_sys_chmod+0x80/0x80 ? trace_hardirqs_on_thunk+0x1a/0x1c __x64_sys_fchownat+0xbf/0x160 ? lockdep_hardirqs_on+0x39a/0x5e0 do_syscall_64+0xc8/0x580 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x462589 Code: f7 d8 64 89 02 b8 ff ff ff ff c3 66 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 bc ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007fb4b2c83c58 EFLAGS: 00000246 ORIG_RAX: 0000000000000104 RAX: ffffffffffffffda RBX: 000000000072bfa0 RCX: 0000000000462589 RDX: 0000000000000000 RSI: 00000000200000c0 RDI: 0000000000000007 RBP: 0000000000000005 R08: 0000000000001000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fb4b2c846bc R13: 00000000004bc733 R14: 00000000006f5138 R15: 00000000ffffffff Allocated by task 4185: kasan_kmalloc+0xa0/0xd0 __kmalloc+0x14a/0x350 sk_prot_alloc+0xf6/0x290 sk_alloc+0x3d/0xc00 af_alg_accept+0x9e/0x670 hash_accept+0x4a3/0x650 __sys_accept4+0x306/0x5c0 __x64_sys_accept4+0x98/0x100 do_syscall_64+0xc8/0x580 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 4184: __kasan_slab_free+0x12e/0x180 kfree+0xeb/0x2f0 __sk_destruct+0x4e6/0x6a0 sk_destruct+0x48/0x70 __sk_free+0xa9/0x270 sk_free+0x2a/0x30 af_alg_release+0x5c/0x70 __sock_release+0xd3/0x280 sock_close+0x1a/0x20 __fput+0x27f/0x7f0 task_work_run+0x136/0x1b0 exit_to_usermode_loop+0x1a7/0x1d0 do_syscall_64+0x461/0x580 entry_SYSCALL_64_after_hwframe+0x49/0xbe Syzkaller reproducer: r0 = perf_event_open(&(0x7f0000000000)={0x0, 0x70, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, @perf_config_ext}, 0x0, 0x0, 0xffffffffffffffff, 0x0) r1 = socket$alg(0x26, 0x5, 0x0) getrusage(0x0, 0x0) bind(r1, &(0x7f00000001c0)=@alg={0x26, 'hash\x00', 0x0, 0x0, 'sha256-ssse3\x00'}, 0x80) r2 = accept(r1, 0x0, 0x0) r3 = accept4$unix(r2, 0x0, 0x0, 0x0) r4 = dup3(r3, r0, 0x0) fchownat(r4, &(0x7f00000000c0)='\x00', 0x0, 0x0, 0x1000) Fixes: 6d8c50dcb029 ("socket: close race condition between sock_close() and sockfs_setattr()") Signed-off-by: Mao Wenan <maowenan@huawei.com> Signed-off-by: David S. Miller <davem@davemloft.net> (cherry picked from commit 9060cb719e61b685ec0102574e10337fa5f445ea) Signed-off-by: Greg Kroah-Hartman <gregkh@google.com> Change-Id: Ia63c10f857d4f1081edd2d8df26b18829b9ec691 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2019-02-18 10:44:44 +08:00
sock->sk = NULL;
}
return 0;
}
EXPORT_SYMBOL_GPL(af_alg_release);
void af_alg_release_parent(struct sock *sk)
{
struct alg_sock *ask = alg_sk(sk);
unsigned int nokey = atomic_read(&ask->nokey_refcnt);
sk = ask->parent;
ask = alg_sk(sk);
if (nokey)
atomic_dec(&ask->nokey_refcnt);
if (atomic_dec_and_test(&ask->refcnt))
sock_put(sk);
}
EXPORT_SYMBOL_GPL(af_alg_release_parent);
static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
const u32 allowed = CRYPTO_ALG_KERN_DRIVER_ONLY;
struct sock *sk = sock->sk;
struct alg_sock *ask = alg_sk(sk);
struct sockaddr_alg *sa = (void *)uaddr;
const struct af_alg_type *type;
void *private;
int err;
if (sock->state == SS_CONNECTED)
return -EINVAL;
if (addr_len != sizeof(*sa))
return -EINVAL;
/* If caller uses non-allowed flag, return error. */
if ((sa->salg_feat & ~allowed) || (sa->salg_mask & ~allowed))
return -EINVAL;
sa->salg_type[sizeof(sa->salg_type) - 1] = 0;
sa->salg_name[sizeof(sa->salg_name) - 1] = 0;
type = alg_get_type(sa->salg_type);
if (IS_ERR(type) && PTR_ERR(type) == -ENOENT) {
request_module("algif-%s", sa->salg_type);
type = alg_get_type(sa->salg_type);
}
if (IS_ERR(type))
return PTR_ERR(type);
private = type->bind(sa->salg_name, sa->salg_feat, sa->salg_mask);
if (IS_ERR(private)) {
module_put(type->owner);
return PTR_ERR(private);
}
err = -EBUSY;
lock_sock(sk);
if (atomic_read(&ask->refcnt))
goto unlock;
swap(ask->type, type);
swap(ask->private, private);
err = 0;
unlock:
release_sock(sk);
alg_do_release(type, private);
return err;
}
static int alg_setkey(struct sock *sk, char __user *ukey,
unsigned int keylen)
{
struct alg_sock *ask = alg_sk(sk);
const struct af_alg_type *type = ask->type;
u8 *key;
int err;
key = sock_kmalloc(sk, keylen, GFP_KERNEL);
if (!key)
return -ENOMEM;
err = -EFAULT;
if (copy_from_user(key, ukey, keylen))
goto out;
err = type->setkey(ask->private, key, keylen);
out:
sock_kzfree_s(sk, key, keylen);
return err;
}
static int alg_setsockopt(struct socket *sock, int level, int optname,
char __user *optval, unsigned int optlen)
{
struct sock *sk = sock->sk;
struct alg_sock *ask = alg_sk(sk);
const struct af_alg_type *type;
int err = -EBUSY;
lock_sock(sk);
if (atomic_read(&ask->refcnt) != atomic_read(&ask->nokey_refcnt))
goto unlock;
type = ask->type;
err = -ENOPROTOOPT;
if (level != SOL_ALG || !type)
goto unlock;
switch (optname) {
case ALG_SET_KEY:
if (sock->state == SS_CONNECTED)
goto unlock;
if (!type->setkey)
goto unlock;
err = alg_setkey(sk, optval, optlen);
break;
case ALG_SET_AEAD_AUTHSIZE:
if (sock->state == SS_CONNECTED)
goto unlock;
if (!type->setauthsize)
goto unlock;
err = type->setauthsize(ask->private, optlen);
}
unlock:
release_sock(sk);
return err;
}
BACKPORT: 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> Signed-off-by: Sorayukii <sorayukii69@gmail.com>
2017-03-09 08:09:05 +00:00
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;
struct sock *sk2;
unsigned int nokey;
int err;
lock_sock(sk);
type = ask->type;
err = -EINVAL;
if (!type)
goto unlock;
BACKPORT: 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> Signed-off-by: Sorayukii <sorayukii69@gmail.com>
2017-03-09 08:09:05 +00:00
sk2 = sk_alloc(sock_net(sk), PF_ALG, GFP_KERNEL, &alg_proto, kern);
err = -ENOMEM;
if (!sk2)
goto unlock;
sock_init_data(newsock, sk2);
sock_graft(sk2, newsock);
security_sk_clone(sk, sk2);
err = type->accept(ask->private, sk2);
nokey = err == -ENOKEY;
if (nokey && type->accept_nokey)
err = type->accept_nokey(ask->private, sk2);
if (err)
goto unlock;
sk2->sk_family = PF_ALG;
if (atomic_inc_return_relaxed(&ask->refcnt) == 1)
sock_hold(sk);
if (nokey) {
atomic_inc(&ask->nokey_refcnt);
atomic_set(&alg_sk(sk2)->nokey_refcnt, 1);
}
alg_sk(sk2)->parent = sk;
alg_sk(sk2)->type = type;
newsock->ops = type->ops;
newsock->state = SS_CONNECTED;
if (nokey)
newsock->ops = type->ops_nokey;
err = 0;
unlock:
release_sock(sk);
return err;
}
EXPORT_SYMBOL_GPL(af_alg_accept);
BACKPORT: 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> Signed-off-by: Sorayukii <sorayukii69@gmail.com>
2017-03-09 08:09:05 +00:00
static int alg_accept(struct socket *sock, struct socket *newsock, int flags,
bool kern)
{
BACKPORT: 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> Signed-off-by: Sorayukii <sorayukii69@gmail.com>
2017-03-09 08:09:05 +00:00
return af_alg_accept(sock->sk, newsock, kern);
}
static const struct proto_ops alg_proto_ops = {
.family = PF_ALG,
.owner = THIS_MODULE,
.connect = sock_no_connect,
.socketpair = sock_no_socketpair,
.getname = sock_no_getname,
.ioctl = sock_no_ioctl,
.listen = sock_no_listen,
.shutdown = sock_no_shutdown,
.getsockopt = sock_no_getsockopt,
.mmap = sock_no_mmap,
.sendpage = sock_no_sendpage,
.sendmsg = sock_no_sendmsg,
.recvmsg = sock_no_recvmsg,
.poll = sock_no_poll,
.bind = alg_bind,
.release = af_alg_release,
.setsockopt = alg_setsockopt,
.accept = alg_accept,
};
static void alg_sock_destruct(struct sock *sk)
{
struct alg_sock *ask = alg_sk(sk);
alg_do_release(ask->type, ask->private);
}
static int alg_create(struct net *net, struct socket *sock, int protocol,
int kern)
{
struct sock *sk;
int err;
if (sock->type != SOCK_SEQPACKET)
return -ESOCKTNOSUPPORT;
if (protocol != 0)
return -EPROTONOSUPPORT;
err = -ENOMEM;
sk = sk_alloc(net, PF_ALG, GFP_KERNEL, &alg_proto, kern);
if (!sk)
goto out;
sock->ops = &alg_proto_ops;
sock_init_data(sock, sk);
sk->sk_family = PF_ALG;
sk->sk_destruct = alg_sock_destruct;
return 0;
out:
return err;
}
static const struct net_proto_family alg_family = {
.family = PF_ALG,
.create = alg_create,
.owner = THIS_MODULE,
};
int af_alg_make_sg(struct af_alg_sgl *sgl, struct iov_iter *iter, int len)
{
size_t off;
ssize_t n;
int npages, i;
n = iov_iter_get_pages(iter, sgl->pages, len, ALG_MAX_PAGES, &off);
if (n < 0)
return n;
npages = (off + n + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (WARN_ON(npages == 0))
return -EINVAL;
/* Add one extra for linking */
sg_init_table(sgl->sg, npages + 1);
for (i = 0, len = n; i < npages; i++) {
int plen = min_t(int, len, PAGE_SIZE - off);
sg_set_page(sgl->sg + i, sgl->pages[i], plen, off);
off = 0;
len -= plen;
}
sg_mark_end(sgl->sg + npages - 1);
sgl->npages = npages;
return n;
}
EXPORT_SYMBOL_GPL(af_alg_make_sg);
void af_alg_link_sg(struct af_alg_sgl *sgl_prev, struct af_alg_sgl *sgl_new)
{
sg_unmark_end(sgl_prev->sg + sgl_prev->npages - 1);
sg_chain(sgl_prev->sg, sgl_prev->npages + 1, sgl_new->sg);
}
EXPORT_SYMBOL_GPL(af_alg_link_sg);
void af_alg_free_sg(struct af_alg_sgl *sgl)
{
int i;
for (i = 0; i < sgl->npages; i++)
put_page(sgl->pages[i]);
}
EXPORT_SYMBOL_GPL(af_alg_free_sg);
int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con)
{
struct cmsghdr *cmsg;
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
if (cmsg->cmsg_level != SOL_ALG)
continue;
switch (cmsg->cmsg_type) {
case ALG_SET_IV:
if (cmsg->cmsg_len < CMSG_LEN(sizeof(*con->iv)))
return -EINVAL;
con->iv = (void *)CMSG_DATA(cmsg);
if (cmsg->cmsg_len < CMSG_LEN(con->iv->ivlen +
sizeof(*con->iv)))
return -EINVAL;
break;
case ALG_SET_OP:
if (cmsg->cmsg_len < CMSG_LEN(sizeof(u32)))
return -EINVAL;
con->op = *(u32 *)CMSG_DATA(cmsg);
break;
case ALG_SET_AEAD_ASSOCLEN:
if (cmsg->cmsg_len < CMSG_LEN(sizeof(u32)))
return -EINVAL;
con->aead_assoclen = *(u32 *)CMSG_DATA(cmsg);
break;
default:
return -EINVAL;
}
}
return 0;
}
EXPORT_SYMBOL_GPL(af_alg_cmsg_send);
int af_alg_wait_for_completion(int err, struct af_alg_completion *completion)
{
switch (err) {
case -EINPROGRESS:
case -EBUSY:
wait_for_completion(&completion->completion);
reinit_completion(&completion->completion);
err = completion->err;
break;
};
return err;
}
EXPORT_SYMBOL_GPL(af_alg_wait_for_completion);
void af_alg_complete(struct crypto_async_request *req, int err)
{
struct af_alg_completion *completion = req->data;
if (err == -EINPROGRESS)
return;
completion->err = err;
complete(&completion->completion);
}
EXPORT_SYMBOL_GPL(af_alg_complete);
static int __init af_alg_init(void)
{
int err = proto_register(&alg_proto, 0);
if (err)
goto out;
err = sock_register(&alg_family);
if (err != 0)
goto out_unregister_proto;
out:
return err;
out_unregister_proto:
proto_unregister(&alg_proto);
goto out;
}
static void __exit af_alg_exit(void)
{
sock_unregister(PF_ALG);
proto_unregister(&alg_proto);
}
module_init(af_alg_init);
module_exit(af_alg_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NETPROTO(AF_ALG);