Revision e91467ecd1ef381377fd327c0ded922835ec52ab authored by Christian Borntraeger on 05 August 2006, 19:13:52 UTC, committed by Linus Torvalds on 06 August 2006, 15:57:46 UTC
This patch adds a barrier() in futex unqueue_me to avoid aliasing of two pointers. On my s390x system I saw the following oops: Unable to handle kernel pointer dereference at virtual kernel address 0000000000000000 Oops: 0004 [#1] CPU: 0 Not tainted Process mytool (pid: 13613, task: 000000003ecb6ac0, ksp: 00000000366bdbd8) Krnl PSW : 0704d00180000000 00000000003c9ac2 (_spin_lock+0xe/0x30) Krnl GPRS: 00000000ffffffff 000000003ecb6ac0 0000000000000000 0700000000000000 0000000000000000 0000000000000000 000001fe00002028 00000000000c091f 000001fe00002054 000001fe00002054 0000000000000000 00000000366bddc0 00000000005ef8c0 00000000003d00e8 0000000000144f91 00000000366bdcb8 Krnl Code: ba 4e 20 00 12 44 b9 16 00 3e a7 84 00 08 e3 e0 f0 88 00 04 Call Trace: ([<0000000000144f90>] unqueue_me+0x40/0xe4) [<0000000000145a0c>] do_futex+0x33c/0xc40 [<000000000014643e>] sys_futex+0x12e/0x144 [<000000000010bb00>] sysc_noemu+0x10/0x16 [<000002000003741c>] 0x2000003741c The code in question is: static int unqueue_me(struct futex_q *q) { int ret = 0; spinlock_t *lock_ptr; /* In the common case we don't take the spinlock, which is nice. */ retry: lock_ptr = q->lock_ptr; if (lock_ptr != 0) { spin_lock(lock_ptr); /* * q->lock_ptr can change between reading it and * spin_lock(), causing us to take the wrong lock. This * corrects the race condition. [...] and my compiler (gcc 4.1.0) makes the following out of it: 00000000000003c8 <unqueue_me>: 3c8: eb bf f0 70 00 24 stmg %r11,%r15,112(%r15) 3ce: c0 d0 00 00 00 00 larl %r13,3ce <unqueue_me+0x6> 3d0: R_390_PC32DBL .rodata+0x2a 3d4: a7 f1 1e 00 tml %r15,7680 3d8: a7 84 00 01 je 3da <unqueue_me+0x12> 3dc: b9 04 00 ef lgr %r14,%r15 3e0: a7 fb ff d0 aghi %r15,-48 3e4: b9 04 00 b2 lgr %r11,%r2 3e8: e3 e0 f0 98 00 24 stg %r14,152(%r15) 3ee: e3 c0 b0 28 00 04 lg %r12,40(%r11) /* write q->lock_ptr in r12 */ 3f4: b9 02 00 cc ltgr %r12,%r12 3f8: a7 84 00 4b je 48e <unqueue_me+0xc6> /* if r12 is zero then jump over the code.... */ 3fc: e3 20 b0 28 00 04 lg %r2,40(%r11) /* write q->lock_ptr in r2 */ 402: c0 e5 00 00 00 00 brasl %r14,402 <unqueue_me+0x3a> 404: R_390_PC32DBL _spin_lock+0x2 /* use r2 as parameter for spin_lock */ So the code becomes more or less: if (q->lock_ptr != 0) spin_lock(q->lock_ptr) instead of if (lock_ptr != 0) spin_lock(lock_ptr) Which caused the oops from above. After adding a barrier gcc creates code without this problem: [...] (the same) 3ee: e3 c0 b0 28 00 04 lg %r12,40(%r11) 3f4: b9 02 00 cc ltgr %r12,%r12 3f8: b9 04 00 2c lgr %r2,%r12 3fc: a7 84 00 48 je 48c <unqueue_me+0xc4> 400: c0 e5 00 00 00 00 brasl %r14,400 <unqueue_me+0x38> 402: R_390_PC32DBL _spin_lock+0x2 As a general note, this code of unqueue_me seems a bit fishy. The retry logic of unqueue_me only works if we can guarantee, that the original value of q->lock_ptr is always a spinlock (Otherwise we overwrite kernel memory). We know that q->lock_ptr can change. I dont know what happens with the original spinlock, as I am not an expert with the futex code. Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Acked-by: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@timesys.com> Signed-off-by: Christian Borntraeger <borntrae@de.ibm.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
1 parent 72f0b4e
pnode.c
/*
* linux/fs/pnode.c
*
* (C) Copyright IBM Corporation 2005.
* Released under GPL v2.
* Author : Ram Pai (linuxram@us.ibm.com)
*
*/
#include <linux/namespace.h>
#include <linux/mount.h>
#include <linux/fs.h>
#include "pnode.h"
/* return the next shared peer mount of @p */
static inline struct vfsmount *next_peer(struct vfsmount *p)
{
return list_entry(p->mnt_share.next, struct vfsmount, mnt_share);
}
static inline struct vfsmount *first_slave(struct vfsmount *p)
{
return list_entry(p->mnt_slave_list.next, struct vfsmount, mnt_slave);
}
static inline struct vfsmount *next_slave(struct vfsmount *p)
{
return list_entry(p->mnt_slave.next, struct vfsmount, mnt_slave);
}
static int do_make_slave(struct vfsmount *mnt)
{
struct vfsmount *peer_mnt = mnt, *master = mnt->mnt_master;
struct vfsmount *slave_mnt;
/*
* slave 'mnt' to a peer mount that has the
* same root dentry. If none is available than
* slave it to anything that is available.
*/
while ((peer_mnt = next_peer(peer_mnt)) != mnt &&
peer_mnt->mnt_root != mnt->mnt_root) ;
if (peer_mnt == mnt) {
peer_mnt = next_peer(mnt);
if (peer_mnt == mnt)
peer_mnt = NULL;
}
list_del_init(&mnt->mnt_share);
if (peer_mnt)
master = peer_mnt;
if (master) {
list_for_each_entry(slave_mnt, &mnt->mnt_slave_list, mnt_slave)
slave_mnt->mnt_master = master;
list_move(&mnt->mnt_slave, &master->mnt_slave_list);
list_splice(&mnt->mnt_slave_list, master->mnt_slave_list.prev);
INIT_LIST_HEAD(&mnt->mnt_slave_list);
} else {
struct list_head *p = &mnt->mnt_slave_list;
while (!list_empty(p)) {
slave_mnt = list_entry(p->next,
struct vfsmount, mnt_slave);
list_del_init(&slave_mnt->mnt_slave);
slave_mnt->mnt_master = NULL;
}
}
mnt->mnt_master = master;
CLEAR_MNT_SHARED(mnt);
INIT_LIST_HEAD(&mnt->mnt_slave_list);
return 0;
}
void change_mnt_propagation(struct vfsmount *mnt, int type)
{
if (type == MS_SHARED) {
set_mnt_shared(mnt);
return;
}
do_make_slave(mnt);
if (type != MS_SLAVE) {
list_del_init(&mnt->mnt_slave);
mnt->mnt_master = NULL;
if (type == MS_UNBINDABLE)
mnt->mnt_flags |= MNT_UNBINDABLE;
}
}
/*
* get the next mount in the propagation tree.
* @m: the mount seen last
* @origin: the original mount from where the tree walk initiated
*/
static struct vfsmount *propagation_next(struct vfsmount *m,
struct vfsmount *origin)
{
/* are there any slaves of this mount? */
if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
return first_slave(m);
while (1) {
struct vfsmount *next;
struct vfsmount *master = m->mnt_master;
if (master == origin->mnt_master) {
next = next_peer(m);
return ((next == origin) ? NULL : next);
} else if (m->mnt_slave.next != &master->mnt_slave_list)
return next_slave(m);
/* back at master */
m = master;
}
}
/*
* return the source mount to be used for cloning
*
* @dest the current destination mount
* @last_dest the last seen destination mount
* @last_src the last seen source mount
* @type return CL_SLAVE if the new mount has to be
* cloned as a slave.
*/
static struct vfsmount *get_source(struct vfsmount *dest,
struct vfsmount *last_dest,
struct vfsmount *last_src,
int *type)
{
struct vfsmount *p_last_src = NULL;
struct vfsmount *p_last_dest = NULL;
*type = CL_PROPAGATION;
if (IS_MNT_SHARED(dest))
*type |= CL_MAKE_SHARED;
while (last_dest != dest->mnt_master) {
p_last_dest = last_dest;
p_last_src = last_src;
last_dest = last_dest->mnt_master;
last_src = last_src->mnt_master;
}
if (p_last_dest) {
do {
p_last_dest = next_peer(p_last_dest);
} while (IS_MNT_NEW(p_last_dest));
}
if (dest != p_last_dest) {
*type |= CL_SLAVE;
return last_src;
} else
return p_last_src;
}
/*
* mount 'source_mnt' under the destination 'dest_mnt' at
* dentry 'dest_dentry'. And propagate that mount to
* all the peer and slave mounts of 'dest_mnt'.
* Link all the new mounts into a propagation tree headed at
* source_mnt. Also link all the new mounts using ->mnt_list
* headed at source_mnt's ->mnt_list
*
* @dest_mnt: destination mount.
* @dest_dentry: destination dentry.
* @source_mnt: source mount.
* @tree_list : list of heads of trees to be attached.
*/
int propagate_mnt(struct vfsmount *dest_mnt, struct dentry *dest_dentry,
struct vfsmount *source_mnt, struct list_head *tree_list)
{
struct vfsmount *m, *child;
int ret = 0;
struct vfsmount *prev_dest_mnt = dest_mnt;
struct vfsmount *prev_src_mnt = source_mnt;
LIST_HEAD(tmp_list);
LIST_HEAD(umount_list);
for (m = propagation_next(dest_mnt, dest_mnt); m;
m = propagation_next(m, dest_mnt)) {
int type;
struct vfsmount *source;
if (IS_MNT_NEW(m))
continue;
source = get_source(m, prev_dest_mnt, prev_src_mnt, &type);
if (!(child = copy_tree(source, source->mnt_root, type))) {
ret = -ENOMEM;
list_splice(tree_list, tmp_list.prev);
goto out;
}
if (is_subdir(dest_dentry, m->mnt_root)) {
mnt_set_mountpoint(m, dest_dentry, child);
list_add_tail(&child->mnt_hash, tree_list);
} else {
/*
* This can happen if the parent mount was bind mounted
* on some subdirectory of a shared/slave mount.
*/
list_add_tail(&child->mnt_hash, &tmp_list);
}
prev_dest_mnt = m;
prev_src_mnt = child;
}
out:
spin_lock(&vfsmount_lock);
while (!list_empty(&tmp_list)) {
child = list_entry(tmp_list.next, struct vfsmount, mnt_hash);
list_del_init(&child->mnt_hash);
umount_tree(child, 0, &umount_list);
}
spin_unlock(&vfsmount_lock);
release_mounts(&umount_list);
return ret;
}
/*
* return true if the refcount is greater than count
*/
static inline int do_refcount_check(struct vfsmount *mnt, int count)
{
int mycount = atomic_read(&mnt->mnt_count);
return (mycount > count);
}
/*
* check if the mount 'mnt' can be unmounted successfully.
* @mnt: the mount to be checked for unmount
* NOTE: unmounting 'mnt' would naturally propagate to all
* other mounts its parent propagates to.
* Check if any of these mounts that **do not have submounts**
* have more references than 'refcnt'. If so return busy.
*/
int propagate_mount_busy(struct vfsmount *mnt, int refcnt)
{
struct vfsmount *m, *child;
struct vfsmount *parent = mnt->mnt_parent;
int ret = 0;
if (mnt == parent)
return do_refcount_check(mnt, refcnt);
/*
* quickly check if the current mount can be unmounted.
* If not, we don't have to go checking for all other
* mounts
*/
if (!list_empty(&mnt->mnt_mounts) || do_refcount_check(mnt, refcnt))
return 1;
for (m = propagation_next(parent, parent); m;
m = propagation_next(m, parent)) {
child = __lookup_mnt(m, mnt->mnt_mountpoint, 0);
if (child && list_empty(&child->mnt_mounts) &&
(ret = do_refcount_check(child, 1)))
break;
}
return ret;
}
/*
* NOTE: unmounting 'mnt' naturally propagates to all other mounts its
* parent propagates to.
*/
static void __propagate_umount(struct vfsmount *mnt)
{
struct vfsmount *parent = mnt->mnt_parent;
struct vfsmount *m;
BUG_ON(parent == mnt);
for (m = propagation_next(parent, parent); m;
m = propagation_next(m, parent)) {
struct vfsmount *child = __lookup_mnt(m,
mnt->mnt_mountpoint, 0);
/*
* umount the child only if the child has no
* other children
*/
if (child && list_empty(&child->mnt_mounts))
list_move_tail(&child->mnt_hash, &mnt->mnt_hash);
}
}
/*
* collect all mounts that receive propagation from the mount in @list,
* and return these additional mounts in the same list.
* @list: the list of mounts to be unmounted.
*/
int propagate_umount(struct list_head *list)
{
struct vfsmount *mnt;
list_for_each_entry(mnt, list, mnt_hash)
__propagate_umount(mnt);
return 0;
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...