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
attr.c
/*
* linux/fs/attr.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
* changes by Thomas Schoebel-Theuer
*/
#include <linux/module.h>
#include <linux/time.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/smp_lock.h>
#include <linux/capability.h>
#include <linux/fsnotify.h>
#include <linux/fcntl.h>
#include <linux/quotaops.h>
#include <linux/security.h>
/* Taken over from the old code... */
/* POSIX UID/GID verification for setting inode attributes. */
int inode_change_ok(struct inode *inode, struct iattr *attr)
{
int retval = -EPERM;
unsigned int ia_valid = attr->ia_valid;
/* If force is set do it anyway. */
if (ia_valid & ATTR_FORCE)
goto fine;
/* Make sure a caller can chown. */
if ((ia_valid & ATTR_UID) &&
(current->fsuid != inode->i_uid ||
attr->ia_uid != inode->i_uid) && !capable(CAP_CHOWN))
goto error;
/* Make sure caller can chgrp. */
if ((ia_valid & ATTR_GID) &&
(current->fsuid != inode->i_uid ||
(!in_group_p(attr->ia_gid) && attr->ia_gid != inode->i_gid)) &&
!capable(CAP_CHOWN))
goto error;
/* Make sure a caller can chmod. */
if (ia_valid & ATTR_MODE) {
if ((current->fsuid != inode->i_uid) && !capable(CAP_FOWNER))
goto error;
/* Also check the setgid bit! */
if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid :
inode->i_gid) && !capable(CAP_FSETID))
attr->ia_mode &= ~S_ISGID;
}
/* Check for setting the inode time. */
if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET)) {
if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER))
goto error;
}
fine:
retval = 0;
error:
return retval;
}
EXPORT_SYMBOL(inode_change_ok);
int inode_setattr(struct inode * inode, struct iattr * attr)
{
unsigned int ia_valid = attr->ia_valid;
if (ia_valid & ATTR_SIZE &&
attr->ia_size != i_size_read(inode)) {
int error = vmtruncate(inode, attr->ia_size);
if (error)
return error;
}
if (ia_valid & ATTR_UID)
inode->i_uid = attr->ia_uid;
if (ia_valid & ATTR_GID)
inode->i_gid = attr->ia_gid;
if (ia_valid & ATTR_ATIME)
inode->i_atime = timespec_trunc(attr->ia_atime,
inode->i_sb->s_time_gran);
if (ia_valid & ATTR_MTIME)
inode->i_mtime = timespec_trunc(attr->ia_mtime,
inode->i_sb->s_time_gran);
if (ia_valid & ATTR_CTIME)
inode->i_ctime = timespec_trunc(attr->ia_ctime,
inode->i_sb->s_time_gran);
if (ia_valid & ATTR_MODE) {
umode_t mode = attr->ia_mode;
if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
mode &= ~S_ISGID;
inode->i_mode = mode;
}
mark_inode_dirty(inode);
return 0;
}
EXPORT_SYMBOL(inode_setattr);
int notify_change(struct dentry * dentry, struct iattr * attr)
{
struct inode *inode = dentry->d_inode;
mode_t mode;
int error;
struct timespec now;
unsigned int ia_valid = attr->ia_valid;
mode = inode->i_mode;
now = current_fs_time(inode->i_sb);
attr->ia_ctime = now;
if (!(ia_valid & ATTR_ATIME_SET))
attr->ia_atime = now;
if (!(ia_valid & ATTR_MTIME_SET))
attr->ia_mtime = now;
if (ia_valid & ATTR_KILL_SUID) {
attr->ia_valid &= ~ATTR_KILL_SUID;
if (mode & S_ISUID) {
if (!(ia_valid & ATTR_MODE)) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;
}
attr->ia_mode &= ~S_ISUID;
}
}
if (ia_valid & ATTR_KILL_SGID) {
attr->ia_valid &= ~ ATTR_KILL_SGID;
if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
if (!(ia_valid & ATTR_MODE)) {
ia_valid = attr->ia_valid |= ATTR_MODE;
attr->ia_mode = inode->i_mode;
}
attr->ia_mode &= ~S_ISGID;
}
}
if (!attr->ia_valid)
return 0;
if (ia_valid & ATTR_SIZE)
down_write(&dentry->d_inode->i_alloc_sem);
if (inode->i_op && inode->i_op->setattr) {
error = security_inode_setattr(dentry, attr);
if (!error)
error = inode->i_op->setattr(dentry, attr);
} else {
error = inode_change_ok(inode, attr);
if (!error)
error = security_inode_setattr(dentry, attr);
if (!error) {
if ((ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
(ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid))
error = DQUOT_TRANSFER(inode, attr) ? -EDQUOT : 0;
if (!error)
error = inode_setattr(inode, attr);
}
}
if (ia_valid & ATTR_SIZE)
up_write(&dentry->d_inode->i_alloc_sem);
if (!error)
fsnotify_change(dentry, ia_valid);
return error;
}
EXPORT_SYMBOL(notify_change);
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...