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
file_table.c
/*
* linux/fs/file_table.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
* Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu)
*/
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/security.h>
#include <linux/eventpoll.h>
#include <linux/rcupdate.h>
#include <linux/mount.h>
#include <linux/capability.h>
#include <linux/cdev.h>
#include <linux/fsnotify.h>
#include <linux/sysctl.h>
#include <linux/percpu_counter.h>
#include <asm/atomic.h>
/* sysctl tunables... */
struct files_stat_struct files_stat = {
.max_files = NR_FILE
};
/* public. Not pretty! */
__cacheline_aligned_in_smp DEFINE_SPINLOCK(files_lock);
static struct percpu_counter nr_files __cacheline_aligned_in_smp;
static inline void file_free_rcu(struct rcu_head *head)
{
struct file *f = container_of(head, struct file, f_u.fu_rcuhead);
kmem_cache_free(filp_cachep, f);
}
static inline void file_free(struct file *f)
{
percpu_counter_dec(&nr_files);
call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
}
/*
* Return the total number of open files in the system
*/
static int get_nr_files(void)
{
return percpu_counter_read_positive(&nr_files);
}
/*
* Return the maximum number of open files in the system
*/
int get_max_files(void)
{
return files_stat.max_files;
}
EXPORT_SYMBOL_GPL(get_max_files);
/*
* Handle nr_files sysctl
*/
#if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS)
int proc_nr_files(ctl_table *table, int write, struct file *filp,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
files_stat.nr_files = get_nr_files();
return proc_dointvec(table, write, filp, buffer, lenp, ppos);
}
#else
int proc_nr_files(ctl_table *table, int write, struct file *filp,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
#endif
/* Find an unused file structure and return a pointer to it.
* Returns NULL, if there are no more free file structures or
* we run out of memory.
*/
struct file *get_empty_filp(void)
{
struct task_struct *tsk;
static int old_max;
struct file * f;
/*
* Privileged users can go above max_files
*/
if (get_nr_files() >= files_stat.max_files && !capable(CAP_SYS_ADMIN)) {
/*
* percpu_counters are inaccurate. Do an expensive check before
* we go and fail.
*/
if (percpu_counter_sum(&nr_files) >= files_stat.max_files)
goto over;
}
f = kmem_cache_alloc(filp_cachep, GFP_KERNEL);
if (f == NULL)
goto fail;
percpu_counter_inc(&nr_files);
memset(f, 0, sizeof(*f));
if (security_file_alloc(f))
goto fail_sec;
tsk = current;
INIT_LIST_HEAD(&f->f_u.fu_list);
atomic_set(&f->f_count, 1);
rwlock_init(&f->f_owner.lock);
f->f_uid = tsk->fsuid;
f->f_gid = tsk->fsgid;
eventpoll_init_file(f);
/* f->f_version: 0 */
return f;
over:
/* Ran out of filps - report that */
if (get_nr_files() > old_max) {
printk(KERN_INFO "VFS: file-max limit %d reached\n",
get_max_files());
old_max = get_nr_files();
}
goto fail;
fail_sec:
file_free(f);
fail:
return NULL;
}
EXPORT_SYMBOL(get_empty_filp);
void fastcall fput(struct file *file)
{
if (atomic_dec_and_test(&file->f_count))
__fput(file);
}
EXPORT_SYMBOL(fput);
/* __fput is called from task context when aio completion releases the last
* last use of a struct file *. Do not use otherwise.
*/
void fastcall __fput(struct file *file)
{
struct dentry *dentry = file->f_dentry;
struct vfsmount *mnt = file->f_vfsmnt;
struct inode *inode = dentry->d_inode;
might_sleep();
fsnotify_close(file);
/*
* The function eventpoll_release() should be the first called
* in the file cleanup chain.
*/
eventpoll_release(file);
locks_remove_flock(file);
if (file->f_op && file->f_op->release)
file->f_op->release(inode, file);
security_file_free(file);
if (unlikely(inode->i_cdev != NULL))
cdev_put(inode->i_cdev);
fops_put(file->f_op);
if (file->f_mode & FMODE_WRITE)
put_write_access(inode);
file_kill(file);
file->f_dentry = NULL;
file->f_vfsmnt = NULL;
file_free(file);
dput(dentry);
mntput(mnt);
}
struct file fastcall *fget(unsigned int fd)
{
struct file *file;
struct files_struct *files = current->files;
rcu_read_lock();
file = fcheck_files(files, fd);
if (file) {
if (!atomic_inc_not_zero(&file->f_count)) {
/* File object ref couldn't be taken */
rcu_read_unlock();
return NULL;
}
}
rcu_read_unlock();
return file;
}
EXPORT_SYMBOL(fget);
/*
* Lightweight file lookup - no refcnt increment if fd table isn't shared.
* You can use this only if it is guranteed that the current task already
* holds a refcnt to that file. That check has to be done at fget() only
* and a flag is returned to be passed to the corresponding fput_light().
* There must not be a cloning between an fget_light/fput_light pair.
*/
struct file fastcall *fget_light(unsigned int fd, int *fput_needed)
{
struct file *file;
struct files_struct *files = current->files;
*fput_needed = 0;
if (likely((atomic_read(&files->count) == 1))) {
file = fcheck_files(files, fd);
} else {
rcu_read_lock();
file = fcheck_files(files, fd);
if (file) {
if (atomic_inc_not_zero(&file->f_count))
*fput_needed = 1;
else
/* Didn't get the reference, someone's freed */
file = NULL;
}
rcu_read_unlock();
}
return file;
}
void put_filp(struct file *file)
{
if (atomic_dec_and_test(&file->f_count)) {
security_file_free(file);
file_kill(file);
file_free(file);
}
}
void file_move(struct file *file, struct list_head *list)
{
if (!list)
return;
file_list_lock();
list_move(&file->f_u.fu_list, list);
file_list_unlock();
}
void file_kill(struct file *file)
{
if (!list_empty(&file->f_u.fu_list)) {
file_list_lock();
list_del_init(&file->f_u.fu_list);
file_list_unlock();
}
}
int fs_may_remount_ro(struct super_block *sb)
{
struct list_head *p;
/* Check that no files are currently opened for writing. */
file_list_lock();
list_for_each(p, &sb->s_files) {
struct file *file = list_entry(p, struct file, f_u.fu_list);
struct inode *inode = file->f_dentry->d_inode;
/* File with pending delete? */
if (inode->i_nlink == 0)
goto too_bad;
/* Writeable file? */
if (S_ISREG(inode->i_mode) && (file->f_mode & FMODE_WRITE))
goto too_bad;
}
file_list_unlock();
return 1; /* Tis' cool bro. */
too_bad:
file_list_unlock();
return 0;
}
void __init files_init(unsigned long mempages)
{
int n;
/* One file with associated inode and dcache is very roughly 1K.
* Per default don't use more than 10% of our memory for files.
*/
n = (mempages * (PAGE_SIZE / 1024)) / 10;
files_stat.max_files = n;
if (files_stat.max_files < NR_FILE)
files_stat.max_files = NR_FILE;
files_defer_init();
percpu_counter_init(&nr_files, 0);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...