2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2007-09-20 16:31:38 +08:00
|
|
|
* fs/sysfs/bin.c - sysfs binary file implementation
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* Copyright (c) 2003 Patrick Mochel
|
|
|
|
* Copyright (c) 2003 Matthew Wilcox
|
|
|
|
* Copyright (c) 2004 Silicon Graphics, Inc.
|
2007-09-20 16:31:38 +08:00
|
|
|
* Copyright (c) 2007 SUSE Linux Products GmbH
|
|
|
|
* Copyright (c) 2007 Tejun Heo <teheo@suse.de>
|
|
|
|
*
|
|
|
|
* This file is released under the GPLv2.
|
|
|
|
*
|
|
|
|
* Please see Documentation/filesystems/sysfs.txt for more information.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
#undef DEBUG
|
|
|
|
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/fs.h>
|
2006-07-11 14:05:25 +08:00
|
|
|
#include <linux/kernel.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#include <linux/kobject.h>
|
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/slab.h>
|
2007-07-26 22:53:53 +08:00
|
|
|
#include <linux/mutex.h>
|
2009-03-05 03:57:20 +08:00
|
|
|
#include <linux/mm.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#include <asm/uaccess.h>
|
|
|
|
|
|
|
|
#include "sysfs.h"
|
|
|
|
|
2009-03-05 03:57:20 +08:00
|
|
|
/*
|
|
|
|
* There's one bin_buffer for each open file.
|
|
|
|
*
|
|
|
|
* filp->private_data points to bin_buffer and
|
|
|
|
* sysfs_dirent->s_bin_attr.buffers points to a the bin_buffer s
|
|
|
|
* sysfs_dirent->s_bin_attr.buffers is protected by sysfs_bin_lock
|
|
|
|
*/
|
|
|
|
static DEFINE_MUTEX(sysfs_bin_lock);
|
|
|
|
|
2007-06-14 02:45:16 +08:00
|
|
|
struct bin_buffer {
|
2009-03-05 03:57:20 +08:00
|
|
|
struct mutex mutex;
|
|
|
|
void *buffer;
|
|
|
|
int mmapped;
|
|
|
|
struct vm_operations_struct *vm_ops;
|
|
|
|
struct file *file;
|
|
|
|
struct hlist_node list;
|
2007-06-14 02:45:16 +08:00
|
|
|
};
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static int
|
|
|
|
fill_read(struct dentry *dentry, char *buffer, loff_t off, size_t count)
|
|
|
|
{
|
2007-06-14 02:45:15 +08:00
|
|
|
struct sysfs_dirent *attr_sd = dentry->d_fsdata;
|
2007-09-20 15:05:11 +08:00
|
|
|
struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
|
|
|
|
struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
|
2007-06-14 02:45:16 +08:00
|
|
|
int rc;
|
|
|
|
|
|
|
|
/* need attr_sd for attr, its parent for kobj */
|
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
|
|
|
return -ENODEV;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-06-14 02:45:16 +08:00
|
|
|
rc = -EIO;
|
|
|
|
if (attr->read)
|
2007-06-09 13:57:22 +08:00
|
|
|
rc = attr->read(kobj, attr, buffer, off, count);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-06-14 02:45:16 +08:00
|
|
|
sysfs_put_active_two(attr_sd);
|
|
|
|
|
|
|
|
return rc;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static ssize_t
|
2007-06-14 02:45:13 +08:00
|
|
|
read(struct file *file, char __user *userbuf, size_t bytes, loff_t *off)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2007-06-14 02:45:16 +08:00
|
|
|
struct bin_buffer *bb = file->private_data;
|
2006-12-08 18:36:36 +08:00
|
|
|
struct dentry *dentry = file->f_path.dentry;
|
2005-04-17 06:20:36 +08:00
|
|
|
int size = dentry->d_inode->i_size;
|
|
|
|
loff_t offs = *off;
|
2007-06-14 02:45:13 +08:00
|
|
|
int count = min_t(size_t, bytes, PAGE_SIZE);
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
char *temp;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-01-21 07:51:16 +08:00
|
|
|
if (!bytes)
|
|
|
|
return 0;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (size) {
|
|
|
|
if (offs > size)
|
|
|
|
return 0;
|
|
|
|
if (offs + count > size)
|
|
|
|
count = size - offs;
|
|
|
|
}
|
|
|
|
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
temp = kmalloc(count, GFP_KERNEL);
|
|
|
|
if (!temp)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2007-06-14 02:45:16 +08:00
|
|
|
mutex_lock(&bb->mutex);
|
|
|
|
|
|
|
|
count = fill_read(dentry, bb->buffer, offs, count);
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
if (count < 0) {
|
|
|
|
mutex_unlock(&bb->mutex);
|
|
|
|
goto out_free;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
memcpy(temp, bb->buffer, count);
|
|
|
|
|
|
|
|
mutex_unlock(&bb->mutex);
|
|
|
|
|
|
|
|
if (copy_to_user(userbuf, temp, count)) {
|
2007-06-14 02:45:16 +08:00
|
|
|
count = -EFAULT;
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
goto out_free;
|
2007-06-14 02:45:16 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-06-14 02:45:13 +08:00
|
|
|
pr_debug("offs = %lld, *off = %lld, count = %d\n", offs, *off, count);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
*off = offs + count;
|
|
|
|
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
out_free:
|
|
|
|
kfree(temp);
|
2005-04-17 06:20:36 +08:00
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
|
|
|
flush_write(struct dentry *dentry, char *buffer, loff_t offset, size_t count)
|
|
|
|
{
|
2007-06-14 02:45:15 +08:00
|
|
|
struct sysfs_dirent *attr_sd = dentry->d_fsdata;
|
2007-09-20 15:05:11 +08:00
|
|
|
struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
|
|
|
|
struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
|
2007-06-14 02:45:16 +08:00
|
|
|
int rc;
|
|
|
|
|
|
|
|
/* need attr_sd for attr, its parent for kobj */
|
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
|
|
|
return -ENODEV;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-06-14 02:45:16 +08:00
|
|
|
rc = -EIO;
|
|
|
|
if (attr->write)
|
2007-06-09 13:57:22 +08:00
|
|
|
rc = attr->write(kobj, attr, buffer, offset, count);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-06-14 02:45:16 +08:00
|
|
|
sysfs_put_active_two(attr_sd);
|
|
|
|
|
|
|
|
return rc;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2007-06-14 02:45:13 +08:00
|
|
|
static ssize_t write(struct file *file, const char __user *userbuf,
|
|
|
|
size_t bytes, loff_t *off)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2007-06-14 02:45:16 +08:00
|
|
|
struct bin_buffer *bb = file->private_data;
|
2006-12-08 18:36:36 +08:00
|
|
|
struct dentry *dentry = file->f_path.dentry;
|
2005-04-17 06:20:36 +08:00
|
|
|
int size = dentry->d_inode->i_size;
|
|
|
|
loff_t offs = *off;
|
2007-06-14 02:45:13 +08:00
|
|
|
int count = min_t(size_t, bytes, PAGE_SIZE);
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
char *temp;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-01-21 07:51:16 +08:00
|
|
|
if (!bytes)
|
|
|
|
return 0;
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (size) {
|
|
|
|
if (offs > size)
|
|
|
|
return 0;
|
|
|
|
if (offs + count > size)
|
|
|
|
count = size - offs;
|
|
|
|
}
|
|
|
|
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
temp = kmalloc(count, GFP_KERNEL);
|
|
|
|
if (!temp)
|
|
|
|
return -ENOMEM;
|
2007-06-14 02:45:16 +08:00
|
|
|
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
if (copy_from_user(temp, userbuf, count)) {
|
2007-06-14 02:45:16 +08:00
|
|
|
count = -EFAULT;
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
goto out_free;
|
2007-06-14 02:45:16 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
mutex_lock(&bb->mutex);
|
|
|
|
|
|
|
|
memcpy(bb->buffer, temp, count);
|
|
|
|
|
2007-06-14 02:45:16 +08:00
|
|
|
count = flush_write(dentry, bb->buffer, offs, count);
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
mutex_unlock(&bb->mutex);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
if (count > 0)
|
|
|
|
*off = offs + count;
|
2007-06-14 02:45:16 +08:00
|
|
|
|
sysfs: fix deadlock
On Thu, Sep 11, 2008 at 10:27:10AM +0200, Ingo Molnar wrote:
> and it's working fine on most boxes. One testbox found this new locking
> scenario:
>
> PM: Adding info for No Bus:vcsa7
> EDAC DEBUG: MC0: i82860_check()
>
> =======================================================
> [ INFO: possible circular locking dependency detected ]
> 2.6.27-rc6-tip #1
> -------------------------------------------------------
> X/4873 is trying to acquire lock:
> (&bb->mutex){--..}, at: [<c020ba20>] mmap+0x40/0xa0
>
> but task is already holding lock:
> (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> which lock already depends on the new lock.
>
>
> the existing dependency chain (in reverse order) is:
>
> -> #1 (&mm->mmap_sem){----}:
> [<c017dc96>] validate_chain+0xa96/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c01aa8fb>] might_fault+0x6b/0x90
> [<c040b618>] copy_to_user+0x38/0x60
> [<c020bcfb>] read+0xfb/0x170
> [<c01c09a5>] vfs_read+0x95/0x110
> [<c01c1443>] sys_pread64+0x63/0x80
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> -> #0 (&bb->mutex){--..}:
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<ffffffff>] 0xffffffff
>
> other info that might help us debug this:
>
> 1 lock held by X/4873:
> #0: (&mm->mmap_sem){----}, at: [<c0125a1e>] sys_mmap2+0x8e/0xc0
>
> stack backtrace:
> Pid: 4873, comm: X Not tainted 2.6.27-rc6-tip #1
> [<c017cd09>] print_circular_bug_tail+0x79/0xc0
> [<c017d8b7>] validate_chain+0x6b7/0xf50
> [<c017a5b5>] ? trace_hardirqs_off_caller+0x15/0xb0
> [<c017ef2b>] __lock_acquire+0x2cb/0x5b0
> [<c017f299>] lock_acquire+0x89/0xc0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f2ab>] __mutex_lock_common+0xab/0x3c0
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c0d6f698>] mutex_lock_nested+0x38/0x50
> [<c020ba20>] ? mmap+0x40/0xa0
> [<c020ba20>] mmap+0x40/0xa0
> [<c01b111e>] mmap_region+0x14e/0x450
> [<c01afb88>] ? arch_get_unmapped_area_topdown+0xf8/0x160
> [<c01b170f>] do_mmap_pgoff+0x2ef/0x310
> [<c0125a3d>] sys_mmap2+0xad/0xc0
> [<c012146f>] sysenter_do_call+0x12/0x43
> [<c0120000>] ? __switch_to+0x130/0x220
> =======================
> evbug.c: Event. Dev: input3, Type: 20, Code: 0, Value: 500
> warning: `sudo' uses deprecated v2 capabilities in a way that may be insecure.
>
> i've attached the config.
>
> at first sight it looks like a genuine bug in fs/sysfs/bin.c?
Yes, it is a real bug by the looks. bin.c takes bb->mutex under mmap_sem
when it is mmapped, and then does its copy_*_user under bb->mutex too.
Here is a basic fix for the sysfs lor.
From: Nick Piggin <npiggin@suse.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2008-09-12 17:24:11 +08:00
|
|
|
out_free:
|
|
|
|
kfree(temp);
|
2005-04-17 06:20:36 +08:00
|
|
|
return count;
|
|
|
|
}
|
|
|
|
|
2009-03-05 03:57:20 +08:00
|
|
|
static void bin_vma_open(struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
struct file *file = vma->vm_file;
|
|
|
|
struct bin_buffer *bb = file->private_data;
|
|
|
|
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
|
|
|
|
|
|
|
|
if (!bb->vm_ops || !bb->vm_ops->open)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
|
|
|
return;
|
|
|
|
|
|
|
|
bb->vm_ops->open(vma);
|
|
|
|
|
|
|
|
sysfs_put_active_two(attr_sd);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void bin_vma_close(struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
struct file *file = vma->vm_file;
|
|
|
|
struct bin_buffer *bb = file->private_data;
|
|
|
|
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
|
|
|
|
|
|
|
|
if (!bb->vm_ops || !bb->vm_ops->close)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
|
|
|
return;
|
|
|
|
|
|
|
|
bb->vm_ops->close(vma);
|
|
|
|
|
|
|
|
sysfs_put_active_two(attr_sd);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int bin_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
|
|
|
|
{
|
|
|
|
struct file *file = vma->vm_file;
|
|
|
|
struct bin_buffer *bb = file->private_data;
|
|
|
|
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (!bb->vm_ops || !bb->vm_ops->fault)
|
|
|
|
return VM_FAULT_SIGBUS;
|
|
|
|
|
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
|
|
|
return VM_FAULT_SIGBUS;
|
|
|
|
|
|
|
|
ret = bb->vm_ops->fault(vma, vmf);
|
|
|
|
|
|
|
|
sysfs_put_active_two(attr_sd);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2009-04-01 06:23:24 +08:00
|
|
|
static int bin_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
|
2009-03-05 03:57:20 +08:00
|
|
|
{
|
|
|
|
struct file *file = vma->vm_file;
|
|
|
|
struct bin_buffer *bb = file->private_data;
|
|
|
|
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
|
|
|
|
int ret;
|
|
|
|
|
2009-03-23 09:41:27 +08:00
|
|
|
if (!bb->vm_ops)
|
2009-04-01 06:23:24 +08:00
|
|
|
return VM_FAULT_SIGBUS;
|
2009-03-05 03:57:20 +08:00
|
|
|
|
2009-03-23 09:41:27 +08:00
|
|
|
if (!bb->vm_ops->page_mkwrite)
|
|
|
|
return 0;
|
|
|
|
|
2009-03-05 03:57:20 +08:00
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
2009-04-01 06:23:24 +08:00
|
|
|
return VM_FAULT_SIGBUS;
|
2009-03-05 03:57:20 +08:00
|
|
|
|
2009-04-01 06:23:24 +08:00
|
|
|
ret = bb->vm_ops->page_mkwrite(vma, vmf);
|
2009-03-05 03:57:20 +08:00
|
|
|
|
|
|
|
sysfs_put_active_two(attr_sd);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int bin_access(struct vm_area_struct *vma, unsigned long addr,
|
|
|
|
void *buf, int len, int write)
|
|
|
|
{
|
|
|
|
struct file *file = vma->vm_file;
|
|
|
|
struct bin_buffer *bb = file->private_data;
|
|
|
|
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (!bb->vm_ops || !bb->vm_ops->access)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
ret = bb->vm_ops->access(vma, addr, buf, len, write);
|
|
|
|
|
|
|
|
sysfs_put_active_two(attr_sd);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2009-03-23 09:41:27 +08:00
|
|
|
#ifdef CONFIG_NUMA
|
|
|
|
static int bin_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
|
|
|
|
{
|
|
|
|
struct file *file = vma->vm_file;
|
|
|
|
struct bin_buffer *bb = file->private_data;
|
|
|
|
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (!bb->vm_ops || !bb->vm_ops->set_policy)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
ret = bb->vm_ops->set_policy(vma, new);
|
|
|
|
|
|
|
|
sysfs_put_active_two(attr_sd);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct mempolicy *bin_get_policy(struct vm_area_struct *vma,
|
|
|
|
unsigned long addr)
|
|
|
|
{
|
|
|
|
struct file *file = vma->vm_file;
|
|
|
|
struct bin_buffer *bb = file->private_data;
|
|
|
|
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
|
|
|
|
struct mempolicy *pol;
|
|
|
|
|
|
|
|
if (!bb->vm_ops || !bb->vm_ops->get_policy)
|
|
|
|
return vma->vm_policy;
|
|
|
|
|
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
|
|
|
return vma->vm_policy;
|
|
|
|
|
|
|
|
pol = bb->vm_ops->get_policy(vma, addr);
|
|
|
|
|
|
|
|
sysfs_put_active_two(attr_sd);
|
|
|
|
return pol;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int bin_migrate(struct vm_area_struct *vma, const nodemask_t *from,
|
|
|
|
const nodemask_t *to, unsigned long flags)
|
|
|
|
{
|
|
|
|
struct file *file = vma->vm_file;
|
|
|
|
struct bin_buffer *bb = file->private_data;
|
|
|
|
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (!bb->vm_ops || !bb->vm_ops->migrate)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
ret = bb->vm_ops->migrate(vma, from, to, flags);
|
|
|
|
|
|
|
|
sysfs_put_active_two(attr_sd);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2009-03-05 03:57:20 +08:00
|
|
|
static struct vm_operations_struct bin_vm_ops = {
|
|
|
|
.open = bin_vma_open,
|
|
|
|
.close = bin_vma_close,
|
|
|
|
.fault = bin_fault,
|
|
|
|
.page_mkwrite = bin_page_mkwrite,
|
|
|
|
.access = bin_access,
|
2009-03-23 09:41:27 +08:00
|
|
|
#ifdef CONFIG_NUMA
|
|
|
|
.set_policy = bin_set_policy,
|
|
|
|
.get_policy = bin_get_policy,
|
|
|
|
.migrate = bin_migrate,
|
|
|
|
#endif
|
2009-03-05 03:57:20 +08:00
|
|
|
};
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
static int mmap(struct file *file, struct vm_area_struct *vma)
|
|
|
|
{
|
2007-06-14 02:45:16 +08:00
|
|
|
struct bin_buffer *bb = file->private_data;
|
2007-06-14 02:45:15 +08:00
|
|
|
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
|
2007-09-20 15:05:11 +08:00
|
|
|
struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
|
|
|
|
struct kobject *kobj = attr_sd->s_parent->s_dir.kobj;
|
2007-06-14 02:45:16 +08:00
|
|
|
int rc;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-06-14 02:45:16 +08:00
|
|
|
mutex_lock(&bb->mutex);
|
2007-06-14 02:45:16 +08:00
|
|
|
|
|
|
|
/* need attr_sd for attr, its parent for kobj */
|
2009-03-05 03:57:20 +08:00
|
|
|
rc = -ENODEV;
|
2007-06-14 02:45:16 +08:00
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
2009-03-05 03:57:20 +08:00
|
|
|
goto out_unlock;
|
2007-06-14 02:45:16 +08:00
|
|
|
|
|
|
|
rc = -EINVAL;
|
2009-03-05 03:57:20 +08:00
|
|
|
if (!attr->mmap)
|
|
|
|
goto out_put;
|
2007-06-14 02:45:16 +08:00
|
|
|
|
2009-03-05 03:57:20 +08:00
|
|
|
rc = attr->mmap(kobj, attr, vma);
|
|
|
|
if (rc)
|
|
|
|
goto out_put;
|
2007-06-14 02:45:16 +08:00
|
|
|
|
2009-03-23 09:41:27 +08:00
|
|
|
/*
|
|
|
|
* PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup()
|
|
|
|
* to satisfy versions of X which crash if the mmap fails: that
|
|
|
|
* substitutes a new vm_file, and we don't then want bin_vm_ops.
|
|
|
|
*/
|
|
|
|
if (vma->vm_file != file)
|
2009-03-05 03:57:20 +08:00
|
|
|
goto out_put;
|
|
|
|
|
|
|
|
rc = -EINVAL;
|
2009-03-23 09:41:27 +08:00
|
|
|
if (bb->mmapped && bb->vm_ops != vma->vm_ops)
|
2009-03-05 03:57:20 +08:00
|
|
|
goto out_put;
|
|
|
|
|
|
|
|
rc = 0;
|
|
|
|
bb->mmapped = 1;
|
2009-03-23 09:41:27 +08:00
|
|
|
bb->vm_ops = vma->vm_ops;
|
|
|
|
vma->vm_ops = &bin_vm_ops;
|
2009-03-05 03:57:20 +08:00
|
|
|
out_put:
|
|
|
|
sysfs_put_active_two(attr_sd);
|
|
|
|
out_unlock:
|
2007-06-14 02:45:16 +08:00
|
|
|
mutex_unlock(&bb->mutex);
|
|
|
|
|
|
|
|
return rc;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int open(struct inode * inode, struct file * file)
|
|
|
|
{
|
2007-06-14 02:45:15 +08:00
|
|
|
struct sysfs_dirent *attr_sd = file->f_path.dentry->d_fsdata;
|
2007-09-20 15:05:11 +08:00
|
|
|
struct bin_attribute *attr = attr_sd->s_bin_attr.bin_attr;
|
2007-06-14 02:45:16 +08:00
|
|
|
struct bin_buffer *bb = NULL;
|
2007-06-14 02:45:16 +08:00
|
|
|
int error;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-09-20 15:05:10 +08:00
|
|
|
/* binary file operations requires both @sd and its parent */
|
|
|
|
if (!sysfs_get_active_two(attr_sd))
|
2007-06-14 02:45:16 +08:00
|
|
|
return -ENODEV;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
error = -EACCES;
|
|
|
|
if ((file->f_mode & FMODE_WRITE) && !(attr->write || attr->mmap))
|
2007-06-14 02:45:17 +08:00
|
|
|
goto err_out;
|
2005-04-17 06:20:36 +08:00
|
|
|
if ((file->f_mode & FMODE_READ) && !(attr->read || attr->mmap))
|
2007-06-14 02:45:17 +08:00
|
|
|
goto err_out;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
error = -ENOMEM;
|
2007-06-14 02:45:16 +08:00
|
|
|
bb = kzalloc(sizeof(*bb), GFP_KERNEL);
|
|
|
|
if (!bb)
|
2007-06-14 02:45:17 +08:00
|
|
|
goto err_out;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-06-14 02:45:16 +08:00
|
|
|
bb->buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
|
|
|
|
if (!bb->buffer)
|
2007-06-14 02:45:17 +08:00
|
|
|
goto err_out;
|
2007-06-14 02:45:16 +08:00
|
|
|
|
|
|
|
mutex_init(&bb->mutex);
|
2009-03-05 03:57:20 +08:00
|
|
|
bb->file = file;
|
2007-06-14 02:45:16 +08:00
|
|
|
file->private_data = bb;
|
|
|
|
|
2009-03-05 03:57:20 +08:00
|
|
|
mutex_lock(&sysfs_bin_lock);
|
|
|
|
hlist_add_head(&bb->list, &attr_sd->s_bin_attr.buffers);
|
|
|
|
mutex_unlock(&sysfs_bin_lock);
|
|
|
|
|
2007-09-20 15:05:10 +08:00
|
|
|
/* open succeeded, put active references */
|
|
|
|
sysfs_put_active_two(attr_sd);
|
2007-06-14 02:45:16 +08:00
|
|
|
return 0;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-06-14 02:45:17 +08:00
|
|
|
err_out:
|
2007-09-20 15:05:10 +08:00
|
|
|
sysfs_put_active_two(attr_sd);
|
2007-06-14 02:45:16 +08:00
|
|
|
kfree(bb);
|
2005-04-17 06:20:36 +08:00
|
|
|
return error;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int release(struct inode * inode, struct file * file)
|
|
|
|
{
|
2007-06-14 02:45:16 +08:00
|
|
|
struct bin_buffer *bb = file->private_data;
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2009-03-05 03:57:20 +08:00
|
|
|
mutex_lock(&sysfs_bin_lock);
|
|
|
|
hlist_del(&bb->list);
|
|
|
|
mutex_unlock(&sysfs_bin_lock);
|
|
|
|
|
2007-06-14 02:45:16 +08:00
|
|
|
kfree(bb->buffer);
|
|
|
|
kfree(bb);
|
2005-04-17 06:20:36 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-03-28 17:56:42 +08:00
|
|
|
const struct file_operations bin_fops = {
|
2005-04-17 06:20:36 +08:00
|
|
|
.read = read,
|
|
|
|
.write = write,
|
|
|
|
.mmap = mmap,
|
|
|
|
.llseek = generic_file_llseek,
|
|
|
|
.open = open,
|
|
|
|
.release = release,
|
|
|
|
};
|
|
|
|
|
2009-03-05 03:57:20 +08:00
|
|
|
|
|
|
|
void unmap_bin_file(struct sysfs_dirent *attr_sd)
|
|
|
|
{
|
|
|
|
struct bin_buffer *bb;
|
|
|
|
struct hlist_node *tmp;
|
|
|
|
|
|
|
|
if (sysfs_type(attr_sd) != SYSFS_KOBJ_BIN_ATTR)
|
|
|
|
return;
|
|
|
|
|
|
|
|
mutex_lock(&sysfs_bin_lock);
|
|
|
|
|
|
|
|
hlist_for_each_entry(bb, tmp, &attr_sd->s_bin_attr.buffers, list) {
|
|
|
|
struct inode *inode = bb->file->f_path.dentry->d_inode;
|
|
|
|
|
|
|
|
unmap_mapping_range(inode->i_mapping, 0, 0, 1);
|
|
|
|
}
|
|
|
|
|
|
|
|
mutex_unlock(&sysfs_bin_lock);
|
|
|
|
}
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/**
|
|
|
|
* sysfs_create_bin_file - create binary file for object.
|
|
|
|
* @kobj: object.
|
|
|
|
* @attr: attribute descriptor.
|
|
|
|
*/
|
|
|
|
|
|
|
|
int sysfs_create_bin_file(struct kobject * kobj, struct bin_attribute * attr)
|
|
|
|
{
|
2007-06-14 03:27:22 +08:00
|
|
|
BUG_ON(!kobj || !kobj->sd || !attr);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-06-14 03:27:22 +08:00
|
|
|
return sysfs_add_file(kobj->sd, &attr->attr, SYSFS_KOBJ_BIN_ATTR);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
/**
|
|
|
|
* sysfs_remove_bin_file - remove binary file for object.
|
|
|
|
* @kobj: object.
|
|
|
|
* @attr: attribute descriptor.
|
|
|
|
*/
|
|
|
|
|
2006-07-11 14:05:25 +08:00
|
|
|
void sysfs_remove_bin_file(struct kobject * kobj, struct bin_attribute * attr)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2007-08-17 04:13:06 +08:00
|
|
|
sysfs_hash_and_remove(kobj->sd, attr->attr.name);
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
|
|
|
|
EXPORT_SYMBOL_GPL(sysfs_remove_bin_file);
|