![Frederic Weisbecker](/assets/img/avatar_default.png)
Prevent from recursively locking the reiserfs lock in reiserfs_unpack() because we may call journal_begin() that requires the lock to be taken only once, otherwise it won't be able to release the lock while taking other mutexes, ending up in inverted dependencies between the journal mutex and the reiserfs lock for example. This fixes: ======================================================= [ INFO: possible circular locking dependency detected ] 2.6.35.4.4a #3 ------------------------------------------------------- lilo/1620 is trying to acquire lock: (&journal->j_mutex){+.+...}, at: [<d0325bff>] do_journal_begin_r+0x7f/0x340 [reiserfs] but task is already holding lock: (&REISERFS_SB(s)->lock){+.+.+.}, at: [<d032a278>] reiserfs_write_lock+0x28/0x40 [reiserfs] which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&REISERFS_SB(s)->lock){+.+.+.}: [<c10562b7>] lock_acquire+0x67/0x80 [<c12facad>] __mutex_lock_common+0x4d/0x410 [<c12fb0c8>] mutex_lock_nested+0x18/0x20 [<d032a278>] reiserfs_write_lock+0x28/0x40 [reiserfs] [<d0325c06>] do_journal_begin_r+0x86/0x340 [reiserfs] [<d0325f77>] journal_begin+0x77/0x140 [reiserfs] [<d0315be4>] reiserfs_remount+0x224/0x530 [reiserfs] [<c10b6a20>] do_remount_sb+0x60/0x110 [<c10cee25>] do_mount+0x625/0x790 [<c10cf014>] sys_mount+0x84/0xb0 [<c12fca3d>] syscall_call+0x7/0xb -> #0 (&journal->j_mutex){+.+...}: [<c10560f6>] __lock_acquire+0x1026/0x1180 [<c10562b7>] lock_acquire+0x67/0x80 [<c12facad>] __mutex_lock_common+0x4d/0x410 [<c12fb0c8>] mutex_lock_nested+0x18/0x20 [<d0325bff>] do_journal_begin_r+0x7f/0x340 [reiserfs] [<d0325f77>] journal_begin+0x77/0x140 [reiserfs] [<d0326271>] reiserfs_persistent_transaction+0x41/0x90 [reiserfs] [<d030d06c>] reiserfs_get_block+0x22c/0x1530 [reiserfs] [<c10db9db>] __block_prepare_write+0x1bb/0x3a0 [<c10dbbe6>] block_prepare_write+0x26/0x40 [<d030b738>] reiserfs_prepare_write+0x88/0x170 [reiserfs] [<d03294d6>] reiserfs_unpack+0xe6/0x120 [reiserfs] [<d0329782>] reiserfs_ioctl+0x272/0x320 [reiserfs] [<c10c3188>] vfs_ioctl+0x28/0xa0 [<c10c3bbd>] do_vfs_ioctl+0x32d/0x5c0 [<c10c3eb3>] sys_ioctl+0x63/0x70 [<c12fca3d>] syscall_call+0x7/0xb other info that might help us debug this: 2 locks held by lilo/1620: #0: (&sb->s_type->i_mutex_key#8){+.+.+.}, at: [<d032945a>] reiserfs_unpack+0x6a/0x120 [reiserfs] #1: (&REISERFS_SB(s)->lock){+.+.+.}, at: [<d032a278>] reiserfs_write_lock+0x28/0x40 [reiserfs] stack backtrace: Pid: 1620, comm: lilo Not tainted 2.6.35.4.4a #3 Call Trace: [<c10560f6>] __lock_acquire+0x1026/0x1180 [<c10562b7>] lock_acquire+0x67/0x80 [<c12facad>] __mutex_lock_common+0x4d/0x410 [<c12fb0c8>] mutex_lock_nested+0x18/0x20 [<d0325bff>] do_journal_begin_r+0x7f/0x340 [reiserfs] [<d0325f77>] journal_begin+0x77/0x140 [reiserfs] [<d0326271>] reiserfs_persistent_transaction+0x41/0x90 [reiserfs] [<d030d06c>] reiserfs_get_block+0x22c/0x1530 [reiserfs] [<c10db9db>] __block_prepare_write+0x1bb/0x3a0 [<c10dbbe6>] block_prepare_write+0x26/0x40 [<d030b738>] reiserfs_prepare_write+0x88/0x170 [reiserfs] [<d03294d6>] reiserfs_unpack+0xe6/0x120 [reiserfs] [<d0329782>] reiserfs_ioctl+0x272/0x320 [reiserfs] [<c10c3188>] vfs_ioctl+0x28/0xa0 [<c10c3bbd>] do_vfs_ioctl+0x32d/0x5c0 [<c10c3eb3>] sys_ioctl+0x63/0x70 [<c12fca3d>] syscall_call+0x7/0xb Reported-by: Jarek Poplawski <jarkao2@gmail.com> Tested-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jeff Mahoney <jeffm@suse.com> Cc: All since 2.6.32 <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
231 lines
5.5 KiB
C
231 lines
5.5 KiB
C
/*
|
|
* Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
|
|
*/
|
|
|
|
#include <linux/capability.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/mount.h>
|
|
#include <linux/reiserfs_fs.h>
|
|
#include <linux/time.h>
|
|
#include <asm/uaccess.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/smp_lock.h>
|
|
#include <linux/compat.h>
|
|
|
|
/*
|
|
* reiserfs_ioctl - handler for ioctl for inode
|
|
* supported commands:
|
|
* 1) REISERFS_IOC_UNPACK - try to unpack tail from direct item into indirect
|
|
* and prevent packing file (argument arg has to be non-zero)
|
|
* 2) REISERFS_IOC_[GS]ETFLAGS, REISERFS_IOC_[GS]ETVERSION
|
|
* 3) That's all for a while ...
|
|
*/
|
|
long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
|
|
{
|
|
struct inode *inode = filp->f_path.dentry->d_inode;
|
|
unsigned int flags;
|
|
int err = 0;
|
|
|
|
reiserfs_write_lock(inode->i_sb);
|
|
|
|
switch (cmd) {
|
|
case REISERFS_IOC_UNPACK:
|
|
if (S_ISREG(inode->i_mode)) {
|
|
if (arg)
|
|
err = reiserfs_unpack(inode, filp);
|
|
} else
|
|
err = -ENOTTY;
|
|
break;
|
|
/*
|
|
* following two cases are taken from fs/ext2/ioctl.c by Remy
|
|
* Card (card@masi.ibp.fr)
|
|
*/
|
|
case REISERFS_IOC_GETFLAGS:
|
|
if (!reiserfs_attrs(inode->i_sb)) {
|
|
err = -ENOTTY;
|
|
break;
|
|
}
|
|
|
|
flags = REISERFS_I(inode)->i_attrs;
|
|
i_attrs_to_sd_attrs(inode, (__u16 *) & flags);
|
|
err = put_user(flags, (int __user *)arg);
|
|
break;
|
|
case REISERFS_IOC_SETFLAGS:{
|
|
if (!reiserfs_attrs(inode->i_sb)) {
|
|
err = -ENOTTY;
|
|
break;
|
|
}
|
|
|
|
err = mnt_want_write(filp->f_path.mnt);
|
|
if (err)
|
|
break;
|
|
|
|
if (!is_owner_or_cap(inode)) {
|
|
err = -EPERM;
|
|
goto setflags_out;
|
|
}
|
|
if (get_user(flags, (int __user *)arg)) {
|
|
err = -EFAULT;
|
|
goto setflags_out;
|
|
}
|
|
/*
|
|
* Is it quota file? Do not allow user to mess with it
|
|
*/
|
|
if (IS_NOQUOTA(inode)) {
|
|
err = -EPERM;
|
|
goto setflags_out;
|
|
}
|
|
if (((flags ^ REISERFS_I(inode)->
|
|
i_attrs) & (REISERFS_IMMUTABLE_FL |
|
|
REISERFS_APPEND_FL))
|
|
&& !capable(CAP_LINUX_IMMUTABLE)) {
|
|
err = -EPERM;
|
|
goto setflags_out;
|
|
}
|
|
if ((flags & REISERFS_NOTAIL_FL) &&
|
|
S_ISREG(inode->i_mode)) {
|
|
int result;
|
|
|
|
result = reiserfs_unpack(inode, filp);
|
|
if (result) {
|
|
err = result;
|
|
goto setflags_out;
|
|
}
|
|
}
|
|
sd_attrs_to_i_attrs(flags, inode);
|
|
REISERFS_I(inode)->i_attrs = flags;
|
|
inode->i_ctime = CURRENT_TIME_SEC;
|
|
mark_inode_dirty(inode);
|
|
setflags_out:
|
|
mnt_drop_write(filp->f_path.mnt);
|
|
break;
|
|
}
|
|
case REISERFS_IOC_GETVERSION:
|
|
err = put_user(inode->i_generation, (int __user *)arg);
|
|
break;
|
|
case REISERFS_IOC_SETVERSION:
|
|
if (!is_owner_or_cap(inode)) {
|
|
err = -EPERM;
|
|
break;
|
|
}
|
|
err = mnt_want_write(filp->f_path.mnt);
|
|
if (err)
|
|
break;
|
|
if (get_user(inode->i_generation, (int __user *)arg)) {
|
|
err = -EFAULT;
|
|
goto setversion_out;
|
|
}
|
|
inode->i_ctime = CURRENT_TIME_SEC;
|
|
mark_inode_dirty(inode);
|
|
setversion_out:
|
|
mnt_drop_write(filp->f_path.mnt);
|
|
break;
|
|
default:
|
|
err = -ENOTTY;
|
|
}
|
|
|
|
reiserfs_write_unlock(inode->i_sb);
|
|
|
|
return err;
|
|
}
|
|
|
|
#ifdef CONFIG_COMPAT
|
|
long reiserfs_compat_ioctl(struct file *file, unsigned int cmd,
|
|
unsigned long arg)
|
|
{
|
|
/* These are just misnamed, they actually get/put from/to user an int */
|
|
switch (cmd) {
|
|
case REISERFS_IOC32_UNPACK:
|
|
cmd = REISERFS_IOC_UNPACK;
|
|
break;
|
|
case REISERFS_IOC32_GETFLAGS:
|
|
cmd = REISERFS_IOC_GETFLAGS;
|
|
break;
|
|
case REISERFS_IOC32_SETFLAGS:
|
|
cmd = REISERFS_IOC_SETFLAGS;
|
|
break;
|
|
case REISERFS_IOC32_GETVERSION:
|
|
cmd = REISERFS_IOC_GETVERSION;
|
|
break;
|
|
case REISERFS_IOC32_SETVERSION:
|
|
cmd = REISERFS_IOC_SETVERSION;
|
|
break;
|
|
default:
|
|
return -ENOIOCTLCMD;
|
|
}
|
|
|
|
return reiserfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
|
|
}
|
|
#endif
|
|
|
|
int reiserfs_commit_write(struct file *f, struct page *page,
|
|
unsigned from, unsigned to);
|
|
int reiserfs_prepare_write(struct file *f, struct page *page,
|
|
unsigned from, unsigned to);
|
|
/*
|
|
** reiserfs_unpack
|
|
** Function try to convert tail from direct item into indirect.
|
|
** It set up nopack attribute in the REISERFS_I(inode)->nopack
|
|
*/
|
|
int reiserfs_unpack(struct inode *inode, struct file *filp)
|
|
{
|
|
int retval = 0;
|
|
int depth;
|
|
int index;
|
|
struct page *page;
|
|
struct address_space *mapping;
|
|
unsigned long write_from;
|
|
unsigned long blocksize = inode->i_sb->s_blocksize;
|
|
|
|
if (inode->i_size == 0) {
|
|
REISERFS_I(inode)->i_flags |= i_nopack_mask;
|
|
return 0;
|
|
}
|
|
/* ioctl already done */
|
|
if (REISERFS_I(inode)->i_flags & i_nopack_mask) {
|
|
return 0;
|
|
}
|
|
|
|
/* we need to make sure nobody is changing the file size beneath
|
|
** us
|
|
*/
|
|
reiserfs_mutex_lock_safe(&inode->i_mutex, inode->i_sb);
|
|
depth = reiserfs_write_lock_once(inode->i_sb);
|
|
|
|
write_from = inode->i_size & (blocksize - 1);
|
|
/* if we are on a block boundary, we are already unpacked. */
|
|
if (write_from == 0) {
|
|
REISERFS_I(inode)->i_flags |= i_nopack_mask;
|
|
goto out;
|
|
}
|
|
|
|
/* we unpack by finding the page with the tail, and calling
|
|
** reiserfs_prepare_write on that page. This will force a
|
|
** reiserfs_get_block to unpack the tail for us.
|
|
*/
|
|
index = inode->i_size >> PAGE_CACHE_SHIFT;
|
|
mapping = inode->i_mapping;
|
|
page = grab_cache_page(mapping, index);
|
|
retval = -ENOMEM;
|
|
if (!page) {
|
|
goto out;
|
|
}
|
|
retval = reiserfs_prepare_write(NULL, page, write_from, write_from);
|
|
if (retval)
|
|
goto out_unlock;
|
|
|
|
/* conversion can change page contents, must flush */
|
|
flush_dcache_page(page);
|
|
retval = reiserfs_commit_write(NULL, page, write_from, write_from);
|
|
REISERFS_I(inode)->i_flags |= i_nopack_mask;
|
|
|
|
out_unlock:
|
|
unlock_page(page);
|
|
page_cache_release(page);
|
|
|
|
out:
|
|
mutex_unlock(&inode->i_mutex);
|
|
reiserfs_write_unlock_once(inode->i_sb, depth);
|
|
return retval;
|
|
}
|