ocfs2: protect extent tree in ocfs2_prepare_inode_for_write()

When the extent tree is modified, it should be protected by inode
cluster lock and ip_alloc_sem.

The extent tree is accessed and modified in the
ocfs2_prepare_inode_for_write, but isn't protected by ip_alloc_sem.

The following is a case.  The function ocfs2_fiemap is accessing the
extent tree, which is modified at the same time.

  kernel BUG at fs/ocfs2/extent_map.c:475!
  invalid opcode: 0000 [#1] SMP
  Modules linked in: tun ocfs2 ocfs2_nodemanager configfs ocfs2_stackglue [...]
  CPU: 16 PID: 14047 Comm: o2info Not tainted 4.1.12-124.23.1.el6uek.x86_64 #2
  Hardware name: Oracle Corporation ORACLE SERVER X7-2L/ASM, MB MECH, X7-2L, BIOS 42040600 10/19/2018
  task: ffff88019487e200 ti: ffff88003daa4000 task.ti: ffff88003daa4000
  RIP: ocfs2_get_clusters_nocache.isra.11+0x390/0x550 [ocfs2]
  Call Trace:
    ocfs2_fiemap+0x1e3/0x430 [ocfs2]
    do_vfs_ioctl+0x155/0x510
    SyS_ioctl+0x81/0xa0
    system_call_fastpath+0x18/0xd8
  Code: 18 48 c7 c6 60 7f 65 a0 31 c0 bb e2 ff ff ff 48 8b 4a 40 48 8b 7a 28 48 c7 c2 78 2d 66 a0 e8 38 4f 05 00 e9 28 fe ff ff 0f 1f 00 <0f> 0b 66 0f 1f 44 00 00 bb 86 ff ff ff e9 13 fe ff ff 66 0f 1f
  RIP  ocfs2_get_clusters_nocache.isra.11+0x390/0x550 [ocfs2]
  ---[ end trace c8aa0c8180e869dc ]---
  Kernel panic - not syncing: Fatal exception
  Kernel Offset: disabled

This issue can be reproduced every week in a production environment.

This issue is related to the usage mode.  If others use ocfs2 in this
mode, the kernel will panic frequently.

[akpm@linux-foundation.org: coding style fixes]
[Fix new warning due to unused function by removing said function - Linus ]
Link: http://lkml.kernel.org/r/1568772175-2906-2-git-send-email-sunny.s.zhang@oracle.com
Signed-off-by: Shuning Zhang <sunny.s.zhang@oracle.com>
Reviewed-by: Junxiao Bi <junxiao.bi@oracle.com>
Reviewed-by: Gang He <ghe@suse.com>
Cc: Mark Fasheh <mark@fasheh.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Joseph Qi <jiangqi903@gmail.com>
Cc: Changwei Ge <gechangwei@live.cn>
Cc: Jun Piao <piaojun@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Shuning Zhang 2019-11-05 21:16:34 -08:00 committed by Linus Torvalds
parent 169226f7e0
commit e74540b285
1 changed files with 91 additions and 45 deletions

View File

@ -2098,53 +2098,89 @@ static int ocfs2_is_io_unaligned(struct inode *inode, size_t count, loff_t pos)
return 0;
}
static int ocfs2_prepare_inode_for_refcount(struct inode *inode,
struct file *file,
loff_t pos, size_t count,
int *meta_level)
static int ocfs2_inode_lock_for_extent_tree(struct inode *inode,
struct buffer_head **di_bh,
int meta_level,
int overwrite_io,
int write_sem,
int wait)
{
int ret;
struct buffer_head *di_bh = NULL;
u32 cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
u32 clusters =
ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos;
int ret = 0;
ret = ocfs2_inode_lock(inode, &di_bh, 1);
if (ret) {
mlog_errno(ret);
if (wait)
ret = ocfs2_inode_lock(inode, NULL, meta_level);
else
ret = ocfs2_try_inode_lock(inode,
overwrite_io ? NULL : di_bh, meta_level);
if (ret < 0)
goto out;
if (wait) {
if (write_sem)
down_write(&OCFS2_I(inode)->ip_alloc_sem);
else
down_read(&OCFS2_I(inode)->ip_alloc_sem);
} else {
if (write_sem)
ret = down_write_trylock(&OCFS2_I(inode)->ip_alloc_sem);
else
ret = down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem);
if (!ret) {
ret = -EAGAIN;
goto out_unlock;
}
}
*meta_level = 1;
ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
if (ret)
mlog_errno(ret);
out:
brelse(di_bh);
return ret;
out_unlock:
brelse(*di_bh);
ocfs2_inode_unlock(inode, meta_level);
out:
return ret;
}
static void ocfs2_inode_unlock_for_extent_tree(struct inode *inode,
struct buffer_head **di_bh,
int meta_level,
int write_sem)
{
if (write_sem)
up_write(&OCFS2_I(inode)->ip_alloc_sem);
else
up_read(&OCFS2_I(inode)->ip_alloc_sem);
brelse(*di_bh);
*di_bh = NULL;
if (meta_level >= 0)
ocfs2_inode_unlock(inode, meta_level);
}
static int ocfs2_prepare_inode_for_write(struct file *file,
loff_t pos, size_t count, int wait)
{
int ret = 0, meta_level = 0, overwrite_io = 0;
int write_sem = 0;
struct dentry *dentry = file->f_path.dentry;
struct inode *inode = d_inode(dentry);
struct buffer_head *di_bh = NULL;
u32 cpos;
u32 clusters;
/*
* We start with a read level meta lock and only jump to an ex
* if we need to make modifications here.
*/
for(;;) {
if (wait)
ret = ocfs2_inode_lock(inode, NULL, meta_level);
else
ret = ocfs2_try_inode_lock(inode,
overwrite_io ? NULL : &di_bh, meta_level);
ret = ocfs2_inode_lock_for_extent_tree(inode,
&di_bh,
meta_level,
overwrite_io,
write_sem,
wait);
if (ret < 0) {
meta_level = -1;
if (ret != -EAGAIN)
mlog_errno(ret);
goto out;
@ -2156,15 +2192,8 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
*/
if (!wait && !overwrite_io) {
overwrite_io = 1;
if (!down_read_trylock(&OCFS2_I(inode)->ip_alloc_sem)) {
ret = -EAGAIN;
goto out_unlock;
}
ret = ocfs2_overwrite_io(inode, di_bh, pos, count);
brelse(di_bh);
di_bh = NULL;
up_read(&OCFS2_I(inode)->ip_alloc_sem);
if (ret < 0) {
if (ret != -EAGAIN)
mlog_errno(ret);
@ -2183,7 +2212,10 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
* set inode->i_size at the end of a write. */
if (should_remove_suid(dentry)) {
if (meta_level == 0) {
ocfs2_inode_unlock(inode, meta_level);
ocfs2_inode_unlock_for_extent_tree(inode,
&di_bh,
meta_level,
write_sem);
meta_level = 1;
continue;
}
@ -2197,17 +2229,31 @@ static int ocfs2_prepare_inode_for_write(struct file *file,
ret = ocfs2_check_range_for_refcount(inode, pos, count);
if (ret == 1) {
ocfs2_inode_unlock(inode, meta_level);
meta_level = -1;
ocfs2_inode_unlock_for_extent_tree(inode,
&di_bh,
meta_level,
write_sem);
ret = ocfs2_inode_lock_for_extent_tree(inode,
&di_bh,
meta_level,
overwrite_io,
1,
wait);
write_sem = 1;
if (ret < 0) {
if (ret != -EAGAIN)
mlog_errno(ret);
goto out;
}
ret = ocfs2_prepare_inode_for_refcount(inode,
file,
pos,
count,
&meta_level);
cpos = pos >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
clusters =
ocfs2_clusters_for_bytes(inode->i_sb, pos + count) - cpos;
ret = ocfs2_refcount_cow(inode, di_bh, cpos, clusters, UINT_MAX);
}
if (ret < 0) {
if (ret != -EAGAIN)
mlog_errno(ret);
goto out_unlock;
}
@ -2219,10 +2265,10 @@ out_unlock:
trace_ocfs2_prepare_inode_for_write(OCFS2_I(inode)->ip_blkno,
pos, count, wait);
brelse(di_bh);
if (meta_level >= 0)
ocfs2_inode_unlock(inode, meta_level);
ocfs2_inode_unlock_for_extent_tree(inode,
&di_bh,
meta_level,
write_sem);
out:
return ret;