Commit b6fac63c authored by Wu Fengguang's avatar Wu Fengguang Committed by Linus Torvalds

vfs: skip I_CLEAR state inodes

clear_inode() will switch inode state from I_FREEING to I_CLEAR, and do so
_outside_ of inode_lock.  So any I_FREEING testing is incomplete without a
coupled testing of I_CLEAR.

So add I_CLEAR tests to drop_pagecache_sb(), generic_sync_sb_inodes() and
add_dquot_ref().

Masayoshi MIZUMA discovered the bug in drop_pagecache_sb() and Jan Kara
reminds fixing the other two cases.

Masayoshi MIZUMA has a nice panic flow:

=====================================================================
            [process A]               |        [process B]
 |                                    |
 |    prune_icache()                  | drop_pagecache()
 |      spin_lock(&inode_lock)        |   drop_pagecache_sb()
 |      inode->i_state |= I_FREEING;  |       |
 |      spin_unlock(&inode_lock)      |       V
 |          |                         |     spin_lock(&inode_lock)
 |          V                         |         |
 |      dispose_list()                |         |
 |        list_del()                  |         |
 |        clear_inode()               |         |
 |          inode->i_state = I_CLEAR  |         |
 |            |                       |         V
 |            |                       |      if (inode->i_state & (I_FREEING|I_WILL_FREE))
 |            |                       |              continue;           <==== NOT MATCH
 |            |                       |
 |            |                       | (DANGER from here on! Accessing disposing inode!)
 |            |                       |
 |            |                       |      __iget()
 |            |                       |        list_move() <===== PANIC on poisoned list !!
 V            V                       |
(time)
=====================================================================
Reported-by: default avatarMasayoshi MIZUMA <m.mizuma@jp.fujitsu.com>
Reviewed-by: default avatarJan Kara <jack@suse.cz>
Signed-off-by: default avatarWu Fengguang <fengguang.wu@intel.com>
Cc: <stable@kernel.org>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 33e5d769
...@@ -18,7 +18,7 @@ static void drop_pagecache_sb(struct super_block *sb) ...@@ -18,7 +18,7 @@ static void drop_pagecache_sb(struct super_block *sb)
spin_lock(&inode_lock); spin_lock(&inode_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
continue; continue;
if (inode->i_mapping->nrpages == 0) if (inode->i_mapping->nrpages == 0)
continue; continue;
......
...@@ -538,7 +538,8 @@ void generic_sync_sb_inodes(struct super_block *sb, ...@@ -538,7 +538,8 @@ void generic_sync_sb_inodes(struct super_block *sb,
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
struct address_space *mapping; struct address_space *mapping;
if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) if (inode->i_state &
(I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
continue; continue;
mapping = inode->i_mapping; mapping = inode->i_mapping;
if (mapping->nrpages == 0) if (mapping->nrpages == 0)
......
...@@ -823,7 +823,7 @@ static void add_dquot_ref(struct super_block *sb, int type) ...@@ -823,7 +823,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
spin_lock(&inode_lock); spin_lock(&inode_lock);
list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
continue; continue;
if (!atomic_read(&inode->i_writecount)) if (!atomic_read(&inode->i_writecount))
continue; continue;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment