[patch 25/88] vfs: skip I_CLEAR state inodes

[Greg KH]

2.6.28-stable review patch.  If anyone has any objections, please let us know.

------------------

From: Wu Fengguang <fengguang.wu@xxxxxxxxx>

upstream commit: b6fac63cc1f52ec27f29fe6c6c8494a2ffac33fd

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: Masayoshi MIZUMA <m.mizuma@xxxxxxxxxxxxxx>
Reviewed-by: Jan Kara <jack@xxxxxxx>
Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
[chrisw: backport to 2.6.29]
Signed-off-by: Chris Wright <chrisw@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxx>
---
 fs/dquot.c        |    2 +-
 fs/drop_caches.c  |    2 +-
 fs/fs-writeback.c |    3 ++-
 3 files changed, 4 insertions(+), 3 deletions(-)

--- a/fs/dquot.c
+++ b/fs/dquot.c
@@ -724,7 +724,7 @@ static void add_dquot_ref(struct super_b
 			continue;
 		if (!dqinit_needed(inode, type))
 			continue;
-		if (inode->i_state & (I_FREEING|I_WILL_FREE))
+		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
 			continue;
 
 		__iget(inode);
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -18,7 +18,7 @@ static void drop_pagecache_sb(struct sup
 
 	spin_lock(&inode_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		if (inode->i_state & (I_FREEING|I_WILL_FREE))
+		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE))
 			continue;
 		if (inode->i_mapping->nrpages == 0)
 			continue;
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -538,7 +538,8 @@ void generic_sync_sb_inodes(struct super
 		list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 			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;
 			mapping = inode->i_mapping;
 			if (mapping->nrpages == 0)


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/