From b6fac63cc1f52ec27f29fe6c6c8494a2ffac33fd Mon Sep 17 00:00:00 2001 From: Wu Fengguang Date: Thu, 2 Apr 2009 16:56:34 -0700 Subject: 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: Masayoshi MIZUMA Reviewed-by: Jan Kara Signed-off-by: Wu Fengguang Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/drop_caches.c | 2 +- fs/fs-writeback.c | 3 ++- fs/quota/dquot.c | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 44d725f612cf..b6a719a909f8 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -18,7 +18,7 @@ static void drop_pagecache_sb(struct super_block *sb) spin_lock(&inode_lock); 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; if (inode->i_mapping->nrpages == 0) continue; diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index e3fe9918faaf..f81f9e71871e 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -538,7 +538,8 @@ void generic_sync_sb_inodes(struct super_block *sb, 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) diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 2ca967a5ef77..607c579e5eca 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -823,7 +823,7 @@ static void add_dquot_ref(struct super_block *sb, int type) spin_lock(&inode_lock); 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; if (!atomic_read(&inode->i_writecount)) continue; -- cgit