summaryrefslogtreecommitdiff
path: root/fs/inode.c
diff options
context:
space:
mode:
authorArtem B. Bityuckiy <dedekind@infradead.org>2005-07-13 00:58:12 +0400
committerLinus Torvalds <torvalds@g5.osdl.org>2005-07-13 03:00:59 +0400
commit4120db47198d21d8cd3b2cdbbe1ea6118a50bcd4 (patch)
treeb4e0b69dbf3d2da69aa49423227a1da6036e9566 /fs/inode.c
parent168a9fd6a1bf91041adf9909f6c72cf747f0ca8c (diff)
downloadlinux-4120db47198d21d8cd3b2cdbbe1ea6118a50bcd4.tar.xz
[PATCH] bugfix: two read_inode() calls without clear_inode() call between
Bug symptoms ~~~~~~~~~~~~ For the same inode VFS calls read_inode() twice and doesn't call clear_inode() between the two read_inode() invocations. Bug description ~~~~~~~~~~~~~~~ Suppose we have an inode which has zero reference count but is still in the inode cache. Suppose kswapd invokes shrink_icache_memory() to free some RAM. In prune_icache() inodes are removed from i_hash. prune_icache () is then going to call clear_inode(), but drops the inode_lock spinlock before this. If in this moment another task calls iget() for an inode which was just removed from i_hash by prune_icache(), then iget() invokes read_inode() for this inode, because it is *already removed* from i_hash. The end result is: we call iget(#N) then iput(#N); inode #N has zero i_count now and is in the inode cache; kswapd starts. kswapd removes the inode #N from i_hash ans is preempted; we call iget(#N) again; read_inode() is invoked as the result; but we expect clear_inode() before. Fix ~~~~~~~ To fix the bug I remove inodes from i_hash later, when clear_inode() is actually called. I remove them from i_hash under spinlock protection. Since the i_state is set to I_FREEING, it is safe to do this. The others will sleep waiting for the inode state change. I also postpone removing inodes from i_sb_list. It is not compulsory to do so but I do it for readability reasons. Inodes are added/removed to the lists together everywhere in the code and there is no point to change this rule. This is harmless because the only user of i_sb_list which somehow may interfere with me (invalidate_list()) is excluded by the iprune_sem mutex. The same race is possible in invalidate_list() so I do the same for it. Acked-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'fs/inode.c')
-rw-r--r--fs/inode.c11
1 files changed, 7 insertions, 4 deletions
diff --git a/fs/inode.c b/fs/inode.c
index 0116d06731c2..5bc97507eeaa 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -282,6 +282,13 @@ static void dispose_list(struct list_head *head)
if (inode->i_data.nrpages)
truncate_inode_pages(&inode->i_data, 0);
clear_inode(inode);
+
+ spin_lock(&inode_lock);
+ hlist_del_init(&inode->i_hash);
+ list_del_init(&inode->i_sb_list);
+ spin_unlock(&inode_lock);
+
+ wake_up_inode(inode);
destroy_inode(inode);
nr_disposed++;
}
@@ -317,8 +324,6 @@ static int invalidate_list(struct list_head *head, struct list_head *dispose)
inode = list_entry(tmp, struct inode, i_sb_list);
invalidate_inode_buffers(inode);
if (!atomic_read(&inode->i_count)) {
- hlist_del_init(&inode->i_hash);
- list_del(&inode->i_sb_list);
list_move(&inode->i_list, dispose);
inode->i_state |= I_FREEING;
count++;
@@ -439,8 +444,6 @@ static void prune_icache(int nr_to_scan)
if (!can_unuse(inode))
continue;
}
- hlist_del_init(&inode->i_hash);
- list_del_init(&inode->i_sb_list);
list_move(&inode->i_list, &freeable);
inode->i_state |= I_FREEING;
nr_pruned++;