summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorJiaying Zhang <jiayingz@google.com>2011-08-31 11:50:51 -0400
committerTheodore Ts'o <tytso@mit.edu>2011-08-31 11:50:51 -0400
commit8c0bec2151a47906bf779c6715a10ce04453ab77 (patch)
tree0165e80ba408b5db1e9e2adf9264bf4186b06768
parentfcb8ce5cfe30ca9ca5c9a79cdfe26d1993e65e0c (diff)
downloadlwn-8c0bec2151a47906bf779c6715a10ce04453ab77.tar.gz
lwn-8c0bec2151a47906bf779c6715a10ce04453ab77.zip
ext4: remove i_mutex lock in ext4_evict_inode to fix lockdep complaining
The i_mutex lock and flush_completed_IO() added by commit 2581fdc810 in ext4_evict_inode() causes lockdep complaining about potential deadlock in several places. In most/all of these LOCKDEP complaints it looks like it's a false positive, since many of the potential circular locking cases can't take place by the time the ext4_evict_inode() is called; but since at the very least it may mask real problems, we need to address this. This change removes the flush_completed_IO() and i_mutex lock in ext4_evict_inode(). Instead, we take a different approach to resolve the software lockup that commit 2581fdc810 intends to fix. Rather than having ext4-dio-unwritten thread wait for grabing the i_mutex lock of an inode, we use mutex_trylock() instead, and simply requeue the work item if we fail to grab the inode's i_mutex lock. This should speed up work queue processing in general and also prevents the following deadlock scenario: During page fault, shrink_icache_memory is called that in turn evicts another inode B. Inode B has some pending io_end work so it calls ext4_ioend_wait() that waits for inode B's i_ioend_count to become zero. However, inode B's ioend work was queued behind some of inode A's ioend work on the same cpu's ext4-dio-unwritten workqueue. As the ext4-dio-unwritten thread on that cpu is processing inode A's ioend work, it tries to grab inode A's i_mutex lock. Since the i_mutex lock of inode A is still hold before the page fault happened, we enter a deadlock. Signed-off-by: Jiaying Zhang <jiayingz@google.com> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
-rw-r--r--fs/ext4/ext4.h1
-rw-r--r--fs/ext4/inode.c3
-rw-r--r--fs/ext4/page-io.c18
3 files changed, 18 insertions, 4 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e717dfd2f2b4..b7d7bd0f066e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -175,6 +175,7 @@ struct mpage_da_data {
*/
#define EXT4_IO_END_UNWRITTEN 0x0001
#define EXT4_IO_END_ERROR 0x0002
+#define EXT4_IO_END_QUEUED 0x0004
struct ext4_io_page {
struct page *p_page;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index c4da98a959ae..18d2558b7624 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -121,9 +121,6 @@ void ext4_evict_inode(struct inode *inode)
trace_ext4_evict_inode(inode);
- mutex_lock(&inode->i_mutex);
- ext4_flush_completed_IO(inode);
- mutex_unlock(&inode->i_mutex);
ext4_ioend_wait(inode);
if (inode->i_nlink) {
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 78839af7ce29..92f38ee13f8a 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -142,7 +142,23 @@ static void ext4_end_io_work(struct work_struct *work)
unsigned long flags;
int ret;
- mutex_lock(&inode->i_mutex);
+ if (!mutex_trylock(&inode->i_mutex)) {
+ /*
+ * Requeue the work instead of waiting so that the work
+ * items queued after this can be processed.
+ */
+ queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
+ /*
+ * To prevent the ext4-dio-unwritten thread from keeping
+ * requeueing end_io requests and occupying cpu for too long,
+ * yield the cpu if it sees an end_io request that has already
+ * been requeued.
+ */
+ if (io->flag & EXT4_IO_END_QUEUED)
+ yield();
+ io->flag |= EXT4_IO_END_QUEUED;
+ return;
+ }
ret = ext4_end_io_nolock(io);
if (ret < 0) {
mutex_unlock(&inode->i_mutex);