summaryrefslogtreecommitdiffstats
path: root/fs/fs-writeback.c
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2012-05-03 14:48:03 +0200
committerFengguang Wu <fengguang.wu@intel.com>2012-05-06 13:43:41 +0800
commit169ebd90131b2ffca74bb2dbe7eeacd39fb83714 (patch)
tree513136e110970da388680947c225ef8ca05a6dd7 /fs/fs-writeback.c
parentdbd5768f87ff6fb0a4fe09c4d7b6c4a24de99430 (diff)
downloadop-kernel-dev-169ebd90131b2ffca74bb2dbe7eeacd39fb83714.zip
op-kernel-dev-169ebd90131b2ffca74bb2dbe7eeacd39fb83714.tar.gz
writeback: Avoid iput() from flusher thread
Doing iput() from flusher thread (writeback_sb_inodes()) can create problems because iput() can do a lot of work - for example truncate the inode if it's the last iput on unlinked file. Some filesystems depend on flusher thread progressing (e.g. because they need to flush delay allocated blocks to reduce allocation uncertainty) and so flusher thread doing truncate creates interesting dependencies and possibilities for deadlocks. We get rid of iput() in flusher thread by using the fact that I_SYNC inode flag effectively pins the inode in memory. So if we take care to either hold i_lock or have I_SYNC set, we can get away without taking inode reference in writeback_sb_inodes(). As a side effect of these changes, we also fix possible use-after-free in wb_writeback() because inode_wait_for_writeback() call could try to reacquire i_lock on the inode that was already free. Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Diffstat (limited to 'fs/fs-writeback.c')
-rw-r--r--fs/fs-writeback.c66
1 files changed, 53 insertions, 13 deletions
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 5f2c682..8d2fb8c 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -326,9 +326,12 @@ static int write_inode(struct inode *inode, struct writeback_control *wbc)
}
/*
- * Wait for writeback on an inode to complete.
+ * Wait for writeback on an inode to complete. Called with i_lock held.
+ * Caller must make sure inode cannot go away when we drop i_lock.
*/
-static void inode_wait_for_writeback(struct inode *inode)
+static void __inode_wait_for_writeback(struct inode *inode)
+ __releases(inode->i_lock)
+ __acquires(inode->i_lock)
{
DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
wait_queue_head_t *wqh;
@@ -342,6 +345,36 @@ static void inode_wait_for_writeback(struct inode *inode)
}
/*
+ * Wait for writeback on an inode to complete. Caller must have inode pinned.
+ */
+void inode_wait_for_writeback(struct inode *inode)
+{
+ spin_lock(&inode->i_lock);
+ __inode_wait_for_writeback(inode);
+ spin_unlock(&inode->i_lock);
+}
+
+/*
+ * Sleep until I_SYNC is cleared. This function must be called with i_lock
+ * held and drops it. It is aimed for callers not holding any inode reference
+ * so once i_lock is dropped, inode can go away.
+ */
+static void inode_sleep_on_writeback(struct inode *inode)
+ __releases(inode->i_lock)
+{
+ DEFINE_WAIT(wait);
+ wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
+ int sleep;
+
+ prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+ sleep = inode->i_state & I_SYNC;
+ spin_unlock(&inode->i_lock);
+ if (sleep)
+ schedule();
+ finish_wait(wqh, &wait);
+}
+
+/*
* Find proper writeback list for the inode depending on its current state and
* possibly also change of its state while we were doing writeback. Here we
* handle things such as livelock prevention or fairness of writeback among
@@ -479,9 +512,11 @@ writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
if (wbc->sync_mode != WB_SYNC_ALL)
goto out;
/*
- * It's a data-integrity sync. We must wait.
+ * It's a data-integrity sync. We must wait. Since callers hold
+ * inode reference or inode has I_WILL_FREE set, it cannot go
+ * away under us.
*/
- inode_wait_for_writeback(inode);
+ __inode_wait_for_writeback(inode);
}
WARN_ON(inode->i_state & I_SYNC);
/*
@@ -620,20 +655,28 @@ static long writeback_sb_inodes(struct super_block *sb,
}
spin_unlock(&wb->list_lock);
- __iget(inode);
/*
* We already requeued the inode if it had I_SYNC set and we
* are doing WB_SYNC_NONE writeback. So this catches only the
* WB_SYNC_ALL case.
*/
- if (inode->i_state & I_SYNC)
- inode_wait_for_writeback(inode);
+ if (inode->i_state & I_SYNC) {
+ /* Wait for I_SYNC. This function drops i_lock... */
+ inode_sleep_on_writeback(inode);
+ /* Inode may be gone, start again */
+ continue;
+ }
inode->i_state |= I_SYNC;
spin_unlock(&inode->i_lock);
+
write_chunk = writeback_chunk_size(wb->bdi, work);
wbc.nr_to_write = write_chunk;
wbc.pages_skipped = 0;
+ /*
+ * We use I_SYNC to pin the inode in memory. While it is set
+ * evict_inode() will wait so the inode cannot be freed.
+ */
__writeback_single_inode(inode, wb, &wbc);
work->nr_pages -= write_chunk - wbc.nr_to_write;
@@ -645,10 +688,7 @@ static long writeback_sb_inodes(struct super_block *sb,
requeue_inode(inode, wb, &wbc);
inode_sync_complete(inode);
spin_unlock(&inode->i_lock);
- spin_unlock(&wb->list_lock);
- iput(inode);
- cond_resched();
- spin_lock(&wb->list_lock);
+ cond_resched_lock(&wb->list_lock);
/*
* bail out to wb_writeback() often enough to check
* background threshold and other termination conditions.
@@ -843,8 +883,8 @@ static long wb_writeback(struct bdi_writeback *wb,
inode = wb_inode(wb->b_more_io.prev);
spin_lock(&inode->i_lock);
spin_unlock(&wb->list_lock);
- inode_wait_for_writeback(inode);
- spin_unlock(&inode->i_lock);
+ /* This function drops i_lock... */
+ inode_sleep_on_writeback(inode);
spin_lock(&wb->list_lock);
}
}
OpenPOWER on IntegriCloud