fs: protect inode->i_state with inode->i_lock

Protect inode state transitions and validity checks with the
inode->i_lock. This enables us to make inode state transitions
independently of the inode_lock and is the first step to peeling
away the inode_lock from the code.

This requires that __iget() is done atomically with i_state checks
during list traversals so that we don't race with another thread
marking the inode I_FREEING between the state check and grabbing the
reference.

Also remove the unlock_new_inode() memory barrier optimisation
required to avoid taking the inode_lock when clearing I_NEW.
Simplify the code by simply taking the inode->i_lock around the
state change and wakeup. Because the wakeup is no longer tricky,
remove the wake_up_inode() function and open code the wakeup where
necessary.

Signed-off-by: Dave Chinner <[email protected]>
Signed-off-by: Al Viro <[email protected]>

fs/block_dev.c

@@ -56,9 +56,11 @@ static void bdev_inode_switch_bdi(struct inode *inode,
 			struct backing_dev_info *dst)
 {
 	spin_lock(&inode_lock);
+	spin_lock(&inode->i_lock);
 	inode->i_data.backing_dev_info = dst;
 	if (inode->i_state & I_DIRTY)
 		list_move(&inode->i_wb_list, &dst->wb.b_dirty);
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_lock);
 }
 

fs/buffer.c

@@ -1144,7 +1144,7 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
  * inode list.
  *
  * mark_buffer_dirty() is atomic.  It takes bh->b_page->mapping->private_lock,
- * mapping->tree_lock and the global inode_lock.
+ * mapping->tree_lock and mapping->host->i_lock.
  */
 void mark_buffer_dirty(struct buffer_head *bh)
 {

fs/drop_caches.c

@@ -18,11 +18,14 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused)
 
 	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))
-			continue;
-		if (inode->i_mapping->nrpages == 0)
+		spin_lock(&inode->i_lock);
+		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
+		    (inode->i_mapping->nrpages == 0)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 		__iget(inode);
+		spin_unlock(&inode->i_lock);
 		spin_unlock(&inode_lock);
 		invalidate_mapping_pages(inode->i_mapping, 0, -1);
 		iput(toput_inode);

fs/fs-writeback.c

@@ -306,10 +306,12 @@ static void inode_wait_for_writeback(struct inode *inode)
 	wait_queue_head_t *wqh;
 
 	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
-	 while (inode->i_state & I_SYNC) {
+	while (inode->i_state & I_SYNC) {
+		spin_unlock(&inode->i_lock);
 		spin_unlock(&inode_lock);
 		__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
 		spin_lock(&inode_lock);
+		spin_lock(&inode->i_lock);
 	}
 }
 
@@ -333,6 +335,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	unsigned dirty;
 	int ret;
 
+	spin_lock(&inode->i_lock);
 	if (!atomic_read(&inode->i_count))
 		WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
 	else
@@ -348,6 +351,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 		 * completed a full scan of b_io.
 		 */
 		if (wbc->sync_mode != WB_SYNC_ALL) {
+			spin_unlock(&inode->i_lock);
 			requeue_io(inode);
 			return 0;
 		}
@@ -363,6 +367,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	/* Set I_SYNC, reset I_DIRTY_PAGES */
 	inode->i_state |= I_SYNC;
 	inode->i_state &= ~I_DIRTY_PAGES;
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_lock);
 
 	ret = do_writepages(mapping, wbc);
@@ -384,8 +389,10 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	 * write_inode()
 	 */
 	spin_lock(&inode_lock);
+	spin_lock(&inode->i_lock);
 	dirty = inode->i_state & I_DIRTY;
 	inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
+	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_lock);
 	/* Don't write the inode if only I_DIRTY_PAGES was set */
 	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
@@ -395,6 +402,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 	}
 
 	spin_lock(&inode_lock);
+	spin_lock(&inode->i_lock);
 	inode->i_state &= ~I_SYNC;
 	if (!(inode->i_state & I_FREEING)) {
 		if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
@@ -436,6 +444,7 @@ writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
 		}
 	}
 	inode_sync_complete(inode);
+	spin_unlock(&inode->i_lock);
 	return ret;
 }
 
@@ -506,7 +515,9 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 		 * kind does not need peridic writeout yet, and for the latter
 		 * kind writeout is handled by the freer.
 		 */
+		spin_lock(&inode->i_lock);
 		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+			spin_unlock(&inode->i_lock);
 			requeue_io(inode);
 			continue;
 		}
@@ -515,10 +526,14 @@ static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
 		 * Was this inode dirtied after sync_sb_inodes was called?
 		 * This keeps sync from extra jobs and livelock.
 		 */
-		if (inode_dirtied_after(inode, wbc->wb_start))
+		if (inode_dirtied_after(inode, wbc->wb_start)) {
+			spin_unlock(&inode->i_lock);
 			return 1;
+		}
 
 		__iget(inode);
+		spin_unlock(&inode->i_lock);
+
 		pages_skipped = wbc->pages_skipped;
 		writeback_single_inode(inode, wbc);
 		if (wbc->pages_skipped != pages_skipped) {
@@ -724,7 +739,9 @@ static long wb_writeback(struct bdi_writeback *wb,
 		if (!list_empty(&wb->b_more_io))  {
 			inode = wb_inode(wb->b_more_io.prev);
 			trace_wbc_writeback_wait(&wbc, wb->bdi);
+			spin_lock(&inode->i_lock);
 			inode_wait_for_writeback(inode);
+			spin_unlock(&inode->i_lock);
 		}
 		spin_unlock(&inode_lock);
 	}
@@ -1017,6 +1034,7 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		block_dump___mark_inode_dirty(inode);
 
 	spin_lock(&inode_lock);
+	spin_lock(&inode->i_lock);
 	if ((inode->i_state & flags) != flags) {
 		const int was_dirty = inode->i_state & I_DIRTY;
 
@@ -1028,19 +1046,20 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		 * superblock list, based upon its state.
 		 */
 		if (inode->i_state & I_SYNC)
-			goto out;
+			goto out_unlock_inode;
 
 		/*
 		 * Only add valid (hashed) inodes to the superblock's
 		 * dirty list.  Add blockdev inodes as well.
 		 */
 		if (!S_ISBLK(inode->i_mode)) {
 			if (inode_unhashed(inode))
-				goto out;
+				goto out_unlock_inode;
 		}
 		if (inode->i_state & I_FREEING)
-			goto out;
+			goto out_unlock_inode;
 
+		spin_unlock(&inode->i_lock);
 		/*
 		 * If the inode was already on b_dirty/b_io/b_more_io, don't
 		 * reposition it (that would break b_dirty time-ordering).
@@ -1065,7 +1084,10 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 			inode->dirtied_when = jiffies;
 			list_move(&inode->i_wb_list, &bdi->wb.b_dirty);
 		}
+		goto out;
 	}
+out_unlock_inode:
+	spin_unlock(&inode->i_lock);
 out:
 	spin_unlock(&inode_lock);
 
@@ -1111,14 +1133,16 @@ static void wait_sb_inodes(struct super_block *sb)
 	 * we still have to wait for that writeout.
 	 */
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		struct address_space *mapping;
+		struct address_space *mapping = inode->i_mapping;
 
-		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
-			continue;
-		mapping = inode->i_mapping;
-		if (mapping->nrpages == 0)
+		spin_lock(&inode->i_lock);
+		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
+		    (mapping->nrpages == 0)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 		__iget(inode);
+		spin_unlock(&inode->i_lock);
 		spin_unlock(&inode_lock);
 		/*
 		 * We hold a reference to 'inode' so it couldn't have