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 <dchinner@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

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;
 
@@ -1028,7 +1046,7 @@ 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
@@ -1036,11 +1054,12 @@ void __mark_inode_dirty(struct inode *inode, int flags)
 		 */
 		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

fs/notify/inode_mark.c

@@ -254,8 +254,11 @@ void fsnotify_unmount_inodes(struct list_head *list)
 		 * I_WILL_FREE, or I_NEW which is fine because by that point
 		 * the inode cannot have any associated watches.
 		 */
-		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 
 		/*
 		 * If i_count is zero, the inode cannot have any watches and
@@ -263,8 +266,10 @@ void fsnotify_unmount_inodes(struct list_head *list)
 		 * evict all inodes with zero i_count from icache which is
 		 * unnecessarily violent and may in fact be illegal to do.
 		 */
-		if (!atomic_read(&inode->i_count))
+		if (!atomic_read(&inode->i_count)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 
 		need_iput_tmp = need_iput;
 		need_iput = NULL;
@@ -274,13 +279,17 @@ void fsnotify_unmount_inodes(struct list_head *list)
 			__iget(inode);
 		else
 			need_iput_tmp = NULL;
+		spin_unlock(&inode->i_lock);
 
 		/* In case the dropping of a reference would nuke next_i. */
 		if ((&next_i->i_sb_list != list) &&
-		    atomic_read(&next_i->i_count) &&
-		    !(next_i->i_state & (I_FREEING | I_WILL_FREE))) {
-			__iget(next_i);
-			need_iput = next_i;
+		    atomic_read(&next_i->i_count)) {
+			spin_lock(&next_i->i_lock);
+			if (!(next_i->i_state & (I_FREEING | I_WILL_FREE))) {
+				__iget(next_i);
+				need_iput = next_i;
+			}
+			spin_unlock(&next_i->i_lock);
 		}
 
 		/*

fs/quota/dquot.c

@@ -902,18 +902,19 @@ 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))
+		spin_lock(&inode->i_lock);
+		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
+		    !atomic_read(&inode->i_writecount) ||
+		    !dqinit_needed(inode, type)) {
+			spin_unlock(&inode->i_lock);
 			continue;
+		}
 #ifdef CONFIG_QUOTA_DEBUG
 		if (unlikely(inode_get_rsv_space(inode) > 0))
 			reserved = 1;
 #endif
-		if (!atomic_read(&inode->i_writecount))
-			continue;
-		if (!dqinit_needed(inode, type))
-			continue;
-
 		__iget(inode);
+		spin_unlock(&inode->i_lock);
 		spin_unlock(&inode_lock);
 
 		iput(old_inode);

include/linux/fs.h

@@ -1647,7 +1647,7 @@ struct super_operations {
 };
 
 /*
- * Inode state bits.  Protected by inode_lock.
+ * Inode state bits.  Protected by inode->i_lock
  *
  * Three bits determine the dirty state of the inode, I_DIRTY_SYNC,
  * I_DIRTY_DATASYNC and I_DIRTY_PAGES.

include/linux/quotaops.h

@@ -277,7 +277,7 @@ static inline int dquot_alloc_space(struct inode *inode, qsize_t nr)
 		/*
 		 * Mark inode fully dirty. Since we are allocating blocks, inode
 		 * would become fully dirty soon anyway and it reportedly
-		 * reduces inode_lock contention.
+		 * reduces lock contention.
 		 */
 		mark_inode_dirty(inode);
 	}

mm/filemap.c

@@ -99,7 +99,9 @@
  *    ->private_lock		(page_remove_rmap->set_page_dirty)
  *    ->tree_lock		(page_remove_rmap->set_page_dirty)
  *    ->inode_lock		(page_remove_rmap->set_page_dirty)
+ *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
  *    ->inode_lock		(zap_pte_range->set_page_dirty)
+ *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
  *
  *  (code doesn't rely on that order, so you could switch it around)

mm/rmap.c

@@ -32,6 +32,7 @@
  *               mmlist_lock (in mmput, drain_mmlist and others)
  *               mapping->private_lock (in __set_page_dirty_buffers)
  *               inode_lock (in set_page_dirty's __mark_inode_dirty)
+ *               inode->i_lock (in set_page_dirty's __mark_inode_dirty)
  *                 sb_lock (within inode_lock in fs/fs-writeback.c)
  *                 mapping->tree_lock (widely used, in set_page_dirty,
  *                           in arch-dependent flush_dcache_mmap_lock,