writeback: make writeback_control track the inode being written back

Currently, for cgroup writeback, the IO submission paths directly
associate the bio's with the blkcg from inode_to_wb_blkcg_css();
however, it'd be necessary to keep more writeback context to implement
foreign inode writeback detection.  wbc (writeback_control) is the
natural fit for the extra context - it persists throughout the
writeback of each inode and is passed all the way down to IO
submission paths.

This patch adds wbc_attach_and_unlock_inode(), wbc_detach_inode(), and
wbc_attach_fdatawrite_inode() which are used to associate wbc with the
inode being written back.  IO submission paths now use wbc_init_bio()
instead of directly associating bio's with blkcg themselves.  This
leaves inode_to_wb_blkcg_css() w/o any user.  The function is removed.

wbc currently only tracks the associated wb (bdi_writeback).  Future
patches will add more for foreign inode detection.  The association is
established under i_lock which will be depended upon when migrating
foreign inodes to other wb's.

As currently, once established, inode to wb association never changes,
going through wbc when initializing bio's doesn't cause any behavior
changes.

v2: submit_blk_blkcg() now checks whether the wbc is associated with a
    wb before dereferencing it.  This can happen when pageout() is
    writing pages directly without going through the usual writeback
    path.  As pageout() path is single-threaded, we don't want it to
    be blocked behind a slow cgroup and ultimately want it to delegate
    actual writing to the usual writeback path.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Jan Kara <jack@suse.cz>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Cc: Greg Thelen <gthelen@google.com>
Signed-off-by: Jens Axboe <axboe@fb.com>

2 files changed, 68 insertions, 12 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 5c978a924157..b1d2489a6536 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -332,12 +332,6 @@ static inline struct bdi_writeback *inode_to_wb(struct inode *inode)
 	return inode->i_wb;
 }
 
-static inline struct cgroup_subsys_state *
-inode_to_wb_blkcg_css(struct inode *inode)
-{
-	return inode_to_wb(inode)->blkcg_css;
-}
-
 struct wb_iter {
 	int			start_blkcg_id;
 	struct radix_tree_iter	tree_iter;
@@ -434,12 +428,6 @@ static inline void wb_blkcg_offline(struct blkcg *blkcg)
 {
 }
 
-static inline struct cgroup_subsys_state *
-inode_to_wb_blkcg_css(struct inode *inode)
-{
-	return blkcg_root_css;
-}
-
 struct wb_iter {
 	int		next_id;
 };
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 6726b7e56beb..8f964e558af5 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -86,6 +86,9 @@ struct writeback_control {
 	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 	unsigned for_sync:1;		/* sync(2) WB_SYNC_ALL writeback */
+#ifdef CONFIG_CGROUP_WRITEBACK
+	struct bdi_writeback *wb;	/* wb this writeback is issued under */
+#endif
 };
 
 /*
@@ -176,7 +179,14 @@ static inline void wait_on_inode(struct inode *inode)
 
 #ifdef CONFIG_CGROUP_WRITEBACK
 
+#include <linux/cgroup.h>
+#include <linux/bio.h>
+
 void __inode_attach_wb(struct inode *inode, struct page *page);
+void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
+				 struct inode *inode)
+	__releases(&inode->i_lock);
+void wbc_detach_inode(struct writeback_control *wbc);
 
 /**
  * inode_attach_wb - associate an inode with its wb
@@ -207,6 +217,44 @@ static inline void inode_detach_wb(struct inode *inode)
 	}
 }
 
+/**
+ * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite
+ * @wbc: writeback_control of interest
+ * @inode: target inode
+ *
+ * This function is to be used by __filemap_fdatawrite_range(), which is an
+ * alternative entry point into writeback code, and first ensures @inode is
+ * associated with a bdi_writeback and attaches it to @wbc.
+ */
+static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
+					       struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	inode_attach_wb(inode, NULL);
+	wbc_attach_and_unlock_inode(wbc, inode);
+}
+
+/**
+ * wbc_init_bio - writeback specific initializtion of bio
+ * @wbc: writeback_control for the writeback in progress
+ * @bio: bio to be initialized
+ *
+ * @bio is a part of the writeback in progress controlled by @wbc.  Perform
+ * writeback specific initialization.  This is used to apply the cgroup
+ * writeback context.
+ */
+static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio)
+{
+	/*
+	 * pageout() path doesn't attach @wbc to the inode being written
+	 * out.  This is intentional as we don't want the function to block
+	 * behind a slow cgroup.  Ultimately, we want pageout() to kick off
+	 * regular writeback instead of writing things out itself.
+	 */
+	if (wbc->wb)
+		bio_associate_blkcg(bio, wbc->wb->blkcg_css);
+}
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static inline void inode_attach_wb(struct inode *inode, struct page *page)
@@ -217,6 +265,26 @@ static inline void inode_detach_wb(struct inode *inode)
 {
 }
 
+static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc,
+					       struct inode *inode)
+	__releases(&inode->i_lock)
+{
+	spin_unlock(&inode->i_lock);
+}
+
+static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc,
+					       struct inode *inode)
+{
+}
+
+static inline void wbc_detach_inode(struct writeback_control *wbc)
+{
+}
+
+static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio)
+{
+}
+
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
 /*