writeback: implement unlocked_inode_to_wb transaction and use it for stat updates

The mechanism for detecting whether an inode should switch its wb
(bdi_writeback) association is now in place.  This patch build the
framework for the actual switching.

This patch adds a new inode flag I_WB_SWITCHING, which has two
functions.  First, the easy one, it ensures that there's only one
switching in progress for a give inode.  Second, it's used as a
mechanism to synchronize wb stat updates.

The two stats, WB_RECLAIMABLE and WB_WRITEBACK, aren't event counters
but track the current number of dirty pages and pages under writeback
respectively.  As such, when an inode is moved from one wb to another,
the inode's portion of those stats have to be transferred together;
unfortunately, this is a bit tricky as those stat updates are percpu
operations which are performed without holding any lock in some
places.

This patch solves the problem in a similar way as memcg.  Each such
lockless stat updates are wrapped in transaction surrounded by
unlocked_inode_to_wb_begin/end().  During normal operation, they map
to rcu_read_lock/unlock(); however, if I_WB_SWITCHING is asserted,
mapping->tree_lock is grabbed across the transaction.

In turn, the switching path sets I_WB_SWITCHING and waits for a RCU
grace period to pass before actually starting to switch, which
guarantees that all stat update paths are synchronizing against
mapping->tree_lock.

This patch still doesn't implement the actual switching.

v3: Updated on top of the recent cancel_dirty_page() updates.
    unlocked_inode_to_wb_begin() now nests inside
    mem_cgroup_begin_page_stat() to match the locking order.

v2: The i_wb access transaction will be used for !stat accesses too.
    Function names and comments updated accordingly.

    s/inode_wb_stat_unlocked_{begin|end}/unlocked_inode_to_wb_{begin|end}/
    s/switch_wb/switch_wbs/

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>

1 files changed, 111 insertions, 6 deletions

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index f67b956..08f5496 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -308,6 +308,115 @@ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode)
 	return locked_inode_to_wb_and_lock_list(inode);
 }
 
+struct inode_switch_wbs_context {
+	struct inode		*inode;
+	struct bdi_writeback	*new_wb;
+
+	struct rcu_head		rcu_head;
+	struct work_struct	work;
+};
+
+static void inode_switch_wbs_work_fn(struct work_struct *work)
+{
+	struct inode_switch_wbs_context *isw =
+		container_of(work, struct inode_switch_wbs_context, work);
+	struct inode *inode = isw->inode;
+	struct bdi_writeback *new_wb = isw->new_wb;
+
+	/*
+	 * By the time control reaches here, RCU grace period has passed
+	 * since I_WB_SWITCH assertion and all wb stat update transactions
+	 * between unlocked_inode_to_wb_begin/end() are guaranteed to be
+	 * synchronizing against mapping->tree_lock.
+	 */
+	spin_lock(&inode->i_lock);
+
+	inode->i_wb_frn_winner = 0;
+	inode->i_wb_frn_avg_time = 0;
+	inode->i_wb_frn_history = 0;
+
+	/*
+	 * Paired with load_acquire in unlocked_inode_to_wb_begin() and
+	 * ensures that the new wb is visible if they see !I_WB_SWITCH.
+	 */
+	smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH);
+
+	spin_unlock(&inode->i_lock);
+
+	iput(inode);
+	wb_put(new_wb);
+	kfree(isw);
+}
+
+static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head)
+{
+	struct inode_switch_wbs_context *isw = container_of(rcu_head,
+				struct inode_switch_wbs_context, rcu_head);
+
+	/* needs to grab bh-unsafe locks, bounce to work item */
+	INIT_WORK(&isw->work, inode_switch_wbs_work_fn);
+	schedule_work(&isw->work);
+}
+
+/**
+ * inode_switch_wbs - change the wb association of an inode
+ * @inode: target inode
+ * @new_wb_id: ID of the new wb
+ *
+ * Switch @inode's wb association to the wb identified by @new_wb_id.  The
+ * switching is performed asynchronously and may fail silently.
+ */
+static void inode_switch_wbs(struct inode *inode, int new_wb_id)
+{
+	struct backing_dev_info *bdi = inode_to_bdi(inode);
+	struct cgroup_subsys_state *memcg_css;
+	struct inode_switch_wbs_context *isw;
+
+	/* noop if seems to be already in progress */
+	if (inode->i_state & I_WB_SWITCH)
+		return;
+
+	isw = kzalloc(sizeof(*isw), GFP_ATOMIC);
+	if (!isw)
+		return;
+
+	/* find and pin the new wb */
+	rcu_read_lock();
+	memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys);
+	if (memcg_css)
+		isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC);
+	rcu_read_unlock();
+	if (!isw->new_wb)
+		goto out_free;
+
+	/* while holding I_WB_SWITCH, no one else can update the association */
+	spin_lock(&inode->i_lock);
+	if (inode->i_state & (I_WB_SWITCH | I_FREEING) ||
+	    inode_to_wb(inode) == isw->new_wb) {
+		spin_unlock(&inode->i_lock);
+		goto out_free;
+	}
+	inode->i_state |= I_WB_SWITCH;
+	spin_unlock(&inode->i_lock);
+
+	ihold(inode);
+	isw->inode = inode;
+
+	/*
+	 * In addition to synchronizing among switchers, I_WB_SWITCH tells
+	 * the RCU protected stat update paths to grab the mapping's
+	 * tree_lock so that stat transfer can synchronize against them.
+	 * Let's continue after I_WB_SWITCH is guaranteed to be visible.
+	 */
+	call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn);
+	return;
+
+out_free:
+	if (isw->new_wb)
+		wb_put(isw->new_wb);
+	kfree(isw);
+}
+
 /**
  * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it
  * @wbc: writeback_control of interest
@@ -433,12 +542,8 @@ void wbc_detach_inode(struct writeback_control *wbc)
 		 * is okay.  The main goal is avoiding keeping an inode on
 		 * the wrong wb for an extended period of time.
 		 */
-		if (hweight32(history) > WB_FRN_HIST_THR_SLOTS) {
-			/* switch */
-			max_id = 0;
-			avg_time = 0;
-			history = 0;
-		}
+		if (hweight32(history) > WB_FRN_HIST_THR_SLOTS)
+			inode_switch_wbs(inode, max_id);
 	}
 
 	/*