writeback: use RCU to protect bdi_list
Now that bdi_writeback_all() no longer handles integrity writeback,
it doesn't have to block anymore. This means that we can switch
bdi_list reader side protection to RCU.
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index d3ca0da..fd93566 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -26,6 +26,12 @@
EXPORT_SYMBOL_GPL(default_backing_dev_info);
static struct class *bdi_class;
+
+/*
+ * bdi_lock protects updates to bdi_list and bdi_pending_list, as well as
+ * reader side protection for bdi_pending_list. bdi_list has RCU reader side
+ * locking.
+ */
DEFINE_SPINLOCK(bdi_lock);
LIST_HEAD(bdi_list);
LIST_HEAD(bdi_pending_list);
@@ -284,9 +290,9 @@
/*
* Add us to the active bdi_list
*/
- spin_lock(&bdi_lock);
- list_add(&bdi->bdi_list, &bdi_list);
- spin_unlock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
+ list_add_rcu(&bdi->bdi_list, &bdi_list);
+ spin_unlock_bh(&bdi_lock);
bdi_task_init(bdi, wb);
@@ -389,7 +395,7 @@
if (wb_has_dirty_io(me) || !list_empty(&me->bdi->work_list))
wb_do_writeback(me, 0);
- spin_lock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
/*
* Check if any existing bdi's have dirty data without
@@ -410,7 +416,7 @@
if (list_empty(&bdi_pending_list)) {
unsigned long wait;
- spin_unlock(&bdi_lock);
+ spin_unlock_bh(&bdi_lock);
wait = msecs_to_jiffies(dirty_writeback_interval * 10);
schedule_timeout(wait);
try_to_freeze();
@@ -426,7 +432,7 @@
bdi = list_entry(bdi_pending_list.next, struct backing_dev_info,
bdi_list);
list_del_init(&bdi->bdi_list);
- spin_unlock(&bdi_lock);
+ spin_unlock_bh(&bdi_lock);
wb = &bdi->wb;
wb->task = kthread_run(bdi_start_fn, wb, "flush-%s",
@@ -445,9 +451,9 @@
* a chance to flush other bdi's to free
* memory.
*/
- spin_lock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
list_add_tail(&bdi->bdi_list, &bdi_pending_list);
- spin_unlock(&bdi_lock);
+ spin_unlock_bh(&bdi_lock);
bdi_flush_io(bdi);
}
@@ -456,6 +462,24 @@
return 0;
}
+static void bdi_add_to_pending(struct rcu_head *head)
+{
+ struct backing_dev_info *bdi;
+
+ bdi = container_of(head, struct backing_dev_info, rcu_head);
+ INIT_LIST_HEAD(&bdi->bdi_list);
+
+ spin_lock(&bdi_lock);
+ list_add_tail(&bdi->bdi_list, &bdi_pending_list);
+ spin_unlock(&bdi_lock);
+
+ /*
+ * We are now on the pending list, wake up bdi_forker_task()
+ * to finish the job and add us back to the active bdi_list
+ */
+ wake_up_process(default_backing_dev_info.wb.task);
+}
+
/*
* Add the default flusher task that gets created for any bdi
* that has dirty data pending writeout
@@ -478,16 +502,29 @@
* waiting for previous additions to finish.
*/
if (!test_and_set_bit(BDI_pending, &bdi->state)) {
- list_move_tail(&bdi->bdi_list, &bdi_pending_list);
+ list_del_rcu(&bdi->bdi_list);
/*
- * We are now on the pending list, wake up bdi_forker_task()
- * to finish the job and add us back to the active bdi_list
+ * We must wait for the current RCU period to end before
+ * moving to the pending list. So schedule that operation
+ * from an RCU callback.
*/
- wake_up_process(default_backing_dev_info.wb.task);
+ call_rcu(&bdi->rcu_head, bdi_add_to_pending);
}
}
+/*
+ * Remove bdi from bdi_list, and ensure that it is no longer visible
+ */
+static void bdi_remove_from_list(struct backing_dev_info *bdi)
+{
+ spin_lock_bh(&bdi_lock);
+ list_del_rcu(&bdi->bdi_list);
+ spin_unlock_bh(&bdi_lock);
+
+ synchronize_rcu();
+}
+
int bdi_register(struct backing_dev_info *bdi, struct device *parent,
const char *fmt, ...)
{
@@ -506,9 +543,9 @@
goto exit;
}
- spin_lock(&bdi_lock);
- list_add_tail(&bdi->bdi_list, &bdi_list);
- spin_unlock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
+ list_add_tail_rcu(&bdi->bdi_list, &bdi_list);
+ spin_unlock_bh(&bdi_lock);
bdi->dev = dev;
@@ -526,9 +563,7 @@
wb->task = NULL;
ret = -ENOMEM;
- spin_lock(&bdi_lock);
- list_del(&bdi->bdi_list);
- spin_unlock(&bdi_lock);
+ bdi_remove_from_list(bdi);
goto exit;
}
}
@@ -565,9 +600,7 @@
/*
* Make sure nobody finds us on the bdi_list anymore
*/
- spin_lock(&bdi_lock);
- list_del(&bdi->bdi_list);
- spin_unlock(&bdi_lock);
+ bdi_remove_from_list(bdi);
/*
* Finally, kill the kernel threads. We don't need to be RCU
@@ -599,6 +632,7 @@
bdi->max_ratio = 100;
bdi->max_prop_frac = PROP_FRAC_BASE;
spin_lock_init(&bdi->wb_lock);
+ INIT_RCU_HEAD(&bdi->rcu_head);
INIT_LIST_HEAD(&bdi->bdi_list);
INIT_LIST_HEAD(&bdi->wb_list);
INIT_LIST_HEAD(&bdi->work_list);