writeback: move backing_dev_info->wb_lock and ->worklist into bdi_writeback
Currently, a bdi (backing_dev_info) embeds single wb (bdi_writeback)
and the role of the separation is unclear. For cgroup support for
writeback IOs, a bdi will be updated to host multiple wb's where each
wb serves writeback IOs of a different cgroup on the bdi. To achieve
that, a wb should carry all states necessary for servicing writeback
IOs for a cgroup independently.
This patch moves bdi->wb_lock and ->worklist into wb.
* The lock protects bdi->worklist and bdi->wb.dwork scheduling. While
moving, rename it to wb->work_lock as wb->wb_lock is confusing.
Also, move wb->dwork downwards so that it's colocated with the new
->work_lock and ->work_list fields.
* bdi_writeback_workfn() -> wb_workfn()
bdi_wakeup_thread_delayed(bdi) -> wb_wakeup_delayed(wb)
bdi_wakeup_thread(bdi) -> wb_wakeup(wb)
bdi_queue_work(bdi, ...) -> wb_queue_work(wb, ...)
__bdi_start_writeback(bdi, ...) -> __wb_start_writeback(wb, ...)
get_next_work_item(bdi) -> get_next_work_item(wb)
* bdi_wb_shutdown() is renamed to wb_shutdown() and now takes @wb.
The function contained parts which belong to the containing bdi
rather than the wb itself - testing cap_writeback_dirty and
bdi_remove_from_list() invocation. Those are moved to
bdi_unregister().
* bdi_wb_{init|exit}() are renamed to wb_{init|exit}().
Initializations of the moved bdi->wb_lock and ->work_list are
relocated from bdi_init() to wb_init().
* As there's still only one bdi_writeback per backing_dev_info, all
uses of bdi->state are mechanically replaced with bdi->wb.state
introducing no behavior changes.
Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 9a6c472..597f0ce 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -261,7 +261,7 @@
}
/*
- * This function is used when the first inode for this bdi is marked dirty. It
+ * This function is used when the first inode for this wb is marked dirty. It
* wakes-up the corresponding bdi thread which should then take care of the
* periodic background write-out of dirty inodes. Since the write-out would
* starts only 'dirty_writeback_interval' centisecs from now anyway, we just
@@ -274,15 +274,15 @@
* We have to be careful not to postpone flush work if it is scheduled for
* earlier. Thus we use queue_delayed_work().
*/
-void bdi_wakeup_thread_delayed(struct backing_dev_info *bdi)
+void wb_wakeup_delayed(struct bdi_writeback *wb)
{
unsigned long timeout;
timeout = msecs_to_jiffies(dirty_writeback_interval * 10);
- spin_lock_bh(&bdi->wb_lock);
- if (test_bit(WB_registered, &bdi->wb.state))
- queue_delayed_work(bdi_wq, &bdi->wb.dwork, timeout);
- spin_unlock_bh(&bdi->wb_lock);
+ spin_lock_bh(&wb->work_lock);
+ if (test_bit(WB_registered, &wb->state))
+ queue_delayed_work(bdi_wq, &wb->dwork, timeout);
+ spin_unlock_bh(&wb->work_lock);
}
/*
@@ -335,28 +335,24 @@
/*
* Remove bdi from the global list and shutdown any threads we have running
*/
-static void bdi_wb_shutdown(struct backing_dev_info *bdi)
+static void wb_shutdown(struct bdi_writeback *wb)
{
/* Make sure nobody queues further work */
- spin_lock_bh(&bdi->wb_lock);
- if (!test_and_clear_bit(WB_registered, &bdi->wb.state)) {
- spin_unlock_bh(&bdi->wb_lock);
+ spin_lock_bh(&wb->work_lock);
+ if (!test_and_clear_bit(WB_registered, &wb->state)) {
+ spin_unlock_bh(&wb->work_lock);
return;
}
- spin_unlock_bh(&bdi->wb_lock);
+ spin_unlock_bh(&wb->work_lock);
/*
- * Make sure nobody finds us on the bdi_list anymore
+ * Drain work list and shutdown the delayed_work. !WB_registered
+ * tells wb_workfn() that @wb is dying and its work_list needs to
+ * be drained no matter what.
*/
- bdi_remove_from_list(bdi);
-
- /*
- * Drain work list and shutdown the delayed_work. At this point,
- * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi
- * is dying and its work_list needs to be drained no matter what.
- */
- mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0);
- flush_delayed_work(&bdi->wb.dwork);
+ mod_delayed_work(bdi_wq, &wb->dwork, 0);
+ flush_delayed_work(&wb->dwork);
+ WARN_ON(!list_empty(&wb->work_list));
}
/*
@@ -381,7 +377,7 @@
*/
#define INIT_BW (100 << (20 - PAGE_SHIFT))
-static int bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
{
int i, err;
@@ -394,7 +390,6 @@
INIT_LIST_HEAD(&wb->b_more_io);
INIT_LIST_HEAD(&wb->b_dirty_time);
spin_lock_init(&wb->list_lock);
- INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn);
wb->bw_time_stamp = jiffies;
wb->balanced_dirty_ratelimit = INIT_BW;
@@ -402,6 +397,10 @@
wb->write_bandwidth = INIT_BW;
wb->avg_write_bandwidth = INIT_BW;
+ spin_lock_init(&wb->work_lock);
+ INIT_LIST_HEAD(&wb->work_list);
+ INIT_DELAYED_WORK(&wb->dwork, wb_workfn);
+
err = fprop_local_init_percpu(&wb->completions, GFP_KERNEL);
if (err)
return err;
@@ -419,7 +418,7 @@
return 0;
}
-static void bdi_wb_exit(struct bdi_writeback *wb)
+static void wb_exit(struct bdi_writeback *wb)
{
int i;
@@ -440,11 +439,9 @@
bdi->min_ratio = 0;
bdi->max_ratio = 100;
bdi->max_prop_frac = FPROP_FRAC_BASE;
- spin_lock_init(&bdi->wb_lock);
INIT_LIST_HEAD(&bdi->bdi_list);
- INIT_LIST_HEAD(&bdi->work_list);
- err = bdi_wb_init(&bdi->wb, bdi);
+ err = wb_init(&bdi->wb, bdi);
if (err)
return err;
@@ -454,9 +451,9 @@
void bdi_destroy(struct backing_dev_info *bdi)
{
- bdi_wb_shutdown(bdi);
-
- WARN_ON(!list_empty(&bdi->work_list));
+ /* make sure nobody finds us on the bdi_list anymore */
+ bdi_remove_from_list(bdi);
+ wb_shutdown(&bdi->wb);
if (bdi->dev) {
bdi_debug_unregister(bdi);
@@ -464,7 +461,7 @@
bdi->dev = NULL;
}
- bdi_wb_exit(&bdi->wb);
+ wb_exit(&bdi->wb);
}
EXPORT_SYMBOL(bdi_destroy);