writeback: move backing_dev_info->bdi_stat[] 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->bdi_stat[] into wb.
* enum bdi_stat_item is renamed to wb_stat_item and the prefix of all
enums is changed from BDI_ to WB_.
* BDI_STAT_BATCH() -> WB_STAT_BATCH()
* [__]{add|inc|dec|sum}_wb_stat(bdi, ...) -> [__]{add|inc}_wb_stat(wb, ...)
* bdi_stat[_error]() -> wb_stat[_error]()
* bdi_writeout_inc() -> wb_writeout_inc()
* stat init is moved to bdi_wb_init() and bdi_wb_exit() is added and
frees stat.
* As there's still only one bdi_writeback per backing_dev_info, all
uses of bdi->stat[] are mechanically replaced with bdi->wb.stat[]
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>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jens Axboe <axboe@fb.com>
(cherry picked from commit 93f78d882865cb90020d0f80a9523c99cf46924c)
Signed-off-by: Alex Shi <alex.shi@linaro.org>
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 1f9ebc3..299ef5e 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -84,13 +84,13 @@
"b_dirty_time: %10lu\n"
"bdi_list: %10u\n"
"state: %10lx\n",
- (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
- (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
+ (unsigned long) K(wb_stat(wb, WB_WRITEBACK)),
+ (unsigned long) K(wb_stat(wb, WB_RECLAIMABLE)),
K(bdi_thresh),
K(dirty_thresh),
K(background_thresh),
- (unsigned long) K(bdi_stat(bdi, BDI_DIRTIED)),
- (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)),
+ (unsigned long) K(wb_stat(wb, WB_DIRTIED)),
+ (unsigned long) K(wb_stat(wb, WB_WRITTEN)),
(unsigned long) K(bdi->write_bandwidth),
nr_dirty,
nr_io,
@@ -359,8 +359,27 @@
flush_delayed_work(&bdi->wb.dwork);
}
-static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+/*
+ * Called when the device behind @bdi has been removed or ejected.
+ *
+ * We can't really do much here except for reducing the dirty ratio at
+ * the moment. In the future we should be able to set a flag so that
+ * the filesystem can handle errors at mark_inode_dirty time instead
+ * of only at writeback time.
+ */
+void bdi_unregister(struct backing_dev_info *bdi)
{
+ if (WARN_ON_ONCE(!bdi->dev))
+ return;
+
+ bdi_set_min_ratio(bdi, 0);
+}
+EXPORT_SYMBOL(bdi_unregister);
+
+static int bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
+{
+ int i, err;
+
memset(wb, 0, sizeof(*wb));
wb->bdi = bdi;
@@ -371,6 +390,27 @@
INIT_LIST_HEAD(&wb->b_dirty_time);
spin_lock_init(&wb->list_lock);
INIT_DELAYED_WORK(&wb->dwork, bdi_writeback_workfn);
+
+ for (i = 0; i < NR_WB_STAT_ITEMS; i++) {
+ err = percpu_counter_init(&wb->stat[i], 0, GFP_KERNEL);
+ if (err) {
+ while (--i)
+ percpu_counter_destroy(&wb->stat[i]);
+ return err;
+ }
+ }
+
+ return 0;
+}
+
+static void bdi_wb_exit(struct bdi_writeback *wb)
+{
+ int i;
+
+ WARN_ON(delayed_work_pending(&wb->dwork));
+
+ for (i = 0; i < NR_WB_STAT_ITEMS; i++)
+ percpu_counter_destroy(&wb->stat[i]);
}
/*
@@ -380,7 +420,7 @@
int bdi_init(struct backing_dev_info *bdi)
{
- int i, err;
+ int err;
bdi->dev = NULL;
@@ -391,13 +431,9 @@
INIT_LIST_HEAD(&bdi->bdi_list);
INIT_LIST_HEAD(&bdi->work_list);
- bdi_wb_init(&bdi->wb, bdi);
-
- for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
- err = percpu_counter_init(&bdi->bdi_stat[i], 0, GFP_KERNEL);
- if (err)
- goto err;
- }
+ err = bdi_wb_init(&bdi->wb, bdi);
+ if (err)
+ return err;
bdi->dirty_exceeded = 0;
@@ -410,26 +446,21 @@
bdi->avg_write_bandwidth = INIT_BW;
err = fprop_local_init_percpu(&bdi->completions, GFP_KERNEL);
-
if (err) {
-err:
- while (i--)
- percpu_counter_destroy(&bdi->bdi_stat[i]);
+ bdi_wb_exit(&bdi->wb);
+ return err;
}
- return err;
+ return 0;
}
EXPORT_SYMBOL(bdi_init);
void bdi_destroy(struct backing_dev_info *bdi)
{
- int i;
-
bdi_wb_shutdown(bdi);
bdi_set_min_ratio(bdi, 0);
WARN_ON(!list_empty(&bdi->work_list));
- WARN_ON(delayed_work_pending(&bdi->wb.dwork));
if (bdi->dev) {
bdi_debug_unregister(bdi);
@@ -437,8 +468,8 @@
bdi->dev = NULL;
}
- for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
- percpu_counter_destroy(&bdi->bdi_stat[i]);
+ bdi_wb_exit(&bdi->wb);
+
fprop_local_destroy_percpu(&bdi->completions);
}
EXPORT_SYMBOL(bdi_destroy);