writeback: implement memcg wb_domain

Dirtyable memory is distributed to a wb (bdi_writeback) according to
the relative bandwidth the wb is writing out in the whole system.
This distribution is global - each wb is measured against all other
wb's and gets the proportinately sized portion of the memory in the
whole system.

For cgroup writeback, the amount of dirtyable memory is scoped by
memcg and thus each wb would need to be measured and controlled in its
memcg.  IOW, a wb will belong to two writeback domains - the global
and memcg domains.

The previous patches laid the groundwork to support the two wb_domains
and this patch implements memcg wb_domain.  memcg->cgwb_domain is
initialized on css online and destroyed on css release,
wb->memcg_completions is added, and __wb_writeout_inc() is updated to
increment completions against both global and memcg wb_domains.

The following patches will update balance_dirty_pages() and its
subroutines to actually consider memcg wb_domain for throttling.

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, 25 insertions, 0 deletions

diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index a7ba5cee950b..a146e3389e78 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -171,6 +171,11 @@ static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *m
 	return mdtc->gdtc;
 }
 
+static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb)
+{
+	return &wb->memcg_completions;
+}
+
 static void wb_min_max_ratio(struct bdi_writeback *wb,
 			     unsigned long *minp, unsigned long *maxp)
 {
@@ -213,6 +218,11 @@ static struct dirty_throttle_control *mdtc_gdtc(struct dirty_throttle_control *m
 	return NULL;
 }
 
+static struct fprop_local_percpu *wb_memcg_completions(struct bdi_writeback *wb)
+{
+	return NULL;
+}
+
 static void wb_min_max_ratio(struct bdi_writeback *wb,
 			     unsigned long *minp, unsigned long *maxp)
 {
@@ -530,9 +540,16 @@ static void wb_domain_writeout_inc(struct wb_domain *dom,
  */
 static inline void __wb_writeout_inc(struct bdi_writeback *wb)
 {
+	struct wb_domain *cgdom;
+
 	__inc_wb_stat(wb, WB_WRITTEN);
 	wb_domain_writeout_inc(&global_wb_domain, &wb->completions,
 			       wb->bdi->max_prop_frac);
+
+	cgdom = mem_cgroup_wb_domain(wb);
+	if (cgdom)
+		wb_domain_writeout_inc(cgdom, wb_memcg_completions(wb),
+				       wb->bdi->max_prop_frac);
 }
 
 void wb_writeout_inc(struct bdi_writeback *wb)
@@ -583,6 +600,14 @@ int wb_domain_init(struct wb_domain *dom, gfp_t gfp)
 	return fprop_global_init(&dom->completions, gfp);
 }
 
+#ifdef CONFIG_CGROUP_WRITEBACK
+void wb_domain_exit(struct wb_domain *dom)
+{
+	del_timer_sync(&dom->period_timer);
+	fprop_global_destroy(&dom->completions);
+}
+#endif
+
 /*
  * bdi_min_ratio keeps the sum of the minimum dirty shares of all
  * registered backing devices, which, for obvious reasons, can not