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, 39 insertions, 0 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 701cbee..ce113dd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -345,6 +345,7 @@ struct mem_cgroup {
 
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct list_head cgwb_list;
+	struct wb_domain cgwb_domain;
 #endif
 
 	/* List of events which userspace want to receive */
@@ -3994,6 +3995,37 @@ struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg)
 	return &memcg->cgwb_list;
 }
 
+static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
+{
+	return wb_domain_init(&memcg->cgwb_domain, gfp);
+}
+
+static void memcg_wb_domain_exit(struct mem_cgroup *memcg)
+{
+	wb_domain_exit(&memcg->cgwb_domain);
+}
+
+struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(wb->memcg_css);
+
+	if (!memcg->css.parent)
+		return NULL;
+
+	return &memcg->cgwb_domain;
+}
+
+#else	/* CONFIG_CGROUP_WRITEBACK */
+
+static int memcg_wb_domain_init(struct mem_cgroup *memcg, gfp_t gfp)
+{
+	return 0;
+}
+
+static void memcg_wb_domain_exit(struct mem_cgroup *memcg)
+{
+}
+
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
 /*
@@ -4380,9 +4412,15 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
 	if (!memcg->stat)
 		goto out_free;
+
+	if (memcg_wb_domain_init(memcg, GFP_KERNEL))
+		goto out_free_stat;
+
 	spin_lock_init(&memcg->pcp_counter_lock);
 	return memcg;
 
+out_free_stat:
+	free_percpu(memcg->stat);
 out_free:
 	kfree(memcg);
 	return NULL;
@@ -4409,6 +4447,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 		free_mem_cgroup_per_zone_info(memcg, node);
 
 	free_percpu(memcg->stat);
+	memcg_wb_domain_exit(memcg);
 	kfree(memcg);
 }