fs, mm: account buffer_head to kmemcg

The buffer_head can consume a significant amount of system memory and is
directly related to the amount of page cache.  In our production
environment we have observed that a lot of machines are spending a
significant amount of memory as buffer_head and can not be left as
system memory overhead.

Charging buffer_head is not as simple as adding __GFP_ACCOUNT to the
allocation.  The buffer_heads can be allocated in a memcg different from
the memcg of the page for which buffer_heads are being allocated.  One
concrete example is memory reclaim.  The reclaim can trigger I/O of
pages of any memcg on the system.  So, the right way to charge
buffer_head is to extract the memcg from the page for which buffer_heads
are being allocated and then use targeted memcg charging API.

[shakeelb@google.com: use __GFP_ACCOUNT for directed memcg charging]
  Link: http://lkml.kernel.org/r/20180702220208.213380-1-shakeelb@google.com
Link: http://lkml.kernel.org/r/20180627191250.209150-3-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Amir Goldstein <amir73il@gmail.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

fs/buffer.c

@@ -45,6 +45,7 @@
 #include <linux/mpage.h>
 #include <linux/bit_spinlock.h>
 #include <linux/pagevec.h>
+#include <linux/sched/mm.h>
 #include <trace/events/block.h>
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
@@ -813,12 +814,16 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
 		bool retry)
 {
 	struct buffer_head *bh, *head;
-	gfp_t gfp = GFP_NOFS;
+	gfp_t gfp = GFP_NOFS | __GFP_ACCOUNT;
 	long offset;
+	struct mem_cgroup *memcg;
 
 	if (retry)
 		gfp |= __GFP_NOFAIL;
 
+	memcg = get_mem_cgroup_from_page(page);
+	memalloc_use_memcg(memcg);
+
 	head = NULL;
 	offset = PAGE_SIZE;
 	while ((offset -= size) >= 0) {
@@ -835,6 +840,9 @@ struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
 		/* Link the buffer to its page */
 		set_bh_page(bh, page, offset);
 	}
+out:
+	memalloc_unuse_memcg();
+	mem_cgroup_put(memcg);
 	return head;
 /*
  * In case anything failed, we just free everything we got.
@@ -848,7 +856,7 @@ no_grow:
 		} while (head);
 	}
 
-	return NULL;
+	goto out;
 }
 EXPORT_SYMBOL_GPL(alloc_page_buffers);
 

include/linux/memcontrol.h

@@ -375,6 +375,8 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 
 struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
 
+struct mem_cgroup *get_mem_cgroup_from_page(struct page *page);
+
 static inline
 struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
@@ -863,6 +865,11 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return NULL;
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
+{
+	return NULL;
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }

mm/memcontrol.c

@@ -713,6 +713,28 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 }
 EXPORT_SYMBOL(get_mem_cgroup_from_mm);
 
+/**
+ * get_mem_cgroup_from_page: Obtain a reference on given page's memcg.
+ * @page: page from which memcg should be extracted.
+ *
+ * Obtain a reference on page->memcg and returns it if successful. Otherwise
+ * root_mem_cgroup is returned.
+ */
+struct mem_cgroup *get_mem_cgroup_from_page(struct page *page)
+{
+	struct mem_cgroup *memcg = page->mem_cgroup;
+
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	rcu_read_lock();
+	if (!memcg || !css_tryget_online(&memcg->css))
+		memcg = root_mem_cgroup;
+	rcu_read_unlock();
+	return memcg;
+}
+EXPORT_SYMBOL(get_mem_cgroup_from_page);
+
 /**
  * If current->active_memcg is non-NULL, do not fallback to current->mm->memcg.
  */