mm: memcontrol: hook up vmpressure to socket pressure

Let the networking stack know when a memcg is under reclaim pressure so
that it can clamp its transmit windows accordingly.

Whenever the reclaim efficiency of a cgroup's LRU lists drops low enough
for a MEDIUM or HIGH vmpressure event to occur, assert a pressure state
in the socket and tcp memory code that tells it to curb consumption
growth from sockets associated with said control group.

Traditionally, vmpressure reports for the entire subtree of a memcg
under pressure, which drops useful information on the individual groups
reclaimed.  However, it's too late to change the userinterface, so add a
second reporting mode that reports on the level of reclaim instead of at
the level of pressure, and use that report for sockets.

vmpressure events are naturally edge triggered, so for hysteresis assert
socket pressure for a second to allow for subsequent vmpressure events
to occur before letting the socket code return to normal.

This will likely need finetuning for a wider variety of workloads, but
for now stick to the vmpressure presets and keep hysteresis simple.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 33 insertions, 6 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a355f61a2ed3..c5a51039df57 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -249,6 +249,10 @@ struct mem_cgroup {
 	struct wb_domain cgwb_domain;
 #endif
 
+#ifdef CONFIG_INET
+	unsigned long		socket_pressure;
+#endif
+
 	/* List of events which userspace want to receive */
 	struct list_head event_list;
 	spinlock_t event_list_lock;
@@ -290,18 +294,34 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
 
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
-struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
 
 static inline
 struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
 }
 
+#define mem_cgroup_from_counter(counter, member)	\
+	container_of(counter, struct mem_cgroup, member)
+
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup *,
 				   struct mem_cgroup_reclaim_cookie *);
 void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
 
+/**
+ * parent_mem_cgroup - find the accounting parent of a memcg
+ * @memcg: memcg whose parent to find
+ *
+ * Returns the parent memcg, or NULL if this is the root or the memory
+ * controller is in legacy no-hierarchy mode.
+ */
+static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
+{
+	if (!memcg->memory.parent)
+		return NULL;
+	return mem_cgroup_from_counter(memcg->memory.parent, memory);
+}
+
 static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg,
 			      struct mem_cgroup *root)
 {
@@ -689,10 +709,14 @@ extern struct static_key memcg_sockets_enabled_key;
 static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 {
 #ifdef CONFIG_MEMCG_KMEM
-	return memcg->tcp_mem.memory_pressure;
-#else
-	return false;
+	if (memcg->tcp_mem.memory_pressure)
+		return true;
 #endif
+	do {
+		if (time_before(jiffies, memcg->socket_pressure))
+			return true;
+	} while ((memcg = parent_mem_cgroup(memcg)));
+	return false;
 }
 #else
 #define mem_cgroup_sockets_enabled 0
diff --git a/include/linux/vmpressure.h b/include/linux/vmpressure.h
index 3e4535876d37..3347cc3ec0ab 100644
--- a/include/linux/vmpressure.h
+++ b/include/linux/vmpressure.h
@@ -12,6 +12,9 @@
 struct vmpressure {
 	unsigned long scanned;
 	unsigned long reclaimed;
+
+	unsigned long tree_scanned;
+	unsigned long tree_reclaimed;
 	/* The lock is used to keep the scanned/reclaimed above in sync. */
 	struct spinlock sr_lock;
 
@@ -26,7 +29,7 @@ struct vmpressure {
 struct mem_cgroup;
 
 #ifdef CONFIG_MEMCG
-extern void vmpressure(gfp_t gfp, struct mem_cgroup *memcg,
+extern void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree,
 		       unsigned long scanned, unsigned long reclaimed);
 extern void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio);
 
@@ -40,7 +43,7 @@ extern int vmpressure_register_event(struct mem_cgroup *memcg,
 extern void vmpressure_unregister_event(struct mem_cgroup *memcg,
 					struct eventfd_ctx *eventfd);
 #else
-static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg,
+static inline void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree,
 			      unsigned long scanned, unsigned long reclaimed) {}
 static inline void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg,
 				   int prio) {}