Merge branch 'akpm/master'

6 files changed, 104 insertions, 4 deletions

diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index e0c95c9f1e29..9f1c16224c55 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -84,6 +84,8 @@ struct fsnotify_event_private_data;
 struct fsnotify_fname;
 struct fsnotify_iter_info;
 
+struct mem_cgroup;
+
 /*
  * Each group much define these ops.  The fsnotify infrastructure will call
  * these operations for each relevant group.
@@ -129,6 +131,8 @@ struct fsnotify_event {
  * everything will be cleaned up.
  */
 struct fsnotify_group {
+	const struct fsnotify_ops *ops;	/* how this group handles things */
+
 	/*
 	 * How the refcnt is used is up to each group.  When the refcnt hits 0
 	 * fsnotify will clean up all of the resources associated with this group.
@@ -139,8 +143,6 @@ struct fsnotify_group {
 	 */
 	refcount_t refcnt;		/* things with interest in this group */
 
-	const struct fsnotify_ops *ops;	/* how this group handles things */
-
 	/* needed to send notification to userspace */
 	spinlock_t notification_lock;		/* protect the notification_list */
 	struct list_head notification_list;	/* list of event_holder this group needs to send to userspace */
@@ -162,6 +164,8 @@ struct fsnotify_group {
 	atomic_t num_marks;		/* 1 for each mark and 1 for not being
 					 * past the point of no return when freeing
 					 * a group */
+	atomic_t user_waits;		/* Number of tasks waiting for user
+					 * response */
 	struct list_head marks_list;	/* all inode marks for this group */
 
 	struct fasync_struct *fsn_fa;    /* async notification */
@@ -169,8 +173,8 @@ struct fsnotify_group {
 	struct fsnotify_event *overflow_event;	/* Event we queue when the
 						 * notification list is too
 						 * full */
-	atomic_t user_waits;		/* Number of tasks waiting for user
-					 * response */
+
+	struct mem_cgroup *memcg;	/* memcg to charge allocations */
 
 	/* groups can define private fields here or use the void *private */
 	union {
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index da0ebaec25f0..f12d95fe038b 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -277,6 +277,9 @@ extern int
 walk_system_ram_res(u64 start, u64 end, void *arg,
 		    int (*func)(struct resource *, void *));
 extern int
+walk_system_ram_res_rev(u64 start, u64 end, void *arg,
+			int (*func)(struct resource *, void *));
+extern int
 walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
 		    void *arg, int (*func)(struct resource *, void *));
 
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 2da009958798..af9eed2e3e04 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -356,6 +356,8 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){
 	return css ? container_of(css, struct mem_cgroup, css) : NULL;
 }
 
+struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 	css_put(&memcg->css);
@@ -813,6 +815,11 @@ static inline bool task_in_mem_cgroup(struct task_struct *task,
 	return true;
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
+{
+	return NULL;
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9ae6943b7310..a5022ff33b6f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1097,6 +1097,9 @@ struct task_struct {
 
 	/* Number of pages to reclaim on returning to userland: */
 	unsigned int			memcg_nr_pages_over_high;
+
+	/* Used by memcontrol for targeted memcg charge: */
+	struct mem_cgroup		*target_memcg;
 #endif
 
 #ifdef CONFIG_UPROBES
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 4e1411bbbcfc..1548c3d61fdc 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -206,6 +206,30 @@ static inline void memalloc_noreclaim_restore(unsigned int flags)
 	current->flags = (current->flags & ~PF_MEMALLOC) | flags;
 }
 
+#ifdef CONFIG_MEMCG
+static inline struct mem_cgroup *memalloc_memcg_save(struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *old_memcg = current->target_memcg;
+
+	current->target_memcg = memcg;
+	return old_memcg;
+}
+
+static inline void memalloc_memcg_restore(struct mem_cgroup *memcg)
+{
+	current->target_memcg = memcg;
+}
+#else
+static inline struct mem_cgroup *memalloc_memcg_save(struct mem_cgroup *memcg)
+{
+	return NULL;
+}
+
+static inline void memalloc_memcg_restore(struct mem_cgroup *memcg)
+{
+}
+#endif /* CONFIG_MEMCG */
+
 #ifdef CONFIG_MEMBARRIER
 enum {
 	MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY		= (1U << 0),
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 81ebd71f8c03..9ebe659bd4a5 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -15,6 +15,7 @@
 #include <linux/gfp.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
+#include <linux/sched/mm.h>
 
 
 /*
@@ -374,6 +375,21 @@ static __always_inline void kfree_bulk(size_t size, void **p)
 	kmem_cache_free_bulk(NULL, size, p);
 }
 
+/*
+ * Calling kmem_cache_alloc_memcg implicitly assumes that the caller
+ * wants a __GFP_ACCOUNT allocation.
+ */
+static __always_inline void *kmem_cache_alloc_memcg(struct kmem_cache *cachep,
+						    gfp_t flags,
+						    struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg);
+	void *ptr = kmem_cache_alloc(cachep, flags | __GFP_ACCOUNT);
+
+	memalloc_memcg_restore(old_memcg);
+	return ptr;
+}
+
 #ifdef CONFIG_NUMA
 void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc;
 void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc;
@@ -389,6 +405,21 @@ static __always_inline void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t f
 }
 #endif
 
+/*
+ * Calling kmem_cache_alloc_node_memcg implicitly assumes that the caller
+ * wants a __GFP_ACCOUNT allocation.
+ */
+static __always_inline void *
+kmem_cache_alloc_node_memcg(struct kmem_cache *cachep, gfp_t flags, int node,
+			    struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg);
+	void *ptr = kmem_cache_alloc_node(cachep, flags | __GFP_ACCOUNT, node);
+
+	memalloc_memcg_restore(old_memcg);
+	return ptr;
+}
+
 #ifdef CONFIG_TRACING
 extern void *kmem_cache_alloc_trace(struct kmem_cache *, gfp_t, size_t) __assume_slab_alignment __malloc;
 
@@ -518,6 +549,20 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags)
 }
 
 /*
+ * Calling kmalloc_memcg implicitly assumes that the caller wants a
+ * __GFP_ACCOUNT allocation.
+ */
+static __always_inline void *kmalloc_memcg(size_t size, gfp_t flags,
+					   struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg);
+	void *ptr = kmalloc(size, flags | __GFP_ACCOUNT);
+
+	memalloc_memcg_restore(old_memcg);
+	return ptr;
+}
+
+/*
  * Determine size used for the nth kmalloc cache.
  * return size or 0 if a kmalloc cache for that
  * size does not exist
@@ -554,6 +599,20 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 	return __kmalloc_node(size, flags, node);
 }
 
+/*
+ * Calling kmalloc_node_memcg implicitly assumes that the caller wants a
+ * __GFP_ACCOUNT allocation.
+ */
+static __always_inline void *
+kmalloc_node_memcg(size_t size, gfp_t flags, int node, struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *old_memcg = memalloc_memcg_save(memcg);
+	void *ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node);
+
+	memalloc_memcg_restore(old_memcg);
+	return ptr;
+}
+
 struct memcg_cache_array {
 	struct rcu_head rcu;
 	struct kmem_cache *entries[0];