Memory controller: accounting setup

Basic setup routines, the mm_struct has a pointer to the cgroup that
it belongs to and the the page has a page_cgroup associated with it.

Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Kirill Korotaev <dev@sw.ru>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 104 insertions, 7 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 3f121b2..7d1f119 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -3,6 +3,9 @@
  * Copyright IBM Corporation, 2007
  * Author Balbir Singh <balbir@linux.vnet.ibm.com>
  *
+ * Copyright 2007 OpenVZ SWsoft Inc
+ * Author: Pavel Emelianov <xemul@openvz.org>
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -17,5 +20,38 @@
 #ifndef _LINUX_MEMCONTROL_H
 #define _LINUX_MEMCONTROL_H
 
+struct mem_cgroup;
+struct page_cgroup;
+
+#ifdef CONFIG_CGROUP_MEM_CONT
+
+extern void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p);
+extern void mm_free_cgroup(struct mm_struct *mm);
+extern void page_assign_page_cgroup(struct page *page,
+					struct page_cgroup *pc);
+extern struct page_cgroup *page_get_page_cgroup(struct page *page);
+
+#else /* CONFIG_CGROUP_MEM_CONT */
+static inline void mm_init_cgroup(struct mm_struct *mm,
+					struct task_struct *p)
+{
+}
+
+static inline void mm_free_cgroup(struct mm_struct *mm)
+{
+}
+
+static inline void page_assign_page_cgroup(struct page *page,
+						struct page_cgroup *pc)
+{
+}
+
+static inline struct page_cgroup *page_get_page_cgroup(struct page *page)
+{
+	return NULL;
+}
+
+#endif /* CONFIG_CGROUP_MEM_CONT */
+
 #endif /* _LINUX_MEMCONTROL_H */
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index f4c03e0..34023c6 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -88,6 +88,9 @@ struct page {
 	void *virtual;			/* Kernel virtual address (NULL if
 					   not kmapped, ie. highmem) */
 #endif /* WANT_PAGE_VIRTUAL */
+#ifdef CONFIG_CGROUP_MEM_CONT
+	unsigned long page_cgroup;
+#endif
 };
 
 /*
@@ -219,6 +222,9 @@ struct mm_struct {
 	/* aio bits */
 	rwlock_t		ioctx_list_lock;
 	struct kioctx		*ioctx_list;
+#ifdef CONFIG_CGROUP_MEM_CONT
+	struct mem_cgroup *mem_cgroup;
+#endif
 };
 
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7c8ca05..8a4812c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -92,6 +92,7 @@ struct sched_param {
 
 #include <asm/processor.h>
 
+struct mem_cgroup;
 struct exec_domain;
 struct futex_pi_state;
 struct robust_list_head;
diff --git a/kernel/fork.c b/kernel/fork.c
index 3995297..b2ef8e4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -40,6 +40,7 @@
 #include <linux/ptrace.h>
 #include <linux/mount.h>
 #include <linux/audit.h>
+#include <linux/memcontrol.h>
 #include <linux/profile.h>
 #include <linux/rmap.h>
 #include <linux/acct.h>
@@ -340,7 +341,7 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock);
 
 #include <linux/init_task.h>
 
-static struct mm_struct * mm_init(struct mm_struct * mm)
+static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
 {
 	atomic_set(&mm->mm_users, 1);
 	atomic_set(&mm->mm_count, 1);
@@ -357,11 +358,14 @@ static struct mm_struct * mm_init(struct mm_struct * mm)
 	mm->ioctx_list = NULL;
 	mm->free_area_cache = TASK_UNMAPPED_BASE;
 	mm->cached_hole_size = ~0UL;
+	mm_init_cgroup(mm, p);
 
 	if (likely(!mm_alloc_pgd(mm))) {
 		mm->def_flags = 0;
 		return mm;
 	}
+
+	mm_free_cgroup(mm);
 	free_mm(mm);
 	return NULL;
 }
@@ -376,7 +380,7 @@ struct mm_struct * mm_alloc(void)
 	mm = allocate_mm();
 	if (mm) {
 		memset(mm, 0, sizeof(*mm));
-		mm = mm_init(mm);
+		mm = mm_init(mm, current);
 	}
 	return mm;
 }
@@ -390,6 +394,7 @@ void fastcall __mmdrop(struct mm_struct *mm)
 {
 	BUG_ON(mm == &init_mm);
 	mm_free_pgd(mm);
+	mm_free_cgroup(mm);
 	destroy_context(mm);
 	free_mm(mm);
 }
@@ -511,7 +516,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk)
 	mm->token_priority = 0;
 	mm->last_interval = 0;
 
-	if (!mm_init(mm))
+	if (!mm_init(mm, tsk))
 		goto fail_nomem;
 
 	if (init_new_context(tsk, mm))
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 80e48cd..4d4805e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3,6 +3,9 @@
  * Copyright IBM Corporation, 2007
  * Author Balbir Singh <balbir@linux.vnet.ibm.com>
  *
+ * Copyright 2007 OpenVZ SWsoft Inc
+ * Author: Pavel Emelianov <xemul@openvz.org>
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -17,6 +20,7 @@
 #include <linux/res_counter.h>
 #include <linux/memcontrol.h>
 #include <linux/cgroup.h>
+#include <linux/mm.h>
 
 struct cgroup_subsys mem_cgroup_subsys;
 
@@ -35,6 +39,13 @@ struct mem_cgroup {
 	 * the counter to account for memory usage
 	 */
 	struct res_counter res;
+	/*
+	 * Per cgroup active and inactive list, similar to the
+	 * per zone LRU lists.
+	 * TODO: Consider making these lists per zone
+	 */
+	struct list_head active_list;
+	struct list_head inactive_list;
 };
 
 /*
@@ -56,6 +67,37 @@ struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
 				css);
 }
 
+static inline
+struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
+{
+	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
+				struct mem_cgroup, css);
+}
+
+void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p)
+{
+	struct mem_cgroup *mem;
+
+	mem = mem_cgroup_from_task(p);
+	css_get(&mem->css);
+	mm->mem_cgroup = mem;
+}
+
+void mm_free_cgroup(struct mm_struct *mm)
+{
+	css_put(&mm->mem_cgroup->css);
+}
+
+void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
+{
+	page->page_cgroup = (unsigned long)pc;
+}
+
+struct page_cgroup *page_get_page_cgroup(struct page *page)
+{
+	return page->page_cgroup;
+}
+
 static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
 			struct file *file, char __user *userbuf, size_t nbytes,
 			loff_t *ppos)
@@ -91,14 +133,21 @@ static struct cftype mem_cgroup_files[] = {
 	},
 };
 
+static struct mem_cgroup init_mem_cgroup;
+
 static struct cgroup_subsys_state *
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
 	struct mem_cgroup *mem;
 
-	mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);
-	if (!mem)
-		return -ENOMEM;
+	if (unlikely((cont->parent) == NULL)) {
+		mem = &init_mem_cgroup;
+		init_mm.mem_cgroup = mem;
+	} else
+		mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);
+
+	if (mem == NULL)
+		return NULL;
 
 	res_counter_init(&mem->res);
 	return &mem->css;
@@ -123,5 +172,5 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.create = mem_cgroup_create,
 	.destroy = mem_cgroup_destroy,
 	.populate = mem_cgroup_populate,
-	.early_init = 0,
+	.early_init = 1,
 };