Memory controller remove control_type feature

Based on the discussion at http://lkml.org/lkml/2007/12/20/383, it was felt
that control_type might not be a good thing to implement right away.  We
can add this flexibility at a later point when required.

Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d87090eb14c073dd74c0891273f8a8de97cab034..9815951ec995d43f02ad87ce78f1c0fbf5ecdb2b 100644 (file)
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -38,6 +38,7 @@ extern struct page_cgroup *page_get_page_cgroup(struct page *page);
 extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
                                gfp_t gfp_mask);
 extern void mem_cgroup_uncharge(struct page_cgroup *pc);
+extern void mem_cgroup_uncharge_page(struct page *page);
 extern void mem_cgroup_move_lists(struct page_cgroup *pc, bool active);
 extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
                                        struct list_head *dst,
@@ -55,11 +56,6 @@ static inline struct mem_cgroup *mm_cgroup(const struct mm_struct *mm)
        return rcu_dereference(mm->mem_cgroup);
 }
 
-static inline void mem_cgroup_uncharge_page(struct page *page)
-{
-       mem_cgroup_uncharge(page_get_page_cgroup(page));
-}
-
 extern int mem_cgroup_prepare_migration(struct page *page);
 extern void mem_cgroup_end_migration(struct page *page);
 extern void mem_cgroup_page_migration(struct page *page, struct page *newpage);

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 315dee18012943541300d0a7003512058c5f0b9a..5c2c702af6172e34bced06b2d5693ce2d461b000 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -131,7 +131,6 @@ struct mem_cgroup {
         */
        struct mem_cgroup_lru_info info;
 
-       unsigned long control_type;     /* control RSS or RSS+Pagecache */
        int     prev_priority;  /* for recording reclaim priority */
        /*
         * statistics.
@@ -709,24 +708,17 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
                                gfp_t gfp_mask)
 {
        int ret = 0;
-       struct mem_cgroup *mem;
        if (!mm)
                mm = &init_mm;
 
-       rcu_read_lock();
-       mem = rcu_dereference(mm->mem_cgroup);
-       css_get(&mem->css);
-       rcu_read_unlock();
-       if (mem->control_type == MEM_CGROUP_TYPE_ALL)
-               ret = mem_cgroup_charge_common(page, mm, gfp_mask,
+       ret = mem_cgroup_charge_common(page, mm, gfp_mask,
                                MEM_CGROUP_CHARGE_TYPE_CACHE);
-       css_put(&mem->css);
        return ret;
 }
 
 /*
  * Uncharging is always a welcome operation, we never complain, simply
- * uncharge.
+ * uncharge. This routine should be called with lock_page_cgroup held
  */
 void mem_cgroup_uncharge(struct page_cgroup *pc)
 {
@@ -736,8 +728,7 @@ void mem_cgroup_uncharge(struct page_cgroup *pc)
        unsigned long flags;
 
        /*
-        * This can handle cases when a page is not charged at all and we
-        * are switching between handling the control_type.
+        * Check if our page_cgroup is valid
         */
        if (!pc)
                return;
@@ -749,6 +740,7 @@ void mem_cgroup_uncharge(struct page_cgroup *pc)
                 * get page->cgroup and clear it under lock.
                 * force_empty can drop page->cgroup without checking refcnt.
                 */
+               unlock_page_cgroup(page);
                if (clear_page_cgroup(page, pc) == pc) {
                        mem = pc->mem_cgroup;
                        css_put(&mem->css);
@@ -758,9 +750,17 @@ void mem_cgroup_uncharge(struct page_cgroup *pc)
                        spin_unlock_irqrestore(&mz->lru_lock, flags);
                        kfree(pc);
                }
+               lock_page_cgroup(page);
        }
 }
 
+void mem_cgroup_uncharge_page(struct page *page)
+{
+       lock_page_cgroup(page);
+       mem_cgroup_uncharge(page_get_page_cgroup(page));
+       unlock_page_cgroup(page);
+}
+
 /*
  * Returns non-zero if a page (under migration) has valid page_cgroup member.
  * Refcnt of page_cgroup is incremented.
@@ -780,8 +780,12 @@ int mem_cgroup_prepare_migration(struct page *page)
 
 void mem_cgroup_end_migration(struct page *page)
 {
-       struct page_cgroup *pc = page_get_page_cgroup(page);
+       struct page_cgroup *pc;
+
+       lock_page_cgroup(page);
+       pc = page_get_page_cgroup(page);
        mem_cgroup_uncharge(pc);
+       unlock_page_cgroup(page);
 }
 /*
  * We know both *page* and *newpage* are now not-on-LRU and Pg_locked.
@@ -936,61 +940,6 @@ static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
                                mem_cgroup_write_strategy);
 }
 
-static ssize_t mem_control_type_write(struct cgroup *cont,
-                       struct cftype *cft, struct file *file,
-                       const char __user *userbuf,
-                       size_t nbytes, loff_t *pos)
-{
-       int ret;
-       char *buf, *end;
-       unsigned long tmp;
-       struct mem_cgroup *mem;
-
-       mem = mem_cgroup_from_cont(cont);
-       buf = kmalloc(nbytes + 1, GFP_KERNEL);
-       ret = -ENOMEM;
-       if (buf == NULL)
-               goto out;
-
-       buf[nbytes] = 0;
-       ret = -EFAULT;
-       if (copy_from_user(buf, userbuf, nbytes))
-               goto out_free;
-
-       ret = -EINVAL;
-       tmp = simple_strtoul(buf, &end, 10);
-       if (*end != '\0')
-               goto out_free;
-
-       if (tmp <= MEM_CGROUP_TYPE_UNSPEC || tmp >= MEM_CGROUP_TYPE_MAX)
-               goto out_free;
-
-       mem->control_type = tmp;
-       ret = nbytes;
-out_free:
-       kfree(buf);
-out:
-       return ret;
-}
-
-static ssize_t mem_control_type_read(struct cgroup *cont,
-                               struct cftype *cft,
-                               struct file *file, char __user *userbuf,
-                               size_t nbytes, loff_t *ppos)
-{
-       unsigned long val;
-       char buf[64], *s;
-       struct mem_cgroup *mem;
-
-       mem = mem_cgroup_from_cont(cont);
-       s = buf;
-       val = mem->control_type;
-       s += sprintf(s, "%lu\n", val);
-       return simple_read_from_buffer((void __user *)userbuf, nbytes,
-                       ppos, buf, s - buf);
-}
-
-
 static ssize_t mem_force_empty_write(struct cgroup *cont,
                                struct cftype *cft, struct file *file,
                                const char __user *userbuf,
@@ -1088,11 +1037,6 @@ static struct cftype mem_cgroup_files[] = {
                .private = RES_FAILCNT,
                .read = mem_cgroup_read,
        },
-       {
-               .name = "control_type",
-               .write = mem_control_type_write,
-               .read = mem_control_type_read,
-       },
        {
                .name = "force_empty",
                .write = mem_force_empty_write,
@@ -1161,7 +1105,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 
        res_counter_init(&mem->res);
 
-       mem->control_type = MEM_CGROUP_TYPE_ALL;
        memset(&mem->info, 0, sizeof(mem->info));
 
        for_each_node_state(node, N_POSSIBLE)