Memory controller improve user interface

Change the interface to use bytes instead of pages.  Page sizes can vary
across platforms and configurations.  A new strategy routine has been added
to the resource counters infrastructure to format the data as desired.

Suggested by David Rientjes, Andrew Morton and Herbert Poetzl

Tested on a UML setup with the config for memory control enabled.

[kamezawa.hiroyu@jp.fujitsu.com: possible race fix in res_counter]
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Pavel Emelianov <xemul@openvz.org>
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>
Cc: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-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>

1 files changed, 25 insertions, 10 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9e9ff914c0f1..d73692279ab1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -302,7 +302,7 @@ retry:
          * If we created the page_cgroup, we should free it on exceeding
          * the cgroup limit.
          */
-        while (res_counter_charge(&mem->res, 1)) {
+        while (res_counter_charge(&mem->res, PAGE_SIZE)) {
                 if (try_to_free_mem_cgroup_pages(mem))
                         continue;
 
@@ -341,7 +341,7 @@ retry:
                 kfree(pc);
                 pc = race_pc;
                 atomic_inc(&pc->ref_cnt);
-                res_counter_uncharge(&mem->res, 1);
+                res_counter_uncharge(&mem->res, PAGE_SIZE);
                 css_put(&mem->css);
                 goto done;
         }
@@ -384,7 +384,7 @@ void mem_cgroup_uncharge(struct page_cgroup *pc)
                 css_put(&mem->css);
                 page_assign_page_cgroup(page, NULL);
                 unlock_page_cgroup(page);
-                res_counter_uncharge(&mem->res, 1);
+                res_counter_uncharge(&mem->res, PAGE_SIZE);
 
                 spin_lock_irqsave(&mem->lru_lock, flags);
                 list_del_init(&pc->lru);
@@ -393,12 +393,26 @@ void mem_cgroup_uncharge(struct page_cgroup *pc)
         }
 }
 
-static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
-                        struct file *file, char __user *userbuf, size_t nbytes,
-                        loff_t *ppos)
+int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp)
+{
+        *tmp = memparse(buf, &buf);
+        if (*buf != '\0')
+                return -EINVAL;
+
+        /*
+         * Round up the value to the closest page size
+         */
+        *tmp = ((*tmp + PAGE_SIZE - 1) >> PAGE_SHIFT) << PAGE_SHIFT;
+        return 0;
+}
+
+static ssize_t mem_cgroup_read(struct cgroup *cont,
+                        struct cftype *cft, struct file *file,
+                        char __user *userbuf, size_t nbytes, loff_t *ppos)
 {
         return res_counter_read(&mem_cgroup_from_cont(cont)->res,
-                                cft->private, userbuf, nbytes, ppos);
+                                cft->private, userbuf, nbytes, ppos,
+                                NULL);
 }
 
 static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
@@ -406,17 +420,18 @@ static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
                                 size_t nbytes, loff_t *ppos)
 {
         return res_counter_write(&mem_cgroup_from_cont(cont)->res,
-                                cft->private, userbuf, nbytes, ppos);
+                                cft->private, userbuf, nbytes, ppos,
+                                mem_cgroup_write_strategy);
 }
 
 static struct cftype mem_cgroup_files[] = {
         {
-                .name = "usage",
+                .name = "usage_in_bytes",
                 .private = RES_USAGE,
                 .read = mem_cgroup_read,
         },
         {
-                .name = "limit",
+                .name = "limit_in_bytes",
                 .private = RES_LIMIT,
                 .write = mem_cgroup_write,
                 .read = mem_cgroup_read,