Memory controller: add switch to control what type of pages to limit

Choose if we want cached pages to be accounted or not.  By default both are
accounted for.  A new set of tunables are added.

echo -n 1 > mem_control_type

switches the accounting to account for only mapped pages

echo -n 3 > mem_control_type

switches the behaviour back

[bunk@kernel.org: mm/memcontrol.c: clenups]
[akpm@linux-foundation.org: fix sparc32 build]
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: 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: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 97 insertions, 5 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index b7a01e927953..8ae171cc2811 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -464,7 +464,7 @@ int add_to_page_cache(struct page *page, struct address_space *mapping,
 
         if (error == 0) {
 
-                error = mem_cgroup_charge(page, current->mm);
+                error = mem_cgroup_cache_charge(page, current->mm);
                 if (error)
                         goto out;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5260658c90aa..10833d969e3f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -29,6 +29,8 @@
 #include <linux/spinlock.h>
 #include <linux/fs.h>
 
+#include <asm/uaccess.h>
+
 struct cgroup_subsys mem_cgroup_subsys;
 static const int MEM_CGROUP_RECLAIM_RETRIES = 5;
 
@@ -60,6 +62,7 @@ struct mem_cgroup {
          * spin_lock to protect the per cgroup LRU
          */
         spinlock_t lru_lock;
+        unsigned long control_type;     /* control RSS or RSS+Pagecache */
 };
 
 /*
@@ -82,6 +85,15 @@ struct page_cgroup {
                                         /* mapped and cached states     */
 };
 
+enum {
+        MEM_CGROUP_TYPE_UNSPEC = 0,
+        MEM_CGROUP_TYPE_MAPPED,
+        MEM_CGROUP_TYPE_CACHED,
+        MEM_CGROUP_TYPE_ALL,
+        MEM_CGROUP_TYPE_MAX,
+};
+
+static struct mem_cgroup init_mem_cgroup;
 
 static inline
 struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
@@ -139,18 +151,18 @@ struct page_cgroup *page_get_page_cgroup(struct page *page)
                 (page->page_cgroup & ~PAGE_CGROUP_LOCK);
 }
 
-void __always_inline lock_page_cgroup(struct page *page)
+static void __always_inline lock_page_cgroup(struct page *page)
 {
         bit_spin_lock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
         VM_BUG_ON(!page_cgroup_locked(page));
 }
 
-void __always_inline unlock_page_cgroup(struct page *page)
+static void __always_inline unlock_page_cgroup(struct page *page)
 {
         bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
 }
 
-void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
+static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
 {
         if (active)
                 list_move(&pc->lru, &pc->mem_cgroup->active_list);
@@ -366,6 +378,22 @@ err:
 }
 
 /*
+ * See if the cached pages should be charged at all?
+ */
+int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm)
+{
+        struct mem_cgroup *mem;
+        if (!mm)
+                mm = &init_mm;
+
+        mem = rcu_dereference(mm->mem_cgroup);
+        if (mem->control_type == MEM_CGROUP_TYPE_ALL)
+                return mem_cgroup_charge(page, mm);
+        else
+                return 0;
+}
+
+/*
  * Uncharging is always a welcome operation, we never complain, simply
  * uncharge.
  */
@@ -375,6 +403,10 @@ void mem_cgroup_uncharge(struct page_cgroup *pc)
         struct page *page;
         unsigned long flags;
 
+        /*
+         * This can handle cases when a page is not charged at all and we
+         * are switching between handling the control_type.
+         */
         if (!pc)
                 return;
 
@@ -425,6 +457,60 @@ 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 struct cftype mem_cgroup_files[] = {
         {
                 .name = "usage_in_bytes",
@@ -442,6 +528,11 @@ 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,
+        },
 };
 
 static struct mem_cgroup init_mem_cgroup;
@@ -464,6 +555,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
         INIT_LIST_HEAD(&mem->active_list);
         INIT_LIST_HEAD(&mem->inactive_list);
         spin_lock_init(&mem->lru_lock);
+        mem->control_type = MEM_CGROUP_TYPE_ALL;
         return &mem->css;
 }
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index f96e3ff1e791..88258869c8e7 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -78,7 +78,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
         error = radix_tree_preload(gfp_mask);
         if (!error) {
 
-                error = mem_cgroup_charge(page, current->mm);
+                error = mem_cgroup_cache_charge(page, current->mm);
                 if (error)
                         goto out;