Memory controller: make page_referenced() cgroup aware

Make page_referenced() cgroup aware.  Without this patch, page_referenced()
can cause a page to be skipped while reclaiming pages.  This patch ensures
that other cgroups do not hold pages in a particular cgroup hostage.  It
is required to ensure that shared pages are freed from a cgroup when they
are not actively referenced from the cgroup that brought them in

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: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 31 insertions, 8 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 10833d969e3f..ff7cac602984 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -110,6 +110,11 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
                                 struct mem_cgroup, css);
 }
 
+inline struct mem_cgroup *mm_cgroup(struct mm_struct *mm)
+{
+        return rcu_dereference(mm->mem_cgroup);
+}
+
 void mm_init_cgroup(struct mm_struct *mm, struct task_struct *p)
 {
         struct mem_cgroup *mem;
diff --git a/mm/rmap.c b/mm/rmap.c
index 4a3487921eff..a0e92a263d12 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -302,7 +302,8 @@ out:
         return referenced;
 }
 
-static int page_referenced_anon(struct page *page)
+static int page_referenced_anon(struct page *page,
+                                struct mem_cgroup *mem_cont)
 {
         unsigned int mapcount;
         struct anon_vma *anon_vma;
@@ -315,6 +316,13 @@ static int page_referenced_anon(struct page *page)
 
         mapcount = page_mapcount(page);
         list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
+                /*
+                 * If we are reclaiming on behalf of a cgroup, skip
+                 * counting on behalf of references from different
+                 * cgroups
+                 */
+                if (mem_cont && (mm_cgroup(vma->vm_mm) != mem_cont))
+                        continue;
                 referenced += page_referenced_one(page, vma, &mapcount);
                 if (!mapcount)
                         break;
@@ -335,7 +343,8 @@ static int page_referenced_anon(struct page *page)
  *
  * This function is only called from page_referenced for object-based pages.
  */
-static int page_referenced_file(struct page *page)
+static int page_referenced_file(struct page *page,
+                                struct mem_cgroup *mem_cont)
 {
         unsigned int mapcount;
         struct address_space *mapping = page->mapping;
@@ -368,6 +377,13 @@ static int page_referenced_file(struct page *page)
         mapcount = page_mapcount(page);
 
         vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+                /*
+                 * If we are reclaiming on behalf of a cgroup, skip
+                 * counting on behalf of references from different
+                 * cgroups
+                 */
+                if (mem_cont && (mm_cgroup(vma->vm_mm) != mem_cont))
+                        continue;
                 if ((vma->vm_flags & (VM_LOCKED|VM_MAYSHARE))
                                   == (VM_LOCKED|VM_MAYSHARE)) {
                         referenced++;
@@ -390,7 +406,8 @@ static int page_referenced_file(struct page *page)
  * Quick test_and_clear_referenced for all mappings to a page,
  * returns the number of ptes which referenced the page.
  */
-int page_referenced(struct page *page, int is_locked)
+int page_referenced(struct page *page, int is_locked,
+                        struct mem_cgroup *mem_cont)
 {
         int referenced = 0;
 
@@ -402,14 +419,15 @@ int page_referenced(struct page *page, int is_locked)
 
         if (page_mapped(page) && page->mapping) {
                 if (PageAnon(page))
-                        referenced += page_referenced_anon(page);
+                        referenced += page_referenced_anon(page, mem_cont);
                 else if (is_locked)
-                        referenced += page_referenced_file(page);
+                        referenced += page_referenced_file(page, mem_cont);
                 else if (TestSetPageLocked(page))
                         referenced++;
                 else {
                         if (page->mapping)
-                                referenced += page_referenced_file(page);
+                                referenced +=
+                                        page_referenced_file(page, mem_cont);
                         unlock_page(page);
                 }
         }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7408a8a7d882..215f6a726b2f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -503,7 +503,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
                                 goto keep_locked;
                 }
 
-                referenced = page_referenced(page, 1);
+                referenced = page_referenced(page, 1, sc->mem_cgroup);
                 /* In active use or really unfreeable?  Activate it. */
                 if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
                                         referenced && page_mapping_inuse(page))
@@ -1057,7 +1057,7 @@ force_reclaim_mapped:
                 if (page_mapped(page)) {
                         if (!reclaim_mapped ||
                             (total_swap_pages == 0 && PageAnon(page)) ||
-                            page_referenced(page, 0)) {
+                            page_referenced(page, 0, sc->mem_cgroup)) {
                                 list_add(&page->lru, &l_active);
                                 continue;
                         }