mm: memcontrol: do not uncharge old page in page cache replacement

[deliverable/linux.git] / mm / memcontrol.c

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index bcb38718e174f1af77f362f584e049762ba552f7..bf35bff282fc09412b34929f9829bfe86b88b361 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -366,13 +366,6 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
  *
  * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup
  * is returned.
- *
- * XXX: The above description of behavior on the default hierarchy isn't
- * strictly true yet as replace_page_cache_page() can modify the
- * association before @page is released even on the default hierarchy;
- * however, the current and planned usages don't mix the the two functions
- * and replace_page_cache_page() will soon be updated to make the invariant
- * actually true.
  */
 struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
 {
@@ -5464,7 +5457,8 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
 void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage)
 {
        struct mem_cgroup *memcg;
-       int isolated;
+       unsigned int nr_pages;
+       bool compound;
 
        VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
        VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
@@ -5484,11 +5478,21 @@ void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage)
        if (!memcg)
                return;
 
-       lock_page_lru(oldpage, &isolated);
-       oldpage->mem_cgroup = NULL;
-       unlock_page_lru(oldpage, isolated);
+       /* Force-charge the new page. The old one will be freed soon */
+       compound = PageTransHuge(newpage);
+       nr_pages = compound ? hpage_nr_pages(newpage) : 1;
+
+       page_counter_charge(&memcg->memory, nr_pages);
+       if (do_memsw_account())
+               page_counter_charge(&memcg->memsw, nr_pages);
+       css_get_many(&memcg->css, nr_pages);
 
        commit_charge(newpage, memcg, true);
+
+       local_irq_disable();
+       mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages);
+       memcg_check_events(memcg, newpage);
+       local_irq_enable();
 }
 
 DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key);
@@ -5761,6 +5765,28 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
        return nr_swap_pages;
 }
 
+bool mem_cgroup_swap_full(struct page *page)
+{
+       struct mem_cgroup *memcg;
+
+       VM_BUG_ON_PAGE(!PageLocked(page), page);
+
+       if (vm_swap_full())
+               return true;
+       if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys))
+               return false;
+
+       memcg = page->mem_cgroup;
+       if (!memcg)
+               return false;
+
+       for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg))
+               if (page_counter_read(&memcg->swap) * 2 >= memcg->swap.limit)
+                       return true;
+
+       return false;
+}
+
 /* for remember boot option*/
 #ifdef CONFIG_MEMCG_SWAP_ENABLED
 static int really_do_swap_account __initdata = 1;