memcg: remove direct page_cgroup-to-page pointer

In struct page_cgroup, we have a full word for flags but only a few are
reserved.  Use the remaining upper bits to encode, depending on
configuration, the node or the section, to enable page_cgroup-to-page
lookups without a direct pointer.

This saves a full word for every page in a system with memory cgroups
enabled.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 55 insertions, 36 deletions

diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 59a3cd4c799d..6c3f7a6a481a 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -11,12 +11,11 @@
 #include <linux/swapops.h>
 #include <linux/kmemleak.h>
 
-static void __meminit
-__init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
+static void __meminit init_page_cgroup(struct page_cgroup *pc, unsigned long id)
 {
         pc->flags = 0;
+        set_page_cgroup_array_id(pc, id);
         pc->mem_cgroup = NULL;
-        pc->page = pfn_to_page(pfn);
         INIT_LIST_HEAD(&pc->lru);
 }
 static unsigned long total_usage;
@@ -43,6 +42,19 @@ struct page_cgroup *lookup_page_cgroup(struct page *page)
         return base + offset;
 }
 
+struct page *lookup_cgroup_page(struct page_cgroup *pc)
+{
+        unsigned long pfn;
+        struct page *page;
+        pg_data_t *pgdat;
+
+        pgdat = NODE_DATA(page_cgroup_array_id(pc));
+        pfn = pc - pgdat->node_page_cgroup + pgdat->node_start_pfn;
+        page = pfn_to_page(pfn);
+        VM_BUG_ON(pc != lookup_page_cgroup(page));
+        return page;
+}
+
 static int __init alloc_node_page_cgroup(int nid)
 {
         struct page_cgroup *base, *pc;
@@ -63,7 +75,7 @@ static int __init alloc_node_page_cgroup(int nid)
                 return -ENOMEM;
         for (index = 0; index < nr_pages; index++) {
                 pc = base + index;
-                __init_page_cgroup(pc, start_pfn + index);
+                init_page_cgroup(pc, nid);
         }
         NODE_DATA(nid)->node_page_cgroup = base;
         total_usage += table_size;
@@ -105,46 +117,53 @@ struct page_cgroup *lookup_page_cgroup(struct page *page)
         return section->page_cgroup + pfn;
 }
 
+struct page *lookup_cgroup_page(struct page_cgroup *pc)
+{
+        struct mem_section *section;
+        struct page *page;
+        unsigned long nr;
+
+        nr = page_cgroup_array_id(pc);
+        section = __nr_to_section(nr);
+        page = pfn_to_page(pc - section->page_cgroup);
+        VM_BUG_ON(pc != lookup_page_cgroup(page));
+        return page;
+}
+
 /* __alloc_bootmem...() is protected by !slab_available() */
 static int __init_refok init_section_page_cgroup(unsigned long pfn)
 {
-        struct mem_section *section = __pfn_to_section(pfn);
         struct page_cgroup *base, *pc;
+        struct mem_section *section;
         unsigned long table_size;
+        unsigned long nr;
         int nid, index;
 
-        if (!section->page_cgroup) {
-                nid = page_to_nid(pfn_to_page(pfn));
-                table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-                VM_BUG_ON(!slab_is_available());
-                if (node_state(nid, N_HIGH_MEMORY)) {
-                        base = kmalloc_node(table_size,
-                                GFP_KERNEL | __GFP_NOWARN, nid);
-                        if (!base)
-                                base = vmalloc_node(table_size, nid);
-                } else {
-                        base = kmalloc(table_size, GFP_KERNEL | __GFP_NOWARN);
-                        if (!base)
-                                base = vmalloc(table_size);
-                }
-                /*
-                 * The value stored in section->page_cgroup is (base - pfn)
-                 * and it does not point to the memory block allocated above,
-                 * causing kmemleak false positives.
-                 */
-                kmemleak_not_leak(base);
+        nr = pfn_to_section_nr(pfn);
+        section = __nr_to_section(nr);
+
+        if (section->page_cgroup)
+                return 0;
+
+        nid = page_to_nid(pfn_to_page(pfn));
+        table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
+        VM_BUG_ON(!slab_is_available());
+        if (node_state(nid, N_HIGH_MEMORY)) {
+                base = kmalloc_node(table_size,
+                                    GFP_KERNEL | __GFP_NOWARN, nid);
+                if (!base)
+                        base = vmalloc_node(table_size, nid);
         } else {
-                /*
-                 * We don't have to allocate page_cgroup again, but
-                 * address of memmap may be changed. So, we have to initialize
-                 * again.
-                 */
-                base = section->page_cgroup + pfn;
-                table_size = 0;
-                /* check address of memmap is changed or not. */
-                if (base->page == pfn_to_page(pfn))
-                        return 0;
+                base = kmalloc(table_size, GFP_KERNEL | __GFP_NOWARN);
+                if (!base)
+                        base = vmalloc(table_size);
         }
+        /*
+         * The value stored in section->page_cgroup is (base - pfn)
+         * and it does not point to the memory block allocated above,
+         * causing kmemleak false positives.
+         */
+        kmemleak_not_leak(base);
 
         if (!base) {
                 printk(KERN_ERR "page cgroup allocation failure\n");
@@ -153,7 +172,7 @@ static int __init_refok init_section_page_cgroup(unsigned long pfn)
 
         for (index = 0; index < PAGES_PER_SECTION; index++) {
                 pc = base + index;
-                __init_page_cgroup(pc, pfn + index);
+                init_page_cgroup(pc, nr);
         }
 
         section->page_cgroup = base - pfn;