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>

diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 6b63679ce8a1a3895242eabe9f41fd251ab358a1..f5de21de31dda91b54b05c199616ccf2113864b9 100644 (file)
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -1,8 +1,26 @@
 #ifndef __LINUX_PAGE_CGROUP_H
 #define __LINUX_PAGE_CGROUP_H
 
+enum {
+       /* flags for mem_cgroup */
+       PCG_LOCK,  /* Lock for pc->mem_cgroup and following bits. */
+       PCG_CACHE, /* charged as cache */
+       PCG_USED, /* this object is in use. */
+       PCG_MIGRATION, /* under page migration */
+       /* flags for mem_cgroup and file and I/O status */
+       PCG_MOVE_LOCK, /* For race between move_account v.s. following bits */
+       PCG_FILE_MAPPED, /* page is accounted as "mapped" */
+       /* No lock in page_cgroup */
+       PCG_ACCT_LRU, /* page has been accounted for (under lru_lock) */
+       __NR_PCG_FLAGS,
+};
+
+#ifndef __GENERATING_BOUNDS_H
+#include <generated/bounds.h>
+
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 #include <linux/bit_spinlock.h>
+
 /*
  * Page Cgroup can be considered as an extended mem_map.
  * A page_cgroup page is associated with every page descriptor. The
@@ -13,7 +31,6 @@
 struct page_cgroup {
        unsigned long flags;
        struct mem_cgroup *mem_cgroup;
-       struct page *page;
        struct list_head lru;           /* per cgroup LRU list */
 };
 
@@ -32,19 +49,7 @@ static inline void __init page_cgroup_init(void)
 #endif
 
 struct page_cgroup *lookup_page_cgroup(struct page *page);
-
-enum {
-       /* flags for mem_cgroup */
-       PCG_LOCK,  /* Lock for pc->mem_cgroup and following bits. */
-       PCG_CACHE, /* charged as cache */
-       PCG_USED, /* this object is in use. */
-       PCG_MIGRATION, /* under page migration */
-       /* flags for mem_cgroup and file and I/O status */
-       PCG_MOVE_LOCK, /* For race between move_account v.s. following bits */
-       PCG_FILE_MAPPED, /* page is accounted as "mapped" */
-       /* No lock in page_cgroup */
-       PCG_ACCT_LRU, /* page has been accounted for (under lru_lock) */
-};
+struct page *lookup_cgroup_page(struct page_cgroup *pc);
 
 #define TESTPCGFLAG(uname, lname)                      \
 static inline int PageCgroup##uname(struct page_cgroup *pc)    \
@@ -117,6 +122,39 @@ static inline void move_unlock_page_cgroup(struct page_cgroup *pc,
        local_irq_restore(*flags);
 }
 
+#ifdef CONFIG_SPARSEMEM
+#define PCG_ARRAYID_WIDTH      SECTIONS_SHIFT
+#else
+#define PCG_ARRAYID_WIDTH      NODES_SHIFT
+#endif
+
+#if (PCG_ARRAYID_WIDTH > BITS_PER_LONG - NR_PCG_FLAGS)
+#error Not enough space left in pc->flags to store page_cgroup array IDs
+#endif
+
+/* pc->flags: ARRAY-ID | FLAGS */
+
+#define PCG_ARRAYID_MASK       ((1UL << PCG_ARRAYID_WIDTH) - 1)
+
+#define PCG_ARRAYID_OFFSET     (BITS_PER_LONG - PCG_ARRAYID_WIDTH)
+/*
+ * Zero the shift count for non-existant fields, to prevent compiler
+ * warnings and ensure references are optimized away.
+ */
+#define PCG_ARRAYID_SHIFT      (PCG_ARRAYID_OFFSET * (PCG_ARRAYID_WIDTH != 0))
+
+static inline void set_page_cgroup_array_id(struct page_cgroup *pc,
+                                           unsigned long id)
+{
+       pc->flags &= ~(PCG_ARRAYID_MASK << PCG_ARRAYID_SHIFT);
+       pc->flags |= (id & PCG_ARRAYID_MASK) << PCG_ARRAYID_SHIFT;
+}
+
+static inline unsigned long page_cgroup_array_id(struct page_cgroup *pc)
+{
+       return (pc->flags >> PCG_ARRAYID_SHIFT) & PCG_ARRAYID_MASK;
+}
+
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
 struct page_cgroup;
 
@@ -137,7 +175,7 @@ static inline void __init page_cgroup_init_flatmem(void)
 {
 }
 
-#endif
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
 
 #include <linux/swap.h>
 
@@ -173,5 +211,8 @@ static inline void swap_cgroup_swapoff(int type)
        return;
 }
 
-#endif
-#endif
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR_SWAP */
+
+#endif /* !__GENERATING_BOUNDS_H */
+
+#endif /* __LINUX_PAGE_CGROUP_H */

diff --git a/kernel/bounds.c b/kernel/bounds.c
index 98a51f26c13691b9f6f5955cdc83840f8932c2be..0c9b862292b26dc0494f771f96532fd8995c2b3b 100644 (file)
--- a/kernel/bounds.c
+++ b/kernel/bounds.c
@@ -9,11 +9,13 @@
 #include <linux/page-flags.h>
 #include <linux/mmzone.h>
 #include <linux/kbuild.h>
+#include <linux/page_cgroup.h>
 
 void foo(void)
 {
        /* The enum constants to put into include/generated/bounds.h */
        DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS);
        DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES);
+       DEFINE(NR_PCG_FLAGS, __NR_PCG_FLAGS);
        /* End of constants */
 }

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e286e1603e4f388365506818b016cb2e3049da04..660dfc27d971e83a910e6742eff48576afc048d7 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1080,7 +1080,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
                if (unlikely(!PageCgroupUsed(pc)))
                        continue;
 
-               page = pc->page;
+               page = lookup_cgroup_page(pc);
 
                if (unlikely(!PageLRU(page)))
                        continue;
@@ -3344,7 +3344,7 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *mem,
                }
                spin_unlock_irqrestore(&zone->lru_lock, flags);
 
-               page = pc->page;
+               page = lookup_cgroup_page(pc);
 
                ret = mem_cgroup_move_parent(page, pc, mem, GFP_KERNEL);
                if (ret == -ENOMEM)

diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 59a3cd4c799d5dd4856158e09ccf5a9ab616299e..6c3f7a6a481af84586f01da9a0986329f4e767a3 100644 (file)
--- 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;