summaryrefslogtreecommitdiffstats
path: root/mm/page_cgroup.c
diff options
context:
space:
mode:
authorKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>2008-10-18 20:28:16 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2008-10-20 08:52:39 -0700
commit52d4b9ac0b985168009c2a57098324e67bae171f (patch)
treeb3e3b854166930af893be90ea30a7ab0d65c59e7 /mm/page_cgroup.c
parentc05555b572921c464d064d9267f7f7bc06d424fa (diff)
downloadlinux-stable-52d4b9ac0b985168009c2a57098324e67bae171f.tar.gz
linux-stable-52d4b9ac0b985168009c2a57098324e67bae171f.tar.bz2
linux-stable-52d4b9ac0b985168009c2a57098324e67bae171f.zip
memcg: allocate all page_cgroup at boot
Allocate all page_cgroup at boot and remove page_cgroup poitner from struct page. This patch adds an interface as struct page_cgroup *lookup_page_cgroup(struct page*) All FLATMEM/DISCONTIGMEM/SPARSEMEM and MEMORY_HOTPLUG is supported. Remove page_cgroup pointer reduces the amount of memory by - 4 bytes per PAGE_SIZE. - 8 bytes per PAGE_SIZE if memory controller is disabled. (even if configured.) On usual 8GB x86-32 server, this saves 8MB of NORMAL_ZONE memory. On my x86-64 server with 48GB of memory, this saves 96MB of memory. I think this reduction makes sense. By pre-allocation, kmalloc/kfree in charge/uncharge are removed. This means - we're not necessary to be afraid of kmalloc faiulre. (this can happen because of gfp_mask type.) - we can avoid calling kmalloc/kfree. - we can avoid allocating tons of small objects which can be fragmented. - we can know what amount of memory will be used for this extra-lru handling. I added printk message as "allocated %ld bytes of page_cgroup" "please try cgroup_disable=memory option if you don't want" maybe enough informative for users. Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Reviewed-by: Balbir Singh <balbir@linux.vnet.ibm.com> Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/page_cgroup.c')
-rw-r--r--mm/page_cgroup.c237
1 files changed, 237 insertions, 0 deletions
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
new file mode 100644
index 000000000000..5d86550701f2
--- /dev/null
+++ b/mm/page_cgroup.c
@@ -0,0 +1,237 @@
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/bootmem.h>
+#include <linux/bit_spinlock.h>
+#include <linux/page_cgroup.h>
+#include <linux/hash.h>
+#include <linux/memory.h>
+
+static void __meminit
+__init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
+{
+ pc->flags = 0;
+ pc->mem_cgroup = NULL;
+ pc->page = pfn_to_page(pfn);
+}
+static unsigned long total_usage;
+
+#if !defined(CONFIG_SPARSEMEM)
+
+
+void __init pgdat_page_cgroup_init(struct pglist_data *pgdat)
+{
+ pgdat->node_page_cgroup = NULL;
+}
+
+struct page_cgroup *lookup_page_cgroup(struct page *page)
+{
+ unsigned long pfn = page_to_pfn(page);
+ unsigned long offset;
+ struct page_cgroup *base;
+
+ base = NODE_DATA(page_to_nid(page))->node_page_cgroup;
+ if (unlikely(!base))
+ return NULL;
+
+ offset = pfn - NODE_DATA(page_to_nid(page))->node_start_pfn;
+ return base + offset;
+}
+
+static int __init alloc_node_page_cgroup(int nid)
+{
+ struct page_cgroup *base, *pc;
+ unsigned long table_size;
+ unsigned long start_pfn, nr_pages, index;
+
+ start_pfn = NODE_DATA(nid)->node_start_pfn;
+ nr_pages = NODE_DATA(nid)->node_spanned_pages;
+
+ table_size = sizeof(struct page_cgroup) * nr_pages;
+
+ base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
+ table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+ if (!base)
+ return -ENOMEM;
+ for (index = 0; index < nr_pages; index++) {
+ pc = base + index;
+ __init_page_cgroup(pc, start_pfn + index);
+ }
+ NODE_DATA(nid)->node_page_cgroup = base;
+ total_usage += table_size;
+ return 0;
+}
+
+void __init page_cgroup_init(void)
+{
+
+ int nid, fail;
+
+ for_each_online_node(nid) {
+ fail = alloc_node_page_cgroup(nid);
+ if (fail)
+ goto fail;
+ }
+ printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
+ printk(KERN_INFO "please try cgroup_disable=memory option if you"
+ " don't want\n");
+ return;
+fail:
+ printk(KERN_CRIT "allocation of page_cgroup was failed.\n");
+ printk(KERN_CRIT "please try cgroup_disable=memory boot option\n");
+ panic("Out of memory");
+}
+
+#else /* CONFIG_FLAT_NODE_MEM_MAP */
+
+struct page_cgroup *lookup_page_cgroup(struct page *page)
+{
+ unsigned long pfn = page_to_pfn(page);
+ struct mem_section *section = __pfn_to_section(pfn);
+
+ return section->page_cgroup + pfn;
+}
+
+int __meminit init_section_page_cgroup(unsigned long pfn)
+{
+ struct mem_section *section;
+ struct page_cgroup *base, *pc;
+ unsigned long table_size;
+ int nid, index;
+
+ section = __pfn_to_section(pfn);
+
+ if (section->page_cgroup)
+ return 0;
+
+ nid = page_to_nid(pfn_to_page(pfn));
+
+ table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
+ base = kmalloc_node(table_size, GFP_KERNEL, nid);
+ if (!base)
+ base = vmalloc_node(table_size, nid);
+
+ if (!base) {
+ printk(KERN_ERR "page cgroup allocation failure\n");
+ return -ENOMEM;
+ }
+
+ for (index = 0; index < PAGES_PER_SECTION; index++) {
+ pc = base + index;
+ __init_page_cgroup(pc, pfn + index);
+ }
+
+ section = __pfn_to_section(pfn);
+ section->page_cgroup = base - pfn;
+ total_usage += table_size;
+ return 0;
+}
+#ifdef CONFIG_MEMORY_HOTPLUG
+void __free_page_cgroup(unsigned long pfn)
+{
+ struct mem_section *ms;
+ struct page_cgroup *base;
+
+ ms = __pfn_to_section(pfn);
+ if (!ms || !ms->page_cgroup)
+ return;
+ base = ms->page_cgroup + pfn;
+ ms->page_cgroup = NULL;
+ if (is_vmalloc_addr(base))
+ vfree(base);
+ else
+ kfree(base);
+}
+
+int online_page_cgroup(unsigned long start_pfn,
+ unsigned long nr_pages,
+ int nid)
+{
+ unsigned long start, end, pfn;
+ int fail = 0;
+
+ start = start_pfn & (PAGES_PER_SECTION - 1);
+ end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
+
+ for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
+ if (!pfn_present(pfn))
+ continue;
+ fail = init_section_page_cgroup(pfn);
+ }
+ if (!fail)
+ return 0;
+
+ /* rollback */
+ for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
+ __free_page_cgroup(pfn);
+
+ return -ENOMEM;
+}
+
+int offline_page_cgroup(unsigned long start_pfn,
+ unsigned long nr_pages, int nid)
+{
+ unsigned long start, end, pfn;
+
+ start = start_pfn & (PAGES_PER_SECTION - 1);
+ end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
+
+ for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
+ __free_page_cgroup(pfn);
+ return 0;
+
+}
+
+static int page_cgroup_callback(struct notifier_block *self,
+ unsigned long action, void *arg)
+{
+ struct memory_notify *mn = arg;
+ int ret = 0;
+ switch (action) {
+ case MEM_GOING_ONLINE:
+ ret = online_page_cgroup(mn->start_pfn,
+ mn->nr_pages, mn->status_change_nid);
+ break;
+ case MEM_CANCEL_ONLINE:
+ case MEM_OFFLINE:
+ offline_page_cgroup(mn->start_pfn,
+ mn->nr_pages, mn->status_change_nid);
+ break;
+ case MEM_GOING_OFFLINE:
+ break;
+ case MEM_ONLINE:
+ case MEM_CANCEL_OFFLINE:
+ break;
+ }
+ ret = notifier_from_errno(ret);
+ return ret;
+}
+
+#endif
+
+void __init page_cgroup_init(void)
+{
+ unsigned long pfn;
+ int fail = 0;
+
+ for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
+ if (!pfn_present(pfn))
+ continue;
+ fail = init_section_page_cgroup(pfn);
+ }
+ if (fail) {
+ printk(KERN_CRIT "try cgroup_disable=memory boot option\n");
+ panic("Out of memory");
+ } else {
+ hotplug_memory_notifier(page_cgroup_callback, 0);
+ }
+ printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
+ printk(KERN_INFO "please try cgroup_disable=memory option if you don't"
+ " want\n");
+}
+
+void __init pgdat_page_cgroup_init(struct pglist_data *pgdat)
+{
+ return;
+}
+
+#endif