linux/mm/page_cgroup.c

276 lines
6.1 KiB
C
Raw Normal View History

#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/slab.h>
#include <linux/memory.h>
#include <linux/vmalloc.h>
#include <linux/cgroup.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 __meminit 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;
if (!nr_pages)
return 0;
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;
if (mem_cgroup_subsys.disabled)
return;
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;
}
/* __alloc_bootmem...() is protected by !slab_available() */
int __init_refok 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);
memcg: memory hotplug fix for notifier callback Fixes for memcg/memory hotplug. While memory hotplug allocate/free memmap, page_cgroup doesn't free page_cgroup at OFFLINE when page_cgroup is allocated via bootomem. (Because freeing bootmem requires special care.) Then, if page_cgroup is allocated by bootmem and memmap is freed/allocated by memory hotplug, page_cgroup->page == page is no longer true. But current MEM_ONLINE handler doesn't check it and update page_cgroup->page if it's not necessary to allocate page_cgroup. (This was not found because memmap is not freed if SPARSEMEM_VMEMMAP is y.) And I noticed that MEM_ONLINE can be called against "part of section". So, freeing page_cgroup at CANCEL_ONLINE will cause trouble. (freeing used page_cgroup) Don't rollback at CANCEL. One more, current memory hotplug notifier is stopped by slub because it sets NOTIFY_STOP_MASK to return vaule. So, page_cgroup's callback never be called. (low priority than slub now.) I think this slub's behavior is not intentional(BUG). and fixes it. Another way to be considered about page_cgroup allocation: - free page_cgroup at OFFLINE even if it's from bootmem and remove specieal handler. But it requires more changes. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=12041 Signed-off-by: KAMEZAWA Hiruyoki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 21:13:48 +00:00
if (!section->page_cgroup) {
nid = page_to_nid(pfn_to_page(pfn));
table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
if (slab_is_available()) {
base = kmalloc_node(table_size, GFP_KERNEL, nid);
if (!base)
base = vmalloc_node(table_size, nid);
} else {
base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
table_size,
PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
memcg: memory hotplug fix for notifier callback Fixes for memcg/memory hotplug. While memory hotplug allocate/free memmap, page_cgroup doesn't free page_cgroup at OFFLINE when page_cgroup is allocated via bootomem. (Because freeing bootmem requires special care.) Then, if page_cgroup is allocated by bootmem and memmap is freed/allocated by memory hotplug, page_cgroup->page == page is no longer true. But current MEM_ONLINE handler doesn't check it and update page_cgroup->page if it's not necessary to allocate page_cgroup. (This was not found because memmap is not freed if SPARSEMEM_VMEMMAP is y.) And I noticed that MEM_ONLINE can be called against "part of section". So, freeing page_cgroup at CANCEL_ONLINE will cause trouble. (freeing used page_cgroup) Don't rollback at CANCEL. One more, current memory hotplug notifier is stopped by slub because it sets NOTIFY_STOP_MASK to return vaule. So, page_cgroup's callback never be called. (low priority than slub now.) I think this slub's behavior is not intentional(BUG). and fixes it. Another way to be considered about page_cgroup allocation: - free page_cgroup at OFFLINE even if it's from bootmem and remove specieal handler. But it requires more changes. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=12041 Signed-off-by: KAMEZAWA Hiruyoki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 21:13:48 +00:00
}
} 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;
}
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;
if (is_vmalloc_addr(base)) {
vfree(base);
ms->page_cgroup = NULL;
} else {
struct page *page = virt_to_page(base);
if (!PageReserved(page)) { /* Is bootmem ? */
kfree(base);
ms->page_cgroup = NULL;
}
}
}
int __meminit 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 __meminit 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 __meminit 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_OFFLINE:
offline_page_cgroup(mn->start_pfn,
mn->nr_pages, mn->status_change_nid);
break;
memcg: memory hotplug fix for notifier callback Fixes for memcg/memory hotplug. While memory hotplug allocate/free memmap, page_cgroup doesn't free page_cgroup at OFFLINE when page_cgroup is allocated via bootomem. (Because freeing bootmem requires special care.) Then, if page_cgroup is allocated by bootmem and memmap is freed/allocated by memory hotplug, page_cgroup->page == page is no longer true. But current MEM_ONLINE handler doesn't check it and update page_cgroup->page if it's not necessary to allocate page_cgroup. (This was not found because memmap is not freed if SPARSEMEM_VMEMMAP is y.) And I noticed that MEM_ONLINE can be called against "part of section". So, freeing page_cgroup at CANCEL_ONLINE will cause trouble. (freeing used page_cgroup) Don't rollback at CANCEL. One more, current memory hotplug notifier is stopped by slub because it sets NOTIFY_STOP_MASK to return vaule. So, page_cgroup's callback never be called. (low priority than slub now.) I think this slub's behavior is not intentional(BUG). and fixes it. Another way to be considered about page_cgroup allocation: - free page_cgroup at OFFLINE even if it's from bootmem and remove specieal handler. But it requires more changes. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=12041 Signed-off-by: KAMEZAWA Hiruyoki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 21:13:48 +00:00
case MEM_CANCEL_ONLINE:
case MEM_GOING_OFFLINE:
break;
case MEM_ONLINE:
case MEM_CANCEL_OFFLINE:
break;
}
memcg: memory hotplug fix for notifier callback Fixes for memcg/memory hotplug. While memory hotplug allocate/free memmap, page_cgroup doesn't free page_cgroup at OFFLINE when page_cgroup is allocated via bootomem. (Because freeing bootmem requires special care.) Then, if page_cgroup is allocated by bootmem and memmap is freed/allocated by memory hotplug, page_cgroup->page == page is no longer true. But current MEM_ONLINE handler doesn't check it and update page_cgroup->page if it's not necessary to allocate page_cgroup. (This was not found because memmap is not freed if SPARSEMEM_VMEMMAP is y.) And I noticed that MEM_ONLINE can be called against "part of section". So, freeing page_cgroup at CANCEL_ONLINE will cause trouble. (freeing used page_cgroup) Don't rollback at CANCEL. One more, current memory hotplug notifier is stopped by slub because it sets NOTIFY_STOP_MASK to return vaule. So, page_cgroup's callback never be called. (low priority than slub now.) I think this slub's behavior is not intentional(BUG). and fixes it. Another way to be considered about page_cgroup allocation: - free page_cgroup at OFFLINE even if it's from bootmem and remove specieal handler. But it requires more changes. Addresses http://bugzilla.kernel.org/show_bug.cgi?id=12041 Signed-off-by: KAMEZAWA Hiruyoki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Tested-by: Badari Pulavarty <pbadari@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-12-01 21:13:48 +00:00
if (ret)
ret = notifier_from_errno(ret);
else
ret = NOTIFY_OK;
return ret;
}
#endif
void __init page_cgroup_init(void)
{
unsigned long pfn;
int fail = 0;
if (mem_cgroup_subsys.disabled)
return;
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 __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
{
return;
}
#endif