2008-10-19 10:28:16 +07:00
|
|
|
#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>
|
2008-10-23 04:15:05 +07:00
|
|
|
#include <linux/slab.h>
|
2008-10-19 10:28:16 +07:00
|
|
|
#include <linux/memory.h>
|
2008-10-23 04:14:58 +07:00
|
|
|
#include <linux/vmalloc.h>
|
2008-10-23 04:15:05 +07:00
|
|
|
#include <linux/cgroup.h>
|
2009-01-08 09:07:58 +07:00
|
|
|
#include <linux/swapops.h>
|
2008-10-19 10:28:16 +07:00
|
|
|
|
|
|
|
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);
|
memcg: synchronized LRU
A big patch for changing memcg's LRU semantics.
Now,
- page_cgroup is linked to mem_cgroup's its own LRU (per zone).
- LRU of page_cgroup is not synchronous with global LRU.
- page and page_cgroup is one-to-one and statically allocated.
- To find page_cgroup is on what LRU, you have to check pc->mem_cgroup as
- lru = page_cgroup_zoneinfo(pc, nid_of_pc, zid_of_pc);
- SwapCache is handled.
And, when we handle LRU list of page_cgroup, we do following.
pc = lookup_page_cgroup(page);
lock_page_cgroup(pc); .....................(1)
mz = page_cgroup_zoneinfo(pc);
spin_lock(&mz->lru_lock);
.....add to LRU
spin_unlock(&mz->lru_lock);
unlock_page_cgroup(pc);
But (1) is spin_lock and we have to be afraid of dead-lock with zone->lru_lock.
So, trylock() is used at (1), now. Without (1), we can't trust "mz" is correct.
This is a trial to remove this dirty nesting of locks.
This patch changes mz->lru_lock to be zone->lru_lock.
Then, above sequence will be written as
spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU
mem_cgroup_add/remove/etc_lru() {
pc = lookup_page_cgroup(page);
mz = page_cgroup_zoneinfo(pc);
if (PageCgroupUsed(pc)) {
....add to LRU
}
spin_lock(&zone->lru_lock); # in vmscan.c or swap.c via global LRU
This is much simpler.
(*) We're safe even if we don't take lock_page_cgroup(pc). Because..
1. When pc->mem_cgroup can be modified.
- at charge.
- at account_move().
2. at charge
the PCG_USED bit is not set before pc->mem_cgroup is fixed.
3. at account_move()
the page is isolated and not on LRU.
Pros.
- easy for maintenance.
- memcg can make use of laziness of pagevec.
- we don't have to duplicated LRU/Active/Unevictable bit in page_cgroup.
- LRU status of memcg will be synchronized with global LRU's one.
- # of locks are reduced.
- account_move() is simplified very much.
Cons.
- may increase cost of LRU rotation.
(no impact if memcg is not configured.)
Signed-off-by: KAMEZAWA Hiroyuki <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>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-08 09:08:01 +07:00
|
|
|
INIT_LIST_HEAD(&pc->lru);
|
2008-10-19 10:28:16 +07:00
|
|
|
}
|
|
|
|
static unsigned long total_usage;
|
|
|
|
|
|
|
|
#if !defined(CONFIG_SPARSEMEM)
|
|
|
|
|
|
|
|
|
2008-11-23 00:33:24 +07:00
|
|
|
void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
|
2008-10-19 10:28:16 +07:00
|
|
|
{
|
|
|
|
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;
|
|
|
|
|
2008-12-10 04:14:20 +07:00
|
|
|
if (!nr_pages)
|
|
|
|
return 0;
|
|
|
|
|
2008-10-19 10:28:16 +07:00
|
|
|
table_size = sizeof(struct page_cgroup) * nr_pages;
|
2009-06-12 14:33:53 +07:00
|
|
|
|
|
|
|
base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
|
|
|
|
table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
|
|
|
|
if (!base)
|
2008-10-19 10:28:16 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2009-06-12 14:33:53 +07:00
|
|
|
void __init page_cgroup_init_flatmem(void)
|
2008-10-19 10:28:16 +07:00
|
|
|
{
|
|
|
|
|
|
|
|
int nid, fail;
|
|
|
|
|
2009-01-08 09:08:02 +07:00
|
|
|
if (mem_cgroup_disabled())
|
2008-10-23 04:15:05 +07:00
|
|
|
return;
|
|
|
|
|
2008-10-19 10:28:16 +07:00
|
|
|
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);
|
2009-06-18 06:26:32 +07:00
|
|
|
printk(KERN_INFO "please try 'cgroup_disable=memory' option if you"
|
|
|
|
" don't want memory cgroups\n");
|
2008-10-19 10:28:16 +07:00
|
|
|
return;
|
|
|
|
fail:
|
2009-06-18 06:26:32 +07:00
|
|
|
printk(KERN_CRIT "allocation of page_cgroup failed.\n");
|
|
|
|
printk(KERN_CRIT "please try 'cgroup_disable=memory' boot option\n");
|
2008-10-19 10:28:16 +07:00
|
|
|
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);
|
|
|
|
|
2009-06-18 06:26:34 +07:00
|
|
|
if (!section->page_cgroup)
|
|
|
|
return NULL;
|
2008-10-19 10:28:16 +07:00
|
|
|
return section->page_cgroup + pfn;
|
|
|
|
}
|
|
|
|
|
2008-11-23 00:33:24 +07:00
|
|
|
/* __alloc_bootmem...() is protected by !slab_available() */
|
2009-01-07 05:39:43 +07:00
|
|
|
static int __init_refok init_section_page_cgroup(unsigned long pfn)
|
2008-10-19 10:28:16 +07:00
|
|
|
{
|
2009-01-08 09:07:51 +07:00
|
|
|
struct mem_section *section = __pfn_to_section(pfn);
|
2008-10-19 10:28:16 +07:00
|
|
|
struct page_cgroup *base, *pc;
|
|
|
|
unsigned long table_size;
|
|
|
|
int nid, index;
|
|
|
|
|
2008-12-02 04:13:48 +07:00
|
|
|
if (!section->page_cgroup) {
|
|
|
|
nid = page_to_nid(pfn_to_page(pfn));
|
|
|
|
table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
|
2009-06-12 14:33:53 +07:00
|
|
|
VM_BUG_ON(!slab_is_available());
|
|
|
|
base = kmalloc_node(table_size,
|
|
|
|
GFP_KERNEL | __GFP_NOWARN, nid);
|
|
|
|
if (!base)
|
|
|
|
base = vmalloc_node(table_size, nid);
|
2008-12-02 04:13:48 +07:00
|
|
|
} 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;
|
2008-10-23 04:15:05 +07:00
|
|
|
}
|
2008-10-19 10:28:16 +07:00
|
|
|
|
|
|
|
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->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;
|
2008-10-23 04:15:05 +07:00
|
|
|
if (is_vmalloc_addr(base)) {
|
2008-10-19 10:28:16 +07:00
|
|
|
vfree(base);
|
2008-10-23 04:15:05 +07:00
|
|
|
ms->page_cgroup = NULL;
|
|
|
|
} else {
|
|
|
|
struct page *page = virt_to_page(base);
|
|
|
|
if (!PageReserved(page)) { /* Is bootmem ? */
|
|
|
|
kfree(base);
|
|
|
|
ms->page_cgroup = NULL;
|
|
|
|
}
|
|
|
|
}
|
2008-10-19 10:28:16 +07:00
|
|
|
}
|
|
|
|
|
2008-11-23 00:33:24 +07:00
|
|
|
int __meminit online_page_cgroup(unsigned long start_pfn,
|
2008-10-19 10:28:16 +07:00
|
|
|
unsigned long nr_pages,
|
|
|
|
int nid)
|
|
|
|
{
|
|
|
|
unsigned long start, end, pfn;
|
|
|
|
int fail = 0;
|
|
|
|
|
2008-11-13 04:27:01 +07:00
|
|
|
start = start_pfn & ~(PAGES_PER_SECTION - 1);
|
2008-10-19 10:28:16 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2008-11-23 00:33:24 +07:00
|
|
|
int __meminit offline_page_cgroup(unsigned long start_pfn,
|
2008-10-19 10:28:16 +07:00
|
|
|
unsigned long nr_pages, int nid)
|
|
|
|
{
|
|
|
|
unsigned long start, end, pfn;
|
|
|
|
|
2008-11-13 04:27:01 +07:00
|
|
|
start = start_pfn & ~(PAGES_PER_SECTION - 1);
|
2008-10-19 10:28:16 +07:00
|
|
|
end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
|
|
|
|
|
|
|
|
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
|
|
|
|
__free_page_cgroup(pfn);
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
}
|
|
|
|
|
2008-11-23 00:33:24 +07:00
|
|
|
static int __meminit page_cgroup_callback(struct notifier_block *self,
|
2008-10-19 10:28:16 +07:00
|
|
|
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;
|
2008-12-02 04:13:48 +07:00
|
|
|
case MEM_CANCEL_ONLINE:
|
2008-10-19 10:28:16 +07:00
|
|
|
case MEM_GOING_OFFLINE:
|
|
|
|
break;
|
|
|
|
case MEM_ONLINE:
|
|
|
|
case MEM_CANCEL_OFFLINE:
|
|
|
|
break;
|
|
|
|
}
|
2008-12-02 04:13:48 +07:00
|
|
|
|
|
|
|
if (ret)
|
|
|
|
ret = notifier_from_errno(ret);
|
|
|
|
else
|
|
|
|
ret = NOTIFY_OK;
|
|
|
|
|
2008-10-19 10:28:16 +07:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
void __init page_cgroup_init(void)
|
|
|
|
{
|
|
|
|
unsigned long pfn;
|
|
|
|
int fail = 0;
|
|
|
|
|
2009-01-08 09:08:02 +07:00
|
|
|
if (mem_cgroup_disabled())
|
2008-10-23 04:15:05 +07:00
|
|
|
return;
|
|
|
|
|
2008-10-19 10:28:16 +07:00
|
|
|
for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
|
|
|
|
if (!pfn_present(pfn))
|
|
|
|
continue;
|
|
|
|
fail = init_section_page_cgroup(pfn);
|
|
|
|
}
|
|
|
|
if (fail) {
|
2009-06-18 06:26:32 +07:00
|
|
|
printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
|
2008-10-19 10:28:16 +07:00
|
|
|
panic("Out of memory");
|
|
|
|
} else {
|
|
|
|
hotplug_memory_notifier(page_cgroup_callback, 0);
|
|
|
|
}
|
|
|
|
printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
|
2009-06-18 06:26:32 +07:00
|
|
|
printk(KERN_INFO "please try 'cgroup_disable=memory' option if you don't"
|
|
|
|
" want memory cgroups\n");
|
2008-10-19 10:28:16 +07:00
|
|
|
}
|
|
|
|
|
2008-11-23 00:33:24 +07:00
|
|
|
void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
|
2008-10-19 10:28:16 +07:00
|
|
|
{
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|
2009-01-08 09:07:58 +07:00
|
|
|
|
|
|
|
|
|
|
|
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
|
|
|
|
|
|
|
|
static DEFINE_MUTEX(swap_cgroup_mutex);
|
|
|
|
struct swap_cgroup_ctrl {
|
|
|
|
struct page **map;
|
|
|
|
unsigned long length;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
|
|
|
|
|
|
|
|
struct swap_cgroup {
|
2009-04-03 06:57:45 +07:00
|
|
|
unsigned short id;
|
2009-01-08 09:07:58 +07:00
|
|
|
};
|
|
|
|
#define SC_PER_PAGE (PAGE_SIZE/sizeof(struct swap_cgroup))
|
|
|
|
#define SC_POS_MASK (SC_PER_PAGE - 1)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* SwapCgroup implements "lookup" and "exchange" operations.
|
|
|
|
* In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
|
|
|
|
* against SwapCache. At swap_free(), this is accessed directly from swap.
|
|
|
|
*
|
|
|
|
* This means,
|
|
|
|
* - we have no race in "exchange" when we're accessed via SwapCache because
|
|
|
|
* SwapCache(and its swp_entry) is under lock.
|
|
|
|
* - When called via swap_free(), there is no user of this entry and no race.
|
|
|
|
* Then, we don't need lock around "exchange".
|
|
|
|
*
|
|
|
|
* TODO: we can push these buffers out to HIGHMEM.
|
|
|
|
*/
|
|
|
|
|
|
|
|
/*
|
|
|
|
* allocate buffer for swap_cgroup.
|
|
|
|
*/
|
|
|
|
static int swap_cgroup_prepare(int type)
|
|
|
|
{
|
|
|
|
struct page *page;
|
|
|
|
struct swap_cgroup_ctrl *ctrl;
|
|
|
|
unsigned long idx, max;
|
|
|
|
|
|
|
|
ctrl = &swap_cgroup_ctrl[type];
|
|
|
|
|
|
|
|
for (idx = 0; idx < ctrl->length; idx++) {
|
|
|
|
page = alloc_page(GFP_KERNEL | __GFP_ZERO);
|
|
|
|
if (!page)
|
|
|
|
goto not_enough_page;
|
|
|
|
ctrl->map[idx] = page;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
not_enough_page:
|
|
|
|
max = idx;
|
|
|
|
for (idx = 0; idx < max; idx++)
|
|
|
|
__free_page(ctrl->map[idx]);
|
|
|
|
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* swap_cgroup_record - record mem_cgroup for this swp_entry.
|
|
|
|
* @ent: swap entry to be recorded into
|
|
|
|
* @mem: mem_cgroup to be recorded
|
|
|
|
*
|
2009-04-03 06:57:45 +07:00
|
|
|
* Returns old value at success, 0 at failure.
|
|
|
|
* (Of course, old value can be 0.)
|
2009-01-08 09:07:58 +07:00
|
|
|
*/
|
2009-04-03 06:57:45 +07:00
|
|
|
unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
|
2009-01-08 09:07:58 +07:00
|
|
|
{
|
|
|
|
int type = swp_type(ent);
|
|
|
|
unsigned long offset = swp_offset(ent);
|
|
|
|
unsigned long idx = offset / SC_PER_PAGE;
|
|
|
|
unsigned long pos = offset & SC_POS_MASK;
|
|
|
|
struct swap_cgroup_ctrl *ctrl;
|
|
|
|
struct page *mappage;
|
|
|
|
struct swap_cgroup *sc;
|
2009-04-03 06:57:45 +07:00
|
|
|
unsigned short old;
|
2009-01-08 09:07:58 +07:00
|
|
|
|
|
|
|
ctrl = &swap_cgroup_ctrl[type];
|
|
|
|
|
|
|
|
mappage = ctrl->map[idx];
|
|
|
|
sc = page_address(mappage);
|
|
|
|
sc += pos;
|
2009-04-03 06:57:45 +07:00
|
|
|
old = sc->id;
|
|
|
|
sc->id = id;
|
2009-01-08 09:07:58 +07:00
|
|
|
|
|
|
|
return old;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
|
|
|
|
* @ent: swap entry to be looked up.
|
|
|
|
*
|
2009-04-03 06:57:45 +07:00
|
|
|
* Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
|
2009-01-08 09:07:58 +07:00
|
|
|
*/
|
2009-04-03 06:57:45 +07:00
|
|
|
unsigned short lookup_swap_cgroup(swp_entry_t ent)
|
2009-01-08 09:07:58 +07:00
|
|
|
{
|
|
|
|
int type = swp_type(ent);
|
|
|
|
unsigned long offset = swp_offset(ent);
|
|
|
|
unsigned long idx = offset / SC_PER_PAGE;
|
|
|
|
unsigned long pos = offset & SC_POS_MASK;
|
|
|
|
struct swap_cgroup_ctrl *ctrl;
|
|
|
|
struct page *mappage;
|
|
|
|
struct swap_cgroup *sc;
|
2009-04-03 06:57:45 +07:00
|
|
|
unsigned short ret;
|
2009-01-08 09:07:58 +07:00
|
|
|
|
|
|
|
ctrl = &swap_cgroup_ctrl[type];
|
|
|
|
mappage = ctrl->map[idx];
|
|
|
|
sc = page_address(mappage);
|
|
|
|
sc += pos;
|
2009-04-03 06:57:45 +07:00
|
|
|
ret = sc->id;
|
2009-01-08 09:07:58 +07:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
int swap_cgroup_swapon(int type, unsigned long max_pages)
|
|
|
|
{
|
|
|
|
void *array;
|
|
|
|
unsigned long array_size;
|
|
|
|
unsigned long length;
|
|
|
|
struct swap_cgroup_ctrl *ctrl;
|
|
|
|
|
|
|
|
if (!do_swap_account)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
length = ((max_pages/SC_PER_PAGE) + 1);
|
|
|
|
array_size = length * sizeof(void *);
|
|
|
|
|
|
|
|
array = vmalloc(array_size);
|
|
|
|
if (!array)
|
|
|
|
goto nomem;
|
|
|
|
|
|
|
|
memset(array, 0, array_size);
|
|
|
|
ctrl = &swap_cgroup_ctrl[type];
|
|
|
|
mutex_lock(&swap_cgroup_mutex);
|
|
|
|
ctrl->length = length;
|
|
|
|
ctrl->map = array;
|
|
|
|
if (swap_cgroup_prepare(type)) {
|
|
|
|
/* memory shortage */
|
|
|
|
ctrl->map = NULL;
|
|
|
|
ctrl->length = 0;
|
|
|
|
vfree(array);
|
|
|
|
mutex_unlock(&swap_cgroup_mutex);
|
|
|
|
goto nomem;
|
|
|
|
}
|
|
|
|
mutex_unlock(&swap_cgroup_mutex);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
nomem:
|
|
|
|
printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
|
|
|
|
printk(KERN_INFO
|
|
|
|
"swap_cgroup can be disabled by noswapaccount boot option\n");
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
|
|
|
void swap_cgroup_swapoff(int type)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
struct swap_cgroup_ctrl *ctrl;
|
|
|
|
|
|
|
|
if (!do_swap_account)
|
|
|
|
return;
|
|
|
|
|
|
|
|
mutex_lock(&swap_cgroup_mutex);
|
|
|
|
ctrl = &swap_cgroup_ctrl[type];
|
|
|
|
if (ctrl->map) {
|
|
|
|
for (i = 0; i < ctrl->length; i++) {
|
|
|
|
struct page *page = ctrl->map[i];
|
|
|
|
if (page)
|
|
|
|
__free_page(page);
|
|
|
|
}
|
|
|
|
vfree(ctrl->map);
|
|
|
|
ctrl->map = NULL;
|
|
|
|
ctrl->length = 0;
|
|
|
|
}
|
|
|
|
mutex_unlock(&swap_cgroup_mutex);
|
|
|
|
}
|
|
|
|
|
|
|
|
#endif
|