page_cgroup.c 10.4 KB
Newer Older
1 2 3 4 5 6
#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>
7
#include <linux/slab.h>
8
#include <linux/memory.h>
9
#include <linux/vmalloc.h>
10
#include <linux/cgroup.h>
11
#include <linux/swapops.h>
12 13 14 15 16 17 18

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);
19
	INIT_LIST_HEAD(&pc->lru);
20 21 22 23 24 25
}
static unsigned long total_usage;

#if !defined(CONFIG_SPARSEMEM)


A
Al Viro 已提交
26
void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53
{
	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;

54 55 56
	if (!nr_pages)
		return 0;

57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76
	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;

77
	if (mem_cgroup_disabled())
78 79
		return;

80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104
	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;
}

A
Al Viro 已提交
105
/* __alloc_bootmem...() is protected by !slab_available() */
106
static int __init_refok init_section_page_cgroup(unsigned long pfn)
107
{
108
	struct mem_section *section = __pfn_to_section(pfn);
109 110 111 112
	struct page_cgroup *base, *pc;
	unsigned long table_size;
	int nid, index;

113 114 115 116
	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()) {
117 118
			base = kmalloc_node(table_size,
					GFP_KERNEL | __GFP_NOWARN, nid);
119 120 121 122 123
			if (!base)
				base = vmalloc_node(table_size, nid);
		} else {
			base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
				table_size,
124
				PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
125 126 127 128 129 130 131 132 133 134 135 136
		}
	} 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;
137
	}
138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162

	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;
163
	if (is_vmalloc_addr(base)) {
164
		vfree(base);
165 166 167 168 169 170 171 172
		ms->page_cgroup = NULL;
	} else {
		struct page *page = virt_to_page(base);
		if (!PageReserved(page)) { /* Is bootmem ? */
			kfree(base);
			ms->page_cgroup = NULL;
		}
	}
173 174
}

A
Al Viro 已提交
175
int __meminit online_page_cgroup(unsigned long start_pfn,
176 177 178 179 180 181
			unsigned long nr_pages,
			int nid)
{
	unsigned long start, end, pfn;
	int fail = 0;

182
	start = start_pfn & ~(PAGES_PER_SECTION - 1);
183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199
	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;
}

A
Al Viro 已提交
200
int __meminit offline_page_cgroup(unsigned long start_pfn,
201 202 203 204
		unsigned long nr_pages, int nid)
{
	unsigned long start, end, pfn;

205
	start = start_pfn & ~(PAGES_PER_SECTION - 1);
206 207 208 209 210 211 212 213
	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);

	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
		__free_page_cgroup(pfn);
	return 0;

}

A
Al Viro 已提交
214
static int __meminit page_cgroup_callback(struct notifier_block *self,
215 216 217 218 219 220 221 222 223 224 225 226 227
			       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;
228
	case MEM_CANCEL_ONLINE:
229 230 231 232 233 234
	case MEM_GOING_OFFLINE:
		break;
	case MEM_ONLINE:
	case MEM_CANCEL_OFFLINE:
		break;
	}
235 236 237 238 239 240

	if (ret)
		ret = notifier_from_errno(ret);
	else
		ret = NOTIFY_OK;

241 242 243 244 245 246 247 248 249 250
	return ret;
}

#endif

void __init page_cgroup_init(void)
{
	unsigned long pfn;
	int fail = 0;

251
	if (mem_cgroup_disabled())
252 253
		return;

254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269
	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");
}

A
Al Viro 已提交
270
void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
271 272 273 274 275
{
	return;
}

#endif
276 277 278 279 280 281 282 283 284 285 286 287 288


#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 {
289
	unsigned short		id;
290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340
};
#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;

	if (!do_swap_account)
		return 0;
	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
 *
341 342
 * Returns old value at success, 0 at failure.
 * (Of course, old value can be 0.)
343
 */
344
unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
345 346 347 348 349 350 351 352
{
	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;
353
	unsigned short old;
354 355

	if (!do_swap_account)
356
		return 0;
357 358 359 360 361 362

	ctrl = &swap_cgroup_ctrl[type];

	mappage = ctrl->map[idx];
	sc = page_address(mappage);
	sc += pos;
363 364
	old = sc->id;
	sc->id = id;
365 366 367 368 369 370 371 372

	return old;
}

/**
 * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
 * @ent: swap entry to be looked up.
 *
373
 * Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
374
 */
375
unsigned short lookup_swap_cgroup(swp_entry_t ent)
376 377 378 379 380 381 382 383
{
	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;
384
	unsigned short ret;
385 386

	if (!do_swap_account)
387
		return 0;
388 389 390 391 392

	ctrl = &swap_cgroup_ctrl[type];
	mappage = ctrl->map[idx];
	sc = page_address(mappage);
	sc += pos;
393
	ret = sc->id;
394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430
	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);

	printk(KERN_INFO
		"swap_cgroup: uses %ld bytes of vmalloc for pointer array space"
431
		" and %ld bytes to hold mem_cgroup information per swap ents\n",
432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467
		array_size, length * PAGE_SIZE);
	printk(KERN_INFO
	"swap_cgroup can be disabled by noswapaccount boot option.\n");

	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
新手
引导
客服 返回
顶部