page_cgroup.c 10.9 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
	table_size = sizeof(struct page_cgroup) * nr_pages;
58 59 60 61

	base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
	if (!base)
62 63 64 65 66 67 68 69 70 71
		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;
}

72
void __init page_cgroup_init_flatmem(void)
73 74 75 76
{

	int nid, fail;

77
	if (mem_cgroup_disabled())
78 79
		return;

80 81 82 83 84 85
	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);
86 87
	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you"
	" don't want memory cgroups\n");
88 89
	return;
fail:
90 91
	printk(KERN_CRIT "allocation of page_cgroup failed.\n");
	printk(KERN_CRIT "please try 'cgroup_disable=memory' boot option\n");
92 93 94 95 96 97 98 99 100 101
	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);

102 103
	if (!section->page_cgroup)
		return NULL;
104 105 106
	return section->page_cgroup + pfn;
}

A
Al Viro 已提交
107
/* __alloc_bootmem...() is protected by !slab_available() */
108
static int __init_refok init_section_page_cgroup(unsigned long pfn)
109
{
110
	struct mem_section *section = __pfn_to_section(pfn);
111 112 113 114
	struct page_cgroup *base, *pc;
	unsigned long table_size;
	int nid, index;

115 116 117
	if (!section->page_cgroup) {
		nid = page_to_nid(pfn_to_page(pfn));
		table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
118
		VM_BUG_ON(!slab_is_available());
119 120
		if (node_state(nid, N_HIGH_MEMORY)) {
			base = kmalloc_node(table_size,
121
				GFP_KERNEL | __GFP_NOWARN, nid);
122 123 124 125 126 127 128
			if (!base)
				base = vmalloc_node(table_size, nid);
		} else {
			base = kmalloc(table_size, GFP_KERNEL | __GFP_NOWARN);
			if (!base)
				base = vmalloc(table_size);
		}
129 130 131 132 133 134 135 136 137 138 139
	} 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;
140
	}
141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165

	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;
166
	if (is_vmalloc_addr(base)) {
167
		vfree(base);
168 169 170 171 172 173 174 175
		ms->page_cgroup = NULL;
	} else {
		struct page *page = virt_to_page(base);
		if (!PageReserved(page)) { /* Is bootmem ? */
			kfree(base);
			ms->page_cgroup = NULL;
		}
	}
176 177
}

A
Al Viro 已提交
178
int __meminit online_page_cgroup(unsigned long start_pfn,
179 180 181 182 183 184
			unsigned long nr_pages,
			int nid)
{
	unsigned long start, end, pfn;
	int fail = 0;

185
	start = start_pfn & ~(PAGES_PER_SECTION - 1);
186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202
	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
203
int __meminit offline_page_cgroup(unsigned long start_pfn,
204 205 206 207
		unsigned long nr_pages, int nid)
{
	unsigned long start, end, pfn;

208
	start = start_pfn & ~(PAGES_PER_SECTION - 1);
209 210 211 212 213 214 215 216
	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
217
static int __meminit page_cgroup_callback(struct notifier_block *self,
218 219 220 221 222 223 224 225 226 227 228 229 230
			       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;
231
	case MEM_CANCEL_ONLINE:
232 233 234 235 236 237
	case MEM_GOING_OFFLINE:
		break;
	case MEM_ONLINE:
	case MEM_CANCEL_OFFLINE:
		break;
	}
238 239 240 241 242 243

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

244 245 246 247 248 249 250 251 252 253
	return ret;
}

#endif

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

254
	if (mem_cgroup_disabled())
255 256
		return;

257 258 259 260 261 262
	for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
		if (!pfn_present(pfn))
			continue;
		fail = init_section_page_cgroup(pfn);
	}
	if (fail) {
263
		printk(KERN_CRIT "try 'cgroup_disable=memory' boot option\n");
264 265 266 267 268
		panic("Out of memory");
	} else {
		hotplug_memory_notifier(page_cgroup_callback, 0);
	}
	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
269 270
	printk(KERN_INFO "please try 'cgroup_disable=memory' option if you don't"
	" want memory cgroups\n");
271 272
}

A
Al Viro 已提交
273
void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
274 275 276 277 278
{
	return;
}

#endif
279 280 281 282 283 284 285 286 287 288 289 290 291


#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 {
292
	unsigned short		id;
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
};
#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;
}

337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367
/**
 * swap_cgroup_cmpxchg - cmpxchg mem_cgroup's id for this swp_entry.
 * @end: swap entry to be cmpxchged
 * @old: old id
 * @new: new id
 *
 * Returns old id at success, 0 at failure.
 * (There is no mem_cgroup useing 0 as its id)
 */
unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
					unsigned short old, unsigned short new)
{
	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;

	ctrl = &swap_cgroup_ctrl[type];

	mappage = ctrl->map[idx];
	sc = page_address(mappage);
	sc += pos;
	if (cmpxchg(&sc->id, old, new) == old)
		return old;
	else
		return 0;
}

368 369 370 371 372
/**
 * swap_cgroup_record - record mem_cgroup for this swp_entry.
 * @ent: swap entry to be recorded into
 * @mem: mem_cgroup to be recorded
 *
373 374
 * Returns old value at success, 0 at failure.
 * (Of course, old value can be 0.)
375
 */
376
unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
377 378 379 380 381 382 383 384
{
	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;
385
	unsigned short old;
386 387 388 389 390 391

	ctrl = &swap_cgroup_ctrl[type];

	mappage = ctrl->map[idx];
	sc = page_address(mappage);
	sc += pos;
392
	old = xchg(&sc->id, id);
393 394 395 396 397 398 399 400

	return old;
}

/**
 * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
 * @ent: swap entry to be looked up.
 *
401
 * Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
402
 */
403
unsigned short lookup_swap_cgroup(swp_entry_t ent)
404 405 406 407 408 409 410 411
{
	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;
412
	unsigned short ret;
413 414 415 416 417

	ctrl = &swap_cgroup_ctrl[type];
	mappage = ctrl->map[idx];
	sc = page_address(mappage);
	sc += pos;
418
	ret = sc->id;
419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485
	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
新手
引导
客服 返回
顶部