cmm.c 18.4 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30
/*
 * Collaborative memory management interface.
 *
 * Copyright (C) 2008 IBM Corporation
 * Author(s): Brian King (brking@linux.vnet.ibm.com),
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 */

#include <linux/ctype.h>
#include <linux/delay.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/init.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/oom.h>
31
#include <linux/reboot.h>
32 33 34 35 36 37 38 39 40
#include <linux/sched.h>
#include <linux/stringify.h>
#include <linux/swap.h>
#include <linux/sysdev.h>
#include <asm/firmware.h>
#include <asm/hvcall.h>
#include <asm/mmu.h>
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
41
#include <linux/memory.h>
42 43 44 45 46

#include "plpar_wrappers.h"

#define CMM_DRIVER_VERSION	"1.0.0"
#define CMM_DEFAULT_DELAY	1
47
#define CMM_HOTPLUG_DELAY	5
48 49 50 51 52 53
#define CMM_DEBUG			0
#define CMM_DISABLE		0
#define CMM_OOM_KB		1024
#define CMM_MIN_MEM_MB		256
#define KB2PAGES(_p)		((_p)>>(PAGE_SHIFT-10))
#define PAGES2KB(_p)		((_p)<<(PAGE_SHIFT-10))
54 55 56 57 58 59
/*
 * The priority level tries to ensure that this notifier is called as
 * late as possible to reduce thrashing in the shared memory pool.
 */
#define CMM_MEM_HOTPLUG_PRI	1
#define CMM_MEM_ISOLATE_PRI	15
60 61

static unsigned int delay = CMM_DEFAULT_DELAY;
62
static unsigned int hotplug_delay = CMM_HOTPLUG_DELAY;
63 64 65 66 67 68 69 70 71 72 73 74 75 76
static unsigned int oom_kb = CMM_OOM_KB;
static unsigned int cmm_debug = CMM_DEBUG;
static unsigned int cmm_disabled = CMM_DISABLE;
static unsigned long min_mem_mb = CMM_MIN_MEM_MB;
static struct sys_device cmm_sysdev;

MODULE_AUTHOR("Brian King <brking@linux.vnet.ibm.com>");
MODULE_DESCRIPTION("IBM System p Collaborative Memory Manager");
MODULE_LICENSE("GPL");
MODULE_VERSION(CMM_DRIVER_VERSION);

module_param_named(delay, delay, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(delay, "Delay (in seconds) between polls to query hypervisor paging requests. "
		 "[Default=" __stringify(CMM_DEFAULT_DELAY) "]");
77 78 79 80
module_param_named(hotplug_delay, hotplug_delay, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(delay, "Delay (in seconds) after memory hotplug remove "
		 "before loaning resumes. "
		 "[Default=" __stringify(CMM_HOTPLUG_DELAY) "]");
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107
module_param_named(oom_kb, oom_kb, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(oom_kb, "Amount of memory in kb to free on OOM. "
		 "[Default=" __stringify(CMM_OOM_KB) "]");
module_param_named(min_mem_mb, min_mem_mb, ulong, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(min_mem_mb, "Minimum amount of memory (in MB) to not balloon. "
		 "[Default=" __stringify(CMM_MIN_MEM_MB) "]");
module_param_named(debug, cmm_debug, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(debug, "Enable module debugging logging. Set to 1 to enable. "
		 "[Default=" __stringify(CMM_DEBUG) "]");

#define CMM_NR_PAGES ((PAGE_SIZE - sizeof(void *) - sizeof(unsigned long)) / sizeof(unsigned long))

#define cmm_dbg(...) if (cmm_debug) { printk(KERN_INFO "cmm: "__VA_ARGS__); }

struct cmm_page_array {
	struct cmm_page_array *next;
	unsigned long index;
	unsigned long page[CMM_NR_PAGES];
};

static unsigned long loaned_pages;
static unsigned long loaned_pages_target;
static unsigned long oom_freed_pages;

static struct cmm_page_array *cmm_page_list;
static DEFINE_SPINLOCK(cmm_lock);

108 109 110
static DEFINE_MUTEX(hotplug_mutex);
static int hotplug_occurred; /* protected by the hotplug mutex */

111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
static struct task_struct *cmm_thread_ptr;

/**
 * cmm_alloc_pages - Allocate pages and mark them as loaned
 * @nr:	number of pages to allocate
 *
 * Return value:
 * 	number of pages requested to be allocated which were not
 **/
static long cmm_alloc_pages(long nr)
{
	struct cmm_page_array *pa, *npa;
	unsigned long addr;
	long rc;

	cmm_dbg("Begin request for %ld pages\n", nr);

	while (nr) {
129 130 131 132 133 134 135 136 137 138 139
		/* Exit if a hotplug operation is in progress or occurred */
		if (mutex_trylock(&hotplug_mutex)) {
			if (hotplug_occurred) {
				mutex_unlock(&hotplug_mutex);
				break;
			}
			mutex_unlock(&hotplug_mutex);
		} else {
			break;
		}

140 141 142 143 144 145 146 147 148
		addr = __get_free_page(GFP_NOIO | __GFP_NOWARN |
				       __GFP_NORETRY | __GFP_NOMEMALLOC);
		if (!addr)
			break;
		spin_lock(&cmm_lock);
		pa = cmm_page_list;
		if (!pa || pa->index >= CMM_NR_PAGES) {
			/* Need a new page for the page list. */
			spin_unlock(&cmm_lock);
149 150 151
			npa = (struct cmm_page_array *)__get_free_page(
					GFP_NOIO | __GFP_NOWARN |
					__GFP_NORETRY | __GFP_NOMEMALLOC);
152
			if (!npa) {
153
				pr_info("%s: Can not allocate new page list\n", __func__);
154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169
				free_page(addr);
				break;
			}
			spin_lock(&cmm_lock);
			pa = cmm_page_list;

			if (!pa || pa->index >= CMM_NR_PAGES) {
				npa->next = pa;
				npa->index = 0;
				pa = npa;
				cmm_page_list = pa;
			} else
				free_page((unsigned long) npa);
		}

		if ((rc = plpar_page_set_loaned(__pa(addr)))) {
170
			pr_err("%s: Can not set page to loaned. rc=%ld\n", __func__, rc);
171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259
			spin_unlock(&cmm_lock);
			free_page(addr);
			break;
		}

		pa->page[pa->index++] = addr;
		loaned_pages++;
		totalram_pages--;
		spin_unlock(&cmm_lock);
		nr--;
	}

	cmm_dbg("End request with %ld pages unfulfilled\n", nr);
	return nr;
}

/**
 * cmm_free_pages - Free pages and mark them as active
 * @nr:	number of pages to free
 *
 * Return value:
 * 	number of pages requested to be freed which were not
 **/
static long cmm_free_pages(long nr)
{
	struct cmm_page_array *pa;
	unsigned long addr;

	cmm_dbg("Begin free of %ld pages.\n", nr);
	spin_lock(&cmm_lock);
	pa = cmm_page_list;
	while (nr) {
		if (!pa || pa->index <= 0)
			break;
		addr = pa->page[--pa->index];

		if (pa->index == 0) {
			pa = pa->next;
			free_page((unsigned long) cmm_page_list);
			cmm_page_list = pa;
		}

		plpar_page_set_active(__pa(addr));
		free_page(addr);
		loaned_pages--;
		nr--;
		totalram_pages++;
	}
	spin_unlock(&cmm_lock);
	cmm_dbg("End request with %ld pages unfulfilled\n", nr);
	return nr;
}

/**
 * cmm_oom_notify - OOM notifier
 * @self:	notifier block struct
 * @dummy:	not used
 * @parm:	returned - number of pages freed
 *
 * Return value:
 * 	NOTIFY_OK
 **/
static int cmm_oom_notify(struct notifier_block *self,
			  unsigned long dummy, void *parm)
{
	unsigned long *freed = parm;
	long nr = KB2PAGES(oom_kb);

	cmm_dbg("OOM processing started\n");
	nr = cmm_free_pages(nr);
	loaned_pages_target = loaned_pages;
	*freed += KB2PAGES(oom_kb) - nr;
	oom_freed_pages += KB2PAGES(oom_kb) - nr;
	cmm_dbg("OOM processing complete\n");
	return NOTIFY_OK;
}

/**
 * cmm_get_mpp - Read memory performance parameters
 *
 * Makes hcall to query the current page loan request from the hypervisor.
 *
 * Return value:
 * 	nothing
 **/
static void cmm_get_mpp(void)
{
	int rc;
	struct hvcall_mpp_data mpp_data;
260 261 262
	signed long active_pages_target, page_loan_request, target;
	signed long total_pages = totalram_pages + loaned_pages;
	signed long min_mem_pages = (min_mem_mb * 1024 * 1024) / PAGE_SIZE;
263 264 265 266 267 268 269

	rc = h_get_mpp(&mpp_data);

	if (rc != H_SUCCESS)
		return;

	page_loan_request = div_s64((s64)mpp_data.loan_request, PAGE_SIZE);
270 271 272 273 274 275 276
	target = page_loan_request + (signed long)loaned_pages;

	if (target < 0 || total_pages < min_mem_pages)
		target = 0;

	if (target > oom_freed_pages)
		target -= oom_freed_pages;
277
	else
278 279 280 281 282 283
		target = 0;

	active_pages_target = total_pages - target;

	if (min_mem_pages > active_pages_target)
		target = total_pages - min_mem_pages;
284

285 286
	if (target < 0)
		target = 0;
287

288
	loaned_pages_target = target;
289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312

	cmm_dbg("delta = %ld, loaned = %lu, target = %lu, oom = %lu, totalram = %lu\n",
		page_loan_request, loaned_pages, loaned_pages_target,
		oom_freed_pages, totalram_pages);
}

static struct notifier_block cmm_oom_nb = {
	.notifier_call = cmm_oom_notify
};

/**
 * cmm_thread - CMM task thread
 * @dummy:	not used
 *
 * Return value:
 * 	0
 **/
static int cmm_thread(void *dummy)
{
	unsigned long timeleft;

	while (1) {
		timeleft = msleep_interruptible(delay * 1000);

313
		if (kthread_should_stop() || timeleft)
314
			break;
315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334

		if (mutex_trylock(&hotplug_mutex)) {
			if (hotplug_occurred) {
				hotplug_occurred = 0;
				mutex_unlock(&hotplug_mutex);
				cmm_dbg("Hotplug operation has occurred, "
						"loaning activity suspended "
						"for %d seconds.\n",
						hotplug_delay);
				timeleft = msleep_interruptible(hotplug_delay *
						1000);
				if (kthread_should_stop() || timeleft)
					break;
				continue;
			}
			mutex_unlock(&hotplug_mutex);
		} else {
			cmm_dbg("Hotplug operation in progress, activity "
					"suspended\n");
			continue;
335 336 337 338 339 340 341 342 343 344 345 346 347 348
		}

		cmm_get_mpp();

		if (loaned_pages_target > loaned_pages) {
			if (cmm_alloc_pages(loaned_pages_target - loaned_pages))
				loaned_pages_target = loaned_pages;
		} else if (loaned_pages_target < loaned_pages)
			cmm_free_pages(loaned_pages - loaned_pages_target);
	}
	return 0;
}

#define CMM_SHOW(name, format, args...)			\
349 350 351
	static ssize_t show_##name(struct sys_device *dev,	\
				   struct sysdev_attribute *attr,	\
				   char *buf)			\
352 353 354 355 356 357 358 359
	{							\
		return sprintf(buf, format, ##args);		\
	}							\
	static SYSDEV_ATTR(name, S_IRUGO, show_##name, NULL)

CMM_SHOW(loaned_kb, "%lu\n", PAGES2KB(loaned_pages));
CMM_SHOW(loaned_target_kb, "%lu\n", PAGES2KB(loaned_pages_target));

360 361
static ssize_t show_oom_pages(struct sys_device *dev,
			      struct sysdev_attribute *attr, char *buf)
362 363 364 365 366
{
	return sprintf(buf, "%lu\n", PAGES2KB(oom_freed_pages));
}

static ssize_t store_oom_pages(struct sys_device *dev,
367
			       struct sysdev_attribute *attr,
368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442
			       const char *buf, size_t count)
{
	unsigned long val = simple_strtoul (buf, NULL, 10);

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (val != 0)
		return -EBADMSG;

	oom_freed_pages = 0;
	return count;
}

static SYSDEV_ATTR(oom_freed_kb, S_IWUSR| S_IRUGO,
		   show_oom_pages, store_oom_pages);

static struct sysdev_attribute *cmm_attrs[] = {
	&attr_loaned_kb,
	&attr_loaned_target_kb,
	&attr_oom_freed_kb,
};

static struct sysdev_class cmm_sysdev_class = {
	.name = "cmm",
};

/**
 * cmm_sysfs_register - Register with sysfs
 *
 * Return value:
 * 	0 on success / other on failure
 **/
static int cmm_sysfs_register(struct sys_device *sysdev)
{
	int i, rc;

	if ((rc = sysdev_class_register(&cmm_sysdev_class)))
		return rc;

	sysdev->id = 0;
	sysdev->cls = &cmm_sysdev_class;

	if ((rc = sysdev_register(sysdev)))
		goto class_unregister;

	for (i = 0; i < ARRAY_SIZE(cmm_attrs); i++) {
		if ((rc = sysdev_create_file(sysdev, cmm_attrs[i])))
			goto fail;
	}

	return 0;

fail:
	while (--i >= 0)
		sysdev_remove_file(sysdev, cmm_attrs[i]);
	sysdev_unregister(sysdev);
class_unregister:
	sysdev_class_unregister(&cmm_sysdev_class);
	return rc;
}

/**
 * cmm_unregister_sysfs - Unregister from sysfs
 *
 **/
static void cmm_unregister_sysfs(struct sys_device *sysdev)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(cmm_attrs); i++)
		sysdev_remove_file(sysdev, cmm_attrs[i]);
	sysdev_unregister(sysdev);
	sysdev_class_unregister(&cmm_sysdev_class);
}

443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462
/**
 * cmm_reboot_notifier - Make sure pages are not still marked as "loaned"
 *
 **/
static int cmm_reboot_notifier(struct notifier_block *nb,
			       unsigned long action, void *unused)
{
	if (action == SYS_RESTART) {
		if (cmm_thread_ptr)
			kthread_stop(cmm_thread_ptr);
		cmm_thread_ptr = NULL;
		cmm_free_pages(loaned_pages);
	}
	return NOTIFY_DONE;
}

static struct notifier_block cmm_reboot_nb = {
	.notifier_call = cmm_reboot_notifier,
};

463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649
/**
 * cmm_count_pages - Count the number of pages loaned in a particular range.
 *
 * @arg: memory_isolate_notify structure with address range and count
 *
 * Return value:
 *      0 on success
 **/
static unsigned long cmm_count_pages(void *arg)
{
	struct memory_isolate_notify *marg = arg;
	struct cmm_page_array *pa;
	unsigned long start = (unsigned long)pfn_to_kaddr(marg->start_pfn);
	unsigned long end = start + (marg->nr_pages << PAGE_SHIFT);
	unsigned long idx;

	spin_lock(&cmm_lock);
	pa = cmm_page_list;
	while (pa) {
		if ((unsigned long)pa >= start && (unsigned long)pa < end)
			marg->pages_found++;
		for (idx = 0; idx < pa->index; idx++)
			if (pa->page[idx] >= start && pa->page[idx] < end)
				marg->pages_found++;
		pa = pa->next;
	}
	spin_unlock(&cmm_lock);
	return 0;
}

/**
 * cmm_memory_isolate_cb - Handle memory isolation notifier calls
 * @self:	notifier block struct
 * @action:	action to take
 * @arg:	struct memory_isolate_notify data for handler
 *
 * Return value:
 *	NOTIFY_OK or notifier error based on subfunction return value
 **/
static int cmm_memory_isolate_cb(struct notifier_block *self,
				 unsigned long action, void *arg)
{
	int ret = 0;

	if (action == MEM_ISOLATE_COUNT)
		ret = cmm_count_pages(arg);

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

	return ret;
}

static struct notifier_block cmm_mem_isolate_nb = {
	.notifier_call = cmm_memory_isolate_cb,
	.priority = CMM_MEM_ISOLATE_PRI
};

/**
 * cmm_mem_going_offline - Unloan pages where memory is to be removed
 * @arg: memory_notify structure with page range to be offlined
 *
 * Return value:
 *	0 on success
 **/
static int cmm_mem_going_offline(void *arg)
{
	struct memory_notify *marg = arg;
	unsigned long start_page = (unsigned long)pfn_to_kaddr(marg->start_pfn);
	unsigned long end_page = start_page + (marg->nr_pages << PAGE_SHIFT);
	struct cmm_page_array *pa_curr, *pa_last, *npa;
	unsigned long idx;
	unsigned long freed = 0;

	cmm_dbg("Memory going offline, searching 0x%lx (%ld pages).\n",
			start_page, marg->nr_pages);
	spin_lock(&cmm_lock);

	/* Search the page list for pages in the range to be offlined */
	pa_last = pa_curr = cmm_page_list;
	while (pa_curr) {
		for (idx = (pa_curr->index - 1); (idx + 1) > 0; idx--) {
			if ((pa_curr->page[idx] < start_page) ||
			    (pa_curr->page[idx] >= end_page))
				continue;

			plpar_page_set_active(__pa(pa_curr->page[idx]));
			free_page(pa_curr->page[idx]);
			freed++;
			loaned_pages--;
			totalram_pages++;
			pa_curr->page[idx] = pa_last->page[--pa_last->index];
			if (pa_last->index == 0) {
				if (pa_curr == pa_last)
					pa_curr = pa_last->next;
				pa_last = pa_last->next;
				free_page((unsigned long)cmm_page_list);
				cmm_page_list = pa_last;
				continue;
			}
		}
		pa_curr = pa_curr->next;
	}

	/* Search for page list structures in the range to be offlined */
	pa_last = NULL;
	pa_curr = cmm_page_list;
	while (pa_curr) {
		if (((unsigned long)pa_curr >= start_page) &&
				((unsigned long)pa_curr < end_page)) {
			npa = (struct cmm_page_array *)__get_free_page(
					GFP_NOIO | __GFP_NOWARN |
					__GFP_NORETRY | __GFP_NOMEMALLOC);
			if (!npa) {
				spin_unlock(&cmm_lock);
				cmm_dbg("Failed to allocate memory for list "
						"management. Memory hotplug "
						"failed.\n");
				return ENOMEM;
			}
			memcpy(npa, pa_curr, PAGE_SIZE);
			if (pa_curr == cmm_page_list)
				cmm_page_list = npa;
			if (pa_last)
				pa_last->next = npa;
			free_page((unsigned long) pa_curr);
			freed++;
			pa_curr = npa;
		}

		pa_last = pa_curr;
		pa_curr = pa_curr->next;
	}

	spin_unlock(&cmm_lock);
	cmm_dbg("Released %ld pages in the search range.\n", freed);

	return 0;
}

/**
 * cmm_memory_cb - Handle memory hotplug notifier calls
 * @self:	notifier block struct
 * @action:	action to take
 * @arg:	struct memory_notify data for handler
 *
 * Return value:
 *	NOTIFY_OK or notifier error based on subfunction return value
 *
 **/
static int cmm_memory_cb(struct notifier_block *self,
			unsigned long action, void *arg)
{
	int ret = 0;

	switch (action) {
	case MEM_GOING_OFFLINE:
		mutex_lock(&hotplug_mutex);
		hotplug_occurred = 1;
		ret = cmm_mem_going_offline(arg);
		break;
	case MEM_OFFLINE:
	case MEM_CANCEL_OFFLINE:
		mutex_unlock(&hotplug_mutex);
		cmm_dbg("Memory offline operation complete.\n");
		break;
	case MEM_GOING_ONLINE:
	case MEM_ONLINE:
	case MEM_CANCEL_ONLINE:
		break;
	}

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

	return ret;
}

static struct notifier_block cmm_mem_nb = {
	.notifier_call = cmm_memory_cb,
	.priority = CMM_MEM_HOTPLUG_PRI
};

650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665
/**
 * cmm_init - Module initialization
 *
 * Return value:
 * 	0 on success / other on failure
 **/
static int cmm_init(void)
{
	int rc = -ENOMEM;

	if (!firmware_has_feature(FW_FEATURE_CMO))
		return -EOPNOTSUPP;

	if ((rc = register_oom_notifier(&cmm_oom_nb)) < 0)
		return rc;

666
	if ((rc = register_reboot_notifier(&cmm_reboot_nb)))
667 668
		goto out_oom_notifier;

669 670 671
	if ((rc = cmm_sysfs_register(&cmm_sysdev)))
		goto out_reboot_notifier;

672 673 674 675
	if (register_memory_notifier(&cmm_mem_nb) ||
	    register_memory_isolate_notifier(&cmm_mem_isolate_nb))
		goto out_unregister_notifier;

676 677 678 679 680 681
	if (cmm_disabled)
		return rc;

	cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread");
	if (IS_ERR(cmm_thread_ptr)) {
		rc = PTR_ERR(cmm_thread_ptr);
682
		goto out_unregister_notifier;
683 684 685 686
	}

	return rc;

687 688 689
out_unregister_notifier:
	unregister_memory_notifier(&cmm_mem_nb);
	unregister_memory_isolate_notifier(&cmm_mem_isolate_nb);
690
	cmm_unregister_sysfs(&cmm_sysdev);
691 692
out_reboot_notifier:
	unregister_reboot_notifier(&cmm_reboot_nb);
693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708
out_oom_notifier:
	unregister_oom_notifier(&cmm_oom_nb);
	return rc;
}

/**
 * cmm_exit - Module exit
 *
 * Return value:
 * 	nothing
 **/
static void cmm_exit(void)
{
	if (cmm_thread_ptr)
		kthread_stop(cmm_thread_ptr);
	unregister_oom_notifier(&cmm_oom_nb);
709
	unregister_reboot_notifier(&cmm_reboot_nb);
710 711
	unregister_memory_notifier(&cmm_mem_nb);
	unregister_memory_isolate_notifier(&cmm_mem_isolate_nb);
712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750
	cmm_free_pages(loaned_pages);
	cmm_unregister_sysfs(&cmm_sysdev);
}

/**
 * cmm_set_disable - Disable/Enable CMM
 *
 * Return value:
 * 	0 on success / other on failure
 **/
static int cmm_set_disable(const char *val, struct kernel_param *kp)
{
	int disable = simple_strtoul(val, NULL, 10);

	if (disable != 0 && disable != 1)
		return -EINVAL;

	if (disable && !cmm_disabled) {
		if (cmm_thread_ptr)
			kthread_stop(cmm_thread_ptr);
		cmm_thread_ptr = NULL;
		cmm_free_pages(loaned_pages);
	} else if (!disable && cmm_disabled) {
		cmm_thread_ptr = kthread_run(cmm_thread, NULL, "cmmthread");
		if (IS_ERR(cmm_thread_ptr))
			return PTR_ERR(cmm_thread_ptr);
	}

	cmm_disabled = disable;
	return 0;
}

module_param_call(disable, cmm_set_disable, param_get_uint,
		  &cmm_disabled, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(disable, "Disable CMM. Set to 1 to disable. "
		 "[Default=" __stringify(CMM_DISABLE) "]");

module_init(cmm_init);
module_exit(cmm_exit);