litmus-rt-edfsc.git - LITMUS^RT with the EDF-SC plugin for Real-Time Systems journal paper

about summary refs log tree commit diff stats

path: root/tools/perf/scripts/python/syscall-counts.py

diff options

author	Dave Airlie <airlied@redhat.com>	2014-10-07 00:31:14 -0400
committer	Dave Airlie <airlied@redhat.com>	2014-10-07 00:31:14 -0400
commit	46d987af7649ef9b2f1d1467b9249fb6e24d2658 (patch)
tree	d46ecf4acfb9a84622acaf227d5707d54b34e7fd /tools/perf/scripts/python/syscall-counts.py
parent	7bbc1920c0fd1416e4660b1dee5c467a2996c80e (diff)
parent	c7750e8321155d39625c1ffb03227af4fa7f9122 (diff)

Merge tag 'ipu-fixes-3.18' of git://git.pengutronix.de/git/pza/linux into drm-next

IPUv3 fixes for v3.18 * tag 'ipu-fixes-3.18' of git://git.pengutronix.de/git/pza/linux: gpu: ipu-v3: Kconfig: Remove SOC_IMX6SL from IMX_IPUV3_CORE Kconfig gpu: ipu-v3: ipu-smfc: Do not leave DEBUG defined gpu: ipu-v3: Return proper error on ipu_add_client_devices error path gpu: ipu-v3: Select GENERIC_IRQ_CHIP to fix build error

Diffstat (limited to 'tools/perf/scripts/python/syscall-counts.py')

0 files changed, 0 insertions, 0 deletions

3f41524e886b7f1b8a0c1fc7321cac2'>1da177e4c3f

83144186295

47
48

50
51
52

55
56
57

58
59
60

66
67

68
69

70
71

81
82

128
129
130

168
169

171
172

173
174

187
188

190
191

214
215

216
217

218
219

285
286

287
288
289

309
310

312
313

358
359

369
370
371

400
401

402
403

458
459

484
485

509
510

514
515

526
527
528

551
552
553

606
607
608

628
629

689
690

691
692
693

694
695

708
709
710

713
714
715

813
814

816
817

818
819
820

830
831
832

836
837

838
839

846
847

848
849

875
876

877
878

884
885
886

912
913

928
929

930
931

932
933

1058
1059

1073
1074

1075
1076
1077

1078
1079
1080

1089
1090

1115
1116

1119
1120

1149
1150

1160
1161
1162

1170
1171

1172
1173
1174

1212
1213

1218
1219
1220

1224
1225

1226
1227
1228

1254
1255

1258
1259
1260

1305
1306

1307
1308
1309

1326
1327

1329
1330
1331

1332
1333
1334

1336
1337

1350
1351

1363
1364

1367
1368
1369

1399
1400
1401

1402
1403

1417
1418

1421
1422

1423
1424

1437
1438

1467
1468
1469

1473
1474
1475

1476
1477

1479
1480

1487
1488
1489

1494
1495

1505
1506

1514
1515

1517
1518

1521
1522
1523

1527
1528
1529

1530
1531
1532

1533
1534

1551
1552

1553
1554

1555
1556

1557
1558
1559

1571
1572

1578
1579

1580
1581

1589
1590

1607
1608
1609

1615
1616
1617

1619
1620
1621

1622
1623
1624

1625
1626
1627

1655
1656

1688
1689
1690

1713
1714
1715

1717
1718
1719

1735
1736

1751
1752

1753
1754

1755
1756

1758
1759
1760

1761
1762

1763
1764

1765
1766

1776
1777

1779
1780

1793
1794

1802
1803
1804

1848
1849

1864
1865

1867
1868

1870
1871

1922
1923

1941
1942
1943

1969
1970

1975
1976

1979
1980
1981

1982
1983

1989
1990

1998
1999

2016
2017

2025
2026

2029
2030

2039
2040

2045
2046
2047

2050
2051

2052
2053

2062
2063
2064

2067
2068
2069

/*
 *  linux/mm/vmscan.c
 *
 *  Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
 *
 *  Swap reorganised 29.12.95, Stephen Tweedie.
 *  kswapd added: 7.1.96  sct
 *  Removed kswapd_ctl limits, and swap out as many pages as needed
 *  to bring the system back to freepages.high: 2.4.97, Rik van Riel.
 *  Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com).
 *  Multiqueue VM started 5.8.00, Rik van Riel.
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/kernel_stat.h>
#include <linux/swap.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/highmem.h>
#include <linux/vmstat.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/buffer_head.h>	/* for try_to_release_page(),
					buffer_heads_over_limit */
#include <linux/mm_inline.h>
#include <linux/pagevec.h>
#include <linux/backing-dev.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/notifier.h>
#include <linux/rwsem.h>
#include <linux/delay.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/memcontrol.h>

#include <asm/tlbflush.h>
#include <asm/div64.h>

#include <linux/swapops.h>

#include "internal.h"

struct scan_control {
	/* Incremented by the number of inactive pages that were scanned */
	unsigned long nr_scanned;

	/* This context's GFP mask */
	gfp_t gfp_mask;

	int may_writepage;

	/* Can pages be swapped as part of reclaim? */
	int may_swap;

	/* This context's SWAP_CLUSTER_MAX. If freeing memory for
	 * suspend, we effectively ignore SWAP_CLUSTER_MAX.
	 * In this context, it doesn't matter that we scan the
	 * whole list at once. */
	int swap_cluster_max;

	int swappiness;

	int all_unreclaimable;

	int order;

	/* Which cgroup do we reclaim from */
	struct mem_cgroup *mem_cgroup;

	/* Pluggable isolate pages callback */
	unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst,
			unsigned long *scanned, int order, int mode,
			struct zone *z, struct mem_cgroup *mem_cont,
			int active);
};

#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))

#ifdef ARCH_HAS_PREFETCH
#define prefetch_prev_lru_page(_page, _base, _field)			\
	do {								\
		if ((_page)->lru.prev != _base) {			\
			struct page *prev;				\
									\
			prev = lru_to_page(&(_page->lru));		\
			prefetch(&prev->_field);			\
		}							\
	} while (0)
#else
#define prefetch_prev_lru_page(_page, _base, _field) do { } while (0)
#endif

#ifdef ARCH_HAS_PREFETCHW
#define prefetchw_prev_lru_page(_page, _base, _field)			\
	do {								\
		if ((_page)->lru.prev != _base) {			\
			struct page *prev;				\
									\
			prev = lru_to_page(&(_page->lru));		\
			prefetchw(&prev->_field);			\
		}							\
	} while (0)
#else
#define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0)
#endif

/*
 * From 0 .. 100.  Higher means more swappy.
 */
int vm_swappiness = 60;
long vm_total_pages;	/* The total number of pages which the VM controls */

static LIST_HEAD(shrinker_list);
static DECLARE_RWSEM(shrinker_rwsem);

#ifdef CONFIG_CGROUP_MEM_RES_CTLR
#define scan_global_lru(sc)	(!(sc)->mem_cgroup)
#else
#define scan_global_lru(sc)	(1)
#endif

/*
 * Add a shrinker callback to be called from the vm
 */
void register_shrinker(struct shrinker *shrinker)
{
	shrinker->nr = 0;
	down_write(&shrinker_rwsem);
	list_add_tail(&shrinker->list, &shrinker_list);
	up_write(&shrinker_rwsem);
}
EXPORT_SYMBOL(register_shrinker);

/*
 * Remove one
 */
void unregister_shrinker(struct shrinker *shrinker)
{
	down_write(&shrinker_rwsem);
	list_del(&shrinker->list);
	up_write(&shrinker_rwsem);
}
EXPORT_SYMBOL(unregister_shrinker);

#define SHRINK_BATCH 128
/*
 * Call the shrink functions to age shrinkable caches
 *
 * Here we assume it costs one seek to replace a lru page and that it also
 * takes a seek to recreate a cache object.  With this in mind we age equal
 * percentages of the lru and ageable caches.  This should balance the seeks
 * generated by these structures.
 *
 * If the vm encountered mapped pages on the LRU it increase the pressure on
 * slab to avoid swapping.
 *
 * We do weird things to avoid (scanned*seeks*entries) overflowing 32 bits.
 *
 * `lru_pages' represents the number of on-LRU pages in all the zones which
 * are eligible for the caller's allocation attempt.  It is used for balancing
 * slab reclaim versus page reclaim.
 *
 * Returns the number of slab objects which we shrunk.
 */
unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
			unsigned long lru_pages)
{
	struct shrinker *shrinker;
	unsigned long ret = 0;

	if (scanned == 0)
		scanned = SWAP_CLUSTER_MAX;

	if (!down_read_trylock(&shrinker_rwsem))
		return 1;	/* Assume we'll be able to shrink next time */

	list_for_each_entry(shrinker, &shrinker_list, list) {
		unsigned long long delta;
		unsigned long total_scan;
		unsigned long max_pass = (*shrinker->shrink)(0, gfp_mask);

		delta = (4 * scanned) / shrinker->seeks;
		delta *= max_pass;
		do_div(delta, lru_pages + 1);
		shrinker->nr += delta;
		if (shrinker->nr < 0) {
			printk(KERN_ERR "%s: nr=%ld\n",
					__FUNCTION__, shrinker->nr);
			shrinker->nr = max_pass;
		}

		/*
		 * Avoid risking looping forever due to too large nr value:
		 * never try to free more than twice the estimate number of
		 * freeable entries.
		 */
		if (shrinker->nr > max_pass * 2)
			shrinker->nr = max_pass * 2;

		total_scan = shrinker->nr;
		shrinker->nr = 0;

		while (total_scan >= SHRINK_BATCH) {
			long this_scan = SHRINK_BATCH;
			int shrink_ret;
			int nr_before;

			nr_before = (*shrinker->shrink)(0, gfp_mask);
			shrink_ret = (*shrinker->shrink)(this_scan, gfp_mask);
			if (shrink_ret == -1)
				break;
			if (shrink_ret < nr_before)
				ret += nr_before - shrink_ret;
			count_vm_events(SLABS_SCANNED, this_scan);
			total_scan -= this_scan;

			cond_resched();
		}

		shrinker->nr += total_scan;
	}
	up_read(&shrinker_rwsem);
	return ret;
}

/* Called without lock on whether page is mapped, so answer is unstable */
static inline int page_mapping_inuse(struct page *page)
{
	struct address_space *mapping;

	/* Page is in somebody's page tables. */
	if (page_mapped(page))
		return 1;

	/* Be more reluctant to reclaim swapcache than pagecache */
	if (PageSwapCache(page))
		return 1;

	mapping = page_mapping(page);
	if (!mapping)
		return 0;

	/* File is mmap'd by somebody? */
	return mapping_mapped(mapping);
}

static inline int is_page_cache_freeable(struct page *page)
{
	return page_count(page) - !!PagePrivate(page) == 2;
}

static int may_write_to_queue(struct backing_dev_info *bdi)
{
	if (current->flags & PF_SWAPWRITE)
		return 1;
	if (!bdi_write_congested(bdi))
		return 1;
	if (bdi == current->backing_dev_info)
		return 1;
	return 0;
}

/*
 * We detected a synchronous write error writing a page out.  Probably
 * -ENOSPC.  We need to propagate that into the address_space for a subsequent
 * fsync(), msync() or close().
 *
 * The tricky part is that after writepage we cannot touch the mapping: nothing
 * prevents it from being freed up.  But we have a ref on the page and once
 * that page is locked, the mapping is pinned.
 *
 * We're allowed to run sleeping lock_page() here because we know the caller has
 * __GFP_FS.
 */
static void handle_write_error(struct address_space *mapping,
				struct page *page, int error)
{
	lock_page(page);
	if (page_mapping(page) == mapping)
		mapping_set_error(mapping, error);
	unlock_page(page);
}

/* Request for sync pageout. */
enum pageout_io {
	PAGEOUT_IO_ASYNC,
	PAGEOUT_IO_SYNC,
};

/* possible outcome of pageout() */
typedef enum {
	/* failed to write page out, page is locked */
	PAGE_KEEP,
	/* move page to the active list, page is locked */
	PAGE_ACTIVATE,
	/* page has been sent to the disk successfully, page is unlocked */
	PAGE_SUCCESS,
	/* page is clean and locked */
	PAGE_CLEAN,
} pageout_t;

/*
 * pageout is called by shrink_page_list() for each dirty page.
 * Calls ->writepage().
 */
static pageout_t pageout(struct page *page, struct address_space *mapping,
						enum pageout_io sync_writeback)
{
	/*
	 * If the page is dirty, only perform writeback if that write
	 * will be non-blocking.  To prevent this allocation from being
	 * stalled by pagecache activity.  But note that there may be
	 * stalls if we need to run get_block().  We could test
	 * PagePrivate for that.
	 *
	 * If this process is currently in generic_file_write() against
	 * this page's queue, we can perform writeback even if that
	 * will block.
	 *
	 * If the page is swapcache, write it back even if that would
	 * block, for some throttling. This happens by accident, because
	 * swap_backing_dev_info is bust: it doesn't reflect the
	 * congestion state of the swapdevs.  Easy to fix, if needed.
	 * See swapfile.c:page_queue_congested().
	 */
	if (!is_page_cache_freeable(page))
		return PAGE_KEEP;
	if (!mapping) {
		/*
		 * Some data journaling orphaned pages can have
		 * page->mapping == NULL while being dirty with clean buffers.
		 */
		if (PagePrivate(page)) {
			if (try_to_free_buffers(page)) {
				ClearPageDirty(page);
				printk("%s: orphaned page\n", __FUNCTION__);
				return PAGE_CLEAN;
			}
		}
		return PAGE_KEEP;
	}
	if (mapping->a_ops->writepage == NULL)
		return PAGE_ACTIVATE;
	if (!may_write_to_queue(mapping->backing_dev_info))
		return PAGE_KEEP;

	if (clear_page_dirty_for_io(page)) {
		int res;
		struct writeback_control wbc = {
			.sync_mode = WB_SYNC_NONE,
			.nr_to_write = SWAP_CLUSTER_MAX,
			.range_start = 0,
			.range_end = LLONG_MAX,
			.nonblocking = 1,
			.for_reclaim = 1,
		};

		SetPageReclaim(page);
		res = mapping->a_ops->writepage(page, &wbc);
		if (res < 0)
			handle_write_error(mapping, page, res);
		if (res == AOP_WRITEPAGE_ACTIVATE) {
			ClearPageReclaim(page);
			return PAGE_ACTIVATE;
		}

		/*
		 * Wait on writeback if requested to. This happens when
		 * direct reclaiming a large contiguous area and the
		 * first attempt to free a range of pages fails.
		 */
		if (PageWriteback(page) && sync_writeback == PAGEOUT_IO_SYNC)
			wait_on_page_writeback(page);

		if (!PageWriteback(page)) {
			/* synchronous write or broken a_ops? */
			ClearPageReclaim(page);
		}
		inc_zone_page_state(page, NR_VMSCAN_WRITE);
		return PAGE_SUCCESS;
	}

	return PAGE_CLEAN;
}

/*
 * Attempt to detach a locked page from its ->mapping.  If it is dirty or if
 * someone else has a ref on the page, abort and return 0.  If it was
 * successfully detached, return 1.  Assumes the caller has a single ref on
 * this page.
 */
int remove_mapping(struct address_space *mapping, struct page *page)
{
	BUG_ON(!PageLocked(page));
	BUG_ON(mapping != page_mapping(page));

	write_lock_irq(&mapping->tree_lock);
	/*
	 * The non racy check for a busy page.
	 *
	 * Must be careful with the order of the tests. When someone has
	 * a ref to the page, it may be possible that they dirty it then
	 * drop the reference. So if PageDirty is tested before page_count
	 * here, then the following race may occur:
	 *
	 * get_user_pages(&page);
	 * [user mapping goes away]
	 * write_to(page);
	 *				!PageDirty(page)    [good]
	 * SetPageDirty(page);
	 * put_page(page);
	 *				!page_count(page)   [good, discard it]
	 *
	 * [oops, our write_to data is lost]
	 *
	 * Reversing the order of the tests ensures such a situation cannot
	 * escape unnoticed. The smp_rmb is needed to ensure the page->flags
	 * load is not satisfied before that of page->_count.
	 *
	 * Note that if SetPageDirty is always performed via set_page_dirty,
	 * and thus under tree_lock, then this ordering is not required.
	 */
	if (unlikely(page_count(page) != 2))
		goto cannot_free;
	smp_rmb();
	if (unlikely(PageDirty(page)))
		goto cannot_free;

	if (PageSwapCache(page)) {
		swp_entry_t swap = { .val = page_private(page) };
		__delete_from_swap_cache(page);
		write_unlock_irq(&mapping->tree_lock);
		swap_free(swap);
		__put_page(page);	/* The pagecache ref */
		return 1;
	}

	__remove_from_page_cache(page);
	write_unlock_irq(&mapping->tree_lock);
	__put_page(page);
	return 1;

cannot_free:
	write_unlock_irq(&mapping->tree_lock);
	return 0;
}

/*
 * shrink_page_list() returns the number of reclaimed pages
 */
static unsigned long shrink_page_list(struct list_head *page_list,
					struct scan_control *sc,
					enum pageout_io sync_writeback)
{
	LIST_HEAD(ret_pages);
	struct pagevec freed_pvec;
	int pgactivate = 0;
	unsigned long nr_reclaimed = 0;

	cond_resched();

	pagevec_init(&freed_pvec, 1);
	while (!list_empty(page_list)) {
		struct address_space *mapping;
		struct page *page;
		int may_enter_fs;
		int referenced;

		cond_resched();

		page = lru_to_page(page_list);
		list_del(&page->lru);

		if (TestSetPageLocked(page))
			goto keep;

		VM_BUG_ON(PageActive(page));

		sc->nr_scanned++;

		if (!sc->may_swap && page_mapped(page))
			goto keep_locked;

		/* Double the slab pressure for mapped and swapcache pages */
		if (page_mapped(page) || PageSwapCache(page))
			sc->nr_scanned++;

		may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
			(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));

		if (PageWriteback(page)) {
			/*
			 * Synchronous reclaim is performed in two passes,
			 * first an asynchronous pass over the list to
			 * start parallel writeback, and a second synchronous
			 * pass to wait for the IO to complete.  Wait here
			 * for any page for which writeback has already
			 * started.
			 */
			if (sync_writeback == PAGEOUT_IO_SYNC && may_enter_fs)
				wait_on_page_writeback(page);
			else
				goto keep_locked;
		}

		referenced = page_referenced(page, 1, sc->mem_cgroup);
		/* In active use or really unfreeable?  Activate it. */
		if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
					referenced && page_mapping_inuse(page))
			goto activate_locked;

#ifdef CONFIG_SWAP
		/*
		 * Anonymous process memory has backing store?
		 * Try to allocate it some swap space here.
		 */
		if (PageAnon(page) && !PageSwapCache(page))
			if (!add_to_swap(page, GFP_ATOMIC))
				goto activate_locked;
#endif /* CONFIG_SWAP */

		mapping = page_mapping(page);

		/*
		 * The page is mapped into the page tables of one or more
		 * processes. Try to unmap it here.
		 */
		if (page_mapped(page) && mapping) {
			switch (try_to_unmap(page, 0)) {
			case SWAP_FAIL:
				goto activate_locked;
			case SWAP_AGAIN:
				goto keep_locked;
			case SWAP_SUCCESS:
				; /* try to free the page below */
			}
		}

		if (PageDirty(page)) {
			if (sc->order <= PAGE_ALLOC_COSTLY_ORDER && referenced)
				goto keep_locked;
			if (!may_enter_fs)
				goto keep_locked;
			if (!sc->may_writepage)
				goto keep_locked;

			/* Page is dirty, try to write it out here */
			switch (pageout(page, mapping, sync_writeback)) {
			case PAGE_KEEP:
				goto keep_locked;
			case PAGE_ACTIVATE:
				goto activate_locked;
			case PAGE_SUCCESS:
				if (PageWriteback(page) || PageDirty(page))
					goto keep;
				/*
				 * A synchronous write - probably a ramdisk.  Go
				 * ahead and try to reclaim the page.
				 */
				if (TestSetPageLocked(page))
					goto keep;
				if (PageDirty(page) || PageWriteback(page))
					goto keep_locked;
				mapping = page_mapping(page);
			case PAGE_CLEAN:
				; /* try to free the page below */
			}
		}

		/*
		 * If the page has buffers, try to free the buffer mappings
		 * associated with this page. If we succeed we try to free
		 * the page as well.
		 *
		 * We do this even if the page is PageDirty().
		 * try_to_release_page() does not perform I/O, but it is
		 * possible for a page to have PageDirty set, but it is actually
		 * clean (all its buffers are clean).  This happens if the
		 * buffers were written out directly, with submit_bh(). ext3
		 * will do this, as well as the blockdev mapping. 
		 * try_to_release_page() will discover that cleanness and will
		 * drop the buffers and mark the page clean - it can be freed.
		 *
		 * Rarely, pages can have buffers and no ->mapping.  These are
		 * the pages which were not successfully invalidated in
		 * truncate_complete_page().  We try to drop those buffers here
		 * and if that worked, and the page is no longer mapped into
		 * process address space (page_count == 1) it can be freed.
		 * Otherwise, leave the page on the LRU so it is swappable.
		 */
		if (PagePrivate(page)) {
			if (!try_to_release_page(page, sc->gfp_mask))
				goto activate_locked;
			if (!mapping && page_count(page) == 1)
				goto free_it;
		}

		if (!mapping || !remove_mapping(mapping, page))
			goto keep_locked;

free_it:
		unlock_page(page);
		nr_reclaimed++;
		if (!pagevec_add(&freed_pvec, page))
			__pagevec_release_nonlru(&freed_pvec);
		continue;

activate_locked:
		SetPageActive(page);
		pgactivate++;
keep_locked:
		unlock_page(page);
keep:
		list_add(&page->lru, &ret_pages);
		VM_BUG_ON(PageLRU(page));
	}
	list_splice(&ret_pages, page_list);
	if (pagevec_count(&freed_pvec))
		__pagevec_release_nonlru(&freed_pvec);
	count_vm_events(PGACTIVATE, pgactivate);
	return nr_reclaimed;
}

/* LRU Isolation modes. */
#define ISOLATE_INACTIVE 0	/* Isolate inactive pages. */
#define ISOLATE_ACTIVE 1	/* Isolate active pages. */
#define ISOLATE_BOTH 2		/* Isolate both active and inactive pages. */

/*
 * Attempt to remove the specified page from its LRU.  Only take this page
 * if it is of the appropriate PageActive status.  Pages which are being
 * freed elsewhere are also ignored.
 *
 * page:	page to consider
 * mode:	one of the LRU isolation modes defined above
 *
 * returns 0 on success, -ve errno on failure.
 */
int __isolate_lru_page(struct page *page, int mode)
{
	int ret = -EINVAL;

	/* Only take pages on the LRU. */
	if (!PageLRU(page))
		return ret;

	/*
	 * When checking the active state, we need to be sure we are
	 * dealing with comparible boolean values.  Take the logical not
	 * of each.
	 */
	if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode))
		return ret;

	ret = -EBUSY;
	if (likely(get_page_unless_zero(page))) {
		/*
		 * Be careful not to clear PageLRU until after we're
		 * sure the page is not being freed elsewhere -- the
		 * page release code relies on it.
		 */
		ClearPageLRU(page);
		ret = 0;
	}

	return ret;
}

/*
 * zone->lru_lock is heavily contended.  Some of the functions that
 * shrink the lists perform better by taking out a batch of pages
 * and working on them outside the LRU lock.
 *
 * For pagecache intensive workloads, this function is the hottest
 * spot in the kernel (apart from copy_*_user functions).
 *
 * Appropriate locks must be held before calling this function.
 *
 * @nr_to_scan:	The number of pages to look through on the list.
 * @src:	The LRU list to pull pages off.
 * @dst:	The temp list to put pages on to.
 * @scanned:	The number of pages that were scanned.
 * @order:	The caller's attempted allocation order
 * @mode:	One of the LRU isolation modes
 *
 * returns how many pages were moved onto *@dst.
 */
static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
		struct list_head *src, struct list_head *dst,
		unsigned long *scanned, int order, int mode)
{
	unsigned long nr_taken = 0;
	unsigned long scan;

	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
		struct page *page;
		unsigned long pfn;
		unsigned long end_pfn;
		unsigned long page_pfn;
		int zone_id;

		page = lru_to_page(src);
		prefetchw_prev_lru_page(page, src, flags);

		VM_BUG_ON(!PageLRU(page));

		switch (__isolate_lru_page(page, mode)) {
		case 0:
			list_move(&page->lru, dst);
			nr_taken++;
			break;

		case -EBUSY:
			/* else it is being freed elsewhere */
			list_move(&page->lru, src);
			continue;

		default:
			BUG();
		}

		if (!order)
			continue;

		/*
		 * Attempt to take all pages in the order aligned region
		 * surrounding the tag page.  Only take those pages of
		 * the same active state as that tag page.  We may safely
		 * round the target page pfn down to the requested order
		 * as the mem_map is guarenteed valid out to MAX_ORDER,
		 * where that page is in a different zone we will detect
		 * it from its zone id and abort this block scan.
		 */
		zone_id = page_zone_id(page);
		page_pfn = page_to_pfn(page);
		pfn = page_pfn & ~((1 << order) - 1);
		end_pfn = pfn + (1 << order);
		for (; pfn < end_pfn; pfn++) {
			struct page *cursor_page;

			/* The target page is in the block, ignore it. */
			if (unlikely(pfn == page_pfn))
				continue;

			/* Avoid holes within the zone. */
			if (unlikely(!pfn_valid_within(pfn)))
				break;

			cursor_page = pfn_to_page(pfn);
			/* Check that we have not crossed a zone boundary. */
			if (unlikely(page_zone_id(cursor_page) != zone_id))
				continue;
			switch (__isolate_lru_page(cursor_page, mode)) {
			case 0:
				list_move(&cursor_page->lru, dst);
				nr_taken++;
				scan++;
				break;

			case -EBUSY:
				/* else it is being freed elsewhere */
				list_move(&cursor_page->lru, src);
			default:
				break;
			}
		}
	}

	*scanned = scan;
	return nr_taken;
}

static unsigned long isolate_pages_global(unsigned long nr,
					struct list_head *dst,
					unsigned long *scanned, int order,
					int mode, struct zone *z,
					struct mem_cgroup *mem_cont,
					int active)
{
	if (active)
		return isolate_lru_pages(nr, &z->active_list, dst,
						scanned, order, mode);
	else
		return isolate_lru_pages(nr, &z->inactive_list, dst,
						scanned, order, mode);
}

/*
 * clear_active_flags() is a helper for shrink_active_list(), clearing
 * any active bits from the pages in the list.
 */
static unsigned long clear_active_flags(struct list_head *page_list)
{
	int nr_active = 0;
	struct page *page;

	list_for_each_entry(page, page_list, lru)
		if (PageActive(page)) {
			ClearPageActive(page);
			nr_active++;
		}

	return nr_active;
}

/*
 * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
 * of reclaimed pages
 */
static unsigned long shrink_inactive_list(unsigned long max_scan,
				struct zone *zone, struct scan_control *sc)
{
	LIST_HEAD(page_list);
	struct pagevec pvec;
	unsigned long nr_scanned = 0;
	unsigned long nr_reclaimed = 0;

	pagevec_init(&pvec, 1);

	lru_add_drain();
	spin_lock_irq(&zone->lru_lock);
	do {
		struct page *page;
		unsigned long nr_taken;
		unsigned long nr_scan;
		unsigned long nr_freed;
		unsigned long nr_active;

		nr_taken = sc->isolate_pages(sc->swap_cluster_max,
			     &page_list, &nr_scan, sc->order,
			     (sc->order > PAGE_ALLOC_COSTLY_ORDER)?
					     ISOLATE_BOTH : ISOLATE_INACTIVE,
				zone, sc->mem_cgroup, 0);
		nr_active = clear_active_flags(&page_list);
		__count_vm_events(PGDEACTIVATE, nr_active);

		__mod_zone_page_state(zone, NR_ACTIVE, -nr_active);
		__mod_zone_page_state(zone, NR_INACTIVE,
						-(nr_taken - nr_active));
		if (scan_global_lru(sc))
			zone->pages_scanned += nr_scan;
		spin_unlock_irq(&zone->lru_lock);

		nr_scanned += nr_scan;
		nr_freed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);

		/*
		 * If we are direct reclaiming for contiguous pages and we do
		 * not reclaim everything in the list, try again and wait
		 * for IO to complete. This will stall high-order allocations
		 * but that should be acceptable to the caller
		 */
		if (nr_freed < nr_taken && !current_is_kswapd() &&
					sc->order > PAGE_ALLOC_COSTLY_ORDER) {
			congestion_wait(WRITE, HZ/10);

			/*
			 * The attempt at page out may have made some
			 * of the pages active, mark them inactive again.
			 */
			nr_active = clear_active_flags(&page_list);
			count_vm_events(PGDEACTIVATE, nr_active);

			nr_freed += shrink_page_list(&page_list, sc,
							PAGEOUT_IO_SYNC);
		}

		nr_reclaimed += nr_freed;
		local_irq_disable();
		if (current_is_kswapd()) {
			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
			__count_vm_events(KSWAPD_STEAL, nr_freed);
		} else if (scan_global_lru(sc))
			__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);

		__count_zone_vm_events(PGSTEAL, zone, nr_freed);

		if (nr_taken == 0)
			goto done;

		spin_lock(&zone->lru_lock);
		/*
		 * Put back any unfreeable pages.
		 */
		while (!list_empty(&page_list)) {
			page = lru_to_page(&page_list);
			VM_BUG_ON(PageLRU(page));
			SetPageLRU(page);
			list_del(&page->lru);
			if (PageActive(page))
				add_page_to_active_list(zone, page);
			else
				add_page_to_inactive_list(zone, page);
			if (!pagevec_add(&pvec, page)) {
				spin_unlock_irq(&zone->lru_lock);
				__pagevec_release(&pvec);
				spin_lock_irq(&zone->lru_lock);
			}
		}
  	} while (nr_scanned < max_scan);
	spin_unlock(&zone->lru_lock);
done:
	local_irq_enable();
	pagevec_release(&pvec);
	return nr_reclaimed;
}

/*
 * We are about to scan this zone at a certain priority level.  If that priority
 * level is smaller (ie: more urgent) than the previous priority, then note
 * that priority level within the zone.  This is done so that when the next
 * process comes in to scan this zone, it will immediately start out at this
 * priority level rather than having to build up its own scanning priority.
 * Here, this priority affects only the reclaim-mapped threshold.
 */
static inline void note_zone_scanning_priority(struct zone *zone, int priority)
{
	if (priority < zone->prev_priority)
		zone->prev_priority = priority;
}

static inline int zone_is_near_oom(struct zone *zone)
{
	return zone->pages_scanned >= (zone_page_state(zone, NR_ACTIVE)
				+ zone_page_state(zone, NR_INACTIVE))*3;
}

/*
 * Determine we should try to reclaim mapped pages.
 * This is called only when sc->mem_cgroup is NULL.
 */
static int calc_reclaim_mapped(struct scan_control *sc, struct zone *zone,
				int priority)
{
	long mapped_ratio;
	long distress;
	long swap_tendency;
	long imbalance;
	int reclaim_mapped = 0;
	int prev_priority;

	if (scan_global_lru(sc) && zone_is_near_oom(zone))
		return 1;
	/*
	 * `distress' is a measure of how much trouble we're having
	 * reclaiming pages.  0 -> no problems.  100 -> great trouble.
	 */
	if (scan_global_lru(sc))
		prev_priority = zone->prev_priority;
	else
		prev_priority = mem_cgroup_get_reclaim_priority(sc->mem_cgroup);

	distress = 100 >> min(prev_priority, priority);

	/*
	 * The point of this algorithm is to decide when to start
	 * reclaiming mapped memory instead of just pagecache.  Work out
	 * how much memory
	 * is mapped.
	 */
	if (scan_global_lru(sc))
		mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
				global_page_state(NR_ANON_PAGES)) * 100) /
					vm_total_pages;
	else
		mapped_ratio = mem_cgroup_calc_mapped_ratio(sc->mem_cgroup);

	/*
	 * Now decide how much we really want to unmap some pages.  The
	 * mapped ratio is downgraded - just because there's a lot of
	 * mapped memory doesn't necessarily mean that page reclaim
	 * isn't succeeding.
	 *
	 * The distress ratio is important - we don't want to start
	 * going oom.
	 *
	 * A 100% value of vm_swappiness overrides this algorithm
	 * altogether.
	 */
	swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;

	/*
	 * If there's huge imbalance between active and inactive
	 * (think active 100 times larger than inactive) we should
	 * become more permissive, or the system will take too much
	 * cpu before it start swapping during memory pressure.
	 * Distress is about avoiding early-oom, this is about
	 * making swappiness graceful despite setting it to low
	 * values.
	 *
	 * Avoid div by zero with nr_inactive+1, and max resulting
	 * value is vm_total_pages.
	 */
	if (scan_global_lru(sc)) {
		imbalance  = zone_page_state(zone, NR_ACTIVE);
		imbalance /= zone_page_state(zone, NR_INACTIVE) + 1;
	} else
		imbalance = mem_cgroup_reclaim_imbalance(sc->mem_cgroup);

	/*
	 * Reduce the effect of imbalance if swappiness is low,
	 * this means for a swappiness very low, the imbalance
	 * must be much higher than 100 for this logic to make
	 * the difference.
	 *
	 * Max temporary value is vm_total_pages*100.
	 */
	imbalance *= (vm_swappiness + 1);
	imbalance /= 100;

	/*
	 * If not much of the ram is mapped, makes the imbalance
	 * less relevant, it's high priority we refill the inactive
	 * list with mapped pages only in presence of high ratio of
	 * mapped pages.
	 *
	 * Max temporary value is vm_total_pages*100.
	 */
	imbalance *= mapped_ratio;
	imbalance /= 100;

	/* apply imbalance feedback to swap_tendency */
	swap_tendency += imbalance;

	/*
	 * Now use this metric to decide whether to start moving mapped
	 * memory onto the inactive list.
	 */
	if (swap_tendency >= 100)
		reclaim_mapped = 1;

	return reclaim_mapped;
}

/*
 * This moves pages from the active list to the inactive list.
 *
 * We move them the other way if the page is referenced by one or more
 * processes, from rmap.
 *
 * If the pages are mostly unmapped, the processing is fast and it is
 * appropriate to hold zone->lru_lock across the whole operation.  But if
 * the pages are mapped, the processing is slow (page_referenced()) so we
 * should drop zone->lru_lock around each page.  It's impossible to balance
 * this, so instead we remove the pages from the LRU while processing them.
 * It is safe to rely on PG_active against the non-LRU pages in here because
 * nobody will play with that bit on a non-LRU page.
 *
 * The downside is that we have to touch page->_count against each page.
 * But we had to alter page->flags anyway.
 */


static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
				struct scan_control *sc, int priority)
{
	unsigned long pgmoved;
	int pgdeactivate = 0;
	unsigned long pgscanned;
	LIST_HEAD(l_hold);	/* The pages which were snipped off */
	LIST_HEAD(l_inactive);	/* Pages to go onto the inactive_list */
	LIST_HEAD(l_active);	/* Pages to go onto the active_list */
	struct page *page;
	struct pagevec pvec;
	int reclaim_mapped = 0;

	if (sc->may_swap)
		reclaim_mapped = calc_reclaim_mapped(sc, zone, priority);

	lru_add_drain();
	spin_lock_irq(&zone->lru_lock);
	pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
					ISOLATE_ACTIVE, zone,
					sc->mem_cgroup, 1);
	/*
	 * zone->pages_scanned is used for detect zone's oom
	 * mem_cgroup remembers nr_scan by itself.
	 */
	if (scan_global_lru(sc))
		zone->pages_scanned += pgscanned;

	__mod_zone_page_state(zone, NR_ACTIVE, -pgmoved);
	spin_unlock_irq(&zone->lru_lock);

	while (!list_empty(&l_hold)) {
		cond_resched();
		page = lru_to_page(&l_hold);
		list_del(&page->lru);
		if (page_mapped(page)) {
			if (!reclaim_mapped ||
			    (total_swap_pages == 0 && PageAnon(page)) ||
			    page_referenced(page, 0, sc->mem_cgroup)) {
				list_add(&page->lru, &l_active);
				continue;
			}
		}
		list_add(&page->lru, &l_inactive);
	}

	pagevec_init(&pvec, 1);
	pgmoved = 0;
	spin_lock_irq(&zone->lru_lock);
	while (!list_empty(&l_inactive)) {
		page = lru_to_page(&l_inactive);
		prefetchw_prev_lru_page(page, &l_inactive, flags);
		VM_BUG_ON(PageLRU(page));
		SetPageLRU(page);
		VM_BUG_ON(!PageActive(page));
		ClearPageActive(page);

		list_move(&page->lru, &zone->inactive_list);
		mem_cgroup_move_lists(page, false);
		pgmoved++;
		if (!pagevec_add(&pvec, page)) {
			__mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
			spin_unlock_irq(&zone->lru_lock);
			pgdeactivate += pgmoved;
			pgmoved = 0;
			if (buffer_heads_over_limit)
				pagevec_strip(&pvec);
			__pagevec_release(&pvec);
			spin_lock_irq(&zone->lru_lock);
		}
	}
	__mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
	pgdeactivate += pgmoved;
	if (buffer_heads_over_limit) {
		spin_unlock_irq(&zone->lru_lock);
		pagevec_strip(&pvec);
		spin_lock_irq(&zone->lru_lock);
	}

	pgmoved = 0;
	while (!list_empty(&l_active)) {
		page = lru_to_page(&l_active);
		prefetchw_prev_lru_page(page, &l_active, flags);
		VM_BUG_ON(PageLRU(page));
		SetPageLRU(page);
		VM_BUG_ON(!PageActive(page));

		list_move(&page->lru, &zone->active_list);
		mem_cgroup_move_lists(page, true);
		pgmoved++;
		if (!pagevec_add(&pvec, page)) {
			__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
			pgmoved = 0;
			spin_unlock_irq(&zone->lru_lock);
			__pagevec_release(&pvec);
			spin_lock_irq(&zone->lru_lock);
		}
	}
	__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);

	__count_zone_vm_events(PGREFILL, zone, pgscanned);
	__count_vm_events(PGDEACTIVATE, pgdeactivate);
	spin_unlock_irq(&zone->lru_lock);

	pagevec_release(&pvec);
}

/*
 * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
 */
static unsigned long shrink_zone(int priority, struct zone *zone,
				struct scan_control *sc)
{
	unsigned long nr_active;
	unsigned long nr_inactive;
	unsigned long nr_to_scan;
	unsigned long nr_reclaimed = 0;

	if (scan_global_lru(sc)) {
		/*
		 * Add one to nr_to_scan just to make sure that the kernel
		 * will slowly sift through the active list.
		 */
		zone->nr_scan_active +=
			(zone_page_state(zone, NR_ACTIVE) >> priority) + 1;
		nr_active = zone->nr_scan_active;
		zone->nr_scan_inactive +=
			(zone_page_state(zone, NR_INACTIVE) >> priority) + 1;
		nr_inactive = zone->nr_scan_inactive;
		if (nr_inactive >= sc->swap_cluster_max)
			zone->nr_scan_inactive = 0;
		else
			nr_inactive = 0;

		if (nr_active >= sc->swap_cluster_max)
			zone->nr_scan_active = 0;
		else
			nr_active = 0;
	} else {
		/*
		 * This reclaim occurs not because zone memory shortage but
		 * because memory controller hits its limit.
		 * Then, don't modify zone reclaim related data.
		 */
		nr_active = mem_cgroup_calc_reclaim_active(sc->mem_cgroup,
					zone, priority);

		nr_inactive = mem_cgroup_calc_reclaim_inactive(sc->mem_cgroup,
					zone, priority);
	}


	while (nr_active || nr_inactive) {
		if (nr_active) {
			nr_to_scan = min(nr_active,
					(unsigned long)sc->swap_cluster_max);
			nr_active -= nr_to_scan;
			shrink_active_list(nr_to_scan, zone, sc, priority);
		}

		if (nr_inactive) {
			nr_to_scan = min(nr_inactive,
					(unsigned long)sc->swap_cluster_max);
			nr_inactive -= nr_to_scan;
			nr_reclaimed += shrink_inactive_list(nr_to_scan, zone,
								sc);
		}
	}

	throttle_vm_writeout(sc->gfp_mask);
	return nr_reclaimed;
}

/*
 * This is the direct reclaim path, for page-allocating processes.  We only
 * try to reclaim pages from zones which will satisfy the caller's allocation
 * request.
 *
 * We reclaim from a zone even if that zone is over pages_high.  Because:
 * a) The caller may be trying to free *extra* pages to satisfy a higher-order
 *    allocation or
 * b) The zones may be over pages_high but they must go *over* pages_high to
 *    satisfy the `incremental min' zone defense algorithm.
 *
 * Returns the number of reclaimed pages.
 *
 * If a zone is deemed to be full of pinned pages then just give it a light
 * scan then give up on it.
 */
static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
					struct scan_control *sc)
{
	unsigned long nr_reclaimed = 0;
	struct zone **zones = zonelist->zones;
	int i;


	sc->all_unreclaimable = 1;
	for (i = 0; zones[i] != NULL; i++) {
		struct zone *zone = zones[i];

		if (!populated_zone(zone))
			continue;
		/*
		 * Take care memory controller reclaiming has small influence
		 * to global LRU.
		 */
		if (scan_global_lru(sc)) {
			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
				continue;
			note_zone_scanning_priority(zone, priority);

			if (zone_is_all_unreclaimable(zone) &&
						priority != DEF_PRIORITY)
				continue;	/* Let kswapd poll it */
			sc->all_unreclaimable = 0;
		} else {
			/*
			 * Ignore cpuset limitation here. We just want to reduce
			 * # of used pages by us regardless of memory shortage.
			 */
			sc->all_unreclaimable = 0;
			mem_cgroup_note_reclaim_priority(sc->mem_cgroup,
							priority);
		}

		nr_reclaimed += shrink_zone(priority, zone, sc);
	}

	return nr_reclaimed;
}
 
/*
 * This is the main entry point to direct page reclaim.
 *
 * If a full scan of the inactive list fails to free enough memory then we
 * are "out of memory" and something needs to be killed.
 *
 * If the caller is !__GFP_FS then the probability of a failure is reasonably
 * high - the zone may be full of dirty or under-writeback pages, which this
 * caller can't do much about.  We kick pdflush and take explicit naps in the
 * hope that some of these pages can be written.  But if the allocating task
 * holds filesystem locks which prevent writeout this might not work, and the
 * allocation attempt will fail.
 */
static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
					gfp_t gfp_mask, struct scan_control *sc)
{
	int priority;
	int ret = 0;
	unsigned long total_scanned = 0;
	unsigned long nr_reclaimed = 0;
	struct reclaim_state *reclaim_state = current->reclaim_state;
	unsigned long lru_pages = 0;
	struct zone **zones = zonelist->zones;
	int i;

	if (scan_global_lru(sc))
		count_vm_event(ALLOCSTALL);
	/*
	 * mem_cgroup will not do shrink_slab.
	 */
	if (scan_global_lru(sc)) {
		for (i = 0; zones[i] != NULL; i++) {
			struct zone *zone = zones[i];

			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
				continue;

			lru_pages += zone_page_state(zone, NR_ACTIVE)
					+ zone_page_state(zone, NR_INACTIVE);
		}
	}

	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
		sc->nr_scanned = 0;
		if (!priority)
			disable_swap_token();
		nr_reclaimed += shrink_zones(priority, zonelist, sc);
		/*
		 * Don't shrink slabs when reclaiming memory from
		 * over limit cgroups
		 */
		if (scan_global_lru(sc)) {


context:
space:
mode: