litmus-rt.git - The LITMUS^RT kernel.

index : litmus-rt.git

The LITMUS^RT kernel.

Bjoern Brandenburg

about summary refs log tree commit diff stats

path: root/tools/perf/scripts/python/check-perf-trace.py

diff options

Diffstat (limited to 'tools/perf/scripts/python/check-perf-trace.py')

0 files changed, 0 insertions, 0 deletions

gt; 2008-02-07 03:14:24 -0500 committer Linus Torvalds <torvalds@woody.linux-foundation.org> 2008-02-07 11:42:20 -0500 memory cgroup enhancements: add status accounting function for memory cgroup' href='/cgit/cgit.cgi/litmus-rt.git/commit/mm/memcontrol.c?h=wip-shared-lib&id=d52aa412d43827033a8e2ce4415ef6e8f8d53635'>d52aa412d438

6
7
8

28
29

32
33
34

41
42

65
66

83
84

99
100

102
103
104

105
106

107
108

128
129
130

143
144

154
155
156

158
159

167
168

171
172

173
174

175
176
177

181
182
183

184
185
186

188
189

190
191
192

194
195

207
208
209

210
211
212

221
222

224
225

229
230

232
233

234
235
236

244
245
246

263
264

332
333
334

341
342

344
345

346
347

350
351

372
373

376
377

380
381

386
387

392
393

416
417

432
433
434

436
437
438

439
440

485
486

495
496

498
499
500

501
502

598
599
600

607
608

611
612

613
614

635
636

648
649
650

656
657

665
666
667

688
689

691
692

693
694
695

709
710
711

713
714

718
719

727
728

781
782

785
786

789
790

816
817
818

821
822

835
836

837
838
839

840
841
842

852
853
854

857
858
859

860
861

877
878

879
880

881
882

890
891

892
893

935
936
937

943
944

1001
1002
1003

1004
1005

1021
1022
1023

1031
1032

1036
1037

1050
1051
1052

1053
1054

1064
1065
1066

1067
1068
1069

1093
1094
1095

1097
1098

1099
1100

1104
1105

1119
1120

1121
1122

1124
1125
1126

1129
1130

1139
1140

1152
1153

1155
1156

1170
1171

1191
1192

1219
1220

1244
1245
1246

1247
1248
1249

1272
1273

1297
1298

1303
1304

1340
1341
1342

1345
1346
1347

1349
1350

1351
1352

1365
1366
1367

1383
1384

1408
1409

1412
1413

1418
1419

1420
1421
1422

1423
1424

1430
1431

1437
1438

1465
1466
1467

1484
1485

1493
1494
1495

1498
1499
1500

1509
1510

1521
1522

1530
1531

1547
1548

1555
1556

1557
1558

1598
1599

1607
1608

1612
1613

1619
1620

1639
1640

1655
1656
1657

1666
1667
1668

1672
1673

1674
1675
1676

1685
1686

1691
1692

1694
1695
1696

1710
1711

1712
1713

1714
1715
1716

1717
1718

1728
1729

1732
1733
1734

1735
1736

1743
1744

1815
1816

1820
1821
1822

1823
1824
1825

1826
1827
1828

1829
1830
1831

1833
1834

1841
1842

1872
1873

1875
1876

1877
1878
1879

1885
1886

1891
1892

1894
1895

1902
1903

1904
1905

1906
1907

1920
1921

1922
1923

1934
1935
1936

1941
1942

1951
1952

1981
1982
1983

2004
2005
2006

2007
2008

2009
2010

2018
2019

2020
2021
2022

2024
2025

2029
2030

2034
2035
2036

2041
2042
2043

2066
2067

2109
2110
2111

2123
2124
2125

2126
2127

2129
2130

2131
2132
2133

2134
2135

2137
2138
2139

2151
2152
2153

2156
2157

2160
2161

2163
2164
2165

2174
2175
2176

2179
2180

2181
2182
2183

2197
2198

2200
2201
2202

2203
2204

2215
2216
2217

2228
2229

2233
2234
2235

2237
2238
2239

2246
2247

2249
2250
2251

2266
2267

2273
2274

2280
2281

2282
2283
2284

2306
2307

2315
2316

2319
2320

2326
2327

/* memcontrol.c - Memory Controller
 *
 * Copyright IBM Corporation, 2007
 * Author Balbir Singh <balbir@linux.vnet.ibm.com>
 *
 * Copyright 2007 OpenVZ SWsoft Inc
 * Author: Pavel Emelianov <xemul@openvz.org>
 *
 * 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.
 */

#include <linux/res_counter.h>
#include <linux/memcontrol.h>
#include <linux/cgroup.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/smp.h>
#include <linux/page-flags.h>
#include <linux/backing-dev.h>
#include <linux/bit_spinlock.h>
#include <linux/rcupdate.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/vmalloc.h>
#include <linux/mm_inline.h>
#include <linux/page_cgroup.h>
#include "internal.h"

#include <asm/uaccess.h>

struct cgroup_subsys mem_cgroup_subsys __read_mostly;
#define MEM_CGROUP_RECLAIM_RETRIES	5

#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */
int do_swap_account __read_mostly;
static int really_do_swap_account __initdata = 1; /* for remember boot option*/
#else
#define do_swap_account		(0)
#endif

static DEFINE_MUTEX(memcg_tasklist);	/* can be hold under cgroup_mutex */

/*
 * Statistics for memory cgroup.
 */
enum mem_cgroup_stat_index {
	/*
	 * For MEM_CONTAINER_TYPE_ALL, usage = pagecache + rss.
	 */
	MEM_CGROUP_STAT_CACHE, 	   /* # of pages charged as cache */
	MEM_CGROUP_STAT_RSS,	   /* # of pages charged as rss */
	MEM_CGROUP_STAT_PGPGIN_COUNT,	/* # of pages paged in */
	MEM_CGROUP_STAT_PGPGOUT_COUNT,	/* # of pages paged out */

	MEM_CGROUP_STAT_NSTATS,
};

struct mem_cgroup_stat_cpu {
	s64 count[MEM_CGROUP_STAT_NSTATS];
} ____cacheline_aligned_in_smp;

struct mem_cgroup_stat {
	struct mem_cgroup_stat_cpu cpustat[0];
};

/*
 * For accounting under irq disable, no need for increment preempt count.
 */
static inline void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat_cpu *stat,
		enum mem_cgroup_stat_index idx, int val)
{
	stat->count[idx] += val;
}

static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
		enum mem_cgroup_stat_index idx)
{
	int cpu;
	s64 ret = 0;
	for_each_possible_cpu(cpu)
		ret += stat->cpustat[cpu].count[idx];
	return ret;
}

/*
 * per-zone information in memory controller.
 */
struct mem_cgroup_per_zone {
	/*
	 * spin_lock to protect the per cgroup LRU
	 */
	struct list_head	lists[NR_LRU_LISTS];
	unsigned long		count[NR_LRU_LISTS];

	struct zone_reclaim_stat reclaim_stat;
};
/* Macro for accessing counter */
#define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])

struct mem_cgroup_per_node {
	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
};

struct mem_cgroup_lru_info {
	struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES];
};

/*
 * The memory controller data structure. The memory controller controls both
 * page cache and RSS per cgroup. We would eventually like to provide
 * statistics based on the statistics developed by Rik Van Riel for clock-pro,
 * to help the administrator determine what knobs to tune.
 *
 * TODO: Add a water mark for the memory controller. Reclaim will begin when
 * we hit the water mark. May be even add a low water mark, such that
 * no reclaim occurs from a cgroup at it's low water mark, this is
 * a feature that will be implemented much later in the future.
 */
struct mem_cgroup {
	struct cgroup_subsys_state css;
	/*
	 * the counter to account for memory usage
	 */
	struct res_counter res;
	/*
	 * the counter to account for mem+swap usage.
	 */
	struct res_counter memsw;
	/*
	 * Per cgroup active and inactive list, similar to the
	 * per zone LRU lists.
	 */
	struct mem_cgroup_lru_info info;

	/*
	  protect against reclaim related member.
	*/
	spinlock_t reclaim_param_lock;

	int	prev_priority;	/* for recording reclaim priority */

	/*
	 * While reclaiming in a hiearchy, we cache the last child we
	 * reclaimed from. Protected by hierarchy_mutex
	 */
	struct mem_cgroup *last_scanned_child;
	/*
	 * Should the accounting and control be hierarchical, per subtree?
	 */
	bool use_hierarchy;
	unsigned long	last_oom_jiffies;
	atomic_t	refcnt;

	unsigned int	swappiness;

	/*
	 * statistics. This must be placed at the end of memcg.
	 */
	struct mem_cgroup_stat stat;
};

enum charge_type {
	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
	MEM_CGROUP_CHARGE_TYPE_MAPPED,
	MEM_CGROUP_CHARGE_TYPE_SHMEM,	/* used by page migration of shmem */
	MEM_CGROUP_CHARGE_TYPE_FORCE,	/* used by force_empty */
	MEM_CGROUP_CHARGE_TYPE_SWAPOUT,	/* for accounting swapcache */
	NR_CHARGE_TYPE,
};

/* only for here (for easy reading.) */
#define PCGF_CACHE	(1UL << PCG_CACHE)
#define PCGF_USED	(1UL << PCG_USED)
#define PCGF_LOCK	(1UL << PCG_LOCK)
static const unsigned long
pcg_default_flags[NR_CHARGE_TYPE] = {
	PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* File Cache */
	PCGF_USED | PCGF_LOCK, /* Anon */
	PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */
	0, /* FORCE */
};

/* for encoding cft->private value on file */
#define _MEM			(0)
#define _MEMSWAP		(1)
#define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
#define MEMFILE_TYPE(val)	(((val) >> 16) & 0xffff)
#define MEMFILE_ATTR(val)	((val) & 0xffff)

static void mem_cgroup_get(struct mem_cgroup *mem);
static void mem_cgroup_put(struct mem_cgroup *mem);
static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);

static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
					 struct page_cgroup *pc,
					 bool charge)
{
	int val = (charge)? 1 : -1;
	struct mem_cgroup_stat *stat = &mem->stat;
	struct mem_cgroup_stat_cpu *cpustat;
	int cpu = get_cpu();

	cpustat = &stat->cpustat[cpu];
	if (PageCgroupCache(pc))
		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_CACHE, val);
	else
		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_RSS, val);

	if (charge)
		__mem_cgroup_stat_add_safe(cpustat,
				MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
	else
		__mem_cgroup_stat_add_safe(cpustat,
				MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
	put_cpu();
}

static struct mem_cgroup_per_zone *
mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
{
	return &mem->info.nodeinfo[nid]->zoneinfo[zid];
}

static struct mem_cgroup_per_zone *
page_cgroup_zoneinfo(struct page_cgroup *pc)
{
	struct mem_cgroup *mem = pc->mem_cgroup;
	int nid = page_cgroup_nid(pc);
	int zid = page_cgroup_zid(pc);

	if (!mem)
		return NULL;

	return mem_cgroup_zoneinfo(mem, nid, zid);
}

static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
					enum lru_list idx)
{
	int nid, zid;
	struct mem_cgroup_per_zone *mz;
	u64 total = 0;

	for_each_online_node(nid)
		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
			mz = mem_cgroup_zoneinfo(mem, nid, zid);
			total += MEM_CGROUP_ZSTAT(mz, idx);
		}
	return total;
}

static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
{
	return container_of(cgroup_subsys_state(cont,
				mem_cgroup_subsys_id), struct mem_cgroup,
				css);
}

struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
{
	/*
	 * mm_update_next_owner() may clear mm->owner to NULL
	 * if it races with swapoff, page migration, etc.
	 * So this can be called with p == NULL.
	 */
	if (unlikely(!p))
		return NULL;

	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
				struct mem_cgroup, css);
}

static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
{
	struct mem_cgroup *mem = NULL;
	/*
	 * Because we have no locks, mm->owner's may be being moved to other
	 * cgroup. We use css_tryget() here even if this looks
	 * pessimistic (rather than adding locks here).
	 */
	rcu_read_lock();
	do {
		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
		if (unlikely(!mem))
			break;
	} while (!css_tryget(&mem->css));
	rcu_read_unlock();
	return mem;
}

static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
{
	if (!mem)
		return true;
	return css_is_removed(&mem->css);
}

/*
 * Following LRU functions are allowed to be used without PCG_LOCK.
 * Operations are called by routine of global LRU independently from memcg.
 * What we have to take care of here is validness of pc->mem_cgroup.
 *
 * Changes to pc->mem_cgroup happens when
 * 1. charge
 * 2. moving account
 * In typical case, "charge" is done before add-to-lru. Exception is SwapCache.
 * It is added to LRU before charge.
 * If PCG_USED bit is not set, page_cgroup is not added to this private LRU.
 * When moving account, the page is not on LRU. It's isolated.
 */

void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru)
{
	struct page_cgroup *pc;
	struct mem_cgroup *mem;
	struct mem_cgroup_per_zone *mz;

	if (mem_cgroup_disabled())
		return;


context:
space:
mode: