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

diff options

author	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>	2009-01-07 21:07:56 -0500
committer	Linus Torvalds <torvalds@linux-foundation.org>	2009-01-08 11:31:05 -0500
commit	d13d144309d2e5a3e6ad978b16c1d0226ddc9231 (patch)
tree	37c19902b527823956db969d9428737081b2a94d /net/tipc
parent	c1e862c1f5ad34771b6d0a528cf681e0dcad7c86 (diff)

memcg: handle swap caches

SwapCache support for memory resource controller (memcg) Before mem+swap controller, memcg itself should handle SwapCache in proper way. This is cut-out from it. In current memcg, SwapCache is just leaked and the user can create tons of SwapCache. This is a leak of account and should be handled. SwapCache accounting is done as following. charge (anon) - charged when it's mapped. (because of readahead, charge at add_to_swap_cache() is not sane) uncharge (anon) - uncharged when it's dropped from swapcache and fully unmapped. means it's not uncharged at unmap. Note: delete from swap cache at swap-in is done after rmap information is established. charge (shmem) - charged at swap-in. this prevents charge at add_to_page_cache(). uncharge (shmem) - uncharged when it's dropped from swapcache and not on shmem's radix-tree. at migration, check against 'old page' is modified to handle shmem. Comparing to the old version discussed (and caused troubles), we have advantages of - PCG_USED bit. - simple migrating handling. So, situation is much easier than several months ago, maybe. [hugh@veritas.com: memcg: handle swap caches build fix] Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Tested-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Balbir Singh <balbir@in.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Diffstat (limited to 'net/tipc')

0 files changed, 0 insertions, 0 deletions

#ifndef _LINUX_CGROUP_H #define _LINUX_CGROUP_H /* * cgroup interface * * Copyright (C) 2003 BULL SA * Copyright (C) 2004-2006 Silicon Graphics, Inc. * */ #include <linux/sched.h> #include <linux/cpumask.h> #include <linux/nodemask.h> #include <linux/rcupdate.h> #include <linux/cgroupstats.h> #include <linux/prio_heap.h> #include <linux/rwsem.h> #include <linux/idr.h> #include <linux/workqueue.h> #ifdef CONFIG_CGROUPS struct cgroupfs_root; struct cgroup_subsys; struct inode; struct cgroup; struct css_id; extern int cgroup_init_early(void); extern int cgroup_init(void); extern void cgroup_lock(void); extern int cgroup_lock_is_held(void); extern bool cgroup_lock_live_group(struct cgroup *cgrp); extern void cgroup_unlock(void); extern void cgroup_fork(struct task_struct *p); extern void cgroup_fork_callbacks(struct task_struct *p); extern void cgroup_post_fork(struct task_struct *p); extern void cgroup_exit(struct task_struct *p, int run_callbacks); extern int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry); extern int cgroup_load_subsys(struct cgroup_subsys *ss); extern void cgroup_unload_subsys(struct cgroup_subsys *ss); extern const struct file_operations proc_cgroup_operations; /* Define the enumeration of all builtin cgroup subsystems */ #define SUBSYS(_x) _x ## _subsys_id, enum cgroup_subsys_id { #include <linux/cgroup_subsys.h> CGROUP_BUILTIN_SUBSYS_COUNT }; #undef SUBSYS /* * This define indicates the maximum number of subsystems that can be loaded * at once. We limit to this many since cgroupfs_root has subsys_bits to keep * track of all of them. */ #define CGROUP_SUBSYS_COUNT (BITS_PER_BYTE*sizeof(unsigned long)) /* Per-subsystem/per-cgroup state maintained by the system. */ struct cgroup_subsys_state { /* * The cgroup that this subsystem is attached to. Useful * for subsystems that want to know about the cgroup * hierarchy structure */ struct cgroup *cgroup; /* * State maintained by the cgroup system to allow subsystems * to be "busy". Should be accessed via css_get(), * css_tryget() and and css_put(). */ atomic_t refcnt; unsigned long flags; /* ID for this css, if possible */ struct css_id __rcu *id; /* Used to put @cgroup->dentry on the last css_put() */ struct work_struct dput_work; }; /* bits in struct cgroup_subsys_state flags field */ enum { CSS_ROOT, /* This CSS is the root of the subsystem */ CSS_REMOVED, /* This CSS is dead */ CSS_CLEAR_CSS_REFS, /* @ss->__DEPRECATED_clear_css_refs */ }; /* Caller must verify that the css is not for root cgroup */ static inline void __css_get(struct cgroup_subsys_state *css, int count) { atomic_add(count, &css->refcnt); } /* * Call css_get() to hold a reference on the css; it can be used * for a reference obtained via: * - an existing ref-counted reference to the css * - task->cgroups for a locked task */ static inline void css_get(struct cgroup_subsys_state *css) { /* We don't need to reference count the root state */ if (!test_bit(CSS_ROOT, &css->flags)) __css_get(css, 1); } static inline bool css_is_removed(struct cgroup_subsys_state *css) { return test_bit(CSS_REMOVED, &css->flags); } /* * Call css_tryget() to take a reference on a css if your existing * (known-valid) reference isn't already ref-counted. Returns false if * the css has been destroyed. */ extern bool __css_tryget(struct cgroup_subsys_state *css); static inline bool css_tryget(struct cgroup_subsys_state *css) { if (test_bit(CSS_ROOT, &css->flags)) return true; return __css_tryget(css); } /* * css_put() should be called to release a reference taken by * css_get() or css_tryget() */ extern void __css_put(struct cgroup_subsys_state *css); static inline void css_put(struct cgroup_subsys_state *css) { if (!test_bit(CSS_ROOT, &css->flags)) __css_put(css); } /* bits in struct cgroup flags field */ enum { /* Control Group is dead */ CGRP_REMOVED, /* * Control Group has previously had a child cgroup or a task, * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set) */ CGRP_RELEASABLE, /* Control Group requires release notifications to userspace */ CGRP_NOTIFY_ON_RELEASE, /* * A thread in rmdir() is wating for this cgroup. */ CGRP_WAIT_ON_RMDIR, /* * Clone cgroup values when creating a new child cgroup */ CGRP_CLONE_CHILDREN, }; struct cgroup { unsigned long flags; /* "unsigned long" so bitops work */ /* * count users of this cgroup. >0 means busy, but doesn't * necessarily indicate the number of tasks in the cgroup */ atomic_t count; /* * We link our 'sibling' struct into our parent's 'children'. * Our children link their 'sibling' into our 'children'. */ struct list_head sibling; /* my parent's children */ struct list_head children; /* my children */ struct list_head files; /* my files */ struct cgroup *parent; /* my parent */ struct dentry __rcu *dentry; /* cgroup fs entry, RCU protected */ /* Private pointers for each registered subsystem */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; struct cgroupfs_root *root; struct cgroup *top_cgroup; /* * List of cg_cgroup_links pointing at css_sets with * tasks in this cgroup. Protected by css_set_lock */ struct list_head css_sets; struct list_head allcg_node; /* cgroupfs_root->allcg_list */ struct list_head cft_q_node; /* used during cftype add/rm */ /* * Linked list running through all cgroups that can * potentially be reaped by the release agent. Protected by * release_list_lock */ struct list_head release_list; /* * list of pidlists, up to two for each namespace (one for procs, one * for tasks); created on demand. */ struct list_head pidlists; struct mutex pidlist_mutex; /* For RCU-protected deletion */ struct rcu_head rcu_head; /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; }; /* * A css_set is a structure holding pointers to a set of * cgroup_subsys_state objects. This saves space in the task struct * object and speeds up fork()/exit(), since a single inc/dec and a * list_add()/del() can bump the reference count on the entire cgroup * set for a task. */ struct css_set { /* Reference count */ atomic_t refcount; /* * List running through all cgroup groups in the same hash * slot. Protected by css_set_lock */ struct hlist_node hlist; /* * List running through all tasks using this cgroup * group. Protected by css_set_lock */ struct list_head tasks; /* * List of cg_cgroup_link objects on link chains from * cgroups referenced from this css_set. Protected by * css_set_lock */ struct list_head cg_links; /* * Set of subsystem states, one for each subsystem. This array * is immutable after creation apart from the init_css_set * during subsystem registration (at boot time) and modular subsystem * loading/unloading. */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; /* For RCU-protected deletion */ struct rcu_head rcu_head; }; /* * cgroup_map_cb is an abstract callback API for reporting map-valued * control files */ struct cgroup_map_cb { int (*fill)(struct cgroup_map_cb *cb, const char *key, u64 value); void *state; }; /* * struct cftype: handler definitions for cgroup control files * * When reading/writing to a file: * - the cgroup to use is file->f_dentry->d_parent->d_fsdata * - the 'cftype' of the file is file->f_dentry->d_fsdata */ /* cftype->flags */ #define CFTYPE_ONLY_ON_ROOT (1U << 0) /* only create on root cg */ #define CFTYPE_NOT_ON_ROOT (1U << 1) /* don't create onp root cg */ #define MAX_CFTYPE_NAME 64 struct cftype { /* * By convention, the name should begin with the name of the * subsystem, followed by a period. Zero length string indicates * end of cftype array. */ char name[MAX_CFTYPE_NAME]; int private; /* * If not 0, file mode is set to this value, otherwise it will * be figured out automatically */ umode_t mode; /* * If non-zero, defines the maximum length of string that can * be passed to write_string; defaults to 64 */ size_t max_write_len; /* CFTYPE_* flags */ unsigned int flags; int (*open)(struct inode *inode, struct file *file); ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, struct file *file, char __user *buf, size_t nbytes, loff_t *ppos); /* * read_u64() is a shortcut for the common case of returning a * single integer. Use it in place of read() */ u64 (*read_u64)(struct cgroup *cgrp, struct cftype *cft); /* * read_s64() is a signed version of read_u64() */ s64 (*read_s64)(struct cgroup *cgrp, struct cftype *cft); /* * read_map() is used for defining a map of key/value * pairs. It should call cb->fill(cb, key, value) for each * entry. The key/value pairs (and their ordering) should not * change between reboots. */ int (*read_map)(struct cgroup *cont, struct cftype *cft, struct cgroup_map_cb *cb); /* * read_seq_string() is used for outputting a simple sequence * using seqfile. */ int (*read_seq_string)(struct cgroup *cont, struct cftype *cft, struct seq_file *m); ssize_t (*write)(struct cgroup *cgrp, struct cftype *cft, struct file *file, const char __user *buf, size_t nbytes, loff_t *ppos); /* * write_u64() is a shortcut for the common case of accepting * a single integer (as parsed by simple_strtoull) from * userspace. Use in place of write(); return 0 or error. */ int (*write_u64)(struct cgroup *cgrp, struct cftype *cft, u64 val); /* * write_s64() is a signed version of write_u64() */ int (*write_s64)(struct cgroup *cgrp, struct cftype *cft, s64 val); /* * write_string() is passed a nul-terminated kernelspace * buffer of maximum length determined by max_write_len. * Returns 0 or -ve error code. */ int (*write_string)(struct cgroup *cgrp, struct cftype *cft, const char *buffer); /* * trigger() callback can be used to get some kick from the * userspace, when the actual string written is not important * at all. The private field can be used to determine the * kick type for multiplexing. */ int (*trigger)(struct cgroup *cgrp, unsigned int event); int (*release)(struct inode *inode, struct file *file); /* * register_event() callback will be used to add new userspace * waiter for changes related to the cftype. Implement it if * you want to provide this functionality. Use eventfd_signal() * on eventfd to send notification to userspace. */ int (*register_event)(struct cgroup *cgrp, struct cftype *cft, struct eventfd_ctx *eventfd, const char *args); /* * unregister_event() callback will be called when userspace * closes the eventfd or on cgroup removing. * This callback must be implemented, if you want provide * notification functionality. */ void (*unregister_event)(struct cgroup *cgrp, struct cftype *cft, struct eventfd_ctx *eventfd); }; /* * cftype_sets describe cftypes belonging to a subsystem and are chained at * cgroup_subsys->cftsets. Each cftset points to an array of cftypes * terminated by zero length name. */ struct cftype_set { struct list_head node; /* chained at subsys->cftsets */ const struct cftype *cfts; }; struct cgroup_scanner { struct cgroup *cg; int (*test_task)(struct task_struct *p, struct cgroup_scanner *scan); void (*process_task)(struct task_struct *p, struct cgroup_scanner *scan); struct ptr_heap *heap; void *data; }; int cgroup_add_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts); int cgroup_rm_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts); int cgroup_is_removed(const struct cgroup *cgrp); int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen); int cgroup_task_count(const struct cgroup *cgrp); /* Return true if cgrp is a descendant of the task's cgroup */ int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task); /* * When the subsys has to access css and may add permanent refcnt to css, * it should take care of racy conditions with rmdir(). Following set of * functions, is for stop/restart rmdir if necessary. * Because these will call css_get/put, "css" should be alive css. * * cgroup_exclude_rmdir(); * ...do some jobs which may access arbitrary empty cgroup * cgroup_release_and_wakeup_rmdir(); * * When someone removes a cgroup while cgroup_exclude_rmdir() holds it, * it sleeps and cgroup_release_and_wakeup_rmdir() will wake him up. */ void cgroup_exclude_rmdir(struct cgroup_subsys_state *css); void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css); /* * Control Group taskset, used to pass around set of tasks to cgroup_subsys * methods. */ struct cgroup_taskset; struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset); struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset); struct cgroup *cgroup_taskset_cur_cgroup(struct cgroup_taskset *tset); int cgroup_taskset_size(struct cgroup_taskset *tset); /** * cgroup_taskset_for_each - iterate cgroup_taskset * @task: the loop cursor * @skip_cgrp: skip if task's cgroup matches this, %NULL to iterate through all * @tset: taskset to iterate */ #define cgroup_taskset_for_each(task, skip_cgrp, tset) \ for ((task) = cgroup_taskset_first((tset)); (task); \ (task) = cgroup_taskset_next((tset))) \ if (!(skip_cgrp) || \ cgroup_taskset_cur_cgroup((tset)) != (skip_cgrp)) /* * Control Group subsystem type. * See Documentation/cgroups/cgroups.txt for details */ struct cgroup_subsys { struct cgroup_subsys_state *(*create)(struct cgroup *cgrp); int (*pre_destroy)(struct cgroup *cgrp); void (*destroy)(struct cgroup *cgrp); int (*can_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); void (*attach)(struct cgroup *cgrp, struct cgroup_taskset *tset); void (*fork)(struct task_struct *task); void (*exit)(struct cgroup *cgrp, struct cgroup *old_cgrp, struct task_struct *task); void (*post_clone)(struct cgroup *cgrp); void (*bind)(struct cgroup *root); int subsys_id; int active; int disabled; int early_init; /* * True if this subsys uses ID. ID is not available before cgroup_init()


context:
space:
mode: