diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/linux/auxvec.h | 6 | ||||
| -rw-r--r-- | include/linux/cgroup.h | 61 | ||||
| -rw-r--r-- | include/linux/cpuset.h | 10 | ||||
| -rw-r--r-- | include/linux/ext2_fs.h | 24 | ||||
| -rw-r--r-- | include/linux/ext2_fs_sb.h | 4 | ||||
| -rw-r--r-- | include/linux/ext3_fs.h | 24 | ||||
| -rw-r--r-- | include/linux/ext3_fs_sb.h | 4 | ||||
| -rw-r--r-- | include/linux/jbd.h | 15 | ||||
| -rw-r--r-- | include/linux/kernel.h | 6 | ||||
| -rw-r--r-- | include/linux/magic.h | 1 | ||||
| -rw-r--r-- | include/linux/memcontrol.h | 154 | ||||
| -rw-r--r-- | include/linux/mm_inline.h | 22 | ||||
| -rw-r--r-- | include/linux/mmzone.h | 24 | ||||
| -rw-r--r-- | include/linux/page_cgroup.h | 52 | ||||
| -rw-r--r-- | include/linux/pid.h | 18 | ||||
| -rw-r--r-- | include/linux/pid_namespace.h | 6 | ||||
| -rw-r--r-- | include/linux/res_counter.h | 8 | ||||
| -rw-r--r-- | include/linux/swap.h | 25 | ||||
| -rw-r--r-- | include/xen/xenbus.h | 2 |
19 files changed, 372 insertions, 94 deletions
diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h index d7afa9dd663..f3b5d4e3a2a 100644 --- a/include/linux/auxvec.h +++ b/include/linux/auxvec.h @@ -23,16 +23,16 @@ #define AT_PLATFORM 15 /* string identifying CPU for optimizations */ #define AT_HWCAP 16 /* arch dependent hints at CPU capabilities */ #define AT_CLKTCK 17 /* frequency at which times() increments */ - +/* AT_* values 18 through 22 are reserved */ #define AT_SECURE 23 /* secure mode boolean */ - #define AT_BASE_PLATFORM 24 /* string identifying real platform, may * differ from AT_PLATFORM. */ +#define AT_RANDOM 25 /* address of 16 random bytes */ #define AT_EXECFN 31 /* filename of program */ #ifdef __KERNEL__ -#define AT_VECTOR_SIZE_BASE 18 /* NEW_AUX_ENT entries in auxiliary table */ +#define AT_VECTOR_SIZE_BASE 19 /* NEW_AUX_ENT entries in auxiliary table */ /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */ #endif diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 08b78c09b09..e267e62827b 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -52,9 +52,9 @@ struct cgroup_subsys_state { * hierarchy structure */ struct cgroup *cgroup; - /* State maintained by the cgroup system to allow - * subsystems to be "busy". Should be accessed via css_get() - * and css_put() */ + /* 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; @@ -64,11 +64,14 @@ struct cgroup_subsys_state { /* 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 */ }; /* - * Call css_get() to hold a reference on the cgroup; - * + * 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) @@ -77,9 +80,32 @@ static inline void css_get(struct cgroup_subsys_state *css) if (!test_bit(CSS_ROOT, &css->flags)) atomic_inc(&css->refcnt); } + +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. + */ + +static inline bool css_tryget(struct cgroup_subsys_state *css) +{ + if (test_bit(CSS_ROOT, &css->flags)) + return true; + while (!atomic_inc_not_zero(&css->refcnt)) { + if (test_bit(CSS_REMOVED, &css->flags)) + return false; + } + return true; +} + /* * css_put() should be called to release a reference taken by - * css_get() + * css_get() or css_tryget() */ extern void __css_put(struct cgroup_subsys_state *css); @@ -116,7 +142,7 @@ struct cgroup { struct list_head children; /* my children */ struct cgroup *parent; /* my parent */ - struct dentry *dentry; /* cgroup fs entry */ + struct dentry *dentry; /* cgroup fs entry, RCU protected */ /* Private pointers for each registered subsystem */ struct cgroup_subsys_state *subsys[CGROUP_SUBSYS_COUNT]; @@ -145,6 +171,9 @@ struct cgroup { int pids_use_count; /* Length of the current tasks_pids array */ int pids_length; + + /* For RCU-protected deletion */ + struct rcu_head rcu_head; }; /* A css_set is a structure holding pointers to a set of @@ -337,9 +366,23 @@ struct cgroup_subsys { #define MAX_CGROUP_TYPE_NAMELEN 32 const char *name; - /* Protected by RCU */ - struct cgroupfs_root *root; + /* + * Protects sibling/children links of cgroups in this + * hierarchy, plus protects which hierarchy (or none) the + * subsystem is a part of (i.e. root/sibling). To avoid + * potential deadlocks, the following operations should not be + * undertaken while holding any hierarchy_mutex: + * + * - allocating memory + * - initiating hotplug events + */ + struct mutex hierarchy_mutex; + /* + * Link to parent, and list entry in parent's children. + * Protected by this->hierarchy_mutex and cgroup_lock() + */ + struct cgroupfs_root *root; struct list_head sibling; }; diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 51ea2bdea0f..90c6074a36c 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -20,8 +20,9 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */ extern int cpuset_init_early(void); extern int cpuset_init(void); extern void cpuset_init_smp(void); -extern void cpuset_cpus_allowed(struct task_struct *p, cpumask_t *mask); -extern void cpuset_cpus_allowed_locked(struct task_struct *p, cpumask_t *mask); +extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); +extern void cpuset_cpus_allowed_locked(struct task_struct *p, + struct cpumask *mask); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); @@ -86,12 +87,13 @@ static inline int cpuset_init_early(void) { return 0; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} -static inline void cpuset_cpus_allowed(struct task_struct *p, cpumask_t *mask) +static inline void cpuset_cpus_allowed(struct task_struct *p, + struct cpumask *mask) { *mask = cpu_possible_map; } static inline void cpuset_cpus_allowed_locked(struct task_struct *p, - cpumask_t *mask) + struct cpumask *mask) { *mask = cpu_possible_map; } diff --git a/include/linux/ext2_fs.h b/include/linux/ext2_fs.h index 78c775a83f7..121720d74e1 100644 --- a/include/linux/ext2_fs.h +++ b/include/linux/ext2_fs.h @@ -194,6 +194,30 @@ struct ext2_group_desc #define EXT2_FL_USER_VISIBLE FS_FL_USER_VISIBLE /* User visible flags */ #define EXT2_FL_USER_MODIFIABLE FS_FL_USER_MODIFIABLE /* User modifiable flags */ +/* Flags that should be inherited by new inodes from their parent. */ +#define EXT2_FL_INHERITED (EXT2_SECRM_FL | EXT2_UNRM_FL | EXT2_COMPR_FL |\ + EXT2_SYNC_FL | EXT2_IMMUTABLE_FL | EXT2_APPEND_FL |\ + EXT2_NODUMP_FL | EXT2_NOATIME_FL | EXT2_COMPRBLK_FL|\ + EXT2_NOCOMP_FL | EXT2_JOURNAL_DATA_FL |\ + EXT2_NOTAIL_FL | EXT2_DIRSYNC_FL) + +/* Flags that are appropriate for regular files (all but dir-specific ones). */ +#define EXT2_REG_FLMASK (~(EXT2_DIRSYNC_FL | EXT2_TOPDIR_FL)) + +/* Flags that are appropriate for non-directories/regular files. */ +#define EXT2_OTHER_FLMASK (EXT2_NODUMP_FL | EXT2_NOATIME_FL) + +/* Mask out flags that are inappropriate for the given type of inode. */ +static inline __u32 ext2_mask_flags(umode_t mode, __u32 flags) +{ + if (S_ISDIR(mode)) + return flags; + else if (S_ISREG(mode)) + return flags & EXT2_REG_FLMASK; + else + return flags & EXT2_OTHER_FLMASK; +} + /* * ioctl commands */ diff --git a/include/linux/ext2_fs_sb.h b/include/linux/ext2_fs_sb.h index dc541f3653d..1cdb66367c9 100644 --- a/include/linux/ext2_fs_sb.h +++ b/include/linux/ext2_fs_sb.h @@ -101,7 +101,7 @@ struct ext2_sb_info { struct percpu_counter s_freeblocks_counter; struct percpu_counter s_freeinodes_counter; struct percpu_counter s_dirs_counter; - struct blockgroup_lock s_blockgroup_lock; + struct blockgroup_lock *s_blockgroup_lock; /* root of the per fs reservation window tree */ spinlock_t s_rsv_window_lock; struct rb_root s_rsv_window_root; @@ -111,7 +111,7 @@ struct ext2_sb_info { static inline spinlock_t * sb_bgl_lock(struct ext2_sb_info *sbi, unsigned int block_group) { - return bgl_lock_ptr(&sbi->s_blockgroup_lock, block_group); + return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group); } #endif /* _LINUX_EXT2_FS_SB */ diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index d14f0291848..d76800f6ecf 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -178,6 +178,30 @@ struct ext3_group_desc #define EXT3_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ #define EXT3_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ +/* Flags that should be inherited by new inodes from their parent. */ +#define EXT3_FL_INHERITED (EXT3_SECRM_FL | EXT3_UNRM_FL | EXT3_COMPR_FL |\ + EXT3_SYNC_FL | EXT3_IMMUTABLE_FL | EXT3_APPEND_FL |\ + EXT3_NODUMP_FL | EXT3_NOATIME_FL | EXT3_COMPRBLK_FL|\ + EXT3_NOCOMPR_FL | EXT3_JOURNAL_DATA_FL |\ + EXT3_NOTAIL_FL | EXT3_DIRSYNC_FL) + +/* Flags that are appropriate for regular files (all but dir-specific ones). */ +#define EXT3_REG_FLMASK (~(EXT3_DIRSYNC_FL | EXT3_TOPDIR_FL)) + +/* Flags that are appropriate for non-directories/regular files. */ +#define EXT3_OTHER_FLMASK (EXT3_NODUMP_FL | EXT3_NOATIME_FL) + +/* Mask out flags that are inappropriate for the given type of inode. */ +static inline __u32 ext3_mask_flags(umode_t mode, __u32 flags) +{ + if (S_ISDIR(mode)) + return flags; + else if (S_ISREG(mode)) + return flags & EXT3_REG_FLMASK; + else + return flags & EXT3_OTHER_FLMASK; +} + /* * Inode dynamic state flags */ diff --git a/include/linux/ext3_fs_sb.h b/include/linux/ext3_fs_sb.h index e024e38248f..76fdc0f4b02 100644 --- a/include/linux/ext3_fs_sb.h +++ b/include/linux/ext3_fs_sb.h @@ -60,7 +60,7 @@ struct ext3_sb_info { struct percpu_counter s_freeblocks_counter; struct percpu_counter s_freeinodes_counter; struct percpu_counter s_dirs_counter; - struct blockgroup_lock s_blockgroup_lock; + struct blockgroup_lock *s_blockgroup_lock; /* root of the per fs reservation window tree */ spinlock_t s_rsv_window_lock; @@ -86,7 +86,7 @@ struct ext3_sb_info { static inline spinlock_t * sb_bgl_lock(struct ext3_sb_info *sbi, unsigned int block_group) { - return bgl_lock_ptr(&sbi->s_blockgroup_lock, block_group); + return bgl_lock_ptr(sbi->s_blockgroup_lock, block_group); } #endif /* _LINUX_EXT3_FS_SB */ diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 346e2b80be7..6384b19efe6 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -543,6 +543,11 @@ struct transaction_s unsigned long t_expires; /* + * When this transaction started, in nanoseconds [no locking] + */ + ktime_t t_start_time; + + /* * How many handles used this transaction? [t_handle_lock] */ int t_handle_count; @@ -798,9 +803,19 @@ struct journal_s struct buffer_head **j_wbuf; int j_wbufsize; + /* + * this is the pid of the last person to run a synchronous operation + * through the journal. + */ pid_t j_last_sync_writer; /* + * the average amount of time in nanoseconds it takes to commit a + * transaction to the disk. [j_state_lock] + */ + u64 j_average_commit_time; + + /* * An opaque pointer to fs-private information. ext3 puts its * superblock pointer here */ diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 6b8e2027165..343df9ef241 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -476,6 +476,12 @@ static inline char *pack_hex_byte(char *buf, u8 byte) __val = __val < __min ? __min: __val; \ __val > __max ? __max: __val; }) + +/* + * swap - swap value of @a and @b + */ +#define swap(a, b) ({ typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; }) + /** * container_of - cast a member of a structure out to the containing structure * @ptr: the pointer to the member. diff --git a/include/linux/magic.h b/include/linux/magic.h index f7f3fdddbef..439f6f3cb0c 100644 --- a/include/linux/magic.h +++ b/include/linux/magic.h @@ -13,6 +13,7 @@ #define EFS_SUPER_MAGIC 0x414A53 #define EXT2_SUPER_MAGIC 0xEF53 #define EXT3_SUPER_MAGIC 0xEF53 +#define XENFS_SUPER_MAGIC 0xabba1974 #define EXT4_SUPER_MAGIC 0xEF53 #define HPFS_SUPER_MAGIC 0xf995e849 #define ISOFS_SUPER_MAGIC 0x9660 diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 1fbe14d3952..326f45c8653 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -19,22 +19,45 @@ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H - +#include <linux/cgroup.h> struct mem_cgroup; struct page_cgroup; struct page; struct mm_struct; #ifdef CONFIG_CGROUP_MEM_RES_CTLR +/* + * All "charge" functions with gfp_mask should use GFP_KERNEL or + * (gfp_mask & GFP_RECLAIM_MASK). In current implementatin, memcg doesn't + * alloc memory but reclaims memory from all available zones. So, "where I want + * memory from" bits of gfp_mask has no meaning. So any bits of that field is + * available but adding a rule is better. charge functions' gfp_mask should + * be set to GFP_KERNEL or gfp_mask & GFP_RECLAIM_MASK for avoiding ambiguous + * codes. + * (Of course, if memcg does memory allocation in future, GFP_KERNEL is sane.) + */ -extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm, +extern int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); +/* for swap handling */ +extern int mem_cgroup_try_charge_swapin(struct mm_struct *mm, + struct page *page, gfp_t mask, struct mem_cgroup **ptr); +extern void mem_cgroup_commit_charge_swapin(struct page *page, + struct mem_cgroup *ptr); +extern void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *ptr); + extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); -extern void mem_cgroup_move_lists(struct page *page, enum lru_list lru); +extern void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru); +extern void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru); +extern void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru); +extern void mem_cgroup_del_lru(struct page *page); +extern void mem_cgroup_move_lists(struct page *page, + enum lru_list from, enum lru_list to); extern void mem_cgroup_uncharge_page(struct page *page); extern void mem_cgroup_uncharge_cache_page(struct page *page); -extern int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask); +extern int mem_cgroup_shrink_usage(struct page *page, + struct mm_struct *mm, gfp_t gfp_mask); extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, struct list_head *dst, @@ -47,12 +70,20 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem); extern struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); -#define mm_match_cgroup(mm, cgroup) \ - ((cgroup) == mem_cgroup_from_task((mm)->owner)) +static inline +int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup) +{ + struct mem_cgroup *mem; + rcu_read_lock(); + mem = mem_cgroup_from_task((mm)->owner); + rcu_read_unlock(); + return cgroup == mem; +} extern int -mem_cgroup_prepare_migration(struct page *page, struct page *newpage); -extern void mem_cgroup_end_migration(struct page *page); +mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr); +extern void mem_cgroup_end_migration(struct mem_cgroup *mem, + struct page *oldpage, struct page *newpage); /* * For memory reclaim. @@ -65,13 +96,32 @@ extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority); extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority); +int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg); +unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, + struct zone *zone, + enum lru_list lru); +struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, + struct zone *zone); +struct zone_reclaim_stat* +mem_cgroup_get_reclaim_stat_from_page(struct page *page); -extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone, - int priority, enum lru_list lru); +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +extern int do_swap_account; +#endif +static inline bool mem_cgroup_disabled(void) +{ + if (mem_cgroup_subsys.disabled) + return true; + return false; +} + +extern bool mem_cgroup_oom_called(struct task_struct *task); #else /* CONFIG_CGROUP_MEM_RES_CTLR */ -static inline int mem_cgroup_charge(struct page *page, +struct mem_cgroup; + +static inline int mem_cgroup_newpage_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { return 0; @@ -83,6 +133,21 @@ static inline int mem_cgroup_cache_charge(struct page *page, return 0; } +static inline int mem_cgroup_try_charge_swapin(struct mm_struct *mm, + struct page *page, gfp_t gfp_mask, struct mem_cgroup **ptr) +{ + return 0; +} + +static inline void mem_cgroup_commit_charge_swapin(struct page *page, + struct mem_cgroup *ptr) +{ +} + +static inline void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *ptr) +{ +} + static inline void mem_cgroup_uncharge_page(struct page *page) { } @@ -91,12 +156,33 @@ static inline void mem_cgroup_uncharge_cache_page(struct page *page) { } -static inline int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask) +static inline int mem_cgroup_shrink_usage(struct page *page, + struct mm_struct *mm, gfp_t gfp_mask) { return 0; } -static inline void mem_cgroup_move_lists(struct page *page, bool active) +static inline void mem_cgroup_add_lru_list(struct page *page, int lru) +{ +} + +static inline void mem_cgroup_del_lru_list(struct page *page, int lru) +{ + return ; +} + +static inline void mem_cgroup_rotate_lru_list(struct page *page, int lru) +{ + return ; +} + +static inline void mem_cgroup_del_lru(struct page *page) +{ + return ; +} + +static inline void +mem_cgroup_move_lists(struct page *page, enum lru_list from, enum lru_list to) { } @@ -112,12 +198,14 @@ static inline int task_in_mem_cgroup(struct task_struct *task, } static inline int -mem_cgroup_prepare_migration(struct page *page, struct page *newpage) +mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr) { return 0; } -static inline void mem_cgroup_end_migration(struct page *page) +static inline void mem_cgroup_end_migration(struct mem_cgroup *mem, + struct page *oldpage, + struct page *newpage) { } @@ -146,12 +234,42 @@ static inline void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, { } -static inline long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, - struct zone *zone, int priority, - enum lru_list lru) +static inline bool mem_cgroup_disabled(void) +{ + return true; +} + +static inline bool mem_cgroup_oom_called(struct task_struct *task) +{ + return false; +} + +static inline int +mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg) +{ + return 1; +} + +static inline unsigned long +mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, struct zone *zone, + enum lru_list lru) { return 0; } + + +static inline struct zone_reclaim_stat* +mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg, struct zone *zone) +{ + return NULL; +} + +static inline struct zone_reclaim_stat* +mem_cgroup_get_reclaim_stat_from_page(struct page *page) +{ + return NULL; +} + #endif /* CONFIG_CGROUP_MEM_CONT */ #endif /* _LINUX_MEMCONTROL_H */ diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index c948350c378..7fbb9726755 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -28,6 +28,7 @@ add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l) { list_add(&page->lru, &zone->lru[l].list); __inc_zone_state(zone, NR_LRU_BASE + l); + mem_cgroup_add_lru_list(page, l); } static inline void @@ -35,6 +36,7 @@ del_page_from_lru_list(struct zone *zone, struct page *page, enum lru_list l) { list_del(&page->lru); __dec_zone_state(zone, NR_LRU_BASE + l); + mem_cgroup_del_lru_list(page, l); } static inline void @@ -54,6 +56,7 @@ del_page_from_lru(struct zone *zone, struct page *page) l += page_is_file_cache(page); } __dec_zone_state(zone, NR_LRU_BASE + l); + mem_cgroup_del_lru_list(page, l); } /** @@ -78,23 +81,4 @@ static inline enum lru_list page_lru(struct page *page) return lru; } -/** - * inactive_anon_is_low - check if anonymous pages need to be deactivated - * @zone: zone to check - * - * Returns true if the zone does not have enough inactive anon pages, - * meaning some active anon pages need to be deactivated. - */ -static inline int inactive_anon_is_low(struct zone *zone) -{ - unsigned long active, inactive; - - active = zone_page_state(zone, NR_ACTIVE_ANON); - inactive = zone_page_state(zone, NR_INACTIVE_ANON); - - if (inactive * zone->inactive_ratio < active) - return 1; - - return 0; -} #endif diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 35a7b5e1946..09c14e213b6 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -263,6 +263,19 @@ enum zone_type { #error ZONES_SHIFT -- too many zones configured adjust calculation #endif +struct zone_reclaim_stat { + /* + * The pageout code in vmscan.c keeps track of how many of the + * mem/swap backed and file backed pages are refeferenced. + * The higher the rotated/scanned ratio, the more valuable + * that cache is. + * + * The anon LRU stats live in [0], file LRU stats in [1] + */ + unsigned long recent_rotated[2]; + unsigned long recent_scanned[2]; +}; + struct zone { /* Fields commonly accessed by the page allocator */ unsigned long pages_min, pages_low, pages_high; @@ -315,16 +328,7 @@ struct zone { unsigned long nr_scan; } lru[NR_LRU_LISTS]; - /* - * The pageout code in vmscan.c keeps track of how many of the - * mem/swap backed and file backed pages are refeferenced. - * The higher the rotated/scanned ratio, the more valuable - * that cache is. - * - * The anon LRU stats live in [0], file LRU stats in [1] - */ - unsigned long recent_rotated[2]; - unsigned long recent_scanned[2]; + struct zone_reclaim_stat reclaim_stat; unsigned long pages_scanned; /* since last reclaim */ unsigned long flags; /* zone flags, see below */ diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h index 1e6d34bfa09..602cc1fdee9 100644 --- a/include/linux/page_cgroup.h +++ b/include/linux/page_cgroup.h @@ -26,10 +26,6 @@ enum { PCG_LOCK, /* page cgroup is locked */ PCG_CACHE, /* charged as cache */ PCG_USED, /* this object is in use. */ - /* flags for LRU placement */ - PCG_ACTIVE, /* page is active in this cgroup */ - PCG_FILE, /* page is file system backed */ - PCG_UNEVICTABLE, /* page is unevictableable */ }; #define TESTPCGFLAG(uname, lname) \ @@ -50,19 +46,6 @@ TESTPCGFLAG(Cache, CACHE) TESTPCGFLAG(Used, USED) CLEARPCGFLAG(Used, USED) -/* LRU management flags (from global-lru definition) */ -TESTPCGFLAG(File, FILE) -SETPCGFLAG(File, FILE) -CLEARPCGFLAG(File, FILE) - -TESTPCGFLAG(Active, ACTIVE) -SETPCGFLAG(Active, ACTIVE) -CLEARPCGFLAG(Active, ACTIVE) - -TESTPCGFLAG(Unevictable, UNEVICTABLE) -SETPCGFLAG(Unevictable, UNEVICTABLE) -CLEARPCGFLAG(Unevictable, UNEVICTABLE) - static inline int page_cgroup_nid(struct page_cgroup *pc) { return page_to_nid(pc->page); @@ -105,4 +88,39 @@ static inline void page_cgroup_init(void) } #endif + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +#include <linux/swap.h> +extern struct mem_cgroup * +swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem); +extern struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent); +extern int swap_cgroup_swapon(int type, unsigned long max_pages); +extern void swap_cgroup_swapoff(int type); +#else +#include <linux/swap.h> + +static inline +struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem) +{ + return NULL; +} + +static inline +struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent) +{ + return NULL; +} + +static inline int +swap_cgroup_swapon(int type, unsigned long max_pages) +{ + return 0; +} + +static inline void swap_cgroup_swapoff(int type) +{ + return; +} + +#endif #endif diff --git a/include/linux/pid.h b/include/linux/pid.h index bb206c56d1f..49f1c2f66e9 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -123,6 +123,24 @@ extern struct pid *alloc_pid(struct pid_namespace *ns); extern void free_pid(struct pid *pid); /* + * ns_of_pid() returns the pid namespace in which the specified pid was + * allocated. + * + * NOTE: + * ns_of_pid() is expected to be called for a process (task) that has + * an attached 'struct pid' (see attach_pid(), detach_pid()) i.e @pid + * is expected to be non-NULL. If @pid is NULL, caller should handle + * the resulting NULL pid-ns. + */ +static inline struct pid_namespace *ns_of_pid(struct pid *pid) +{ + struct pid_namespace *ns = NULL; + if (pid) + ns = pid->numbers[pid->level].ns; + return ns; +} + +/* * the helpers to get the pid's id seen from different namespaces * * pid_nr() : global id, i.e. the id seen from the init namespace; diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index d82fe825d62..38d10326246 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -79,11 +79,7 @@ static inline void zap_pid_ns_processes(struct pid_namespace *ns) } #endif /* CONFIG_PID_NS */ -static inline struct pid_namespace *task_active_pid_ns(struct task_struct *tsk) -{ - return tsk->nsproxy->pid_ns; -} - +extern struct pid_namespace *task_active_pid_ns(struct task_struct *tsk); void pidhash_init(void); void pidmap_init(void); diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h index 271c1c2c9f6..dede0a2cfc4 100644 --- a/include/linux/res_counter.h +++ b/include/linux/res_counter.h @@ -43,6 +43,10 @@ struct res_counter { * the routines below consider this to be IRQ-safe */ spinlock_t lock; + /* + * Parent counter, used for hierarchial resource accounting + */ + struct res_counter *parent; }; /** @@ -87,7 +91,7 @@ enum { * helpers for accounting */ -void res_counter_init(struct res_counter *counter); +void res_counter_init(struct res_counter *counter, struct res_counter *parent); /* * charge - try to consume more resource. @@ -103,7 +107,7 @@ void res_counter_init(struct res_counter *counter); int __must_check res_counter_charge_locked(struct res_counter *counter, unsigned long val); int __must_check res_counter_charge(struct res_counter *counter, - unsigned long val); + unsigned long val, struct res_counter **limit_fail_at); /* * uncharge - tell that some portion of the resource is released diff --git a/include/linux/swap.h b/include/linux/swap.h index 91dee50fe26..d3021557887 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -214,7 +214,8 @@ static inline void lru_cache_add_active_file(struct page *page) extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask); extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem, - gfp_t gfp_mask); + gfp_t gfp_mask, bool noswap, + unsigned int swappiness); extern int __isolate_lru_page(struct page *page, int mode, int file); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; @@ -333,6 +334,22 @@ static inline void disable_swap_token(void) put_swap_token(swap_token_mm); } +#ifdef CONFIG_CGROUP_MEM_RES_CTLR +extern void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent); +#else +static inline void +mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent) +{ +} +#endif +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP +extern void mem_cgroup_uncharge_swap(swp_entry_t ent); +#else +static inline void mem_cgroup_uncharge_swap(swp_entry_t ent) +{ +} +#endif + #else /* CONFIG_SWAP */ #define nr_swap_pages 0L @@ -409,6 +426,12 @@ static inline swp_entry_t get_swap_page(void) #define has_swap_token(x) 0 #define disable_swap_token() do { } while(0) +static inline int mem_cgroup_cache_charge_swapin(struct page *page, + struct mm_struct *mm, gfp_t mask, bool locked) +{ + return 0; +} + #endif /* CONFIG_SWAP */ #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h index 6369d89c25d..f87f9614844 100644 --- a/include/xen/xenbus.h +++ b/include/xen/xenbus.h @@ -136,8 +136,6 @@ struct xenbus_transaction /* Nil transaction ID. */ #define XBT_NIL ((struct xenbus_transaction) { 0 }) -int __init xenbus_dev_init(void); - char **xenbus_directory(struct xenbus_transaction t, const char *dir, const char *node, unsigned int *num); void *xenbus_read(struct xenbus_transaction t, |