diff options
Diffstat (limited to 'include/linux')
43 files changed, 823 insertions, 165 deletions
diff --git a/include/linux/Kbuild b/include/linux/Kbuild index bf9aca548f1..e531783e5d7 100644 --- a/include/linux/Kbuild +++ b/include/linux/Kbuild @@ -183,6 +183,7 @@ unifdef-y += auto_fs.h unifdef-y += auxvec.h unifdef-y += binfmts.h unifdef-y += blktrace_api.h +unifdef-y += byteorder.h unifdef-y += capability.h unifdef-y += capi.h unifdef-y += cciss_ioctl.h @@ -340,6 +341,7 @@ unifdef-y += soundcard.h unifdef-y += stat.h unifdef-y += stddef.h unifdef-y += string.h +unifdef-y += swab.h unifdef-y += synclink.h unifdef-y += sysctl.h unifdef-y += tcp.h diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 0a24d5550eb..bee52abb8a4 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -175,6 +175,8 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); * BDI_CAP_READ_MAP: Can be mapped for reading * BDI_CAP_WRITE_MAP: Can be mapped for writing * BDI_CAP_EXEC_MAP: Can be mapped for execution + * + * BDI_CAP_SWAP_BACKED: Count shmem/tmpfs objects as swap-backed. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 @@ -184,6 +186,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); #define BDI_CAP_WRITE_MAP 0x00000020 #define BDI_CAP_EXEC_MAP 0x00000040 #define BDI_CAP_NO_ACCT_WB 0x00000080 +#define BDI_CAP_SWAP_BACKED 0x00000100 #define BDI_CAP_VMFLAGS \ (BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP) @@ -248,6 +251,11 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi) BDI_CAP_NO_WRITEBACK)); } +static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi) +{ + return bdi->capabilities & BDI_CAP_SWAP_BACKED; +} + static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { return bdi_cap_writeback_dirty(mapping->backing_dev_info); @@ -258,4 +266,9 @@ static inline bool mapping_cap_account_dirty(struct address_space *mapping) return bdi_cap_account_dirty(mapping->backing_dev_info); } +static inline bool mapping_cap_swap_backed(struct address_space *mapping) +{ + return bdi_cap_swap_backed(mapping->backing_dev_info); +} + #endif /* _LINUX_BACKING_DEV_H */ diff --git a/include/linux/bcd.h b/include/linux/bcd.h index 7ac518e3c15..22ea563ba3e 100644 --- a/include/linux/bcd.h +++ b/include/linux/bcd.h @@ -1,12 +1,3 @@ -/* Permission is hereby granted to copy, modify and redistribute this code - * in terms of the GNU Library General Public License, Version 2 or later, - * at your option. - */ - -/* macros to translate to/from binary and binary-coded decimal (frequently - * found in RTC chips). - */ - #ifndef _BCD_H #define _BCD_H @@ -15,11 +6,4 @@ unsigned bcd2bin(unsigned char val) __attribute_const__; unsigned char bin2bcd(unsigned val) __attribute_const__; -#define BCD2BIN(val) bcd2bin(val) -#define BIN2BCD(val) bin2bcd(val) - -/* backwards compat */ -#define BCD_TO_BIN(val) ((val)=BCD2BIN(val)) -#define BIN_TO_BCD(val) ((val)=BIN2BCD(val)) - #endif /* _BCD_H */ diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 89781fd4885..1abfe664c44 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -110,7 +110,6 @@ extern int __bitmap_weight(const unsigned long *bitmap, int bits); extern int bitmap_scnprintf(char *buf, unsigned int len, const unsigned long *src, int nbits); -extern int bitmap_scnprintf_len(unsigned int nr_bits); extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user, unsigned long *dst, int nbits); extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index eadaab44015..3ce64b90118 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -322,7 +322,7 @@ static inline void wait_on_buffer(struct buffer_head *bh) static inline int trylock_buffer(struct buffer_head *bh) { - return likely(!test_and_set_bit(BH_Lock, &bh->b_state)); + return likely(!test_and_set_bit_lock(BH_Lock, &bh->b_state)); } static inline void lock_buffer(struct buffer_head *bh) diff --git a/include/linux/byteorder/Kbuild b/include/linux/byteorder/Kbuild index 1133d5f9d81..fbaa7f9cee3 100644 --- a/include/linux/byteorder/Kbuild +++ b/include/linux/byteorder/Kbuild @@ -1,3 +1,4 @@ unifdef-y += big_endian.h unifdef-y += little_endian.h unifdef-y += swab.h +unifdef-y += swabb.h diff --git a/include/linux/byteorder/big_endian.h b/include/linux/byteorder/big_endian.h index 44f95b92393..1cba3f3efe5 100644 --- a/include/linux/byteorder/big_endian.h +++ b/include/linux/byteorder/big_endian.h @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/byteorder/swab.h> +#include <linux/byteorder/swabb.h> #define __constant_htonl(x) ((__force __be32)(__u32)(x)) #define __constant_ntohl(x) ((__force __u32)(__be32)(x)) diff --git a/include/linux/byteorder/little_endian.h b/include/linux/byteorder/little_endian.h index 4cc170a3176..cedc1b5a289 100644 --- a/include/linux/byteorder/little_endian.h +++ b/include/linux/byteorder/little_endian.h @@ -10,6 +10,7 @@ #include <linux/types.h> #include <linux/byteorder/swab.h> +#include <linux/byteorder/swabb.h> #define __constant_htonl(x) ((__force __be32)___constant_swab32((x))) #define __constant_ntohl(x) ___constant_swab32((__force __be32)(x)) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 30934e4bfaa..8b00f6643e9 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -9,12 +9,12 @@ */ #include <linux/sched.h> -#include <linux/kref.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> #ifdef CONFIG_CGROUPS @@ -137,6 +137,15 @@ struct cgroup { * release_list_lock */ struct list_head release_list; + + /* pids_mutex protects the fields below */ + struct rw_semaphore pids_mutex; + /* Array of process ids in the cgroup */ + pid_t *tasks_pids; + /* How many files are using the current tasks_pids array */ + int pids_use_count; + /* Length of the current tasks_pids array */ + int pids_length; }; /* A css_set is a structure holding pointers to a set of @@ -149,7 +158,7 @@ struct cgroup { struct css_set { /* Reference count */ - struct kref ref; + atomic_t refcount; /* * List running through all cgroup groups in the same hash @@ -394,6 +403,9 @@ void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it); int cgroup_scan_tasks(struct cgroup_scanner *scan); int cgroup_attach_task(struct cgroup *, struct task_struct *); +void cgroup_mm_owner_callbacks(struct task_struct *old, + struct task_struct *new); + #else /* !CONFIG_CGROUPS */ static inline int cgroup_init_early(void) { return 0; } @@ -412,15 +424,9 @@ static inline int cgroupstats_build(struct cgroupstats *stats, return -EINVAL; } +static inline void cgroup_mm_owner_callbacks(struct task_struct *old, + struct task_struct *new) {} + #endif /* !CONFIG_CGROUPS */ -#ifdef CONFIG_MM_OWNER -extern void -cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new); -#else /* !CONFIG_MM_OWNER */ -static inline void -cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new) -{ -} -#endif /* CONFIG_MM_OWNER */ #endif /* _LINUX_CGROUP_H */ diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h index e2877454ec8..9c22396e8b5 100644 --- a/include/linux/cgroup_subsys.h +++ b/include/linux/cgroup_subsys.h @@ -48,3 +48,9 @@ SUBSYS(devices) #endif /* */ + +#ifdef CONFIG_CGROUP_FREEZER +SUBSYS(freezer) +#endif + +/* */ diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 025e4f57510..0acf3b737e2 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -8,12 +8,9 @@ #include <linux/proc_fs.h> #define ELFCORE_ADDR_MAX (-1ULL) +#define ELFCORE_ADDR_ERR (-2ULL) -#ifdef CONFIG_PROC_VMCORE extern unsigned long long elfcorehdr_addr; -#else -static const unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX; -#endif extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); @@ -28,10 +25,43 @@ extern struct proc_dir_entry *proc_vmcore; #define vmcore_elf_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x)) +/* + * is_kdump_kernel() checks whether this kernel is booting after a panic of + * previous kernel or not. This is determined by checking if previous kernel + * has passed the elf core header address on command line. + * + * This is not just a test if CONFIG_CRASH_DUMP is enabled or not. It will + * return 1 if CONFIG_CRASH_DUMP=y and if kernel is booting after a panic of + * previous kernel. + */ + static inline int is_kdump_kernel(void) { return (elfcorehdr_addr != ELFCORE_ADDR_MAX) ? 1 : 0; } + +/* is_vmcore_usable() checks if the kernel is booting after a panic and + * the vmcore region is usable. + * + * This makes use of the fact that due to alignment -2ULL is not + * a valid pointer, much in the vain of IS_ERR(), except + * dealing directly with an unsigned long long rather than a pointer. + */ + +static inline int is_vmcore_usable(void) +{ + return is_kdump_kernel() && elfcorehdr_addr != ELFCORE_ADDR_ERR ? 1 : 0; +} + +/* vmcore_unusable() marks the vmcore as unusable, + * without disturbing the logic of is_kdump_kernel() + */ + +static inline void vmcore_unusable(void) +{ + if (is_kdump_kernel()) + elfcorehdr_addr = ELFCORE_ADDR_ERR; +} #else /* !CONFIG_CRASH_DUMP */ static inline int is_kdump_kernel(void) { return 0; } #endif /* CONFIG_CRASH_DUMP */ diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 159d9b476cd..d14f0291848 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -380,6 +380,8 @@ struct ext3_inode { #define EXT3_MOUNT_QUOTA 0x80000 /* Some quota option set */ #define EXT3_MOUNT_USRQUOTA 0x100000 /* "old" user quota */ #define EXT3_MOUNT_GRPQUOTA 0x200000 /* "old" group quota */ +#define EXT3_MOUNT_DATA_ERR_ABORT 0x400000 /* Abort on file data write + * error in ordered mode */ /* Compatibility, for having both ext2_fs.h and ext3_fs.h included at once */ #ifndef _LINUX_EXT2_FS_H diff --git a/include/linux/fb.h b/include/linux/fb.h index 531ccd5f596..75a81eaf343 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -808,6 +808,7 @@ struct fb_tile_ops { struct fb_info { int node; int flags; + struct mutex lock; /* Lock for open/release/ioctl funcs */ struct fb_var_screeninfo var; /* Current var */ struct fb_fix_screeninfo fix; /* Current fix */ struct fb_monspecs monspecs; /* Current Monitor specs */ diff --git a/include/linux/freezer.h b/include/linux/freezer.h index deddeedf325..8f225339eee 100644 --- a/include/linux/freezer.h +++ b/include/linux/freezer.h @@ -6,7 +6,7 @@ #include <linux/sched.h> #include <linux/wait.h> -#ifdef CONFIG_PM_SLEEP +#ifdef CONFIG_FREEZER /* * Check if a process has been frozen */ @@ -39,28 +39,18 @@ static inline void clear_freeze_flag(struct task_struct *p) clear_tsk_thread_flag(p, TIF_FREEZE); } +static inline bool should_send_signal(struct task_struct *p) +{ + return !(p->flags & PF_FREEZER_NOSIG); +} + /* * Wake up a frozen process - * - * task_lock() is taken to prevent the race with refrigerator() which may - * occur if the freezing of tasks fails. Namely, without the lock, if the - * freezing of tasks failed, thaw_tasks() might have run before a task in - * refrigerator() could call frozen_process(), in which case the task would be - * frozen and no one would thaw it. */ -static inline int thaw_process(struct task_struct *p) -{ - task_lock(p); - if (frozen(p)) { - p->flags &= ~PF_FROZEN; - task_unlock(p); - wake_up_process(p); - return 1; - } - clear_freeze_flag(p); - task_unlock(p); - return 0; -} +extern int __thaw_process(struct task_struct *p); + +/* Takes and releases task alloc lock using task_lock() */ +extern int thaw_process(struct task_struct *p); extern void refrigerator(void); extern int freeze_processes(void); @@ -75,6 +65,15 @@ static inline int try_to_freeze(void) return 0; } +extern bool freeze_task(struct task_struct *p, bool sig_only); +extern void cancel_freezing(struct task_struct *p); + +#ifdef CONFIG_CGROUP_FREEZER +extern int cgroup_frozen(struct task_struct *task); +#else /* !CONFIG_CGROUP_FREEZER */ +static inline int cgroup_frozen(struct task_struct *task) { return 0; } +#endif /* !CONFIG_CGROUP_FREEZER */ + /* * The PF_FREEZER_SKIP flag should be set by a vfork parent right before it * calls wait_for_completion(&vfork) and reset right after it returns from this @@ -166,7 +165,7 @@ static inline void set_freezable_with_signal(void) } while (try_to_freeze()); \ __retval; \ }) -#else /* !CONFIG_PM_SLEEP */ +#else /* !CONFIG_FREEZER */ static inline int frozen(struct task_struct *p) { return 0; } static inline int freezing(struct task_struct *p) { return 0; } static inline void set_freeze_flag(struct task_struct *p) {} @@ -191,6 +190,6 @@ static inline void set_freezable_with_signal(void) {} #define wait_event_freezable_timeout(wq, condition, timeout) \ wait_event_interruptible_timeout(wq, condition, timeout) -#endif /* !CONFIG_PM_SLEEP */ +#endif /* !CONFIG_FREEZER */ #endif /* FREEZER_H_INCLUDED */ diff --git a/include/linux/jbd.h b/include/linux/jbd.h index 7ebbcb1c9ba..35d4f6342fa 100644 --- a/include/linux/jbd.h +++ b/include/linux/jbd.h @@ -816,6 +816,9 @@ struct journal_s #define JFS_FLUSHED 0x008 /* The journal superblock has been flushed */ #define JFS_LOADED 0x010 /* The journal superblock has been loaded */ #define JFS_BARRIER 0x020 /* Use IDE barriers */ +#define JFS_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file + * data write error in ordered + * mode */ /* * Function declarations for the journaling transaction and buffer diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index fdf3967e139..1fbe14d3952 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -27,16 +27,13 @@ struct mm_struct; #ifdef CONFIG_CGROUP_MEM_RES_CTLR -#define page_reset_bad_cgroup(page) ((page)->page_cgroup = 0) - -extern struct page_cgroup *page_get_page_cgroup(struct page *page); extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask); 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_uncharge_page(struct page *page); extern void mem_cgroup_uncharge_cache_page(struct page *page); -extern void mem_cgroup_move_lists(struct page *page, bool active); extern int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask); extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, @@ -44,7 +41,7 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan, unsigned long *scanned, int order, int mode, struct zone *z, struct mem_cgroup *mem_cont, - int active); + int active, int file); extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask); int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem); @@ -69,21 +66,11 @@ extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority); -extern long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem, - struct zone *zone, int priority); -extern long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem, - struct zone *zone, int priority); - -#else /* CONFIG_CGROUP_MEM_RES_CTLR */ -static inline void page_reset_bad_cgroup(struct page *page) -{ -} +extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone, + int priority, enum lru_list lru); -static inline struct page_cgroup *page_get_page_cgroup(struct page *page) -{ - return NULL; -} +#else /* CONFIG_CGROUP_MEM_RES_CTLR */ static inline int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { @@ -159,14 +146,9 @@ static inline void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, { } -static inline long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem, - struct zone *zone, int priority) -{ - return 0; -} - -static inline long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem, - struct zone *zone, int priority) +static inline long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, + struct zone *zone, int priority, + enum lru_list lru) { return 0; } diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 03aea612d28..3f34005068d 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -7,7 +7,6 @@ typedef struct page *new_page_t(struct page *, unsigned long private, int **); #ifdef CONFIG_MIGRATION -extern int isolate_lru_page(struct page *p, struct list_head *pagelist); extern int putback_lru_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *); @@ -21,8 +20,6 @@ extern int migrate_vmas(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, unsigned long flags); #else -static inline int isolate_lru_page(struct page *p, struct list_head *list) - { return -ENOSYS; } static inline int putback_lru_pages(struct list_head *l) { return 0; } static inline int migrate_pages(struct list_head *l, new_page_t x, unsigned long private) { return -ENOSYS; } diff --git a/include/linux/mm.h b/include/linux/mm.h index c61ba10768e..ffee2f74341 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -132,6 +132,11 @@ extern unsigned int kobjsize(const void *objp); #define VM_RandomReadHint(v) ((v)->vm_flags & VM_RAND_READ) /* + * special vmas that are non-mergable, non-mlock()able + */ +#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP) + +/* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ @@ -700,10 +705,10 @@ static inline int page_mapped(struct page *page) extern void show_free_areas(void); #ifdef CONFIG_SHMEM -int shmem_lock(struct file *file, int lock, struct user_struct *user); +extern int shmem_lock(struct file *file, int lock, struct user_struct *user); #else static inline int shmem_lock(struct file *file, int lock, - struct user_struct *user) + struct user_struct *user) { return 0; } diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 895bc4e9303..c948350c378 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -1,40 +1,100 @@ -static inline void -add_page_to_active_list(struct zone *zone, struct page *page) -{ - list_add(&page->lru, &zone->active_list); - __inc_zone_state(zone, NR_ACTIVE); -} +#ifndef LINUX_MM_INLINE_H +#define LINUX_MM_INLINE_H -static inline void -add_page_to_inactive_list(struct zone *zone, struct page *page) +/** + * page_is_file_cache - should the page be on a file LRU or anon LRU? + * @page: the page to test + * + * Returns LRU_FILE if @page is page cache page backed by a regular filesystem, + * or 0 if @page is anonymous, tmpfs or otherwise ram or swap backed. + * Used by functions that manipulate the LRU lists, to sort a page + * onto the right LRU list. + * + * We would like to get this info without a page flag, but the state + * needs to survive until the page is last deleted from the LRU, which + * could be as far down as __page_cache_release. + */ +static inline int page_is_file_cache(struct page *page) { - list_add(&page->lru, &zone->inactive_list); - __inc_zone_state(zone, NR_INACTIVE); + if (PageSwapBacked(page)) + return 0; + + /* The page is page cache backed by a normal filesystem. */ + return LRU_FILE; } static inline void -del_page_from_active_list(struct zone *zone, struct page *page) +add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l) { - list_del(&page->lru); - __dec_zone_state(zone, NR_ACTIVE); + list_add(&page->lru, &zone->lru[l].list); + __inc_zone_state(zone, NR_LRU_BASE + l); } static inline void -del_page_from_inactive_list(struct zone *zone, struct page *page) +del_page_from_lru_list(struct zone *zone, struct page *page, enum lru_list l) { list_del(&page->lru); - __dec_zone_state(zone, NR_INACTIVE); + __dec_zone_state(zone, NR_LRU_BASE + l); } static inline void del_page_from_lru(struct zone *zone, struct page *page) { + enum lru_list l = LRU_BASE; + list_del(&page->lru); - if (PageActive(page)) { - __ClearPageActive(page); - __dec_zone_state(zone, NR_ACTIVE); + if (PageUnevictable(page)) { + __ClearPageUnevictable(page); + l = LRU_UNEVICTABLE; } else { - __dec_zone_state(zone, NR_INACTIVE); + if (PageActive(page)) { + __ClearPageActive(page); + l += LRU_ACTIVE; + } + l += page_is_file_cache(page); + } + __dec_zone_state(zone, NR_LRU_BASE + l); +} + +/** + * page_lru - which LRU list should a page be on? + * @page: the page to test + * + * Returns the LRU list a page should be on, as an index + * into the array of LRU lists. + */ +static inline enum lru_list page_lru(struct page *page) +{ + enum lru_list lru = LRU_BASE; + + if (PageUnevictable(page)) + lru = LRU_UNEVICTABLE; + else { + if (PageActive(page)) + lru += LRU_ACTIVE; + lru += page_is_file_cache(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/mm_types.h b/include/linux/mm_types.h index 9d49fa36bbe..fe825471d5a 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -94,9 +94,6 @@ struct page { void *virtual; /* Kernel virtual address (NULL if not kmapped, ie. highmem) */ #endif /* WANT_PAGE_VIRTUAL */ -#ifdef CONFIG_CGROUP_MEM_RES_CTLR - unsigned long page_cgroup; -#endif }; /* diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 428328a05fa..35a7b5e1946 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -81,21 +81,31 @@ struct zone_padding { enum zone_stat_item { /* First 128 byte cacheline (assuming 64 bit words) */ NR_FREE_PAGES, - NR_INACTIVE, - NR_ACTIVE, + NR_LRU_BASE, + NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */ + NR_ACTIVE_ANON, /* " " " " " */ + NR_INACTIVE_FILE, /* " " " " " */ + NR_ACTIVE_FILE, /* " " " " " */ +#ifdef CONFIG_UNEVICTABLE_LRU + NR_UNEVICTABLE, /* " " " " " */ + NR_MLOCK, /* mlock()ed pages found and moved off LRU */ +#else + NR_UNEVICTABLE = NR_ACTIVE_FILE, /* avoid compiler errors in dead code */ + NR_MLOCK = NR_ACTIVE_FILE, +#endif NR_ANON_PAGES, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. only modified from process context */ NR_FILE_PAGES, NR_FILE_DIRTY, NR_WRITEBACK, - /* Second 128 byte cacheline */ NR_SLAB_RECLAIMABLE, NR_SLAB_UNRECLAIMABLE, NR_PAGETABLE, /* used for pagetables */ NR_UNSTABLE_NFS, /* NFS unstable pages */ NR_BOUNCE, NR_VMSCAN_WRITE, + /* Second 128 byte cacheline */ NR_WRITEBACK_TEMP, /* Writeback using temporary buffers */ #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ @@ -107,6 +117,55 @@ enum zone_stat_item { #endif NR_VM_ZONE_STAT_ITEMS }; +/* + * We do arithmetic on the LRU lists in various places in the code, + * so it is important to keep the active lists LRU_ACTIVE higher in + * the array than the corresponding inactive lists, and to keep + * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists. + * + * This has to be kept in sync with the statistics in zone_stat_item + * above and the descriptions in vmstat_text in mm/vmstat.c + */ +#define LRU_BASE 0 +#define LRU_ACTIVE 1 +#define LRU_FILE 2 + +enum lru_list { + LRU_INACTIVE_ANON = LRU_BASE, + LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE, + LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE, + LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE, +#ifdef CONFIG_UNEVICTABLE_LRU + LRU_UNEVICTABLE, +#else + LRU_UNEVICTABLE = LRU_ACTIVE_FILE, /* avoid compiler errors in dead code */ +#endif + NR_LRU_LISTS +}; + +#define for_each_lru(l) for (l = 0; l < NR_LRU_LISTS; l++) + +#define for_each_evictable_lru(l) for (l = 0; l <= LRU_ACTIVE_FILE; l++) + +static inline int is_file_lru(enum lru_list l) +{ + return (l == LRU_INACTIVE_FILE || l == LRU_ACTIVE_FILE); +} + +static inline int is_active_lru(enum lru_list l) +{ + return (l == LRU_ACTIVE_ANON || l == LRU_ACTIVE_FILE); +} + +static inline int is_unevictable_lru(enum lru_list l) +{ +#ifdef CONFIG_UNEVICTABLE_LRU + return (l == LRU_UNEVICTABLE); +#else + return 0; +#endif +} + struct per_cpu_pages { int count; /* number of pages in the list */ int high; /* high watermark, emptying needed */ @@ -251,10 +310,22 @@ struct zone { /* Fields commonly accessed by the page reclaim scanner */ spinlock_t lru_lock; - struct list_head active_list; - struct list_head inactive_list; - unsigned long nr_scan_active; - unsigned long nr_scan_inactive; + struct { + struct list_head list; + 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]; + unsigned long pages_scanned; /* since last reclaim */ unsigned long flags; /* zone flags, see below */ @@ -276,6 +347,12 @@ struct zone { */ int prev_priority; + /* + * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on + * this zone's LRU. Maintained by the pageout code. + */ + unsigned int inactive_ratio; + ZONE_PADDING(_pad2_) /* Rarely used or read-mostly fields */ @@ -524,8 +601,11 @@ typedef struct pglist_data { struct zone node_zones[MAX_NR_ZONES]; struct zonelist node_zonelists[MAX_ZONELISTS]; int nr_zones; -#ifdef CONFIG_FLAT_NODE_MEM_MAP +#ifdef CONFIG_FLAT_NODE_MEM_MAP /* means !SPARSEMEM */ struct page *node_mem_map; +#ifdef CONFIG_CGROUP_MEM_RES_CTLR + struct page_cgroup *node_page_cgroup; +#endif #endif struct bootmem_data *bdata; #ifdef CONFIG_MEMORY_HOTPLUG @@ -854,6 +934,7 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn) #endif struct page; +struct page_cgroup; struct mem_section { /* * This is, logically, a pointer to an array of struct @@ -871,6 +952,14 @@ struct mem_section { /* See declaration of similar field in struct zone */ unsigned long *pageblock_flags; +#ifdef CONFIG_CGROUP_MEM_RES_CTLR + /* + * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use + * section. (see memcontrol.h/page_cgroup.h about this.) + */ + struct page_cgroup *page_cgroup; + unsigned long pad; +#endif }; #ifdef CONFIG_SPARSEMEM_EXTREME diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h index d6fb115f5a0..ee5124ec319 100644 --- a/include/linux/mtd/cfi.h +++ b/include/linux/mtd/cfi.h @@ -12,6 +12,7 @@ #include <linux/mtd/flashchip.h> #include <linux/mtd/map.h> #include <linux/mtd/cfi_endian.h> +#include <linux/mtd/xip.h> #ifdef CONFIG_MTD_CFI_I1 #define cfi_interleave(cfi) 1 @@ -430,7 +431,6 @@ static inline uint32_t cfi_send_gen_cmd(u_char cmd, uint32_t cmd_addr, uint32_t { map_word val; uint32_t addr = base + cfi_build_cmd_addr(cmd_addr, cfi_interleave(cfi), type); - val = cfi_build_cmd(cmd, map, cfi); if (prev_val) @@ -483,6 +483,13 @@ static inline void cfi_udelay(int us) } } +int __xipram cfi_qry_present(struct map_info *map, __u32 base, + struct cfi_private *cfi); +int __xipram cfi_qry_mode_on(uint32_t base, struct map_info *map, + struct cfi_private *cfi); +void __xipram cfi_qry_mode_off(uint32_t base, struct map_info *map, + struct cfi_private *cfi); + struct cfi_extquery *cfi_read_pri(struct map_info *map, uint16_t adr, uint16_t size, const char* name); struct cfi_fixup { diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index 08dd131301c..d4f38c5fd44 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -73,6 +73,10 @@ struct flchip { int buffer_write_time; int erase_time; + int word_write_time_max; + int buffer_write_time_max; + int erase_time_max; + void *priv; }; diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h index 92263654855..eae26bb6430 100644 --- a/include/linux/mtd/mtd.h +++ b/include/linux/mtd/mtd.h @@ -25,8 +25,10 @@ #define MTD_ERASE_DONE 0x08 #define MTD_ERASE_FAILED 0x10 +#define MTD_FAIL_ADDR_UNKNOWN 0xffffffff + /* If the erase fails, fail_addr might indicate exactly which block failed. If - fail_addr = 0xffffffff, the failure was not at the device level or was not + fail_addr = MTD_FAIL_ADDR_UNKNOWN, the failure was not at the device level or was not specific to any particular block. */ struct erase_info { struct mtd_info *mtd; diff --git a/include/linux/mtd/nand-gpio.h b/include/linux/mtd/nand-gpio.h new file mode 100644 index 00000000000..51534e50f7f --- /dev/null +++ b/include/linux/mtd/nand-gpio.h @@ -0,0 +1,19 @@ +#ifndef __LINUX_MTD_NAND_GPIO_H +#define __LINUX_MTD_NAND_GPIO_H + +#include <linux/mtd/nand.h> + +struct gpio_nand_platdata { + int gpio_nce; + int gpio_nwp; + int gpio_cle; + int gpio_ale; + int gpio_rdy; + void (*adjust_parts)(struct gpio_nand_platdata *, size_t); + struct mtd_partition *parts; + unsigned int num_parts; + unsigned int options; + int chip_delay; +}; + +#endif diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h index 81774e5facf..733d3f3b4eb 100644 --- a/include/linux/mtd/nand.h +++ b/include/linux/mtd/nand.h @@ -248,6 +248,7 @@ struct nand_hw_control { * @read_page_raw: function to read a raw page without ECC * @write_page_raw: function to write a raw page without ECC * @read_page: function to read a page according to the ecc generator requirements + * @read_subpage: function to read parts of the page covered by ECC. * @write_page: function to write a page according to the ecc generator requirements * @read_oob: function to read chip OOB data * @write_oob: function to write chip OOB data diff --git a/include/linux/mtd/onenand_regs.h b/include/linux/mtd/onenand_regs.h index d1b310c92eb..0c6bbe28f38 100644 --- a/include/linux/mtd/onenand_regs.h +++ b/include/linux/mtd/onenand_regs.h @@ -152,6 +152,8 @@ #define ONENAND_SYS_CFG1_INT (1 << 6) #define ONENAND_SYS_CFG1_IOBE (1 << 5) #define ONENAND_SYS_CFG1_RDY_CONF (1 << 4) +#define ONENAND_SYS_CFG1_HF (1 << 2) +#define ONENAND_SYS_CFG1_SYNC_WRITE (1 << 1) /* * Controller Status Register F240h (R) diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h index 5014f7a9f5d..c92b4d43960 100644 --- a/include/linux/mtd/partitions.h +++ b/include/linux/mtd/partitions.h @@ -73,7 +73,6 @@ struct device; struct device_node; int __devinit of_mtd_parse_partitions(struct device *dev, - struct mtd_info *mtd, struct device_node *node, struct mtd_partition **pparts); diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h new file mode 100644 index 00000000000..e77c1cea404 --- /dev/null +++ b/include/linux/mtd/sh_flctl.h @@ -0,0 +1,125 @@ +/* + * SuperH FLCTL nand controller + * + * Copyright © 2008 Renesas Solutions Corp. + * + * 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; version 2 of the License. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#ifndef __SH_FLCTL_H__ +#define __SH_FLCTL_H__ + +#include <linux/mtd/mtd.h> +#include <linux/mtd/nand.h> +#include <linux/mtd/partitions.h> + +/* FLCTL registers */ +#define FLCMNCR(f) (f->reg + 0x0) +#define FLCMDCR(f) (f->reg + 0x4) +#define FLCMCDR(f) (f->reg + 0x8) +#define FLADR(f) (f->reg + 0xC) +#define FLADR2(f) (f->reg + 0x3C) +#define FLDATAR(f) (f->reg + 0x10) +#define FLDTCNTR(f) (f->reg + 0x14) +#define FLINTDMACR(f) (f->reg + 0x18) +#define FLBSYTMR(f) (f->reg + 0x1C) +#define FLBSYCNT(f) (f->reg + 0x20) +#define FLDTFIFO(f) (f->reg + 0x24) +#define FLECFIFO(f) (f->reg + 0x28) +#define FLTRCR(f) (f->reg + 0x2C) +#define FL4ECCRESULT0(f) (f->reg + 0x80) +#define FL4ECCRESULT1(f) (f->reg + 0x84) +#define FL4ECCRESULT2(f) (f->reg + 0x88) +#define FL4ECCRESULT3(f) (f->reg + 0x8C) +#define FL4ECCCR(f) (f->reg + 0x90) +#define FL4ECCCNT(f) (f->reg + 0x94) +#define FLERRADR(f) (f->reg + 0x98) + +/* FLCMNCR control bits */ +#define ECCPOS2 (0x1 << 25) +#define _4ECCCNTEN (0x1 << 24) +#define _4ECCEN (0x1 << 23) +#define _4ECCCORRECT (0x1 << 22) +#define SNAND_E (0x1 << 18) /* SNAND (0=512 1=2048)*/ +#define QTSEL_E (0x1 << 17) +#define ENDIAN (0x1 << 16) /* 1 = little endian */ +#define FCKSEL_E (0x1 << 15) +#define ECCPOS_00 (0x00 << 12) +#define ECCPOS_01 (0x01 << 12) +#define ECCPOS_02 (0x02 << 12) +#define ACM_SACCES_MODE (0x01 << 10) +#define NANWF_E (0x1 << 9) +#define SE_D (0x1 << 8) /* Spare area disable */ +#define CE1_ENABLE (0x1 << 4) /* Chip Enable 1 */ +#define CE0_ENABLE (0x1 << 3) /* Chip Enable 0 */ +#define TYPESEL_SET (0x1 << 0) + +/* FLCMDCR control bits */ +#define ADRCNT2_E (0x1 << 31) /* 5byte address enable */ +#define ADRMD_E (0x1 << 26) /* Sector address access */ +#define CDSRC_E (0x1 << 25) /* Data buffer selection */ +#define DOSR_E (0x1 << 24) /* Status read check */ +#define SELRW (0x1 << 21) /* 0:read 1:write */ +#define DOADR_E (0x1 << 20) /* Address stage execute */ +#define ADRCNT_1 (0x00 << 18) /* Address data bytes: 1byte */ +#define ADRCNT_2 (0x01 << 18) /* Address data bytes: 2byte */ +#define ADRCNT_3 (0x02 << 18) /* Address data bytes: 3byte */ +#define ADRCNT_4 (0x03 << 18) /* Address data bytes: 4byte */ +#define DOCMD2_E (0x1 << 17) /* 2nd cmd stage execute */ +#define DOCMD1_E (0x1 << 16) /* 1st cmd stage execute */ + +/* FLTRCR control bits */ +#define TRSTRT (0x1 << 0) /* translation start */ +#define TREND (0x1 << 1) /* translation end */ + +/* FL4ECCCR control bits */ +#define _4ECCFA (0x1 << 2) /* 4 symbols correct fault */ +#define _4ECCEND (0x1 << 1) /* 4 symbols end */ +#define _4ECCEXST (0x1 << 0) /* 4 symbols exist */ + +#define INIT_FL4ECCRESULT_VAL 0x03FF03FF +#define LOOP_TIMEOUT_MAX 0x00010000 + +#define mtd_to_flctl(mtd) container_of(mtd, struct sh_flctl, mtd) + +struct sh_flctl { + struct mtd_info mtd; + struct nand_chip chip; + void __iomem *reg; + + uint8_t done_buff[2048 + 64]; /* max size 2048 + 64 */ + int read_bytes; + int index; + int seqin_column; /* column in SEQIN cmd */ + int seqin_page_addr; /* page_addr in SEQIN cmd */ + uint32_t seqin_read_cmd; /* read cmd in SEQIN cmd */ + int erase1_page_addr; /* page_addr in ERASE1 cmd */ + uint32_t erase_ADRCNT; /* bits of FLCMDCR in ERASE1 cmd */ + uint32_t rw_ADRCNT; /* bits of FLCMDCR in READ WRITE cmd */ + + int hwecc_cant_correct[4]; + + unsigned page_size:1; /* NAND page size (0 = 512, 1 = 2048) */ + unsigned hwecc:1; /* Hardware ECC (0 = disabled, 1 = enabled) */ +}; + +struct sh_flctl_platform_data { + struct mtd_partition *parts; + int nr_parts; + unsigned long flcmncr_val; + + unsigned has_hwecc:1; +}; + +#endif /* __SH_FLCTL_H__ */ diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index c74d3e87531..b12f93a3c34 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -93,6 +93,11 @@ enum pageflags { PG_mappedtodisk, /* Has blocks allocated on-disk */ PG_reclaim, /* To be reclaimed asap */ PG_buddy, /* Page is free, on buddy lists */ + PG_swapbacked, /* Page is backed by RAM/swap */ +#ifdef CONFIG_UNEVICTABLE_LRU + PG_unevictable, /* Page is "unevictable" */ + PG_mlocked, /* Page is vma mlocked */ +#endif #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR PG_uncached, /* Page has been mapped as uncached */ #endif @@ -161,6 +166,18 @@ static inline int Page##uname(struct page *page) \ #define TESTSCFLAG(uname, lname) \ TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname) +#define SETPAGEFLAG_NOOP(uname) \ +static inline void SetPage##uname(struct page *page) { } + +#define CLEARPAGEFLAG_NOOP(uname) \ +static inline void ClearPage##uname(struct page *page) { } + +#define __CLEARPAGEFLAG_NOOP(uname) \ +static inline void __ClearPage##uname(struct page *page) { } + +#define TESTCLEARFLAG_FALSE(uname) \ +static inline int TestClearPage##uname(struct page *page) { return 0; } + struct page; /* forward declaration */ TESTPAGEFLAG(Locked, locked) @@ -169,6 +186,7 @@ PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced) PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty) PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru) PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active) + TESTCLEARFLAG(Active, active) __PAGEFLAG(Slab, slab) PAGEFLAG(Checked, checked) /* Used by some filesystems */ PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned) /* Xen */ @@ -176,6 +194,7 @@ PAGEFLAG(SavePinned, savepinned); /* Xen */ PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved) PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private) __SETPAGEFLAG(Private, private) +PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked) __PAGEFLAG(SlobPage, slob_page) __PAGEFLAG(SlobFree, slob_free) @@ -211,6 +230,25 @@ PAGEFLAG(SwapCache, swapcache) PAGEFLAG_FALSE(SwapCache) #endif +#ifdef CONFIG_UNEVICTABLE_LRU +PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable) + TESTCLEARFLAG(Unevictable, unevictable) + +#define MLOCK_PAGES 1 +PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked) + TESTSCFLAG(Mlocked, mlocked) + +#else + +#define MLOCK_PAGES 0 +PAGEFLAG_FALSE(Mlocked) + SETPAGEFLAG_NOOP(Mlocked) TESTCLEARFLAG_FALSE(Mlocked) + +PAGEFLAG_FALSE(Unevictable) TESTCLEARFLAG_FALSE(Unevictable) + SETPAGEFLAG_NOOP(Unevictable) CLEARPAGEFLAG_NOOP(Unevictable) + __CLEARPAGEFLAG_NOOP(Unevictable) +#endif + #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR PAGEFLAG(Uncached, uncached) #else @@ -326,15 +364,25 @@ static inline void __ClearPageTail(struct page *page) #endif /* !PAGEFLAGS_EXTENDED */ +#ifdef CONFIG_UNEVICTABLE_LRU +#define __PG_UNEVICTABLE (1 << PG_unevictable) +#define __PG_MLOCKED (1 << PG_mlocked) +#else +#define __PG_UNEVICTABLE 0 +#define __PG_MLOCKED 0 +#endif + #define PAGE_FLAGS (1 << PG_lru | 1 << PG_private | 1 << PG_locked | \ 1 << PG_buddy | 1 << PG_writeback | \ - 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active) + 1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \ + __PG_UNEVICTABLE | __PG_MLOCKED) /* * Flags checked in bad_page(). Pages on the free list should not have * these flags set. It they are, there is a problem. */ -#define PAGE_FLAGS_CLEAR_WHEN_BAD (PAGE_FLAGS | 1 << PG_reclaim | 1 << PG_dirty) +#define PAGE_FLAGS_CLEAR_WHEN_BAD (PAGE_FLAGS | \ + 1 << PG_reclaim | 1 << PG_dirty | 1 << PG_swapbacked) /* * Flags checked when a page is freed. Pages being freed should not have @@ -347,7 +395,8 @@ static inline void __ClearPageTail(struct page *page) * Pages being prepped should not have these flags set. It they are, there * is a problem. */ -#define PAGE_FLAGS_CHECK_AT_PREP (PAGE_FLAGS | 1 << PG_reserved | 1 << PG_dirty) +#define PAGE_FLAGS_CHECK_AT_PREP (PAGE_FLAGS | \ + 1 << PG_reserved | 1 << PG_dirty | 1 << PG_swapbacked) #endif /* !__GENERATING_BOUNDS_H */ #endif /* PAGE_FLAGS_H */ diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h new file mode 100644 index 00000000000..0fd39f2231e --- /dev/null +++ b/include/linux/page_cgroup.h @@ -0,0 +1,103 @@ +#ifndef __LINUX_PAGE_CGROUP_H +#define __LINUX_PAGE_CGROUP_H + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR +#include <linux/bit_spinlock.h> +/* + * Page Cgroup can be considered as an extended mem_map. + * A page_cgroup page is associated with every page descriptor. The + * page_cgroup helps us identify information about the cgroup + * All page cgroups are allocated at boot or memory hotplug event, + * then the page cgroup for pfn always exists. + */ +struct page_cgroup { + unsigned long flags; + struct mem_cgroup *mem_cgroup; + struct page *page; + struct list_head lru; /* per cgroup LRU list */ +}; + +void __init pgdat_page_cgroup_init(struct pglist_data *pgdat); +void __init page_cgroup_init(void); +struct page_cgroup *lookup_page_cgroup(struct page *page); + +enum { + /* flags for mem_cgroup */ + 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) \ +static inline int PageCgroup##uname(struct page_cgroup *pc) \ + { return test_bit(PCG_##lname, &pc->flags); } + +#define SETPCGFLAG(uname, lname) \ +static inline void SetPageCgroup##uname(struct page_cgroup *pc)\ + { set_bit(PCG_##lname, &pc->flags); } + +#define CLEARPCGFLAG(uname, lname) \ +static inline void ClearPageCgroup##uname(struct page_cgroup *pc) \ + { clear_bit(PCG_##lname, &pc->flags); } + +/* Cache flag is set only once (at allocation) */ +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); +} + +static inline enum zone_type page_cgroup_zid(struct page_cgroup *pc) +{ + return page_zonenum(pc->page); +} + +static inline void lock_page_cgroup(struct page_cgroup *pc) +{ + bit_spin_lock(PCG_LOCK, &pc->flags); +} + +static inline int trylock_page_cgroup(struct page_cgroup *pc) +{ + return bit_spin_trylock(PCG_LOCK, &pc->flags); +} + +static inline void unlock_page_cgroup(struct page_cgroup *pc) +{ + bit_spin_unlock(PCG_LOCK, &pc->flags); +} + +#else /* CONFIG_CGROUP_MEM_RES_CTLR */ +struct page_cgroup; + +static inline void pgdat_page_cgroup_init(struct pglist_data *pgdat) +{ +} + +static inline struct page_cgroup *lookup_page_cgroup(struct page *page) +{ + return NULL; +} +#endif +#endif diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 5da31c12101..709742be02f 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -32,6 +32,34 @@ static inline void mapping_set_error(struct address_space *mapping, int error) } } +#ifdef CONFIG_UNEVICTABLE_LRU +#define AS_UNEVICTABLE (__GFP_BITS_SHIFT + 2) /* e.g., ramdisk, SHM_LOCK */ + +static inline void mapping_set_unevictable(struct address_space *mapping) +{ + set_bit(AS_UNEVICTABLE, &mapping->flags); +} + +static inline void mapping_clear_unevictable(struct address_space *mapping) +{ + clear_bit(AS_UNEVICTABLE, &mapping->flags); +} + +static inline int mapping_unevictable(struct address_space *mapping) +{ + if (likely(mapping)) + return test_bit(AS_UNEVICTABLE, &mapping->flags); + return !!mapping; +} +#else +static inline void mapping_set_unevictable(struct address_space *mapping) { } +static inline void mapping_clear_unevictable(struct address_space *mapping) { } +static inline int mapping_unevictable(struct address_space *mapping) +{ + return 0; +} +#endif + static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { return (__force gfp_t)mapping->flags & __GFP_BITS_MASK; @@ -271,19 +299,19 @@ extern int __lock_page_killable(struct page *page); extern void __lock_page_nosync(struct page *page); extern void unlock_page(struct page *page); -static inline void set_page_locked(struct page *page) +static inline void __set_page_locked(struct page *page) { - set_bit(PG_locked, &page->flags); + __set_bit(PG_locked, &page->flags); } -static inline void clear_page_locked(struct page *page) +static inline void __clear_page_locked(struct page *page) { - clear_bit(PG_locked, &page->flags); + __clear_bit(PG_locked, &page->flags); } static inline int trylock_page(struct page *page) { - return !test_and_set_bit(PG_locked, &page->flags); + return (likely(!test_and_set_bit_lock(PG_locked, &page->flags))); } /* @@ -410,17 +438,17 @@ extern void __remove_from_page_cache(struct page *page); /* * Like add_to_page_cache_locked, but used to add newly allocated pages: - * the page is new, so we can just run set_page_locked() against it. + * the page is new, so we can just run __set_page_locked() against it. */ static inline int add_to_page_cache(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { int error; - set_page_locked(page); + __set_page_locked(page); error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); if (unlikely(error)) - clear_page_locked(page); + __clear_page_locked(page); return error; } diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 8eb7fa76c1d..e90a2cb0291 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -23,9 +23,9 @@ struct pagevec { void __pagevec_release(struct pagevec *pvec); void __pagevec_release_nonlru(struct pagevec *pvec); void __pagevec_free(struct pagevec *pvec); -void __pagevec_lru_add(struct pagevec *pvec); -void __pagevec_lru_add_active(struct pagevec *pvec); +void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru); void pagevec_strip(struct pagevec *pvec); +void pagevec_swap_free(struct pagevec *pvec); unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping, pgoff_t start, unsigned nr_pages); unsigned pagevec_lookup_tag(struct pagevec *pvec, @@ -81,10 +81,36 @@ static inline void pagevec_free(struct pagevec *pvec) __pagevec_free(pvec); } -static inline void pagevec_lru_add(struct pagevec *pvec) +static inline void __pagevec_lru_add_anon(struct pagevec *pvec) +{ + ____pagevec_lru_add(pvec, LRU_INACTIVE_ANON); +} + +static inline void __pagevec_lru_add_active_anon(struct pagevec *pvec) +{ + ____pagevec_lru_add(pvec, LRU_ACTIVE_ANON); +} + +static inline void __pagevec_lru_add_file(struct pagevec *pvec) +{ + ____pagevec_lru_add(pvec, LRU_INACTIVE_FILE); +} + +static inline void __pagevec_lru_add_active_file(struct pagevec *pvec) +{ + ____pagevec_lru_add(pvec, LRU_ACTIVE_FILE); +} + +static inline void pagevec_lru_add_file(struct pagevec *pvec) +{ + if (pagevec_count(pvec)) + __pagevec_lru_add_file(pvec); +} + +static inline void pagevec_lru_add_anon(struct pagevec *pvec) { if (pagevec_count(pvec)) - __pagevec_lru_add(pvec); + __pagevec_lru_add_anon(pvec); } #endif /* _LINUX_PAGEVEC_H */ diff --git a/include/linux/pci.h b/include/linux/pci.h index 98dc6243a70..acf8f24037c 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -631,6 +631,8 @@ int __must_check pci_assign_resource(struct pci_dev *dev, int i); int pci_select_bars(struct pci_dev *dev, unsigned long flags); /* ROM control related routines */ +int pci_enable_rom(struct pci_dev *pdev); +void pci_disable_rom(struct pci_dev *pdev); void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size); void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom); size_t pci_get_rom_size(void __iomem *rom, size_t size); diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h index ea7416c901d..22641d5d45d 100644 --- a/include/linux/ptrace.h +++ b/include/linux/ptrace.h @@ -94,7 +94,6 @@ extern void ptrace_notify(int exit_code); extern void __ptrace_link(struct task_struct *child, struct task_struct *new_parent); extern void __ptrace_unlink(struct task_struct *child); -extern void ptrace_untrace(struct task_struct *child); #define PTRACE_MODE_READ 1 #define PTRACE_MODE_ATTACH 2 /* Returns 0 on success, -errno on denial. */ diff --git a/include/linux/rmap.h b/include/linux/rmap.h index fed6f5e0b41..89f0564b10c 100644 --- a/include/linux/rmap.h +++ b/include/linux/rmap.h @@ -39,18 +39,6 @@ struct anon_vma { #ifdef CONFIG_MMU -extern struct kmem_cache *anon_vma_cachep; - -static inline struct anon_vma *anon_vma_alloc(void) -{ - return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); -} - -static inline void anon_vma_free(struct anon_vma *anon_vma) -{ - kmem_cache_free(anon_vma_cachep, anon_vma); -} - static inline void anon_vma_lock(struct vm_area_struct *vma) { struct anon_vma *anon_vma = vma->anon_vma; @@ -75,6 +63,9 @@ void anon_vma_unlink(struct vm_area_struct *); void anon_vma_link(struct vm_area_struct *); void __anon_vma_link(struct vm_area_struct *); +extern struct anon_vma *page_lock_anon_vma(struct page *page); +extern void page_unlock_anon_vma(struct anon_vma *anon_vma); + /* * rmap interfaces called when adding or removing pte of page */ @@ -117,6 +108,19 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *); */ int page_mkclean(struct page *); +#ifdef CONFIG_UNEVICTABLE_LRU +/* + * called in munlock()/munmap() path to check for other vmas holding + * the page mlocked. + */ +int try_to_munlock(struct page *); +#else +static inline int try_to_munlock(struct page *page) +{ + return 0; /* a.k.a. SWAP_SUCCESS */ +} +#endif + #else /* !CONFIG_MMU */ #define anon_vma_init() do {} while (0) @@ -140,5 +144,6 @@ static inline int page_mkclean(struct page *page) #define SWAP_SUCCESS 0 #define SWAP_AGAIN 1 #define SWAP_FAIL 2 +#define SWAP_MLOCK 3 #endif /* _LINUX_RMAP_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index c226c7b8294..f52dbd3587a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -403,12 +403,21 @@ extern int get_dumpable(struct mm_struct *mm); #define MMF_DUMP_MAPPED_PRIVATE 4 #define MMF_DUMP_MAPPED_SHARED 5 #define MMF_DUMP_ELF_HEADERS 6 +#define MMF_DUMP_HUGETLB_PRIVATE 7 +#define MMF_DUMP_HUGETLB_SHARED 8 #define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS -#define MMF_DUMP_FILTER_BITS 5 +#define MMF_DUMP_FILTER_BITS 7 #define MMF_DUMP_FILTER_MASK \ (((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT) #define MMF_DUMP_FILTER_DEFAULT \ - ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED)) + ((1 << MMF_DUMP_ANON_PRIVATE) | (1 << MMF_DUMP_ANON_SHARED) |\ + (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF) + +#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS +# define MMF_DUMP_MASK_DEFAULT_ELF (1 << MMF_DUMP_ELF_HEADERS) +#else +# define MMF_DUMP_MASK_DEFAULT_ELF 0 +#endif struct sighand_struct { atomic_t count; diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h index a1783b229ef..dc50bcc282a 100644 --- a/include/linux/seq_file.h +++ b/include/linux/seq_file.h @@ -60,6 +60,19 @@ static inline int seq_nodemask(struct seq_file *m, nodemask_t *mask) return seq_bitmap(m, mask->bits, MAX_NUMNODES); } +int seq_bitmap_list(struct seq_file *m, unsigned long *bits, + unsigned int nr_bits); + +static inline int seq_cpumask_list(struct seq_file *m, cpumask_t *mask) +{ + return seq_bitmap_list(m, mask->bits, NR_CPUS); +} + +static inline int seq_nodemask_list(struct seq_file *m, nodemask_t *mask) +{ + return seq_bitmap_list(m, mask->bits, MAX_NUMNODES); +} + int single_open(struct file *, int (*)(struct seq_file *, void *), void *); int single_release(struct inode *, struct file *); void *__seq_open_private(struct file *, const struct seq_operations *, int); diff --git a/include/linux/swab.h b/include/linux/swab.h index 270d5c208a8..bbed279f3b3 100644 --- a/include/linux/swab.h +++ b/include/linux/swab.h @@ -47,8 +47,6 @@ static inline __attribute_const__ __u16 ___swab16(__u16 val) { #ifdef __arch_swab16 return __arch_swab16(val); -#elif defined(__arch_swab16p) - return __arch_swab16p(&val); #else return __const_swab16(val); #endif @@ -58,8 +56,6 @@ static inline __attribute_const__ __u32 ___swab32(__u32 val) { #ifdef __arch_swab32 return __arch_swab32(val); -#elif defined(__arch_swab32p) - return __arch_swab32p(&val); #else return __const_swab32(val); #endif @@ -69,8 +65,6 @@ static inline __attribute_const__ __u64 ___swab64(__u64 val) { #ifdef __arch_swab64 return __arch_swab64(val); -#elif defined(__arch_swab64p) - return __arch_swab64p(&val); #elif defined(__SWAB_64_THRU_32__) __u32 h = val >> 32; __u32 l = val & ((1ULL << 32) - 1); @@ -84,8 +78,6 @@ static inline __attribute_const__ __u32 ___swahw32(__u32 val) { #ifdef __arch_swahw32 return __arch_swahw32(val); -#elif defined(__arch_swahw32p) - return __arch_swahw32p(&val); #else return __const_swahw32(val); #endif @@ -95,8 +87,6 @@ static inline __attribute_const__ __u32 ___swahb32(__u32 val) { #ifdef __arch_swahb32 return __arch_swahb32(val); -#elif defined(__arch_swahb32p) - return __arch_swahb32p(&val); #else return __const_swahb32(val); #endif diff --git a/include/linux/swap.h b/include/linux/swap.h index de40f169a4e..a3af95b2cb6 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -7,6 +7,7 @@ #include <linux/list.h> #include <linux/memcontrol.h> #include <linux/sched.h> +#include <linux/node.h> #include <asm/atomic.h> #include <asm/page.h> @@ -171,8 +172,10 @@ extern unsigned int nr_free_pagecache_pages(void); /* linux/mm/swap.c */ -extern void lru_cache_add(struct page *); -extern void lru_cache_add_active(struct page *); +extern void __lru_cache_add(struct page *, enum lru_list lru); +extern void lru_cache_add_lru(struct page *, enum lru_list lru); +extern void lru_cache_add_active_or_unevictable(struct page *, + struct vm_area_struct *); extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); extern void lru_add_drain(void); @@ -180,12 +183,38 @@ extern int lru_add_drain_all(void); extern void rotate_reclaimable_page(struct page *page); extern void swap_setup(void); +extern void add_page_to_unevictable_list(struct page *page); + +/** + * lru_cache_add: add a page to the page lists + * @page: the page to add + */ +static inline void lru_cache_add_anon(struct page *page) +{ + __lru_cache_add(page, LRU_INACTIVE_ANON); +} + +static inline void lru_cache_add_active_anon(struct page *page) +{ + __lru_cache_add(page, LRU_ACTIVE_ANON); +} + +static inline void lru_cache_add_file(struct page *page) +{ + __lru_cache_add(page, LRU_INACTIVE_FILE); +} + +static inline void lru_cache_add_active_file(struct page *page) +{ + __lru_cache_add(page, LRU_ACTIVE_FILE); +} + /* linux/mm/vmscan.c */ 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); -extern int __isolate_lru_page(struct page *page, int mode); +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; extern int remove_mapping(struct address_space *mapping, struct page *page); @@ -204,6 +233,34 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order) } #endif +#ifdef CONFIG_UNEVICTABLE_LRU +extern int page_evictable(struct page *page, struct vm_area_struct *vma); +extern void scan_mapping_unevictable_pages(struct address_space *); + +extern unsigned long scan_unevictable_pages; +extern int scan_unevictable_handler(struct ctl_table *, int, struct file *, + void __user *, size_t *, loff_t *); +extern int scan_unevictable_register_node(struct node *node); +extern void scan_unevictable_unregister_node(struct node *node); +#else +static inline int page_evictable(struct page *page, + struct vm_area_struct *vma) +{ + return 1; +} + +static inline void scan_mapping_unevictable_pages(struct address_space *mapping) +{ +} + +static inline int scan_unevictable_register_node(struct node *node) +{ + return 0; +} + +static inline void scan_unevictable_unregister_node(struct node *node) { } +#endif + extern int kswapd_run(int nid); #ifdef CONFIG_MMU @@ -251,6 +308,7 @@ extern sector_t swapdev_block(int, pgoff_t); extern struct swap_info_struct *get_swap_info_struct(unsigned); extern int can_share_swap_page(struct page *); extern int remove_exclusive_swap_page(struct page *); +extern int remove_exclusive_swap_page_ref(struct page *); struct backing_dev_info; /* linux/mm/thrash.c */ @@ -339,6 +397,11 @@ static inline int remove_exclusive_swap_page(struct page *p) return 0; } +static inline int remove_exclusive_swap_page_ref(struct page *page) +{ + return 0; +} + static inline swp_entry_t get_swap_page(void) { swp_entry_t entry; diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index b330e289d71..9d68fed50f1 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -21,8 +21,9 @@ struct kobject; struct module; /* FIXME - * The *owner field is no longer used, but leave around - * until the tree gets cleaned up fully. + * The *owner field is no longer used. + * x86 tree has been cleaned up. The owner + * attribute is still left for other arches. */ struct attribute { const char *name; diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 328eb402272..4c28c4d564e 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -2,6 +2,7 @@ #define _LINUX_VMALLOC_H #include <linux/spinlock.h> +#include <linux/init.h> #include <asm/page.h> /* pgprot_t */ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ @@ -23,7 +24,6 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ #endif struct vm_struct { - /* keep next,addr,size together to speedup lookups */ struct vm_struct *next; void *addr; unsigned long size; @@ -37,6 +37,19 @@ struct vm_struct { /* * Highlevel APIs for driver use */ +extern void vm_unmap_ram(const void *mem, unsigned int count); +extern void *vm_map_ram(struct page **pages, unsigned int count, + int node, pgprot_t prot); +extern void vm_unmap_aliases(void); + +#ifdef CONFIG_MMU +extern void __init vmalloc_init(void); +#else +static inline void vmalloc_init(void) +{ +} +#endif + extern void *vmalloc(unsigned long size); extern void *vmalloc_user(unsigned long size); extern void *vmalloc_node(unsigned long size, int node); diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h index 58334d43951..9cd3ab0f554 100644 --- a/include/linux/vmstat.h +++ b/include/linux/vmstat.h @@ -41,6 +41,16 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_HUGETLB_PAGE HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL, #endif +#ifdef CONFIG_UNEVICTABLE_LRU + UNEVICTABLE_PGCULLED, /* culled to noreclaim list */ + UNEVICTABLE_PGSCANNED, /* scanned for reclaimability */ + UNEVICTABLE_PGRESCUED, /* rescued from noreclaim list */ + UNEVICTABLE_PGMLOCKED, + UNEVICTABLE_PGMUNLOCKED, + UNEVICTABLE_PGCLEARED, /* on COW, page truncate */ + UNEVICTABLE_PGSTRANDED, /* unable to isolate on unlock */ + UNEVICTABLE_MLOCKFREED, +#endif NR_VM_EVENT_ITEMS }; @@ -159,6 +169,16 @@ static inline unsigned long zone_page_state(struct zone *zone, return x; } +extern unsigned long global_lru_pages(void); + +static inline unsigned long zone_lru_pages(struct zone *zone) +{ + return (zone_page_state(zone, NR_ACTIVE_ANON) + + zone_page_state(zone, NR_ACTIVE_FILE) + + zone_page_state(zone, NR_INACTIVE_ANON) + + zone_page_state(zone, NR_INACTIVE_FILE)); +} + #ifdef CONFIG_NUMA /* * Determine the per node value of a stat item. This function |