diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-07 04:14:42 (GMT) |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-08-07 04:14:42 (GMT) |
commit | 33caee39925b887a99a2400dc5c980097c3573f9 (patch) | |
tree | 8e68ad97e1fee88c4a3f31453041f8d139f2027e /include | |
parent | 6456a0438b984186a0c9c8ecc9fe3d97b7ac3613 (diff) | |
parent | f84223087402c45179be5e7060c5736c17a7b271 (diff) | |
download | linux-33caee39925b887a99a2400dc5c980097c3573f9.tar.xz |
Merge branch 'akpm' (patchbomb from Andrew Morton)
Merge incoming from Andrew Morton:
- Various misc things.
- arch/sh updates.
- Part of ocfs2. Review is slow.
- Slab updates.
- Most of -mm.
- printk updates.
- lib/ updates.
- checkpatch updates.
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (226 commits)
checkpatch: update $declaration_macros, add uninitialized_var
checkpatch: warn on missing spaces in broken up quoted
checkpatch: fix false positives for --strict "space after cast" test
checkpatch: fix false positive MISSING_BREAK warnings with --file
checkpatch: add test for native c90 types in unusual order
checkpatch: add signed generic types
checkpatch: add short int to c variable types
checkpatch: add for_each tests to indentation and brace tests
checkpatch: fix brace style misuses of else and while
checkpatch: add --fix option for a couple OPEN_BRACE misuses
checkpatch: use the correct indentation for which()
checkpatch: add fix_insert_line and fix_delete_line helpers
checkpatch: add ability to insert and delete lines to patch/file
checkpatch: add an index variable for fixed lines
checkpatch: warn on break after goto or return with same tab indentation
checkpatch: emit a warning on file add/move/delete
checkpatch: add test for commit id formatting style in commit log
checkpatch: emit fewer kmalloc_array/kcalloc conversion warnings
checkpatch: improve "no space after cast" test
checkpatch: allow multiple const * types
...
Diffstat (limited to 'include')
32 files changed, 371 insertions, 322 deletions
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 7ad6345..e1c8d08 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -88,32 +88,32 @@ * lib/bitmap.c provides these functions: */ -extern int __bitmap_empty(const unsigned long *bitmap, int bits); -extern int __bitmap_full(const unsigned long *bitmap, int bits); +extern int __bitmap_empty(const unsigned long *bitmap, unsigned int nbits); +extern int __bitmap_full(const unsigned long *bitmap, unsigned int nbits); extern int __bitmap_equal(const unsigned long *bitmap1, - const unsigned long *bitmap2, int bits); + const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_complement(unsigned long *dst, const unsigned long *src, - int bits); + unsigned int nbits); extern void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, int shift, int bits); extern void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, int shift, int bits); extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, - const unsigned long *bitmap2, int bits); + const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, - const unsigned long *bitmap2, int bits); + const unsigned long *bitmap2, unsigned int nbits); extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, - const unsigned long *bitmap2, int bits); + const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, - const unsigned long *bitmap2, int bits); + const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_intersects(const unsigned long *bitmap1, - const unsigned long *bitmap2, int bits); + const unsigned long *bitmap2, unsigned int nbits); extern int __bitmap_subset(const unsigned long *bitmap1, - const unsigned long *bitmap2, int bits); -extern int __bitmap_weight(const unsigned long *bitmap, int bits); + const unsigned long *bitmap2, unsigned int nbits); +extern int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); -extern void bitmap_set(unsigned long *map, int i, int len); -extern void bitmap_clear(unsigned long *map, int start, int nr); +extern void bitmap_set(unsigned long *map, unsigned int start, int len); +extern void bitmap_clear(unsigned long *map, unsigned int start, int len); extern unsigned long bitmap_find_next_zero_area(unsigned long *map, unsigned long size, unsigned long start, @@ -140,9 +140,9 @@ extern void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, int bits); extern void bitmap_fold(unsigned long *dst, const unsigned long *orig, int sz, int bits); -extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order); -extern void bitmap_release_region(unsigned long *bitmap, int pos, int order); -extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order); +extern int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order); +extern void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order); +extern int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order); extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits); extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits); @@ -188,15 +188,15 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, } static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, int nbits) + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) - return (*dst = *src1 & *src2) != 0; + return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_and(dst, src1, src2, nbits); } static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, int nbits) + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 | *src2; @@ -205,7 +205,7 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1, } static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, int nbits) + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = *src1 ^ *src2; @@ -214,24 +214,24 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, } static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1, - const unsigned long *src2, int nbits) + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) - return (*dst = *src1 & ~(*src2)) != 0; + return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; return __bitmap_andnot(dst, src1, src2, nbits); } static inline void bitmap_complement(unsigned long *dst, const unsigned long *src, - int nbits) + unsigned int nbits) { if (small_const_nbits(nbits)) - *dst = ~(*src) & BITMAP_LAST_WORD_MASK(nbits); + *dst = ~(*src); else __bitmap_complement(dst, src, nbits); } static inline int bitmap_equal(const unsigned long *src1, - const unsigned long *src2, int nbits) + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits)); @@ -240,7 +240,7 @@ static inline int bitmap_equal(const unsigned long *src1, } static inline int bitmap_intersects(const unsigned long *src1, - const unsigned long *src2, int nbits) + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0; @@ -249,7 +249,7 @@ static inline int bitmap_intersects(const unsigned long *src1, } static inline int bitmap_subset(const unsigned long *src1, - const unsigned long *src2, int nbits) + const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits)); @@ -257,7 +257,7 @@ static inline int bitmap_subset(const unsigned long *src1, return __bitmap_subset(src1, src2, nbits); } -static inline int bitmap_empty(const unsigned long *src, int nbits) +static inline int bitmap_empty(const unsigned long *src, unsigned nbits) { if (small_const_nbits(nbits)) return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); @@ -265,7 +265,7 @@ static inline int bitmap_empty(const unsigned long *src, int nbits) return __bitmap_empty(src, nbits); } -static inline int bitmap_full(const unsigned long *src, int nbits) +static inline int bitmap_full(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); @@ -273,7 +273,7 @@ static inline int bitmap_full(const unsigned long *src, int nbits) return __bitmap_full(src, nbits); } -static inline int bitmap_weight(const unsigned long *src, int nbits) +static inline int bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); @@ -284,7 +284,7 @@ static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src, int n, int nbits) { if (small_const_nbits(nbits)) - *dst = *src >> n; + *dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> n; else __bitmap_shift_right(dst, src, n, nbits); } diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h index 0846e6b..89f67c1 100644 --- a/include/linux/byteorder/generic.h +++ b/include/linux/byteorder/generic.h @@ -2,7 +2,7 @@ #define _LINUX_BYTEORDER_GENERIC_H /* - * linux/byteorder_generic.h + * linux/byteorder/generic.h * Generic Byte-reordering support * * The "... p" macros, like le64_to_cpup, can be used with pointers diff --git a/include/linux/cma.h b/include/linux/cma.h new file mode 100644 index 0000000..371b930 --- /dev/null +++ b/include/linux/cma.h @@ -0,0 +1,27 @@ +#ifndef __CMA_H__ +#define __CMA_H__ + +/* + * There is always at least global CMA area and a few optional + * areas configured in kernel .config. + */ +#ifdef CONFIG_CMA_AREAS +#define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) + +#else +#define MAX_CMA_AREAS (0) + +#endif + +struct cma; + +extern phys_addr_t cma_get_base(struct cma *cma); +extern unsigned long cma_get_size(struct cma *cma); + +extern int __init cma_declare_contiguous(phys_addr_t size, + phys_addr_t base, phys_addr_t limit, + phys_addr_t alignment, unsigned int order_per_bit, + bool fixed, struct cma **res_cma); +extern struct page *cma_alloc(struct cma *cma, int count, unsigned int align); +extern bool cma_release(struct cma *cma, struct page *pages, int count); +#endif diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h index 772eab5..569bbd0 100644 --- a/include/linux/dma-contiguous.h +++ b/include/linux/dma-contiguous.h @@ -53,18 +53,13 @@ #ifdef __KERNEL__ +#include <linux/device.h> + struct cma; struct page; -struct device; #ifdef CONFIG_DMA_CMA -/* - * There is always at least global CMA area and a few optional device - * private areas configured in kernel .config. - */ -#define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) - extern struct cma *dma_contiguous_default_area; static inline struct cma *dev_get_cma_area(struct device *dev) @@ -123,8 +118,6 @@ bool dma_release_from_contiguous(struct device *dev, struct page *pages, #else -#define MAX_CMA_AREAS (0) - static inline struct cma *dev_get_cma_area(struct device *dev) { return NULL; diff --git a/include/linux/fs.h b/include/linux/fs.h index 2daccaf..1ab6c69 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2688,7 +2688,7 @@ static const struct file_operations __fops = { \ .read = simple_attr_read, \ .write = simple_attr_write, \ .llseek = generic_file_llseek, \ -}; +} static inline __printf(1, 2) void __simple_attr_check_format(const char *fmt, ...) diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h index fc7718c..ca060d7 100644 --- a/include/linux/fsnotify_backend.h +++ b/include/linux/fsnotify_backend.h @@ -322,16 +322,18 @@ extern int fsnotify_fasync(int fd, struct file *file, int on); extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ -extern int fsnotify_add_notify_event(struct fsnotify_group *group, - struct fsnotify_event *event, - int (*merge)(struct list_head *, - struct fsnotify_event *)); +extern int fsnotify_add_event(struct fsnotify_group *group, + struct fsnotify_event *event, + int (*merge)(struct list_head *, + struct fsnotify_event *)); +/* Remove passed event from groups notification queue */ +extern void fsnotify_remove_event(struct fsnotify_group *group, struct fsnotify_event *event); /* true if the group notification queue is empty */ extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ -extern struct fsnotify_event *fsnotify_peek_notify_event(struct fsnotify_group *group); +extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group); /* return AND dequeue the first event on the notification queue */ -extern struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group); +extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group); /* functions used to manipulate the marks attached to inodes */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 6eb1fb3..5e7219d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -360,7 +360,7 @@ extern unsigned long get_zeroed_page(gfp_t gfp_mask); void *alloc_pages_exact(size_t size, gfp_t gfp_mask); void free_pages_exact(void *virt, size_t size); /* This is different from alloc_pages_exact_node !!! */ -void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); +void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); #define __get_free_page(gfp_mask) \ __get_free_pages((gfp_mask), 0) diff --git a/include/linux/glob.h b/include/linux/glob.h new file mode 100644 index 0000000..861d834 --- /dev/null +++ b/include/linux/glob.h @@ -0,0 +1,9 @@ +#ifndef _LINUX_GLOB_H +#define _LINUX_GLOB_H + +#include <linux/types.h> /* For bool */ +#include <linux/compiler.h> /* For __pure */ + +bool __pure glob_match(char const *pat, char const *str); + +#endif /* _LINUX_GLOB_H */ diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 7fb31da..9286a46 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -93,7 +93,7 @@ static inline int kmap_atomic_idx_push(void) #ifdef CONFIG_DEBUG_HIGHMEM WARN_ON_ONCE(in_irq() && !irqs_disabled()); - BUG_ON(idx > KM_TYPE_NR); + BUG_ON(idx >= KM_TYPE_NR); #endif return idx; } diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index b826239..63579cb 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -93,10 +93,6 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); #endif /* CONFIG_DEBUG_VM */ extern unsigned long transparent_hugepage_flags; -extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, - pmd_t *dst_pmd, pmd_t *src_pmd, - struct vm_area_struct *vma, - unsigned long addr, unsigned long end); extern int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a23c096..6e6d338 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -87,7 +87,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud); #endif extern unsigned long hugepages_treat_as_movable; -extern const unsigned long hugetlb_zero, hugetlb_infinity; extern int sysctl_hugetlb_shm_group; extern struct list_head huge_boot_pages; diff --git a/include/linux/kernel.h b/include/linux/kernel.h index a9e2268..3dc22ab 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -493,11 +493,6 @@ static inline char *hex_byte_pack_upper(char *buf, u8 byte) return buf; } -static inline char * __deprecated pack_hex_byte(char *buf, u8 byte) -{ - return hex_byte_pack(buf, byte); -} - extern int hex_to_bin(char ch); extern int __must_check hex2bin(u8 *dst, const char *src, size_t count); diff --git a/include/linux/klist.h b/include/linux/klist.h index a370ce5..61e5b72 100644 --- a/include/linux/klist.h +++ b/include/linux/klist.h @@ -44,7 +44,7 @@ struct klist_node { extern void klist_add_tail(struct klist_node *n, struct klist *k); extern void klist_add_head(struct klist_node *n, struct klist *k); -extern void klist_add_after(struct klist_node *n, struct klist_node *pos); +extern void klist_add_behind(struct klist_node *n, struct klist_node *pos); extern void klist_add_before(struct klist_node *n, struct klist_node *pos); extern void klist_del(struct klist_node *n); diff --git a/include/linux/list.h b/include/linux/list.h index ef95941..cbbb96f 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -654,15 +654,15 @@ static inline void hlist_add_before(struct hlist_node *n, *(n->pprev) = n; } -static inline void hlist_add_after(struct hlist_node *n, - struct hlist_node *next) +static inline void hlist_add_behind(struct hlist_node *n, + struct hlist_node *prev) { - next->next = n->next; - n->next = next; - next->pprev = &n->next; + n->next = prev->next; + prev->next = n; + n->pprev = &prev->next; - if(next->next) - next->next->pprev = &next->next; + if (n->next) + n->next->pprev = &n->next; } /* after that we'll appear to be on some hlist and hlist_del will work */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index b660e05..e8cc453 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -249,7 +249,7 @@ phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align); /* * Set the allocation direction to bottom-up or top-down. */ -static inline void memblock_set_bottom_up(bool enable) +static inline void __init memblock_set_bottom_up(bool enable) { memblock.bottom_up = enable; } @@ -264,7 +264,7 @@ static inline bool memblock_bottom_up(void) return memblock.bottom_up; } #else -static inline void memblock_set_bottom_up(bool enable) {} +static inline void __init memblock_set_bottom_up(bool enable) {} static inline bool memblock_bottom_up(void) { return false; } #endif diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 010d125..d9524c4 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -26,11 +26,12 @@ enum { MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO, }; -/* Types for control the zone type of onlined memory */ +/* Types for control the zone type of onlined and offlined memory */ enum { - ONLINE_KEEP, - ONLINE_KERNEL, - ONLINE_MOVABLE, + MMOP_OFFLINE = -1, + MMOP_ONLINE_KEEP, + MMOP_ONLINE_KERNEL, + MMOP_ONLINE_MOVABLE, }; /* @@ -258,6 +259,7 @@ static inline void remove_memory(int nid, u64 start, u64 size) {} extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); extern int add_memory(int nid, u64 start, u64 size); +extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default); extern int arch_add_memory(int nid, u64 start, u64 size); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h index edd82a1..2f348d0 100644 --- a/include/linux/mmdebug.h +++ b/include/linux/mmdebug.h @@ -20,11 +20,13 @@ extern void dump_page_badflags(struct page *page, const char *reason, } while (0) #define VM_WARN_ON(cond) WARN_ON(cond) #define VM_WARN_ON_ONCE(cond) WARN_ON_ONCE(cond) +#define VM_WARN_ONCE(cond, format...) WARN_ONCE(cond, format) #else #define VM_BUG_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_BUG_ON_PAGE(cond, page) VM_BUG_ON(cond) #define VM_WARN_ON(cond) BUILD_BUG_ON_INVALID(cond) #define VM_WARN_ON_ONCE(cond) BUILD_BUG_ON_INVALID(cond) +#define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond) #endif #ifdef CONFIG_DEBUG_VIRTUAL diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index deca874..2728869 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -170,6 +170,8 @@ extern int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm); extern void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm); +extern void mmu_notifier_unregister_no_release(struct mmu_notifier *mn, + struct mm_struct *mm); extern void __mmu_notifier_mm_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, @@ -288,6 +290,10 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) set_pte_at(___mm, ___address, __ptep, ___pte); \ }) +extern void mmu_notifier_call_srcu(struct rcu_head *rcu, + void (*func)(struct rcu_head *rcu)); +extern void mmu_notifier_synchronize(void); + #else /* CONFIG_MMU_NOTIFIER */ static inline void mmu_notifier_release(struct mm_struct *mm) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 6cbd1b6..318df70 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -143,6 +143,7 @@ enum zone_stat_item { NR_SHMEM, /* shmem pages (included tmpfs/GEM pages) */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ + NR_PAGES_SCANNED, /* pages scanned since last reclaim */ #ifdef CONFIG_NUMA NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ @@ -324,19 +325,12 @@ enum zone_type { #ifndef __GENERATING_BOUNDS_H struct zone { - /* Fields commonly accessed by the page allocator */ + /* Read-mostly fields */ /* zone watermarks, access with *_wmark_pages(zone) macros */ unsigned long watermark[NR_WMARK]; /* - * When free pages are below this point, additional steps are taken - * when reading the number of free pages to avoid per-cpu counter - * drift allowing watermarks to be breached - */ - unsigned long percpu_drift_mark; - - /* * We don't know if the memory that we're going to allocate will be freeable * or/and it will be released eventually, so to avoid totally wasting several * GB of ram we must reserve some of the lower zone memory (otherwise we risk @@ -344,41 +338,26 @@ struct zone { * on the higher zones). This array is recalculated at runtime if the * sysctl_lowmem_reserve_ratio sysctl changes. */ - unsigned long lowmem_reserve[MAX_NR_ZONES]; - - /* - * This is a per-zone reserve of pages that should not be - * considered dirtyable memory. - */ - unsigned long dirty_balance_reserve; + long lowmem_reserve[MAX_NR_ZONES]; #ifdef CONFIG_NUMA int node; +#endif + /* - * zone reclaim becomes active if more unmapped pages exist. + * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on + * this zone's LRU. Maintained by the pageout code. */ - unsigned long min_unmapped_pages; - unsigned long min_slab_pages; -#endif + unsigned int inactive_ratio; + + struct pglist_data *zone_pgdat; struct per_cpu_pageset __percpu *pageset; + /* - * free areas of different sizes + * This is a per-zone reserve of pages that should not be + * considered dirtyable memory. */ - spinlock_t lock; -#if defined CONFIG_COMPACTION || defined CONFIG_CMA - /* Set to true when the PG_migrate_skip bits should be cleared */ - bool compact_blockskip_flush; - - /* pfn where compaction free scanner should start */ - unsigned long compact_cached_free_pfn; - /* pfn where async and sync compaction migration scanner should start */ - unsigned long compact_cached_migrate_pfn[2]; -#endif -#ifdef CONFIG_MEMORY_HOTPLUG - /* see spanned/present_pages for more description */ - seqlock_t span_seqlock; -#endif - struct free_area free_area[MAX_ORDER]; + unsigned long dirty_balance_reserve; #ifndef CONFIG_SPARSEMEM /* @@ -388,74 +367,14 @@ struct zone { unsigned long *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ -#ifdef CONFIG_COMPACTION - /* - * On compaction failure, 1<<compact_defer_shift compactions - * are skipped before trying again. The number attempted since - * last failure is tracked with compact_considered. - */ - unsigned int compact_considered; - unsigned int compact_defer_shift; - int compact_order_failed; -#endif - - ZONE_PADDING(_pad1_) - - /* Fields commonly accessed by the page reclaim scanner */ - spinlock_t lru_lock; - struct lruvec lruvec; - - /* Evictions & activations on the inactive file list */ - atomic_long_t inactive_age; - - unsigned long pages_scanned; /* since last reclaim */ - unsigned long flags; /* zone flags, see below */ - - /* Zone statistics */ - atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; - - /* - * 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 */ - +#ifdef CONFIG_NUMA /* - * wait_table -- the array holding the hash table - * wait_table_hash_nr_entries -- the size of the hash table array - * wait_table_bits -- wait_table_size == (1 << wait_table_bits) - * - * The purpose of all these is to keep track of the people - * waiting for a page to become available and make them - * runnable again when possible. The trouble is that this - * consumes a lot of space, especially when so few things - * wait on pages at a given time. So instead of using - * per-page waitqueues, we use a waitqueue hash table. - * - * The bucket discipline is to sleep on the same queue when - * colliding and wake all in that wait queue when removing. - * When something wakes, it must check to be sure its page is - * truly available, a la thundering herd. The cost of a - * collision is great, but given the expected load of the - * table, they should be so rare as to be outweighed by the - * benefits from the saved space. - * - * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the - * primary users of these fields, and in mm/page_alloc.c - * free_area_init_core() performs the initialization of them. + * zone reclaim becomes active if more unmapped pages exist. */ - wait_queue_head_t * wait_table; - unsigned long wait_table_hash_nr_entries; - unsigned long wait_table_bits; + unsigned long min_unmapped_pages; + unsigned long min_slab_pages; +#endif /* CONFIG_NUMA */ - /* - * Discontig memory support fields. - */ - struct pglist_data *zone_pgdat; /* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */ unsigned long zone_start_pfn; @@ -500,9 +419,11 @@ struct zone { * adjust_managed_page_count() should be used instead of directly * touching zone->managed_pages and totalram_pages. */ + unsigned long managed_pages; unsigned long spanned_pages; unsigned long present_pages; - unsigned long managed_pages; + + const char *name; /* * Number of MIGRATE_RESEVE page block. To maintain for just @@ -510,10 +431,94 @@ struct zone { */ int nr_migrate_reserve_block; +#ifdef CONFIG_MEMORY_HOTPLUG + /* see spanned/present_pages for more description */ + seqlock_t span_seqlock; +#endif + /* - * rarely used fields: + * wait_table -- the array holding the hash table + * wait_table_hash_nr_entries -- the size of the hash table array + * wait_table_bits -- wait_table_size == (1 << wait_table_bits) + * + * The purpose of all these is to keep track of the people + * waiting for a page to become available and make them + * runnable again when possible. The trouble is that this + * consumes a lot of space, especially when so few things + * wait on pages at a given time. So instead of using + * per-page waitqueues, we use a waitqueue hash table. + * + * The bucket discipline is to sleep on the same queue when + * colliding and wake all in that wait queue when removing. + * When something wakes, it must check to be sure its page is + * truly available, a la thundering herd. The cost of a + * collision is great, but given the expected load of the + * table, they should be so rare as to be outweighed by the + * benefits from the saved space. + * + * __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the + * primary users of these fields, and in mm/page_alloc.c + * free_area_init_core() performs the initialization of them. */ - const char *name; + wait_queue_head_t *wait_table; + unsigned long wait_table_hash_nr_entries; + unsigned long wait_table_bits; + + ZONE_PADDING(_pad1_) + + /* Write-intensive fields used from the page allocator */ + spinlock_t lock; + + /* free areas of different sizes */ + struct free_area free_area[MAX_ORDER]; + + /* zone flags, see below */ + unsigned long flags; + + ZONE_PADDING(_pad2_) + + /* Write-intensive fields used by page reclaim */ + + /* Fields commonly accessed by the page reclaim scanner */ + spinlock_t lru_lock; + struct lruvec lruvec; + + /* Evictions & activations on the inactive file list */ + atomic_long_t inactive_age; + + /* + * When free pages are below this point, additional steps are taken + * when reading the number of free pages to avoid per-cpu counter + * drift allowing watermarks to be breached + */ + unsigned long percpu_drift_mark; + +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + /* pfn where compaction free scanner should start */ + unsigned long compact_cached_free_pfn; + /* pfn where async and sync compaction migration scanner should start */ + unsigned long compact_cached_migrate_pfn[2]; +#endif + +#ifdef CONFIG_COMPACTION + /* + * On compaction failure, 1<<compact_defer_shift compactions + * are skipped before trying again. The number attempted since + * last failure is tracked with compact_considered. + */ + unsigned int compact_considered; + unsigned int compact_defer_shift; + int compact_order_failed; +#endif + +#if defined CONFIG_COMPACTION || defined CONFIG_CMA + /* Set to true when the PG_migrate_skip bits should be cleared */ + bool compact_blockskip_flush; +#endif + + ZONE_PADDING(_pad3_) + /* Zone statistics */ + atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; } ____cacheline_internodealigned_in_smp; typedef enum { @@ -529,6 +534,7 @@ typedef enum { ZONE_WRITEBACK, /* reclaim scanning has recently found * many pages under writeback */ + ZONE_FAIR_DEPLETED, /* fair zone policy batch depleted */ } zone_flags_t; static inline void zone_set_flag(struct zone *zone, zone_flags_t flag) @@ -566,6 +572,11 @@ static inline int zone_is_reclaim_locked(const struct zone *zone) return test_bit(ZONE_RECLAIM_LOCKED, &zone->flags); } +static inline int zone_is_fair_depleted(const struct zone *zone) +{ + return test_bit(ZONE_FAIR_DEPLETED, &zone->flags); +} + static inline int zone_is_oom_locked(const struct zone *zone) { return test_bit(ZONE_OOM_LOCKED, &zone->flags); @@ -872,6 +883,8 @@ static inline int zone_movable_is_highmem(void) { #if defined(CONFIG_HIGHMEM) && defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) return movable_zone == ZONE_HIGHMEM; +#elif defined(CONFIG_HIGHMEM) + return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM; #else return 0; #endif diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 58b9a02..83a6aed 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -430,7 +430,15 @@ static inline int num_node_state(enum node_states state) for_each_node_mask((__node), node_states[__state]) #define first_online_node first_node(node_states[N_ONLINE]) -#define next_online_node(nid) next_node((nid), node_states[N_ONLINE]) +#define first_memory_node first_node(node_states[N_MEMORY]) +static inline int next_online_node(int nid) +{ + return next_node(nid, node_states[N_ONLINE]); +} +static inline int next_memory_node(int nid) +{ + return next_node(nid, node_states[N_MEMORY]); +} extern int nr_node_ids; extern int nr_online_nodes; @@ -471,6 +479,7 @@ static inline int num_node_state(enum node_states state) for ( (node) = 0; (node) == 0; (node) = 1) #define first_online_node 0 +#define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define nr_node_ids 1 #define nr_online_nodes 1 diff --git a/include/linux/oom.h b/include/linux/oom.h index 4cd6267..647395a 100644 --- a/include/linux/oom.h +++ b/include/linux/oom.h @@ -55,8 +55,8 @@ extern void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, struct mem_cgroup *memcg, nodemask_t *nodemask, const char *message); -extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); -extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags); +extern bool oom_zonelist_trylock(struct zonelist *zonelist, gfp_t gfp_flags); +extern void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_flags); extern void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, int order, const nodemask_t *nodemask); diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 8304959..e1f5fcd 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -171,13 +171,12 @@ static inline int __TestClearPage##uname(struct page *page) \ #define __PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname) \ __SETPAGEFLAG(uname, lname) __CLEARPAGEFLAG(uname, lname) -#define PAGEFLAG_FALSE(uname) \ -static inline int Page##uname(const struct page *page) \ - { return 0; } - #define TESTSCFLAG(uname, lname) \ TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname) +#define TESTPAGEFLAG_FALSE(uname) \ +static inline int Page##uname(const struct page *page) { return 0; } + #define SETPAGEFLAG_NOOP(uname) \ static inline void SetPage##uname(struct page *page) { } @@ -187,12 +186,21 @@ static inline void ClearPage##uname(struct page *page) { } #define __CLEARPAGEFLAG_NOOP(uname) \ static inline void __ClearPage##uname(struct page *page) { } +#define TESTSETFLAG_FALSE(uname) \ +static inline int TestSetPage##uname(struct page *page) { return 0; } + #define TESTCLEARFLAG_FALSE(uname) \ static inline int TestClearPage##uname(struct page *page) { return 0; } #define __TESTCLEARFLAG_FALSE(uname) \ static inline int __TestClearPage##uname(struct page *page) { return 0; } +#define PAGEFLAG_FALSE(uname) TESTPAGEFLAG_FALSE(uname) \ + SETPAGEFLAG_NOOP(uname) CLEARPAGEFLAG_NOOP(uname) + +#define TESTSCFLAG_FALSE(uname) \ + TESTSETFLAG_FALSE(uname) TESTCLEARFLAG_FALSE(uname) + struct page; /* forward declaration */ TESTPAGEFLAG(Locked, locked) @@ -248,7 +256,6 @@ PAGEFLAG_FALSE(HighMem) PAGEFLAG(SwapCache, swapcache) #else PAGEFLAG_FALSE(SwapCache) - SETPAGEFLAG_NOOP(SwapCache) CLEARPAGEFLAG_NOOP(SwapCache) #endif PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable) @@ -258,8 +265,8 @@ PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable) PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked) TESTSCFLAG(Mlocked, mlocked) __TESTCLEARFLAG(Mlocked, mlocked) #else -PAGEFLAG_FALSE(Mlocked) SETPAGEFLAG_NOOP(Mlocked) - TESTCLEARFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked) +PAGEFLAG_FALSE(Mlocked) __CLEARPAGEFLAG_NOOP(Mlocked) + TESTSCFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked) #endif #ifdef CONFIG_ARCH_USES_PG_UNCACHED diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index e1474ae..3df8c7d 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -484,6 +484,9 @@ static inline int lock_page_killable(struct page *page) /* * lock_page_or_retry - Lock the page, unless this would block and the * caller indicated that it can handle a retry. + * + * Return value and mmap_sem implications depend on flags; see + * __lock_page_or_retry(). */ static inline int lock_page_or_retry(struct page *page, struct mm_struct *mm, unsigned int flags) diff --git a/include/linux/printk.h b/include/linux/printk.h index 319ff7e..0990997 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -31,7 +31,7 @@ static inline const char *printk_skip_level(const char *buffer) } /* printk's without a loglevel use this.. */ -#define DEFAULT_MESSAGE_LOGLEVEL CONFIG_DEFAULT_MESSAGE_LOGLEVEL +#define MESSAGE_LOGLEVEL_DEFAULT CONFIG_MESSAGE_LOGLEVEL_DEFAULT /* We show everything that is MORE important than this.. */ #define CONSOLE_LOGLEVEL_SILENT 0 /* Mum's the word */ diff --git a/include/linux/rculist.h b/include/linux/rculist.h index 8183b46f..372ad5e 100644 --- a/include/linux/rculist.h +++ b/include/linux/rculist.h @@ -432,9 +432,9 @@ static inline void hlist_add_before_rcu(struct hlist_node *n, } /** - * hlist_add_after_rcu - * @prev: the existing element to add the new element after. + * hlist_add_behind_rcu * @n: the new element to add to the hash list. + * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist @@ -449,8 +449,8 @@ static inline void hlist_add_before_rcu(struct hlist_node *n, * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ -static inline void hlist_add_after_rcu(struct hlist_node *prev, - struct hlist_node *n) +static inline void hlist_add_behind_rcu(struct hlist_node *n, + struct hlist_node *prev) { n->next = prev->next; n->pprev = &prev->next; diff --git a/include/linux/swap.h b/include/linux/swap.h index 4bdbee8..1eb6404 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -311,7 +311,6 @@ extern void lru_add_page_tail(struct page *page, struct page *page_tail, struct lruvec *lruvec, struct list_head *head); extern void activate_page(struct page *); extern void mark_page_accessed(struct page *); -extern void init_page_accessed(struct page *page); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_all(void); diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 4b8a891..b87696f 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -113,7 +113,7 @@ extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); extern int map_vm_area(struct vm_struct *area, pgprot_t prot, - struct page ***pages); + struct page **pages); #ifdef CONFIG_MMU extern int map_kernel_range_noflush(unsigned long start, unsigned long size, pgprot_t prot, struct page **pages); diff --git a/include/linux/zbud.h b/include/linux/zbud.h index 13af0d4..f9d41a6 100644 --- a/include/linux/zbud.h +++ b/include/linux/zbud.h @@ -11,7 +11,7 @@ struct zbud_ops { struct zbud_pool *zbud_create_pool(gfp_t gfp, struct zbud_ops *ops); void zbud_destroy_pool(struct zbud_pool *pool); -int zbud_alloc(struct zbud_pool *pool, unsigned int size, gfp_t gfp, +int zbud_alloc(struct zbud_pool *pool, size_t size, gfp_t gfp, unsigned long *handle); void zbud_free(struct zbud_pool *pool, unsigned long handle); int zbud_reclaim_page(struct zbud_pool *pool, unsigned int retries); diff --git a/include/linux/zlib.h b/include/linux/zlib.h index 9c5a6b4..197abb2 100644 --- a/include/linux/zlib.h +++ b/include/linux/zlib.h @@ -493,64 +493,6 @@ extern int deflateInit2 (z_streamp strm, method). msg is set to null if there is no error message. deflateInit2 does not perform any compression: this will be done by deflate(). */ - -#if 0 -extern int zlib_deflateSetDictionary (z_streamp strm, - const Byte *dictionary, - uInt dictLength); -#endif -/* - Initializes the compression dictionary from the given byte sequence - without producing any compressed output. This function must be called - immediately after deflateInit, deflateInit2 or deflateReset, before any - call of deflate. The compressor and decompressor must use exactly the same - dictionary (see inflateSetDictionary). - - The dictionary should consist of strings (byte sequences) that are likely - to be encountered later in the data to be compressed, with the most commonly - used strings preferably put towards the end of the dictionary. Using a - dictionary is most useful when the data to be compressed is short and can be - predicted with good accuracy; the data can then be compressed better than - with the default empty dictionary. - - Depending on the size of the compression data structures selected by - deflateInit or deflateInit2, a part of the dictionary may in effect be - discarded, for example if the dictionary is larger than the window size in - deflate or deflate2. Thus the strings most likely to be useful should be - put at the end of the dictionary, not at the front. - - Upon return of this function, strm->adler is set to the Adler32 value - of the dictionary; the decompressor may later use this value to determine - which dictionary has been used by the compressor. (The Adler32 value - applies to the whole dictionary even if only a subset of the dictionary is - actually used by the compressor.) - - deflateSetDictionary returns Z_OK if success, or Z_STREAM_ERROR if a - parameter is invalid (such as NULL dictionary) or the stream state is - inconsistent (for example if deflate has already been called for this stream - or if the compression method is bsort). deflateSetDictionary does not - perform any compression: this will be done by deflate(). -*/ - -#if 0 -extern int zlib_deflateCopy (z_streamp dest, z_streamp source); -#endif - -/* - Sets the destination stream as a complete copy of the source stream. - - This function can be useful when several compression strategies will be - tried, for example when there are several ways of pre-processing the input - data with a filter. The streams that will be discarded should then be freed - by calling deflateEnd. Note that deflateCopy duplicates the internal - compression state which can be quite large, so this strategy is slow and - can consume lots of memory. - - deflateCopy returns Z_OK if success, Z_MEM_ERROR if there was not - enough memory, Z_STREAM_ERROR if the source stream state was inconsistent - (such as zalloc being NULL). msg is left unchanged in both source and - destination. -*/ extern int zlib_deflateReset (z_streamp strm); /* @@ -568,27 +510,6 @@ static inline unsigned long deflateBound(unsigned long s) return s + ((s + 7) >> 3) + ((s + 63) >> 6) + 11; } -#if 0 -extern int zlib_deflateParams (z_streamp strm, int level, int strategy); -#endif -/* - Dynamically update the compression level and compression strategy. The - interpretation of level and strategy is as in deflateInit2. This can be - used to switch between compression and straight copy of the input data, or - to switch to a different kind of input data requiring a different - strategy. If the compression level is changed, the input available so far - is compressed with the old level (and may be flushed); the new level will - take effect only at the next call of deflate(). - - Before the call of deflateParams, the stream state must be set as for - a call of deflate(), since the currently available input may have to - be compressed and flushed. In particular, strm->avail_out must be non-zero. - - deflateParams returns Z_OK if success, Z_STREAM_ERROR if the source - stream state was inconsistent or if a parameter was invalid, Z_BUF_ERROR - if strm->avail_out was zero. -*/ - /* extern int inflateInit2 (z_streamp strm, int windowBits); @@ -631,45 +552,6 @@ extern int inflateInit2 (z_streamp strm, int windowBits); and avail_out are unchanged.) */ -extern int zlib_inflateSetDictionary (z_streamp strm, - const Byte *dictionary, - uInt dictLength); -/* - Initializes the decompression dictionary from the given uncompressed byte - sequence. This function must be called immediately after a call of inflate, - if that call returned Z_NEED_DICT. The dictionary chosen by the compressor - can be determined from the adler32 value returned by that call of inflate. - The compressor and decompressor must use exactly the same dictionary (see - deflateSetDictionary). For raw inflate, this function can be called - immediately after inflateInit2() or inflateReset() and before any call of - inflate() to set the dictionary. The application must insure that the - dictionary that was used for compression is provided. - - inflateSetDictionary returns Z_OK if success, Z_STREAM_ERROR if a - parameter is invalid (such as NULL dictionary) or the stream state is - inconsistent, Z_DATA_ERROR if the given dictionary doesn't match the - expected one (incorrect adler32 value). inflateSetDictionary does not - perform any decompression: this will be done by subsequent calls of - inflate(). -*/ - -#if 0 -extern int zlib_inflateSync (z_streamp strm); -#endif -/* - Skips invalid compressed data until a full flush point (see above the - description of deflate with Z_FULL_FLUSH) can be found, or until all - available input is skipped. No output is provided. - - inflateSync returns Z_OK if a full flush point has been found, Z_BUF_ERROR - if no more input was provided, Z_DATA_ERROR if no flush point has been found, - or Z_STREAM_ERROR if the stream structure was inconsistent. In the success - case, the application may save the current current value of total_in which - indicates where valid compressed data was found. In the error case, the - application may repeatedly call inflateSync, providing more input each time, - until success or end of the input data. -*/ - extern int zlib_inflateReset (z_streamp strm); /* This function is equivalent to inflateEnd followed by inflateInit, diff --git a/include/linux/zpool.h b/include/linux/zpool.h new file mode 100644 index 0000000..f14bd75 --- /dev/null +++ b/include/linux/zpool.h @@ -0,0 +1,106 @@ +/* + * zpool memory storage api + * + * Copyright (C) 2014 Dan Streetman + * + * This is a common frontend for the zbud and zsmalloc memory + * storage pool implementations. Typically, this is used to + * store compressed memory. + */ + +#ifndef _ZPOOL_H_ +#define _ZPOOL_H_ + +struct zpool; + +struct zpool_ops { + int (*evict)(struct zpool *pool, unsigned long handle); +}; + +/* + * Control how a handle is mapped. It will be ignored if the + * implementation does not support it. Its use is optional. + * Note that this does not refer to memory protection, it + * refers to how the memory will be copied in/out if copying + * is necessary during mapping; read-write is the safest as + * it copies the existing memory in on map, and copies the + * changed memory back out on unmap. Write-only does not copy + * in the memory and should only be used for initialization. + * If in doubt, use ZPOOL_MM_DEFAULT which is read-write. + */ +enum zpool_mapmode { + ZPOOL_MM_RW, /* normal read-write mapping */ + ZPOOL_MM_RO, /* read-only (no copy-out at unmap time) */ + ZPOOL_MM_WO, /* write-only (no copy-in at map time) */ + + ZPOOL_MM_DEFAULT = ZPOOL_MM_RW +}; + +struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops); + +char *zpool_get_type(struct zpool *pool); + +void zpool_destroy_pool(struct zpool *pool); + +int zpool_malloc(struct zpool *pool, size_t size, gfp_t gfp, + unsigned long *handle); + +void zpool_free(struct zpool *pool, unsigned long handle); + +int zpool_shrink(struct zpool *pool, unsigned int pages, + unsigned int *reclaimed); + +void *zpool_map_handle(struct zpool *pool, unsigned long handle, + enum zpool_mapmode mm); + +void zpool_unmap_handle(struct zpool *pool, unsigned long handle); + +u64 zpool_get_total_size(struct zpool *pool); + + +/** + * struct zpool_driver - driver implementation for zpool + * @type: name of the driver. + * @list: entry in the list of zpool drivers. + * @create: create a new pool. + * @destroy: destroy a pool. + * @malloc: allocate mem from a pool. + * @free: free mem from a pool. + * @shrink: shrink the pool. + * @map: map a handle. + * @unmap: unmap a handle. + * @total_size: get total size of a pool. + * + * This is created by a zpool implementation and registered + * with zpool. + */ +struct zpool_driver { + char *type; + struct module *owner; + atomic_t refcount; + struct list_head list; + + void *(*create)(gfp_t gfp, struct zpool_ops *ops); + void (*destroy)(void *pool); + + int (*malloc)(void *pool, size_t size, gfp_t gfp, + unsigned long *handle); + void (*free)(void *pool, unsigned long handle); + + int (*shrink)(void *pool, unsigned int pages, + unsigned int *reclaimed); + + void *(*map)(void *pool, unsigned long handle, + enum zpool_mapmode mm); + void (*unmap)(void *pool, unsigned long handle); + + u64 (*total_size)(void *pool); +}; + +void zpool_register_driver(struct zpool_driver *driver); + +int zpool_unregister_driver(struct zpool_driver *driver); + +int zpool_evict(void *pool, unsigned long handle); + +#endif diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 4e4f2f8..dd2b546 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -17,6 +17,7 @@ {MR_MEMORY_HOTPLUG, "memory_hotplug"}, \ {MR_SYSCALL, "syscall_or_cpuset"}, \ {MR_MEMPOLICY_MBIND, "mempolicy_mbind"}, \ + {MR_NUMA_MISPLACED, "numa_misplaced"}, \ {MR_CMA, "cma"} TRACE_EVENT(mm_migrate_pages, diff --git a/include/trace/events/pagemap.h b/include/trace/events/pagemap.h index 1c9fabd..ce0803b 100644 --- a/include/trace/events/pagemap.h +++ b/include/trace/events/pagemap.h @@ -28,12 +28,10 @@ TRACE_EVENT(mm_lru_insertion, TP_PROTO( struct page *page, - unsigned long pfn, - int lru, - unsigned long flags + int lru ), - TP_ARGS(page, pfn, lru, flags), + TP_ARGS(page, lru), TP_STRUCT__entry( __field(struct page *, page ) @@ -44,9 +42,9 @@ TRACE_EVENT(mm_lru_insertion, TP_fast_assign( __entry->page = page; - __entry->pfn = pfn; + __entry->pfn = page_to_pfn(page); __entry->lru = lru; - __entry->flags = flags; + __entry->flags = trace_pagemap_flags(page); ), /* Flag format is based on page-types.c formatting for pagemap */ @@ -64,9 +62,9 @@ TRACE_EVENT(mm_lru_insertion, TRACE_EVENT(mm_lru_activate, - TP_PROTO(struct page *page, unsigned long pfn), + TP_PROTO(struct page *page), - TP_ARGS(page, pfn), + TP_ARGS(page), TP_STRUCT__entry( __field(struct page *, page ) @@ -75,7 +73,7 @@ TRACE_EVENT(mm_lru_activate, TP_fast_assign( __entry->page = page; - __entry->pfn = pfn; + __entry->pfn = page_to_pfn(page); ), /* Flag format is based on page-types.c formatting for pagemap */ |