X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=include%2Flinux%2Fpagemap.h;h=3c62ed4084922c4f01977bb48ceb18ab4ce805d8;hb=49c39b4953e545ce3b5957cce22e1ade01c6e642;hp=ee700c6eb4427f5582438aaf9f861c134f626a41;hpb=2d6c666e8704cf06267f29a4fa3d2cf823469c38;p=safe%2Fjmp%2Flinux-2.6 diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index ee700c6..3c62ed4 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -11,13 +11,46 @@ #include #include #include +#include +#include /* for in_interrupt() */ /* * Bits in mapping->flags. The lower __GFP_BITS_SHIFT bits are the page * allocation mode flags. */ -#define AS_EIO (__GFP_BITS_SHIFT + 0) /* IO error on async write */ -#define AS_ENOSPC (__GFP_BITS_SHIFT + 1) /* ENOSPC on async write */ +enum mapping_flags { + AS_EIO = __GFP_BITS_SHIFT + 0, /* IO error on async write */ + AS_ENOSPC = __GFP_BITS_SHIFT + 1, /* ENOSPC on async write */ + AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */ + AS_UNEVICTABLE = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */ +}; + +static inline void mapping_set_error(struct address_space *mapping, int error) +{ + if (unlikely(error)) { + if (error == -ENOSPC) + set_bit(AS_ENOSPC, &mapping->flags); + else + set_bit(AS_EIO, &mapping->flags); + } +} + +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; +} static inline gfp_t mapping_gfp_mask(struct address_space * mapping) { @@ -51,97 +84,193 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) #define page_cache_release(page) put_page(page) void release_pages(struct page **pages, int nr, int cold); +/* + * speculatively take a reference to a page. + * If the page is free (_count == 0), then _count is untouched, and 0 + * is returned. Otherwise, _count is incremented by 1 and 1 is returned. + * + * This function must be called inside the same rcu_read_lock() section as has + * been used to lookup the page in the pagecache radix-tree (or page table): + * this allows allocators to use a synchronize_rcu() to stabilize _count. + * + * Unless an RCU grace period has passed, the count of all pages coming out + * of the allocator must be considered unstable. page_count may return higher + * than expected, and put_page must be able to do the right thing when the + * page has been finished with, no matter what it is subsequently allocated + * for (because put_page is what is used here to drop an invalid speculative + * reference). + * + * This is the interesting part of the lockless pagecache (and lockless + * get_user_pages) locking protocol, where the lookup-side (eg. find_get_page) + * has the following pattern: + * 1. find page in radix tree + * 2. conditionally increment refcount + * 3. check the page is still in pagecache (if no, goto 1) + * + * Remove-side that cares about stability of _count (eg. reclaim) has the + * following (with tree_lock held for write): + * A. atomically check refcount is correct and set it to 0 (atomic_cmpxchg) + * B. remove page from pagecache + * C. free the page + * + * There are 2 critical interleavings that matter: + * - 2 runs before A: in this case, A sees elevated refcount and bails out + * - A runs before 2: in this case, 2 sees zero refcount and retries; + * subsequently, B will complete and 1 will find no page, causing the + * lookup to return NULL. + * + * It is possible that between 1 and 2, the page is removed then the exact same + * page is inserted into the same position in pagecache. That's OK: the + * old find_get_page using tree_lock could equally have run before or after + * such a re-insertion, depending on order that locks are granted. + * + * Lookups racing against pagecache insertion isn't a big problem: either 1 + * will find the page or it will not. Likewise, the old find_get_page could run + * either before the insertion or afterwards, depending on timing. + */ +static inline int page_cache_get_speculative(struct page *page) +{ + VM_BUG_ON(in_interrupt()); + +#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU) +# ifdef CONFIG_PREEMPT + VM_BUG_ON(!in_atomic()); +# endif + /* + * Preempt must be disabled here - we rely on rcu_read_lock doing + * this for us. + * + * Pagecache won't be truncated from interrupt context, so if we have + * found a page in the radix tree here, we have pinned its refcount by + * disabling preempt, and hence no need for the "speculative get" that + * SMP requires. + */ + VM_BUG_ON(page_count(page) == 0); + atomic_inc(&page->_count); + +#else + if (unlikely(!get_page_unless_zero(page))) { + /* + * Either the page has been freed, or will be freed. + * In either case, retry here and the caller should + * do the right thing (see comments above). + */ + return 0; + } +#endif + VM_BUG_ON(PageTail(page)); + + return 1; +} + +/* + * Same as above, but add instead of inc (could just be merged) + */ +static inline int page_cache_add_speculative(struct page *page, int count) +{ + VM_BUG_ON(in_interrupt()); + +#if !defined(CONFIG_SMP) && defined(CONFIG_TREE_RCU) +# ifdef CONFIG_PREEMPT + VM_BUG_ON(!in_atomic()); +# endif + VM_BUG_ON(page_count(page) == 0); + atomic_add(count, &page->_count); + +#else + if (unlikely(!atomic_add_unless(&page->_count, count, 0))) + return 0; +#endif + VM_BUG_ON(PageCompound(page) && page != compound_head(page)); + + return 1; +} + +static inline int page_freeze_refs(struct page *page, int count) +{ + return likely(atomic_cmpxchg(&page->_count, count, 0) == count); +} + +static inline void page_unfreeze_refs(struct page *page, int count) +{ + VM_BUG_ON(page_count(page) != 0); + VM_BUG_ON(count == 0); + + atomic_set(&page->_count, count); +} + +#ifdef CONFIG_NUMA +extern struct page *__page_cache_alloc(gfp_t gfp); +#else +static inline struct page *__page_cache_alloc(gfp_t gfp) +{ + return alloc_pages(gfp, 0); +} +#endif + static inline struct page *page_cache_alloc(struct address_space *x) { - return alloc_pages(mapping_gfp_mask(x), 0); + return __page_cache_alloc(mapping_gfp_mask(x)); } static inline struct page *page_cache_alloc_cold(struct address_space *x) { - return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0); + return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_COLD); } typedef int filler_t(void *, struct page *); extern struct page * find_get_page(struct address_space *mapping, - unsigned long index); + pgoff_t index); extern struct page * find_lock_page(struct address_space *mapping, - unsigned long index); -extern struct page * find_trylock_page(struct address_space *mapping, - unsigned long index); + pgoff_t index); extern struct page * find_or_create_page(struct address_space *mapping, - unsigned long index, gfp_t gfp_mask); + pgoff_t index, gfp_t gfp_mask); unsigned find_get_pages(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); +unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, + unsigned int nr_pages, struct page **pages); unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, int tag, unsigned int nr_pages, struct page **pages); +struct page *grab_cache_page_write_begin(struct address_space *mapping, + pgoff_t index, unsigned flags); + /* * Returns locked page at given index in given cache, creating it if needed. */ -static inline struct page *grab_cache_page(struct address_space *mapping, unsigned long index) +static inline struct page *grab_cache_page(struct address_space *mapping, + pgoff_t index) { return find_or_create_page(mapping, index, mapping_gfp_mask(mapping)); } extern struct page * grab_cache_page_nowait(struct address_space *mapping, - unsigned long index); + pgoff_t index); +extern struct page * read_cache_page_async(struct address_space *mapping, + pgoff_t index, filler_t *filler, + void *data); extern struct page * read_cache_page(struct address_space *mapping, - unsigned long index, filler_t *filler, + pgoff_t index, filler_t *filler, void *data); +extern struct page * read_cache_page_gfp(struct address_space *mapping, + pgoff_t index, gfp_t gfp_mask); extern int read_cache_pages(struct address_space *mapping, struct list_head *pages, filler_t *filler, void *data); -int add_to_page_cache(struct page *page, struct address_space *mapping, - unsigned long index, gfp_t gfp_mask); -int add_to_page_cache_lru(struct page *page, struct address_space *mapping, - unsigned long index, gfp_t gfp_mask); -extern void remove_from_page_cache(struct page *page); -extern void __remove_from_page_cache(struct page *page); - -extern atomic_t nr_pagecache; - -#ifdef CONFIG_SMP - -#define PAGECACHE_ACCT_THRESHOLD max(16, NR_CPUS * 2) -DECLARE_PER_CPU(long, nr_pagecache_local); - -/* - * pagecache_acct implements approximate accounting for pagecache. - * vm_enough_memory() do not need high accuracy. Writers will keep - * an offset in their per-cpu arena and will spill that into the - * global count whenever the absolute value of the local count - * exceeds the counter's threshold. - * - * MUST be protected from preemption. - * current protection is mapping->page_lock. - */ -static inline void pagecache_acct(int count) +static inline struct page *read_mapping_page_async( + struct address_space *mapping, + pgoff_t index, void *data) { - long *local; - - local = &__get_cpu_var(nr_pagecache_local); - *local += count; - if (*local > PAGECACHE_ACCT_THRESHOLD || *local < -PAGECACHE_ACCT_THRESHOLD) { - atomic_add(*local, &nr_pagecache); - *local = 0; - } + filler_t *filler = (filler_t *)mapping->a_ops->readpage; + return read_cache_page_async(mapping, index, filler, data); } -#else - -static inline void pagecache_acct(int count) +static inline struct page *read_mapping_page(struct address_space *mapping, + pgoff_t index, void *data) { - atomic_add(count, &nr_pagecache); -} -#endif - -static inline unsigned long get_page_cache_size(void) -{ - int ret = atomic_read(&nr_pagecache); - if (unlikely(ret < 0)) - ret = 0; - return ret; + filler_t *filler = (filler_t *)mapping->a_ops->readpage; + return read_cache_page(mapping, index, filler, data); } /* @@ -160,21 +289,65 @@ static inline pgoff_t linear_page_index(struct vm_area_struct *vma, return pgoff >> (PAGE_CACHE_SHIFT - PAGE_SHIFT); } -extern void FASTCALL(__lock_page(struct page *page)); -extern void FASTCALL(unlock_page(struct page *page)); +extern void __lock_page(struct page *page); +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) +{ + __set_bit(PG_locked, &page->flags); +} + +static inline void __clear_page_locked(struct page *page) +{ + __clear_bit(PG_locked, &page->flags); +} +static inline int trylock_page(struct page *page) +{ + return (likely(!test_and_set_bit_lock(PG_locked, &page->flags))); +} + +/* + * lock_page may only be called if we have the page's inode pinned. + */ static inline void lock_page(struct page *page) { might_sleep(); - if (TestSetPageLocked(page)) + if (!trylock_page(page)) __lock_page(page); } + +/* + * lock_page_killable is like lock_page but can be interrupted by fatal + * signals. It returns 0 if it locked the page and -EINTR if it was + * killed while waiting. + */ +static inline int lock_page_killable(struct page *page) +{ + might_sleep(); + if (!trylock_page(page)) + return __lock_page_killable(page); + return 0; +} + +/* + * lock_page_nosync should only be used if we can't pin the page's inode. + * Doesn't play quite so well with block device plugging. + */ +static inline void lock_page_nosync(struct page *page) +{ + might_sleep(); + if (!trylock_page(page)) + __lock_page_nosync(page); +} /* * This is exported only for wait_on_page_locked/wait_on_page_writeback. * Never use this directly! */ -extern void FASTCALL(wait_on_page_bit(struct page *page, int bit_nr)); +extern void wait_on_page_bit(struct page *page, int bit_nr); /* * Wait for a page to be unlocked. @@ -201,6 +374,11 @@ static inline void wait_on_page_writeback(struct page *page) extern void end_page_writeback(struct page *page); /* + * Add an arbitrary waiter to a page's wait queue + */ +extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter); + +/* * Fault a userspace page into pagetables. Return non-zero on a fault. * * This assumes that two userspace pages are always sufficient. That's @@ -210,6 +388,9 @@ static inline int fault_in_pages_writeable(char __user *uaddr, int size) { int ret; + if (unlikely(size == 0)) + return 0; + /* * Writing zeroes into userspace here is OK, because we know that if * the zero gets there, we'll be overwriting it. @@ -229,19 +410,46 @@ static inline int fault_in_pages_writeable(char __user *uaddr, int size) return ret; } -static inline void fault_in_pages_readable(const char __user *uaddr, int size) +static inline int fault_in_pages_readable(const char __user *uaddr, int size) { volatile char c; int ret; + if (unlikely(size == 0)) + return 0; + ret = __get_user(c, uaddr); if (ret == 0) { const char __user *end = uaddr + size - 1; if (((unsigned long)uaddr & PAGE_MASK) != ((unsigned long)end & PAGE_MASK)) - __get_user(c, end); + ret = __get_user(c, end); } + return ret; +} + +int add_to_page_cache_locked(struct page *page, struct address_space *mapping, + pgoff_t index, gfp_t gfp_mask); +int add_to_page_cache_lru(struct page *page, struct address_space *mapping, + pgoff_t index, gfp_t gfp_mask); +extern void remove_from_page_cache(struct page *page); +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. + */ +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); + error = add_to_page_cache_locked(page, mapping, offset, gfp_mask); + if (unlikely(error)) + __clear_page_locked(page); + return error; } #endif /* _LINUX_PAGEMAP_H */