X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=mm%2Ftruncate.c;h=5df947de7654461d43f1ba0a7ab80b46747239c8;hb=refs%2Fheads%2Fvserver;hp=c9a30ae6206b2eed40bf573d8ae52fac014bba2f;hpb=9bf4aaab3e101692164d49b7ca357651eb691cb6;p=linux-2.6.git diff --git a/mm/truncate.c b/mm/truncate.c index c9a30ae62..5df947de7 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -9,20 +9,39 @@ #include #include +#include #include #include #include +#include #include /* grr. try_to_release_page, - block_invalidatepage */ + do_invalidatepage */ -static int do_invalidatepage(struct page *page, unsigned long offset) +/** + * do_invalidatepage - invalidate part of all of a page + * @page: the page which is affected + * @offset: the index of the truncation point + * + * do_invalidatepage() is called when all or part of the page has become + * invalidated by a truncate operation. + * + * do_invalidatepage() does not have to release all buffers, but it must + * ensure that no dirty buffer is left outside @offset and that no I/O + * is underway against any of the blocks which are outside the truncation + * point. Because the caller is about to free (and possibly reuse) those + * blocks on-disk. + */ +void do_invalidatepage(struct page *page, unsigned long offset) { - int (*invalidatepage)(struct page *, unsigned long); + void (*invalidatepage)(struct page *, unsigned long); invalidatepage = page->mapping->a_ops->invalidatepage; - if (invalidatepage == NULL) +#ifdef CONFIG_BLOCK + if (!invalidatepage) invalidatepage = block_invalidatepage; - return (*invalidatepage)(page, offset); +#endif + if (invalidatepage) + (*invalidatepage)(page, offset); } static inline void truncate_partial_page(struct page *page, unsigned partial) @@ -32,6 +51,33 @@ static inline void truncate_partial_page(struct page *page, unsigned partial) do_invalidatepage(page, partial); } +/* + * This cancels just the dirty bit on the kernel page itself, it + * does NOT actually remove dirty bits on any mmap's that may be + * around. It also leaves the page tagged dirty, so any sync + * activity will still find it on the dirty lists, and in particular, + * clear_page_dirty_for_io() will still look at the dirty bits in + * the VM. + * + * Doing this should *normally* only ever be done when a page + * is truncated, and is not actually mapped anywhere at all. However, + * fs/buffer.c does this when it notices that somebody has cleaned + * out all the buffers on a page without actually doing it through + * the VM. Can you say "ext3 is horribly ugly"? Tought you could. + */ +void cancel_dirty_page(struct page *page, unsigned int account_size) +{ + if (TestClearPageDirty(page)) { + struct address_space *mapping = page->mapping; + if (mapping && mapping_cap_account_dirty(mapping)) { + dec_zone_page_state(page, NR_FILE_DIRTY); + if (account_size) + task_io_account_cancelled_write(account_size); + } + } +} +EXPORT_SYMBOL(cancel_dirty_page); + /* * If truncate cannot remove the fs-private metadata from the page, the page * becomes anonymous. It will be left on the LRU and may even be mapped into @@ -48,10 +94,11 @@ truncate_complete_page(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return; + cancel_dirty_page(page, PAGE_CACHE_SIZE); + if (PagePrivate(page)) do_invalidatepage(page, 0); - clear_page_dirty(page); ClearPageUptodate(page); ClearPageMappedToDisk(page); remove_from_page_cache(page); @@ -61,38 +108,37 @@ truncate_complete_page(struct address_space *mapping, struct page *page) /* * This is for invalidate_inode_pages(). That function can be called at * any time, and is not supposed to throw away dirty pages. But pages can - * be marked dirty at any time too. So we re-check the dirtiness inside - * ->tree_lock. That provides exclusion against the __set_page_dirty - * functions. + * be marked dirty at any time too, so use remove_mapping which safely + * discards clean, unused pages. + * + * Returns non-zero if the page was successfully invalidated. */ static int invalidate_complete_page(struct address_space *mapping, struct page *page) { + int ret; + if (page->mapping != mapping) return 0; if (PagePrivate(page) && !try_to_release_page(page, 0)) return 0; - spin_lock_irq(&mapping->tree_lock); - if (PageDirty(page)) { - spin_unlock_irq(&mapping->tree_lock); - return 0; - } - __remove_from_page_cache(page); - spin_unlock_irq(&mapping->tree_lock); - ClearPageUptodate(page); - page_cache_release(page); /* pagecache ref */ - return 1; + ret = remove_mapping(mapping, page); + + return ret; } /** - * truncate_inode_pages - truncate *all* the pages from an offset + * truncate_inode_pages - truncate range of pages specified by start and + * end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate + * @lend: offset to which to truncate * - * Truncate the page cache at a set offset, removing the pages that are beyond - * that offset (and zeroing out partial pages). + * Truncate the page cache, removing the pages that are between + * specified offsets (and zeroing out partial page + * (if lstart is not page aligned)). * * Truncate takes two passes - the first pass is nonblocking. It will not * block on page locks and it will not block on writeback. The second pass @@ -106,12 +152,12 @@ invalidate_complete_page(struct address_space *mapping, struct page *page) * We pass down the cache-hot hint to the page freeing code. Even if the * mapping is large, it is probably the case that the final pages are the most * recently touched, and freeing happens in ascending file offset order. - * - * Called under (and serialised by) inode->i_sem. */ -void truncate_inode_pages(struct address_space *mapping, loff_t lstart) +void truncate_inode_pages_range(struct address_space *mapping, + loff_t lstart, loff_t lend) { const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; + pgoff_t end; const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1); struct pagevec pvec; pgoff_t next; @@ -120,13 +166,22 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) if (mapping->nrpages == 0) return; + BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1)); + end = (lend >> PAGE_CACHE_SHIFT); + pagevec_init(&pvec, 0); next = start; - while (pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { + while (next <= end && + pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; pgoff_t page_index = page->index; + if (page_index > end) { + next = page_index; + break; + } + if (page_index > next) next = page_index; next++; @@ -155,15 +210,22 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) next = start; for ( ; ; ) { + cond_resched(); if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { if (next == start) break; next = start; continue; } + if (pvec.pages[0]->index > end) { + pagevec_release(&pvec); + break; + } for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; + if (page->index > end) + break; lock_page(page); wait_on_page_writeback(page); if (page->index > next) @@ -175,7 +237,19 @@ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) pagevec_release(&pvec); } } +EXPORT_SYMBOL(truncate_inode_pages_range); +/** + * truncate_inode_pages - truncate *all* the pages from an offset + * @mapping: mapping to truncate + * @lstart: offset from which to truncate + * + * Called under (and serialised by) inode->i_mutex. + */ +void truncate_inode_pages(struct address_space *mapping, loff_t lstart) +{ + truncate_inode_pages_range(mapping, lstart, (loff_t)-1); +} EXPORT_SYMBOL(truncate_inode_pages); /** @@ -204,14 +278,24 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; + pgoff_t index; + int lock_failed; - if (TestSetPageLocked(page)) { - next++; - continue; - } - if (page->index > next) - next = page->index; + lock_failed = TestSetPageLocked(page); + + /* + * We really shouldn't be looking at the ->index of an + * unlocked page. But we're not allowed to lock these + * pages. So we rely upon nobody altering the ->index + * of this (pinned-by-us) page. + */ + index = page->index; + if (index > next) + next = index; next++; + if (lock_failed) + continue; + if (PageDirty(page) || PageWriteback(page)) goto unlock; if (page_mapped(page)) @@ -223,7 +307,6 @@ unlock: break; } pagevec_release(&pvec); - cond_resched(); } return ret; } @@ -232,50 +315,135 @@ unsigned long invalidate_inode_pages(struct address_space *mapping) { return invalidate_mapping_pages(mapping, 0, ~0UL); } - EXPORT_SYMBOL(invalidate_inode_pages); +/* + * This is like invalidate_complete_page(), except it ignores the page's + * refcount. We do this because invalidate_inode_pages2() needs stronger + * invalidation guarantees, and cannot afford to leave pages behind because + * shrink_list() has a temp ref on them, or because they're transiently sitting + * in the lru_cache_add() pagevecs. + */ +static int +invalidate_complete_page2(struct address_space *mapping, struct page *page) +{ + if (page->mapping != mapping) + return 0; + + if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL)) + return 0; + + write_lock_irq(&mapping->tree_lock); + if (PageDirty(page)) + goto failed; + + BUG_ON(PagePrivate(page)); + __remove_from_page_cache(page); + write_unlock_irq(&mapping->tree_lock); + ClearPageUptodate(page); + page_cache_release(page); /* pagecache ref */ + return 1; +failed: + write_unlock_irq(&mapping->tree_lock); + return 0; +} + +static int do_launder_page(struct address_space *mapping, struct page *page) +{ + if (!PageDirty(page)) + return 0; + if (page->mapping != mapping || mapping->a_ops->launder_page == NULL) + return 0; + return mapping->a_ops->launder_page(page); +} + /** - * invalidate_inode_pages2 - remove all unmapped pages from an address_space - * @mapping - the address_space - * - * invalidate_inode_pages2() is like truncate_inode_pages(), except for the case - * where the page is seen to be mapped into process pagetables. In that case, - * the page is marked clean but is left attached to its address_space. + * invalidate_inode_pages2_range - remove range of pages from an address_space + * @mapping: the address_space + * @start: the page offset 'from' which to invalidate + * @end: the page offset 'to' which to invalidate (inclusive) * - * The page is also marked not uptodate so that a subsequent pagefault will - * perform I/O to bringthe page's contents back into sync with its backing - * store. + * Any pages which are found to be mapped into pagetables are unmapped prior to + * invalidation. * - * FIXME: invalidate_inode_pages2() is probably trivially livelockable. + * Returns -EIO if any pages could not be invalidated. */ -void invalidate_inode_pages2(struct address_space *mapping) +int invalidate_inode_pages2_range(struct address_space *mapping, + pgoff_t start, pgoff_t end) { struct pagevec pvec; - pgoff_t next = 0; + pgoff_t next; int i; + int ret = 0; + int did_range_unmap = 0; + int wrapped = 0; pagevec_init(&pvec, 0); - while (pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { - for (i = 0; i < pagevec_count(&pvec); i++) { + next = start; + while (next <= end && !ret && !wrapped && + pagevec_lookup(&pvec, mapping, next, + min(end - next, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + for (i = 0; !ret && i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; + pgoff_t page_index; lock_page(page); - if (page->mapping == mapping) { /* truncate race? */ - wait_on_page_writeback(page); - next = page->index + 1; - if (page_mapped(page)) { - clear_page_dirty(page); - ClearPageUptodate(page); + if (page->mapping != mapping) { + unlock_page(page); + continue; + } + page_index = page->index; + next = page_index + 1; + if (next == 0) + wrapped = 1; + if (page_index > end) { + unlock_page(page); + break; + } + wait_on_page_writeback(page); + while (page_mapped(page)) { + if (!did_range_unmap) { + /* + * Zap the rest of the file in one hit. + */ + unmap_mapping_range(mapping, + (loff_t)page_index<