/* *	linux/mm/filemap.c * * Copyright (C) 1994-1999  Linus Torvalds */ /* * This file handles the generic file mmap semantics used by * most "normal" filesystems (but you don't /have/ to use this: * the NFS filesystem used to do this differently, for example) */#include <linux/export.h>#include <linux/compiler.h>#include <linux/fs.h>#include <linux/uaccess.h>#include <linux/capability.h>#include <linux/kernel_stat.h>#include <linux/gfp.h>#include <linux/mm.h>#include <linux/swap.h>#include <linux/mman.h>#include <linux/pagemap.h>#include <linux/file.h>#include <linux/uio.h>#include <linux/hash.h>#include <linux/writeback.h>#include <linux/backing-dev.h>#include <linux/pagevec.h>#include <linux/blkdev.h>#include <linux/security.h>#include <linux/cpuset.h>#include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */#include <linux/hugetlb.h>#include <linux/memcontrol.h>#include <linux/cleancache.h>#include <linux/rmap.h>#include "internal.h" #define CREATE_TRACE_POINTS#include <trace/events/filemap.h> /* * FIXME: remove all knowledge of the buffer layer from the core VM */#include <linux/buffer_head.h> /* for try_to_free_buffers */ #include <asm/mman.h> /* * Shared mappings implemented 30.11.1994. It's not fully working yet, * though. * * Shared mappings now work. 15.8.1995  Bruno. * * finished 'unifying' the page and buffer cache and SMP-threaded the * page-cache, 21.05.1999, Ingo Molnar <mingo@redhat.com> * * SMP-threaded pagemap-LRU 1999, Andrea Arcangeli <andrea@suse.de> */ /* * Lock ordering: * *  ->i_mmap_rwsem		(truncate_pagecache) *    ->private_lock		(__free_pte->__set_page_dirty_buffers) *      ->swap_lock		(exclusive_swap_page, others) *        ->mapping->tree_lock * *  ->i_mutex *    ->i_mmap_rwsem		(truncate->unmap_mapping_range) * *  ->mmap_sem *    ->i_mmap_rwsem *      ->page_table_lock or pte_lock	(various, mainly in memory.c) *        ->mapping->tree_lock	(arch-dependent flush_dcache_mmap_lock) * *  ->mmap_sem *    ->lock_page		(access_process_vm) * *  ->i_mutex			(generic_perform_write) *    ->mmap_sem		(fault_in_pages_readable->do_page_fault) * *  bdi->wb.list_lock *    sb_lock			(fs/fs-writeback.c) *    ->mapping->tree_lock	(__sync_single_inode) * *  ->i_mmap_rwsem *    ->anon_vma.lock		(vma_adjust) * *  ->anon_vma.lock *    ->page_table_lock or pte_lock	(anon_vma_prepare and various) * *  ->page_table_lock or pte_lock *    ->swap_lock		(try_to_unmap_one) *    ->private_lock		(try_to_unmap_one) *    ->tree_lock		(try_to_unmap_one) *    ->zone.lru_lock		(follow_page->mark_page_accessed) *    ->zone.lru_lock		(check_pte_range->isolate_lru_page) *    ->private_lock		(page_remove_rmap->set_page_dirty) *    ->tree_lock		(page_remove_rmap->set_page_dirty) *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty) *    ->inode->i_lock		(page_remove_rmap->set_page_dirty) *    ->memcg->move_lock	(page_remove_rmap->mem_cgroup_begin_page_stat) *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty) *    ->inode->i_lock		(zap_pte_range->set_page_dirty) *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers) * * ->i_mmap_rwsem *   ->tasklist_lock            (memory_failure, collect_procs_ao) */ static void page_cache_tree_delete(struct address_space *mapping,				   struct page *page, void *shadow){	struct radix_tree_node *node;	unsigned long index;	unsigned int offset;	unsigned int tag;	void **slot; 	VM_BUG_ON(!PageLocked(page)); 	__radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot); 	if (shadow) {		mapping->nrshadows++;		/*		 * Make sure the nrshadows update is committed before		 * the nrpages update so that final truncate racing		 * with reclaim does not see both counters 0 at the		 * same time and miss a shadow entry.		 */		smp_wmb();	}	mapping->nrpages--; 	if (!node) {		/* Clear direct pointer tags in root node */		mapping->page_tree.gfp_mask &= __GFP_BITS_MASK;		radix_tree_replace_slot(slot, shadow);		return;	} 	/* Clear tree tags for the removed page */	index = page->index;	offset = index & RADIX_TREE_MAP_MASK;	for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {		if (test_bit(offset, node->tags[tag]))			radix_tree_tag_clear(&mapping->page_tree, index, tag);	} 	/* Delete page, swap shadow entry */	radix_tree_replace_slot(slot, shadow);	workingset_node_pages_dec(node);	if (shadow)		workingset_node_shadows_inc(node);	else		if (__radix_tree_delete_node(&mapping->page_tree, node))			return; 	/*	 * Track node that only contains shadow entries.	 *	 * Avoid acquiring the list_lru lock if already tracked.  The	 * list_empty() test is safe as node->private_list is	 * protected by mapping->tree_lock.	 */	if (!workingset_node_pages(node) &&	    list_empty(&node->private_list)) {		node->private_data = mapping;		list_lru_add(&workingset_shadow_nodes, &node->private_list);	}} /* * Delete a page from the page cache and free it. Caller has to make * sure the page is locked and that nobody else uses it - or that usage * is safe.  The caller must hold the mapping's tree_lock and * mem_cgroup_begin_page_stat(). */void __delete_from_page_cache(struct page *page, void *shadow,			      struct mem_cgroup *memcg){	struct address_space *mapping = page->mapping; 	trace_mm_filemap_delete_from_page_cache(page);	/*	 * if we're uptodate, flush out into the cleancache, otherwise	 * invalidate any existing cleancache entries.  We can't leave	 * stale data around in the cleancache once our page is gone	 */	if (PageUptodate(page) && PageMappedToDisk(page))		cleancache_put_page(page);	else		cleancache_invalidate_page(mapping, page); 	page_cache_tree_delete(mapping, page, shadow); 	page->mapping = NULL;	/* Leave page->index set: truncation lookup relies upon it */ 	/* hugetlb pages do not participate in page cache accounting. */	if (!PageHuge(page))		__dec_zone_page_state(page, NR_FILE_PAGES);	if (PageSwapBacked(page))		__dec_zone_page_state(page, NR_SHMEM);	BUG_ON(page_mapped(page)); 	/*	 * At this point page must be either written or cleaned by truncate.	 * Dirty page here signals a bug and loss of unwritten data.	 *	 * This fixes dirty accounting after removing the page entirely but	 * leaves PageDirty set: it has no effect for truncated page and	 * anyway will be cleared before returning page into buddy allocator.	 */	if (WARN_ON_ONCE(PageDirty(page)))		account_page_cleaned(page, mapping, memcg,				     inode_to_wb(mapping->host));} /** * delete_from_page_cache - delete page from page cache * @page: the page which the kernel is trying to remove from page cache * * This must be called only on pages that have been verified to be in the page * cache and locked.  It will never put the page into the free list, the caller * has a reference on the page. */void delete_from_page_cache(struct page *page){	struct address_space *mapping = page->mapping;	struct mem_cgroup *memcg;	unsigned long flags; 	void (*freepage)(struct page *); 	BUG_ON(!PageLocked(page)); 	freepage = mapping->a_ops->freepage; 	memcg = mem_cgroup_begin_page_stat(page);	spin_lock_irqsave(&mapping->tree_lock, flags);	__delete_from_page_cache(page, NULL, memcg);	spin_unlock_irqrestore(&mapping->tree_lock, flags);	mem_cgroup_end_page_stat(memcg); 	if (freepage)		freepage(page);	page_cache_release(page);}EXPORT_SYMBOL(delete_from_page_cache); static int filemap_check_errors(struct address_space *mapping){	int ret = 0;	/* Check for outstanding write errors */	if (test_bit(AS_ENOSPC, &mapping->flags) &&	    test_and_clear_bit(AS_ENOSPC, &mapping->flags))		ret = -ENOSPC;	if (test_bit(AS_EIO, &mapping->flags) &&	    test_and_clear_bit(AS_EIO, &mapping->flags))		ret = -EIO;	return ret;} /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping:	address space structure to write * @start:	offset in bytes where the range starts * @end:	offset in bytes where the range ends (inclusive) * @sync_mode:	enable synchronous operation * * Start writeback against all of a mapping's dirty pages that lie * within the byte offsets <start, end> inclusive. * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as * opposed to a regular memory cleansing writeback.  The difference between * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. */int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,				loff_t end, int sync_mode){	int ret;	struct writeback_control wbc = {		.sync_mode = sync_mode,		.nr_to_write = LONG_MAX,		.range_start = start,		.range_end = end,	}; 	if (!mapping_cap_writeback_dirty(mapping))		return 0; 	wbc_attach_fdatawrite_inode(&wbc, mapping->host);	ret = do_writepages(mapping, &wbc);	wbc_detach_inode(&wbc);	return ret;} static inline int __filemap_fdatawrite(struct address_space *mapping,	int sync_mode){	return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode);} int filemap_fdatawrite(struct address_space *mapping){	return __filemap_fdatawrite(mapping, WB_SYNC_ALL);}EXPORT_SYMBOL(filemap_fdatawrite); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,				loff_t end){	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);}EXPORT_SYMBOL(filemap_fdatawrite_range); /** * filemap_flush - mostly a non-blocking flush * @mapping:	target address_space * * This is a mostly non-blocking flush.  Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. */int filemap_flush(struct address_space *mapping){	return __filemap_fdatawrite(mapping, WB_SYNC_NONE);}EXPORT_SYMBOL(filemap_flush); /** * filemap_fdatawait_range - wait for writeback to complete * @mapping:		address space structure to wait for * @start_byte:		offset in bytes where the range starts * @end_byte:		offset in bytes where the range ends (inclusive) * * Walk the list of under-writeback pages of the given address space * in the given range and wait for all of them. */int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,			    loff_t end_byte){	pgoff_t index = start_byte >> PAGE_CACHE_SHIFT;	pgoff_t end = end_byte >> PAGE_CACHE_SHIFT;	struct pagevec pvec;	int nr_pages;	int ret2, ret = 0; 	if (end_byte < start_byte)		goto out; 	pagevec_init(&pvec, 0);	while ((index <= end) &&			(nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,			PAGECACHE_TAG_WRITEBACK,			min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1)) != 0) {		unsigned i; 		for (i = 0; i < nr_pages; i++) {			struct page *page = pvec.pages[i]; 			/* until radix tree lookup accepts end_index */			if (page->index > end)				continue; 			wait_on_page_writeback(page);			if (TestClearPageError(page))				ret = -EIO;		}		pagevec_release(&pvec);		cond_resched();	}out:	ret2 = filemap_check_errors(mapping);	if (!ret)		ret = ret2; 	return ret;}EXPORT_SYMBOL(filemap_fdatawait_range); /** * filemap_fdatawait - wait for all under-writeback pages to complete * @mapping: address space structure to wait for * * Walk the list of under-writeback pages of the given address space * and wait for all of them. */int filemap_fdatawait(struct address_space *mapping){	loff_t i_size = i_size_read(mapping->host); 	if (i_size == 0)		return 0; 	return filemap_fdatawait_range(mapping, 0, i_size - 1);}EXPORT_SYMBOL(filemap_fdatawait); int filemap_write_and_wait(struct address_space *mapping){	int err = 0; 	if (mapping->nrpages) {		err = filemap_fdatawrite(mapping);		/*		 * Even if the above returned error, the pages may be		 * written partially (e.g. -ENOSPC), so we wait for it.		 * But the -EIO is special case, it may indicate the worst		 * thing (e.g. bug) happened, so we avoid waiting for it.		 */		if (err != -EIO) {			int err2 = filemap_fdatawait(mapping);			if (!err)				err = err2;		}	} else {		err = filemap_check_errors(mapping);	}	return err;}EXPORT_SYMBOL(filemap_write_and_wait); /** * filemap_write_and_wait_range - write out & wait on a file range * @mapping:	the address_space for the pages * @lstart:	offset in bytes where the range starts * @lend:	offset in bytes where the range ends (inclusive) * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that `lend' is inclusive (describes the last byte to be written) so * that this function can be used to write to the very end-of-file (end = -1). */int filemap_write_and_wait_range(struct address_space *mapping,				 loff_t lstart, loff_t lend){	int err = 0; 	if (mapping->nrpages) {		err = __filemap_fdatawrite_range(mapping, lstart, lend,						 WB_SYNC_ALL);		/* See comment of filemap_write_and_wait() */		if (err != -EIO) {			int err2 = filemap_fdatawait_range(mapping,						lstart, lend);			if (!err)				err = err2;		}	} else {		err = filemap_check_errors(mapping);	}	return err;}EXPORT_SYMBOL(filemap_write_and_wait_range); /** * replace_page_cache_page - replace a pagecache page with a new one * @old:	page to be replaced * @new:	page to replace with * @gfp_mask:	allocation mode * * This function replaces a page in the pagecache with a new one.  On * success it acquires the pagecache reference for the new page and * drops it for the old page.  Both the old and new pages must be * locked.  This function does not add the new page to the LRU, the * caller must do that. * * The remove + add is atomic.  The only way this function can fail is * memory allocation failure. */int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask){	int error; 	VM_BUG_ON_PAGE(!PageLocked(old), old);	VM_BUG_ON_PAGE(!PageLocked(new), new);	VM_BUG_ON_PAGE(new->mapping, new); 	error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);	if (!error) {		struct address_space *mapping = old->mapping;		void (*freepage)(struct page *);		struct mem_cgroup *memcg;		unsigned long flags; 		pgoff_t offset = old->index;		freepage = mapping->a_ops->freepage; 		page_cache_get(new);		new->mapping = mapping;		new->index = offset; 		memcg = mem_cgroup_begin_page_stat(old);		spin_lock_irqsave(&mapping->tree_lock, flags);		__delete_from_page_cache(old, NULL, memcg);		error = radix_tree_insert(&mapping->page_tree, offset, new);

Lines 1–500 of 2692. Load more