// SPDX-License-Identifier: GPL-2.0-only /* * mm/truncate.c - code for taking down pages from address_spaces * * Copyright (C) 2002, Linus Torvalds * * 10Sep2002 Andrew Morton * Initial version. */ #include <linux/kernel.h> #include <linux/backing-dev.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/pagevec.h> #include <linux/task_io_accounting_ops.h> #include <linux/shmem_fs.h> #include <linux/rmap.h> #include "internal.h" /* * Regular page slots are stabilized by the page lock even without the tree * itself locked. These unlocked entries need verification under the tree * lock. */ static inline void __clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { … } static void clear_shadow_entries(struct address_space *mapping, struct folio_batch *fbatch, pgoff_t *indices) { … } /* * Unconditionally remove exceptional entries. Usually called from truncate * path. Note that the folio_batch may be altered by this function by removing * exceptional entries similar to what folio_batch_remove_exceptionals() does. */ static void truncate_folio_batch_exceptionals(struct address_space *mapping, struct folio_batch *fbatch, pgoff_t *indices) { … } /** * folio_invalidate - Invalidate part or all of a folio. * @folio: The folio which is affected. * @offset: start of the range to invalidate * @length: length of the range to invalidate * * folio_invalidate() is called when all or part of the folio has become * invalidated by a truncate operation. * * folio_invalidate() 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 folio_invalidate(struct folio *folio, size_t offset, size_t length) { … } EXPORT_SYMBOL_GPL(…); /* * If truncate cannot remove the fs-private metadata from the page, the page * becomes orphaned. It will be left on the LRU and may even be mapped into * user pagetables if we're racing with filemap_fault(). * * We need to bail out if page->mapping is no longer equal to the original * mapping. This happens a) when the VM reclaimed the page while we waited on * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ static void truncate_cleanup_folio(struct folio *folio) { … } int truncate_inode_folio(struct address_space *mapping, struct folio *folio) { … } /* * Handle partial folios. The folio may be entirely within the * range if a split has raced with us. If not, we zero the part of the * folio that's within the [start, end] range, and then split the folio if * it's large. split_page_range() will discard pages which now lie beyond * i_size, and we rely on the caller to discard pages which lie within a * newly created hole. * * Returns false if splitting failed so the caller can avoid * discarding the entire folio which is stubbornly unsplit. */ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end) { … } /* * Used to get rid of pages on hardware memory corruption. */ int generic_error_remove_folio(struct address_space *mapping, struct folio *folio) { … } EXPORT_SYMBOL(…); /** * mapping_evict_folio() - Remove an unused folio from the page-cache. * @mapping: The mapping this folio belongs to. * @folio: The folio to remove. * * Safely remove one folio from the page cache. * It only drops clean, unused folios. * * Context: Folio must be locked. * Return: The number of pages successfully removed. */ long mapping_evict_folio(struct address_space *mapping, struct folio *folio) { … } /** * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate * @lend: offset to which to truncate (inclusive) * * Truncate the page cache, removing the pages that are between * specified offsets (and zeroing out partial pages * if lstart or lend + 1 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 * will wait. This is to prevent as much IO as possible in the affected region. * The first pass will remove most pages, so the search cost of the second pass * is low. * * 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. * * Note that since ->invalidate_folio() accepts range to invalidate * truncate_inode_pages_range is able to handle cases where lend + 1 is not * page aligned properly. */ void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, loff_t lend) { … } EXPORT_SYMBOL(…); /** * 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_rwsem and * mapping->invalidate_lock. * * Note: When this function returns, there can be a page in the process of * deletion (inside __filemap_remove_folio()) in the specified range. Thus * mapping->nrpages can be non-zero when this function returns even after * truncation of the whole mapping. */ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) { … } EXPORT_SYMBOL(…); /** * truncate_inode_pages_final - truncate *all* pages before inode dies * @mapping: mapping to truncate * * Called under (and serialized by) inode->i_rwsem. * * Filesystems have to use this in the .evict_inode path to inform the * VM that this is the final truncate and the inode is going away. */ void truncate_inode_pages_final(struct address_space *mapping) { … } EXPORT_SYMBOL(…); /** * mapping_try_invalidate - Invalidate all the evictable folios of one inode * @mapping: the address_space which holds the folios to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * @nr_failed: How many folio invalidations failed * * This function is similar to invalidate_mapping_pages(), except that it * returns the number of folios which could not be evicted in @nr_failed. */ unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed) { … } /** * invalidate_mapping_pages - Invalidate all clean, unlocked cache of one inode * @mapping: the address_space which holds the cache to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * * This function removes pages that are clean, unmapped and unlocked, * as well as shadow entries. It will not block on IO activity. * * If you want to remove all the pages of one inode, regardless of * their use and writeback state, use truncate_inode_pages(). * * Return: The number of indices that had their contents invalidated */ unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { … } EXPORT_SYMBOL(…); /* * This is like mapping_evict_folio(), except it ignores the folio's * refcount. We do this because invalidate_inode_pages2() needs stronger * invalidation guarantees, and cannot afford to leave folios behind because * shrink_folio_list() has a temp ref on them, or because they're transiently * sitting in the folio_add_lru() caches. */ static int invalidate_complete_folio2(struct address_space *mapping, struct folio *folio) { … } static int folio_launder(struct address_space *mapping, struct folio *folio) { … } /** * 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) * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { … } EXPORT_SYMBOL_GPL(…); /** * invalidate_inode_pages2 - remove all pages from an address_space * @mapping: the address_space * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2(struct address_space *mapping) { … } EXPORT_SYMBOL_GPL(…); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache * is called. * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache(struct inode *inode, loff_t newsize) { … } EXPORT_SYMBOL(…); /** * truncate_setsize - update inode and pagecache for a new file size * @inode: inode * @newsize: new file size * * truncate_setsize updates i_size and performs pagecache truncation (if * necessary) to @newsize. It will be typically be called from the filesystem's * setattr function when ATTR_SIZE is passed in. * * Must be called with a lock serializing truncates and writes (generally * i_rwsem but e.g. xfs uses a different lock) and before all filesystem * specific block truncation has been performed. */ void truncate_setsize(struct inode *inode, loff_t newsize) { … } EXPORT_SYMBOL(…); /** * pagecache_isize_extended - update pagecache after extension of i_size * @inode: inode for which i_size was extended * @from: original inode size * @to: new inode size * * Handle extension of inode size either caused by extending truncate or * by write starting after current i_size. We mark the page straddling * current i_size RO so that page_mkwrite() is called on the first * write access to the page. The filesystem will update its per-block * information before user writes to the page via mmap after the i_size * has been changed. * * The function must be called after i_size is updated so that page fault * coming after we unlock the folio will already see the new i_size. * The function must be called while we still hold i_rwsem - this not only * makes sure i_size is stable but also that userspace cannot observe new * i_size value before we are prepared to store mmap writes at new inode size. */ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { … } EXPORT_SYMBOL(…); /** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole * @lend: offset of last byte of hole * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) { … } EXPORT_SYMBOL(…);
Codebase Browser
linux