// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/buffer.c * * Copyright (C) 1991, 1992, 2002 Linus Torvalds */ /* * Start bdflush() with kernel_thread not syscall - Paul Gortmaker, 12/95 * * Removed a lot of unnecessary code and simplified things now that * the buffer cache isn't our primary cache - Andrew Tridgell 12/96 * * Speed up hash, lru, and free list operations. Use gfp() for allocating * hash table, use SLAB cache for buffer heads. SMP threading. -DaveM * * Added 32k buffer block sizes - these are required older ARM systems. - RMK * * async buffer flushing, 1999 Andrea Arcangeli <[email protected]> */ #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/syscalls.h> #include <linux/fs.h> #include <linux/iomap.h> #include <linux/mm.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/capability.h> #include <linux/blkdev.h> #include <linux/file.h> #include <linux/quotaops.h> #include <linux/highmem.h> #include <linux/export.h> #include <linux/backing-dev.h> #include <linux/writeback.h> #include <linux/hash.h> #include <linux/suspend.h> #include <linux/buffer_head.h> #include <linux/task_io_accounting_ops.h> #include <linux/bio.h> #include <linux/cpu.h> #include <linux/bitops.h> #include <linux/mpage.h> #include <linux/bit_spinlock.h> #include <linux/pagevec.h> #include <linux/sched/mm.h> #include <trace/events/block.h> #include <linux/fscrypt.h> #include <linux/fsverity.h> #include <linux/sched/isolation.h> #include "internal.h" static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, enum rw_hint hint, struct writeback_control *wbc); #define BH_ENTRY(list) … inline void touch_buffer(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); void __lock_buffer(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); void unlock_buffer(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); /* * Returns if the folio has dirty or writeback buffers. If all the buffers * are unlocked and clean then the folio_test_dirty information is stale. If * any of the buffers are locked, it is assumed they are locked for IO. */ void buffer_check_dirty_writeback(struct folio *folio, bool *dirty, bool *writeback) { … } /* * Block until a buffer comes unlocked. This doesn't stop it * from becoming locked again - you have to lock it yourself * if you want to preserve its state. */ void __wait_on_buffer(struct buffer_head * bh) { … } EXPORT_SYMBOL(…); static void buffer_io_error(struct buffer_head *bh, char *msg) { … } /* * End-of-IO handler helper function which does not touch the bh after * unlocking it. * Note: unlock_buffer() sort-of does touch the bh after unlocking it, but * a race there is benign: unlock_buffer() only use the bh's address for * hashing after unlocking the buffer, so it doesn't actually touch the bh * itself. */ static void __end_buffer_read_notouch(struct buffer_head *bh, int uptodate) { … } /* * Default synchronous end-of-IO handler.. Just mark it up-to-date and * unlock the buffer. */ void end_buffer_read_sync(struct buffer_head *bh, int uptodate) { … } EXPORT_SYMBOL(…); void end_buffer_write_sync(struct buffer_head *bh, int uptodate) { … } EXPORT_SYMBOL(…); /* * Various filesystems appear to want __find_get_block to be non-blocking. * But it's the page lock which protects the buffers. To get around this, * we get exclusion from try_to_free_buffers with the blockdev mapping's * i_private_lock. * * Hack idea: for the blockdev mapping, i_private_lock contention * may be quite high. This code could TryLock the page, and if that * succeeds, there is no need to take i_private_lock. */ static struct buffer_head * __find_get_block_slow(struct block_device *bdev, sector_t block) { … } static void end_buffer_async_read(struct buffer_head *bh, int uptodate) { … } struct postprocess_bh_ctx { … }; static void verify_bh(struct work_struct *work) { … } static bool need_fsverity(struct buffer_head *bh) { … } static void decrypt_bh(struct work_struct *work) { … } /* * I/O completion handler for block_read_full_folio() - pages * which come unlocked at the end of I/O. */ static void end_buffer_async_read_io(struct buffer_head *bh, int uptodate) { … } /* * Completion handler for block_write_full_folio() - folios which are unlocked * during I/O, and which have the writeback flag cleared upon I/O completion. */ static void end_buffer_async_write(struct buffer_head *bh, int uptodate) { … } /* * If a page's buffers are under async readin (end_buffer_async_read * completion) then there is a possibility that another thread of * control could lock one of the buffers after it has completed * but while some of the other buffers have not completed. This * locked buffer would confuse end_buffer_async_read() into not unlocking * the page. So the absence of BH_Async_Read tells end_buffer_async_read() * that this buffer is not under async I/O. * * The page comes unlocked when it has no locked buffer_async buffers * left. * * PageLocked prevents anyone starting new async I/O reads any of * the buffers. * * PageWriteback is used to prevent simultaneous writeout of the same * page. * * PageLocked prevents anyone from starting writeback of a page which is * under read I/O (PageWriteback is only ever set against a locked page). */ static void mark_buffer_async_read(struct buffer_head *bh) { … } static void mark_buffer_async_write_endio(struct buffer_head *bh, bh_end_io_t *handler) { … } void mark_buffer_async_write(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); /* * fs/buffer.c contains helper functions for buffer-backed address space's * fsync functions. A common requirement for buffer-based filesystems is * that certain data from the backing blockdev needs to be written out for * a successful fsync(). For example, ext2 indirect blocks need to be * written back and waited upon before fsync() returns. * * The functions mark_buffer_dirty_inode(), fsync_inode_buffers(), * inode_has_buffers() and invalidate_inode_buffers() are provided for the * management of a list of dependent buffers at ->i_mapping->i_private_list. * * Locking is a little subtle: try_to_free_buffers() will remove buffers * from their controlling inode's queue when they are being freed. But * try_to_free_buffers() will be operating against the *blockdev* mapping * at the time, not against the S_ISREG file which depends on those buffers. * So the locking for i_private_list is via the i_private_lock in the address_space * which backs the buffers. Which is different from the address_space * against which the buffers are listed. So for a particular address_space, * mapping->i_private_lock does *not* protect mapping->i_private_list! In fact, * mapping->i_private_list will always be protected by the backing blockdev's * ->i_private_lock. * * Which introduces a requirement: all buffers on an address_space's * ->i_private_list must be from the same address_space: the blockdev's. * * address_spaces which do not place buffers at ->i_private_list via these * utility functions are free to use i_private_lock and i_private_list for * whatever they want. The only requirement is that list_empty(i_private_list) * be true at clear_inode() time. * * FIXME: clear_inode should not call invalidate_inode_buffers(). The * filesystems should do that. invalidate_inode_buffers() should just go * BUG_ON(!list_empty). * * FIXME: mark_buffer_dirty_inode() is a data-plane operation. It should * take an address_space, not an inode. And it should be called * mark_buffer_dirty_fsync() to clearly define why those buffers are being * queued up. * * FIXME: mark_buffer_dirty_inode() doesn't need to add the buffer to the * list if it is already on a list. Because if the buffer is on a list, * it *must* already be on the right one. If not, the filesystem is being * silly. This will save a ton of locking. But first we have to ensure * that buffers are taken *off* the old inode's list when they are freed * (presumably in truncate). That requires careful auditing of all * filesystems (do it inside bforget()). It could also be done by bringing * b_inode back. */ /* * The buffer's backing address_space's i_private_lock must be held */ static void __remove_assoc_queue(struct buffer_head *bh) { … } int inode_has_buffers(struct inode *inode) { … } /* * osync is designed to support O_SYNC io. It waits synchronously for * all already-submitted IO to complete, but does not queue any new * writes to the disk. * * To do O_SYNC writes, just queue the buffer writes with write_dirty_buffer * as you dirty the buffers, and then use osync_inode_buffers to wait for * completion. Any other dirty buffers which are not yet queued for * write will not be flushed to disk by the osync. */ static int osync_buffers_list(spinlock_t *lock, struct list_head *list) { … } /** * sync_mapping_buffers - write out & wait upon a mapping's "associated" buffers * @mapping: the mapping which wants those buffers written * * Starts I/O against the buffers at mapping->i_private_list, and waits upon * that I/O. * * Basically, this is a convenience function for fsync(). * @mapping is a file or directory which needs those buffers to be written for * a successful fsync(). */ int sync_mapping_buffers(struct address_space *mapping) { … } EXPORT_SYMBOL(…); /** * generic_buffers_fsync_noflush - generic buffer fsync implementation * for simple filesystems with no inode lock * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. */ int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end, bool datasync) { … } EXPORT_SYMBOL(…); /** * generic_buffers_fsync - generic buffer fsync implementation * for simple filesystems with no inode lock * * @file: file to synchronize * @start: start offset in bytes * @end: end offset in bytes (inclusive) * @datasync: only synchronize essential metadata if true * * This is a generic implementation of the fsync method for simple * filesystems which track all non-inode metadata in the buffers list * hanging off the address_space structure. This also makes sure that * a device cache flush operation is called at the end. */ int generic_buffers_fsync(struct file *file, loff_t start, loff_t end, bool datasync) { … } EXPORT_SYMBOL(…); /* * Called when we've recently written block `bblock', and it is known that * `bblock' was for a buffer_boundary() buffer. This means that the block at * `bblock + 1' is probably a dirty indirect block. Hunt it down and, if it's * dirty, schedule it for IO. So that indirects merge nicely with their data. */ void write_boundary_block(struct block_device *bdev, sector_t bblock, unsigned blocksize) { … } void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode) { … } EXPORT_SYMBOL(…); /** * block_dirty_folio - Mark a folio as dirty. * @mapping: The address space containing this folio. * @folio: The folio to mark dirty. * * Filesystems which use buffer_heads can use this function as their * ->dirty_folio implementation. Some filesystems need to do a little * work before calling this function. Filesystems which do not use * buffer_heads should call filemap_dirty_folio() instead. * * If the folio has buffers, the uptodate buffers are set dirty, to * preserve dirty-state coherency between the folio and the buffers. * Buffers added to a dirty folio are created dirty. * * The buffers are dirtied before the folio is dirtied. There's a small * race window in which writeback may see the folio cleanness but not the * buffer dirtiness. That's fine. If this code were to set the folio * dirty before the buffers, writeback could clear the folio dirty flag, * see a bunch of clean buffers and we'd end up with dirty buffers/clean * folio on the dirty folio list. * * We use i_private_lock to lock against try_to_free_buffers() while * using the folio's buffer list. This also prevents clean buffers * being added to the folio after it was set dirty. * * Context: May only be called from process context. Does not sleep. * Caller must ensure that @folio cannot be truncated during this call, * typically by holding the folio lock or having a page in the folio * mapped and holding the page table lock. * * Return: True if the folio was dirtied; false if it was already dirtied. */ bool block_dirty_folio(struct address_space *mapping, struct folio *folio) { … } EXPORT_SYMBOL(…); /* * Write out and wait upon a list of buffers. * * We have conflicting pressures: we want to make sure that all * initially dirty buffers get waited on, but that any subsequently * dirtied buffers don't. After all, we don't want fsync to last * forever if somebody is actively writing to the file. * * Do this in two main stages: first we copy dirty buffers to a * temporary inode list, queueing the writes as we go. Then we clean * up, waiting for those writes to complete. * * During this second stage, any subsequent updates to the file may end * up refiling the buffer on the original inode's dirty list again, so * there is a chance we will end up with a buffer queued for write but * not yet completed on that list. So, as a final cleanup we go through * the osync code to catch these locked, dirty buffers without requeuing * any newly dirty buffers for write. */ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list) { … } /* * Invalidate any and all dirty buffers on a given inode. We are * probably unmounting the fs, but that doesn't mean we have already * done a sync(). Just drop the buffers from the inode list. * * NOTE: we take the inode's blockdev's mapping's i_private_lock. Which * assumes that all the buffers are against the blockdev. Not true * for reiserfs. */ void invalidate_inode_buffers(struct inode *inode) { … } EXPORT_SYMBOL(…); /* * Remove any clean buffers from the inode's buffer list. This is called * when we're trying to free the inode itself. Those buffers can pin it. * * Returns true if all buffers were removed. */ int remove_inode_buffers(struct inode *inode) { … } /* * Create the appropriate buffers when given a folio for data area and * the size of each buffer.. Use the bh->b_this_page linked list to * follow the buffers created. Return NULL if unable to create more * buffers. * * The retry flag is used to differentiate async IO (paging, swapping) * which may not fail from ordinary buffer allocations. */ struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size, gfp_t gfp) { … } EXPORT_SYMBOL_GPL(…); struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size, bool retry) { … } EXPORT_SYMBOL_GPL(…); static inline void link_dev_buffers(struct folio *folio, struct buffer_head *head) { … } static sector_t blkdev_max_block(struct block_device *bdev, unsigned int size) { … } /* * Initialise the state of a blockdev folio's buffers. */ static sector_t folio_init_buffers(struct folio *folio, struct block_device *bdev, unsigned size) { … } /* * Create the page-cache folio that contains the requested block. * * This is used purely for blockdev mappings. * * Returns false if we have a failure which cannot be cured by retrying * without sleeping. Returns true if we succeeded, or the caller should retry. */ static bool grow_dev_folio(struct block_device *bdev, sector_t block, pgoff_t index, unsigned size, gfp_t gfp) { … } /* * Create buffers for the specified block device block's folio. If * that folio was dirty, the buffers are set dirty also. Returns false * if we've hit a permanent error. */ static bool grow_buffers(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { … } static struct buffer_head * __getblk_slow(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { … } /* * The relationship between dirty buffers and dirty pages: * * Whenever a page has any dirty buffers, the page's dirty bit is set, and * the page is tagged dirty in the page cache. * * At all times, the dirtiness of the buffers represents the dirtiness of * subsections of the page. If the page has buffers, the page dirty bit is * merely a hint about the true dirty state. * * When a page is set dirty in its entirety, all its buffers are marked dirty * (if the page has buffers). * * When a buffer is marked dirty, its page is dirtied, but the page's other * buffers are not. * * Also. When blockdev buffers are explicitly read with bread(), they * individually become uptodate. But their backing page remains not * uptodate - even if all of its buffers are uptodate. A subsequent * block_read_full_folio() against that folio will discover all the uptodate * buffers, will set the folio uptodate and will perform no I/O. */ /** * mark_buffer_dirty - mark a buffer_head as needing writeout * @bh: the buffer_head to mark dirty * * mark_buffer_dirty() will set the dirty bit against the buffer, then set * its backing page dirty, then tag the page as dirty in the page cache * and then attach the address_space's inode to its superblock's dirty * inode list. * * mark_buffer_dirty() is atomic. It takes bh->b_folio->mapping->i_private_lock, * i_pages lock and mapping->host->i_lock. */ void mark_buffer_dirty(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); void mark_buffer_write_io_error(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); /** * __brelse - Release a buffer. * @bh: The buffer to release. * * This variant of brelse() can be called if @bh is guaranteed to not be NULL. */ void __brelse(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); /** * __bforget - Discard any dirty data in a buffer. * @bh: The buffer to forget. * * This variant of bforget() can be called if @bh is guaranteed to not * be NULL. */ void __bforget(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); static struct buffer_head *__bread_slow(struct buffer_head *bh) { … } /* * Per-cpu buffer LRU implementation. To reduce the cost of __find_get_block(). * The bhs[] array is sorted - newest buffer is at bhs[0]. Buffers have their * refcount elevated by one when they're in an LRU. A buffer can only appear * once in a particular CPU's LRU. A single buffer can be present in multiple * CPU's LRUs at the same time. * * This is a transparent caching front-end to sb_bread(), sb_getblk() and * sb_find_get_block(). * * The LRUs themselves only need locking against invalidate_bh_lrus. We use * a local interrupt disable for that. */ #define BH_LRU_SIZE … struct bh_lru { … }; static DEFINE_PER_CPU(struct bh_lru, bh_lrus) = …; #ifdef CONFIG_SMP #define bh_lru_lock() … #define bh_lru_unlock() … #else #define bh_lru_lock … #define bh_lru_unlock … #endif static inline void check_irqs_on(void) { … } /* * Install a buffer_head into this cpu's LRU. If not already in the LRU, it is * inserted at the front, and the buffer_head at the back if any is evicted. * Or, if already in the LRU it is moved to the front. */ static void bh_lru_install(struct buffer_head *bh) { … } /* * Look up the bh in this cpu's LRU. If it's there, move it to the head. */ static struct buffer_head * lookup_bh_lru(struct block_device *bdev, sector_t block, unsigned size) { … } /* * Perform a pagecache lookup for the matching buffer. If it's there, refresh * it in the LRU and mark it as accessed. If it is not present then return * NULL */ struct buffer_head * __find_get_block(struct block_device *bdev, sector_t block, unsigned size) { … } EXPORT_SYMBOL(…); /** * bdev_getblk - Get a buffer_head in a block device's buffer cache. * @bdev: The block device. * @block: The block number. * @size: The size of buffer_heads for this @bdev. * @gfp: The memory allocation flags to use. * * The returned buffer head has its reference count incremented, but is * not locked. The caller should call brelse() when it has finished * with the buffer. The buffer may not be uptodate. If needed, the * caller can bring it uptodate either by reading it or overwriting it. * * Return: The buffer head, or NULL if memory could not be allocated. */ struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { … } EXPORT_SYMBOL(…); /* * Do async read-ahead on a buffer.. */ void __breadahead(struct block_device *bdev, sector_t block, unsigned size) { … } EXPORT_SYMBOL(…); /** * __bread_gfp() - Read a block. * @bdev: The block device to read from. * @block: Block number in units of block size. * @size: The block size of this device in bytes. * @gfp: Not page allocation flags; see below. * * You are not expected to call this function. You should use one of * sb_bread(), sb_bread_unmovable() or __bread(). * * Read a specified block, and return the buffer head that refers to it. * If @gfp is 0, the memory will be allocated using the block device's * default GFP flags. If @gfp is __GFP_MOVABLE, the memory may be * allocated from a movable area. Do not pass in a complete set of * GFP flags. * * The returned buffer head has its refcount increased. The caller should * call brelse() when it has finished with the buffer. * * Context: May sleep waiting for I/O. * Return: NULL if the block was unreadable. */ struct buffer_head *__bread_gfp(struct block_device *bdev, sector_t block, unsigned size, gfp_t gfp) { … } EXPORT_SYMBOL(…); static void __invalidate_bh_lrus(struct bh_lru *b) { … } /* * invalidate_bh_lrus() is called rarely - but not only at unmount. * This doesn't race because it runs in each cpu either in irq * or with preempt disabled. */ static void invalidate_bh_lru(void *arg) { … } bool has_bh_in_lru(int cpu, void *dummy) { … } void invalidate_bh_lrus(void) { … } EXPORT_SYMBOL_GPL(…); /* * It's called from workqueue context so we need a bh_lru_lock to close * the race with preemption/irq. */ void invalidate_bh_lrus_cpu(void) { … } void folio_set_bh(struct buffer_head *bh, struct folio *folio, unsigned long offset) { … } EXPORT_SYMBOL(…); /* * Called when truncating a buffer on a page completely. */ /* Bits that are cleared during an invalidate */ #define BUFFER_FLAGS_DISCARD … static void discard_buffer(struct buffer_head * bh) { … } /** * block_invalidate_folio - Invalidate part or all of a buffer-backed folio. * @folio: The folio which is affected. * @offset: start of the range to invalidate * @length: length of the range to invalidate * * block_invalidate_folio() is called when all or part of the folio has been * invalidated by a truncate operation. * * block_invalidate_folio() 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 block_invalidate_folio(struct folio *folio, size_t offset, size_t length) { … } EXPORT_SYMBOL(…); /* * We attach and possibly dirty the buffers atomically wrt * block_dirty_folio() via i_private_lock. try_to_free_buffers * is already excluded via the folio lock. */ struct buffer_head *create_empty_buffers(struct folio *folio, unsigned long blocksize, unsigned long b_state) { … } EXPORT_SYMBOL(…); /** * clean_bdev_aliases: clean a range of buffers in block device * @bdev: Block device to clean buffers in * @block: Start of a range of blocks to clean * @len: Number of blocks to clean * * We are taking a range of blocks for data and we don't want writeback of any * buffer-cache aliases starting from return from this function and until the * moment when something will explicitly mark the buffer dirty (hopefully that * will not happen until we will free that block ;-) We don't even need to mark * it not-uptodate - nobody can expect anything from a newly allocated buffer * anyway. We used to use unmap_buffer() for such invalidation, but that was * wrong. We definitely don't want to mark the alias unmapped, for example - it * would confuse anyone who might pick it with bread() afterwards... * * Also.. Note that bforget() doesn't lock the buffer. So there can be * writeout I/O going on against recently-freed buffers. We don't wait on that * I/O in bforget() - it's more efficient to wait on the I/O only if we really * need to. That happens here. */ void clean_bdev_aliases(struct block_device *bdev, sector_t block, sector_t len) { … } EXPORT_SYMBOL(…); static struct buffer_head *folio_create_buffers(struct folio *folio, struct inode *inode, unsigned int b_state) { … } /* * NOTE! All mapped/uptodate combinations are valid: * * Mapped Uptodate Meaning * * No No "unknown" - must do get_block() * No Yes "hole" - zero-filled * Yes No "allocated" - allocated on disk, not read in * Yes Yes "valid" - allocated and up-to-date in memory. * * "Dirty" is valid only with the last case (mapped+uptodate). */ /* * While block_write_full_folio is writing back the dirty buffers under * the page lock, whoever dirtied the buffers may decide to clean them * again at any time. We handle that by only looking at the buffer * state inside lock_buffer(). * * If block_write_full_folio() is called for regular writeback * (wbc->sync_mode == WB_SYNC_NONE) then it will redirty a page which has a * locked buffer. This only can happen if someone has written the buffer * directly, with submit_bh(). At the address_space level PageWriteback * prevents this contention from occurring. * * If block_write_full_folio() is called with wbc->sync_mode == * WB_SYNC_ALL, the writes are posted using REQ_SYNC; this * causes the writes to be flagged as synchronous writes. */ int __block_write_full_folio(struct inode *inode, struct folio *folio, get_block_t *get_block, struct writeback_control *wbc) { … } EXPORT_SYMBOL(…); /* * If a folio has any new buffers, zero them out here, and mark them uptodate * and dirty so they'll be written out (in order to prevent uninitialised * block data from leaking). And clear the new bit. */ void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to) { … } EXPORT_SYMBOL(…); static int iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh, const struct iomap *iomap) { … } int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap) { … } int __block_write_begin(struct page *page, loff_t pos, unsigned len, get_block_t *get_block) { … } EXPORT_SYMBOL(…); static void __block_commit_write(struct folio *folio, size_t from, size_t to) { … } /* * block_write_begin takes care of the basic task of block allocation and * bringing partial write blocks uptodate first. * * The filesystem needs to handle block truncation upon failure. */ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, get_block_t *get_block) { … } EXPORT_SYMBOL(…); int block_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { … } EXPORT_SYMBOL(…); int generic_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { … } EXPORT_SYMBOL(…); /* * block_is_partially_uptodate checks whether buffers within a folio are * uptodate or not. * * Returns true if all buffers which correspond to the specified part * of the folio are uptodate. */ bool block_is_partially_uptodate(struct folio *folio, size_t from, size_t count) { … } EXPORT_SYMBOL(…); /* * Generic "read_folio" function for block devices that have the normal * get_block functionality. This is most of the block device filesystems. * Reads the folio asynchronously --- the unlock_buffer() and * set/clear_buffer_uptodate() functions propagate buffer state into the * folio once IO has completed. */ int block_read_full_folio(struct folio *folio, get_block_t *get_block) { … } EXPORT_SYMBOL(…); /* utility function for filesystems that need to do work on expanding * truncates. Uses filesystem pagecache writes to allow the filesystem to * deal with the hole. */ int generic_cont_expand_simple(struct inode *inode, loff_t size) { … } EXPORT_SYMBOL(…); static int cont_expand_zero(struct file *file, struct address_space *mapping, loff_t pos, loff_t *bytes) { … } /* * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ int cont_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata, get_block_t *get_block, loff_t *bytes) { … } EXPORT_SYMBOL(…); void block_commit_write(struct page *page, unsigned from, unsigned to) { … } EXPORT_SYMBOL(…); /* * block_page_mkwrite() is not allowed to change the file size as it gets * called from a page fault handler when a page is first dirtied. Hence we must * be careful to check for EOF conditions here. We set the page up correctly * for a written page which means we get ENOSPC checking when writing into * holes and correct delalloc and unwritten extent mapping on filesystems that * support these features. * * We are not allowed to take the i_mutex here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. * * Direct callers of this function should protect against filesystem freezing * using sb_start_pagefault() - sb_end_pagefault() functions. */ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, get_block_t get_block) { … } EXPORT_SYMBOL(…); int block_truncate_page(struct address_space *mapping, loff_t from, get_block_t *get_block) { … } EXPORT_SYMBOL(…); /* * The generic ->writepage function for buffer-backed address_spaces */ int block_write_full_folio(struct folio *folio, struct writeback_control *wbc, void *get_block) { … } sector_t generic_block_bmap(struct address_space *mapping, sector_t block, get_block_t *get_block) { … } EXPORT_SYMBOL(…); static void end_bio_bh_io_sync(struct bio *bio) { … } static void submit_bh_wbc(blk_opf_t opf, struct buffer_head *bh, enum rw_hint write_hint, struct writeback_control *wbc) { … } void submit_bh(blk_opf_t opf, struct buffer_head *bh) { … } EXPORT_SYMBOL(…); void write_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { … } EXPORT_SYMBOL(…); /* * For a data-integrity writeout, we need to wait upon any in-progress I/O * and then start new I/O and then wait upon it. The caller must have a ref on * the buffer_head. */ int __sync_dirty_buffer(struct buffer_head *bh, blk_opf_t op_flags) { … } EXPORT_SYMBOL(…); int sync_dirty_buffer(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); static inline int buffer_busy(struct buffer_head *bh) { … } static bool drop_buffers(struct folio *folio, struct buffer_head **buffers_to_free) { … } /** * try_to_free_buffers - Release buffers attached to this folio. * @folio: The folio. * * If any buffers are in use (dirty, under writeback, elevated refcount), * no buffers will be freed. * * If the folio is dirty but all the buffers are clean then we need to * be sure to mark the folio clean as well. This is because the folio * may be against a block device, and a later reattachment of buffers * to a dirty folio will set *all* buffers dirty. Which would corrupt * filesystem data on the same device. * * The same applies to regular filesystem folios: if all the buffers are * clean then we set the folio clean and proceed. To do that, we require * total exclusion from block_dirty_folio(). That is obtained with * i_private_lock. * * Exclusion against try_to_free_buffers may be obtained by either * locking the folio or by holding its mapping's i_private_lock. * * Context: Process context. @folio must be locked. Will not sleep. * Return: true if all buffers attached to this folio were freed. */ bool try_to_free_buffers(struct folio *folio) { … } EXPORT_SYMBOL(…); /* * Buffer-head allocation */ static struct kmem_cache *bh_cachep __ro_after_init; /* * Once the number of bh's in the machine exceeds this level, we start * stripping them in writeback. */ static unsigned long max_buffer_heads __ro_after_init; int buffer_heads_over_limit; struct bh_accounting { … }; static DEFINE_PER_CPU(struct bh_accounting, bh_accounting) = …; static void recalc_bh_state(void) { … } struct buffer_head *alloc_buffer_head(gfp_t gfp_flags) { … } EXPORT_SYMBOL(…); void free_buffer_head(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); static int buffer_exit_cpu_dead(unsigned int cpu) { … } /** * bh_uptodate_or_lock - Test whether the buffer is uptodate * @bh: struct buffer_head * * Return true if the buffer is up-to-date and false, * with the buffer locked, if not. */ int bh_uptodate_or_lock(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); /** * __bh_read - Submit read for a locked buffer * @bh: struct buffer_head * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ * @wait: wait until reading finish * * Returns zero on success or don't wait, and -EIO on error. */ int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait) { … } EXPORT_SYMBOL(…); /** * __bh_read_batch - Submit read for a batch of unlocked buffers * @nr: entry number of the buffer batch * @bhs: a batch of struct buffer_head * @op_flags: appending REQ_OP_* flags besides REQ_OP_READ * @force_lock: force to get a lock on the buffer if set, otherwise drops any * buffer that cannot lock. * * Returns zero on success or don't wait, and -EIO on error. */ void __bh_read_batch(int nr, struct buffer_head *bhs[], blk_opf_t op_flags, bool force_lock) { … } EXPORT_SYMBOL(…); void __init buffer_init(void) { … }
Codebase Browser
linux