// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ext4/inode.c * * Copyright (C) 1992, 1993, 1994, 1995 * Remy Card ([email protected]) * Laboratoire MASI - Institut Blaise Pascal * Universite Pierre et Marie Curie (Paris VI) * * from * * linux/fs/minix/inode.c * * Copyright (C) 1991, 1992 Linus Torvalds * * 64-bit file support on 64-bit platforms by Jakub Jelinek * ([email protected]) * * Assorted race fixes, rewrite of ext4_get_block() by Al Viro, 2000 */ #include <linux/fs.h> #include <linux/mount.h> #include <linux/time.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/dax.h> #include <linux/quotaops.h> #include <linux/string.h> #include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/pagevec.h> #include <linux/mpage.h> #include <linux/namei.h> #include <linux/uio.h> #include <linux/bio.h> #include <linux/workqueue.h> #include <linux/kernel.h> #include <linux/printk.h> #include <linux/slab.h> #include <linux/bitops.h> #include <linux/iomap.h> #include <linux/iversion.h> #include "ext4_jbd2.h" #include "xattr.h" #include "acl.h" #include "truncate.h" #include <trace/events/ext4.h> static __u32 ext4_inode_csum(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { … } static int ext4_inode_csum_verify(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { … } void ext4_inode_csum_set(struct inode *inode, struct ext4_inode *raw, struct ext4_inode_info *ei) { … } static inline int ext4_begin_ordered_truncate(struct inode *inode, loff_t new_size) { … } static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, int pextents); /* * Test whether an inode is a fast symlink. * A fast symlink has its symlink data stored in ext4_inode_info->i_data. */ int ext4_inode_is_fast_symlink(struct inode *inode) { … } /* * Called at the last iput() if i_nlink is zero. */ void ext4_evict_inode(struct inode *inode) { … } #ifdef CONFIG_QUOTA qsize_t *ext4_get_reserved_space(struct inode *inode) { … } #endif /* * Called with i_data_sem down, which is important since we can call * ext4_discard_preallocations() from here. */ void ext4_da_update_reserve_space(struct inode *inode, int used, int quota_claim) { … } static int __check_block_validity(struct inode *inode, const char *func, unsigned int line, struct ext4_map_blocks *map) { … } int ext4_issue_zeroout(struct inode *inode, ext4_lblk_t lblk, ext4_fsblk_t pblk, ext4_lblk_t len) { … } #define check_block_validity(inode, map) … #ifdef ES_AGGRESSIVE_TEST static void ext4_map_blocks_es_recheck(handle_t *handle, struct inode *inode, struct ext4_map_blocks *es_map, struct ext4_map_blocks *map, int flags) { int retval; map->m_flags = 0; /* * There is a race window that the result is not the same. * e.g. xfstests #223 when dioread_nolock enables. The reason * is that we lookup a block mapping in extent status tree with * out taking i_data_sem. So at the time the unwritten extent * could be converted. */ down_read(&EXT4_I(inode)->i_data_sem); if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) { retval = ext4_ext_map_blocks(handle, inode, map, 0); } else { retval = ext4_ind_map_blocks(handle, inode, map, 0); } up_read((&EXT4_I(inode)->i_data_sem)); /* * We don't check m_len because extent will be collpased in status * tree. So the m_len might not equal. */ if (es_map->m_lblk != map->m_lblk || es_map->m_flags != map->m_flags || es_map->m_pblk != map->m_pblk) { printk("ES cache assertion failed for inode: %lu " "es_cached ex [%d/%d/%llu/%x] != " "found ex [%d/%d/%llu/%x] retval %d flags %x\n", inode->i_ino, es_map->m_lblk, es_map->m_len, es_map->m_pblk, es_map->m_flags, map->m_lblk, map->m_len, map->m_pblk, map->m_flags, retval, flags); } } #endif /* ES_AGGRESSIVE_TEST */ static int ext4_map_query_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map) { … } /* * The ext4_map_blocks() function tries to look up the requested blocks, * and returns if the blocks are already mapped. * * Otherwise it takes the write lock of the i_data_sem and allocate blocks * and store the allocated blocks in the result buffer head and mark it * mapped. * * If file type is extents based, it will call ext4_ext_map_blocks(), * Otherwise, call with ext4_ind_map_blocks() to handle indirect mapping * based files * * On success, it returns the number of blocks being mapped or allocated. * If flags doesn't contain EXT4_GET_BLOCKS_CREATE the blocks are * pre-allocated and unwritten, the resulting @map is marked as unwritten. * If the flags contain EXT4_GET_BLOCKS_CREATE, it will mark @map as mapped. * * It returns 0 if plain look up failed (blocks have not been allocated), in * that case, @map is returned as unmapped but we still do fill map->m_len to * indicate the length of a hole starting at map->m_lblk. * * It returns the error in case of allocation failure. */ int ext4_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { … } /* * Update EXT4_MAP_FLAGS in bh->b_state. For buffer heads attached to pages * we have to be careful as someone else may be manipulating b_state as well. */ static void ext4_update_bh_state(struct buffer_head *bh, unsigned long flags) { … } static int _ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int flags) { … } int ext4_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { … } /* * Get block function used when preparing for buffered write if we require * creating an unwritten extent if blocks haven't been allocated. The extent * will be converted to written after the IO is complete. */ int ext4_get_block_unwritten(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { … } /* Maximum number of blocks we map for direct IO at once. */ #define DIO_MAX_BLOCKS … /* * `handle' can be NULL if create is zero */ struct buffer_head *ext4_getblk(handle_t *handle, struct inode *inode, ext4_lblk_t block, int map_flags) { … } struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode, ext4_lblk_t block, int map_flags) { … } /* Read a contiguous batch of blocks. */ int ext4_bread_batch(struct inode *inode, ext4_lblk_t block, int bh_count, bool wait, struct buffer_head **bhs) { … } int ext4_walk_page_buffers(handle_t *handle, struct inode *inode, struct buffer_head *head, unsigned from, unsigned to, int *partial, int (*fn)(handle_t *handle, struct inode *inode, struct buffer_head *bh)) { … } /* * Helper for handling dirtying of journalled data. We also mark the folio as * dirty so that writeback code knows about this page (and inode) contains * dirty data. ext4_writepages() then commits appropriate transaction to * make data stable. */ static int ext4_dirty_journalled_data(handle_t *handle, struct buffer_head *bh) { … } int do_journal_get_write_access(handle_t *handle, struct inode *inode, struct buffer_head *bh) { … } #ifdef CONFIG_FS_ENCRYPTION static int ext4_block_write_begin(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block) { … } #endif /* * To preserve ordering, it is essential that the hole instantiation and * the data write be encapsulated in a single transaction. We cannot * close off a transaction and start a new one between the ext4_get_block() * and the ext4_write_end(). So doing the jbd2_journal_start at the start of * ext4_write_begin() is the right place. */ static int ext4_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata) { … } /* For write_end() in data=journal mode */ static int write_end_fn(handle_t *handle, struct inode *inode, struct buffer_head *bh) { … } /* * We need to pick up the new inode size which generic_commit_write gave us * `file' can be NULL - eg, when called from page_symlink(). * * ext4 never places buffers on inode->i_mapping->i_private_list. metadata * buffers are managed internally. */ static int ext4_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { … } /* * This is a private version of folio_zero_new_buffers() which doesn't * set the buffer to be dirty, since in data=journalled mode we need * to call ext4_dirty_journalled_data() instead. */ static void ext4_journalled_zero_new_buffers(handle_t *handle, struct inode *inode, struct folio *folio, unsigned from, unsigned to) { … } static int ext4_journalled_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { … } /* * Reserve space for 'nr_resv' clusters */ static int ext4_da_reserve_space(struct inode *inode, int nr_resv) { … } void ext4_da_release_space(struct inode *inode, int to_free) { … } /* * Delayed allocation stuff */ struct mpage_da_data { … }; static void mpage_release_unused_pages(struct mpage_da_data *mpd, bool invalidate) { … } static void ext4_print_free_blocks(struct inode *inode) { … } /* * Check whether the cluster containing lblk has been allocated or has * delalloc reservation. * * Returns 0 if the cluster doesn't have either, 1 if it has delalloc * reservation, 2 if it's already been allocated, negative error code on * failure. */ static int ext4_clu_alloc_state(struct inode *inode, ext4_lblk_t lblk) { … } /* * ext4_insert_delayed_blocks - adds a multiple delayed blocks to the extents * status tree, incrementing the reserved * cluster/block count or making pending * reservations where needed * * @inode - file containing the newly added block * @lblk - start logical block to be added * @len - length of blocks to be added * * Returns 0 on success, negative error code on failure. */ static int ext4_insert_delayed_blocks(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len) { … } /* * Looks up the requested blocks and sets the delalloc extent map. * First try to look up for the extent entry that contains the requested * blocks in the extent status tree without i_data_sem, then try to look * up for the ondisk extent mapping with i_data_sem in read mode, * finally hold i_data_sem in write mode, looks up again and add a * delalloc extent entry if it still couldn't find any extent. Pass out * the mapped extent through @map and return 0 on success. */ static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map) { … } /* * This is a special get_block_t callback which is used by * ext4_da_write_begin(). It will either return mapped block or * reserve space for a single block. * * For delayed buffer_head we have BH_Mapped, BH_New, BH_Delay set. * We also have b_blocknr = -1 and b_bdev initialized properly * * For unwritten buffer_head we have BH_Mapped, BH_New, BH_Unwritten set. * We also have b_blocknr = physicalblock mapping unwritten extent and b_bdev * initialized properly. */ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock, struct buffer_head *bh, int create) { … } static void mpage_folio_done(struct mpage_da_data *mpd, struct folio *folio) { … } static int mpage_submit_folio(struct mpage_da_data *mpd, struct folio *folio) { … } #define BH_FLAGS … /* * mballoc gives us at most this number of blocks... * XXX: That seems to be only a limitation of ext4_mb_normalize_request(). * The rest of mballoc seems to handle chunks up to full group size. */ #define MAX_WRITEPAGES_EXTENT_LEN … /* * mpage_add_bh_to_extent - try to add bh to extent of blocks to map * * @mpd - extent of blocks * @lblk - logical number of the block in the file * @bh - buffer head we want to add to the extent * * The function is used to collect contig. blocks in the same state. If the * buffer doesn't require mapping for writeback and we haven't started the * extent of buffers to map yet, the function returns 'true' immediately - the * caller can write the buffer right away. Otherwise the function returns true * if the block has been added to the extent, false if the block couldn't be * added. */ static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk, struct buffer_head *bh) { … } /* * mpage_process_page_bufs - submit page buffers for IO or add them to extent * * @mpd - extent of blocks for mapping * @head - the first buffer in the page * @bh - buffer we should start processing from * @lblk - logical number of the block in the file corresponding to @bh * * Walk through page buffers from @bh upto @head (exclusive) and either submit * the page for IO if all buffers in this page were mapped and there's no * accumulated extent of buffers to map or add buffers in the page to the * extent of buffers to map. The function returns 1 if the caller can continue * by processing the next page, 0 if it should stop adding buffers to the * extent to map because we cannot extend it anymore. It can also return value * < 0 in case of error during IO submission. */ static int mpage_process_page_bufs(struct mpage_da_data *mpd, struct buffer_head *head, struct buffer_head *bh, ext4_lblk_t lblk) { … } /* * mpage_process_folio - update folio buffers corresponding to changed extent * and may submit fully mapped page for IO * @mpd: description of extent to map, on return next extent to map * @folio: Contains these buffers. * @m_lblk: logical block mapping. * @m_pblk: corresponding physical mapping. * @map_bh: determines on return whether this page requires any further * mapping or not. * * Scan given folio buffers corresponding to changed extent and update buffer * state according to new extent state. * We map delalloc buffers to their physical location, clear unwritten bits. * If the given folio is not fully mapped, we update @mpd to the next extent in * the given folio that needs mapping & return @map_bh as true. */ static int mpage_process_folio(struct mpage_da_data *mpd, struct folio *folio, ext4_lblk_t *m_lblk, ext4_fsblk_t *m_pblk, bool *map_bh) { … } /* * mpage_map_buffers - update buffers corresponding to changed extent and * submit fully mapped pages for IO * * @mpd - description of extent to map, on return next extent to map * * Scan buffers corresponding to changed extent (we expect corresponding pages * to be already locked) and update buffer state according to new extent state. * We map delalloc buffers to their physical location, clear unwritten bits, * and mark buffers as uninit when we perform writes to unwritten extents * and do extent conversion after IO is finished. If the last page is not fully * mapped, we update @map to the next extent in the last page that needs * mapping. Otherwise we submit the page for IO. */ static int mpage_map_and_submit_buffers(struct mpage_da_data *mpd) { … } static int mpage_map_one_extent(handle_t *handle, struct mpage_da_data *mpd) { … } /* * mpage_map_and_submit_extent - map extent starting at mpd->lblk of length * mpd->len and submit pages underlying it for IO * * @handle - handle for journal operations * @mpd - extent to map * @give_up_on_write - we set this to true iff there is a fatal error and there * is no hope of writing the data. The caller should discard * dirty pages to avoid infinite loops. * * The function maps extent starting at mpd->lblk of length mpd->len. If it is * delayed, blocks are allocated, if it is unwritten, we may need to convert * them to initialized or split the described range from larger unwritten * extent. Note that we need not map all the described range since allocation * can return less blocks or the range is covered by more unwritten extents. We * cannot map more because we are limited by reserved transaction credits. On * the other hand we always make sure that the last touched page is fully * mapped so that it can be written out (and thus forward progress is * guaranteed). After mapping we submit all mapped pages for IO. */ static int mpage_map_and_submit_extent(handle_t *handle, struct mpage_da_data *mpd, bool *give_up_on_write) { … } /* * Calculate the total number of credits to reserve for one writepages * iteration. This is called from ext4_writepages(). We map an extent of * up to MAX_WRITEPAGES_EXTENT_LEN blocks and then we go on and finish mapping * the last partial page. So in total we can map MAX_WRITEPAGES_EXTENT_LEN + * bpp - 1 blocks in bpp different extents. */ static int ext4_da_writepages_trans_blocks(struct inode *inode) { … } static int ext4_journal_folio_buffers(handle_t *handle, struct folio *folio, size_t len) { … } static int mpage_journal_page_buffers(handle_t *handle, struct mpage_da_data *mpd, struct folio *folio) { … } /* * mpage_prepare_extent_to_map - find & lock contiguous range of dirty pages * needing mapping, submit mapped pages * * @mpd - where to look for pages * * Walk dirty pages in the mapping. If they are fully mapped, submit them for * IO immediately. If we cannot map blocks, we submit just already mapped * buffers in the page for IO and keep page dirty. When we can map blocks and * we find a page which isn't mapped we start accumulating extent of buffers * underlying these pages that needs mapping (formed by either delayed or * unwritten buffers). We also lock the pages containing these buffers. The * extent found is returned in @mpd structure (starting at mpd->lblk with * length mpd->len blocks). * * Note that this function can attach bios to one io_end structure which are * neither logically nor physically contiguous. Although it may seem as an * unnecessary complication, it is actually inevitable in blocksize < pagesize * case as we need to track IO to all buffers underlying a page in one io_end. */ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) { … } static int ext4_do_writepages(struct mpage_da_data *mpd) { … } static int ext4_writepages(struct address_space *mapping, struct writeback_control *wbc) { … } int ext4_normal_submit_inode_data_buffers(struct jbd2_inode *jinode) { … } static int ext4_dax_writepages(struct address_space *mapping, struct writeback_control *wbc) { … } static int ext4_nonda_switch(struct super_block *sb) { … } static int ext4_da_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata) { … } /* * Check if we should update i_disksize * when write to the end of file but not require block allocation */ static int ext4_da_should_update_i_disksize(struct folio *folio, unsigned long offset) { … } static int ext4_da_do_write_end(struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct folio *folio) { … } static int ext4_da_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { … } /* * Force all delayed allocation blocks to be allocated for a given inode. */ int ext4_alloc_da_blocks(struct inode *inode) { … } /* * bmap() is special. It gets used by applications such as lilo and by * the swapper to find the on-disk block of a specific piece of data. * * Naturally, this is dangerous if the block concerned is still in the * journal. If somebody makes a swapfile on an ext4 data-journaling * filesystem and enables swap, then they may get a nasty shock when the * data getting swapped to that swapfile suddenly gets overwritten by * the original zero's written out previously to the journal and * awaiting writeback in the kernel's buffer cache. * * So, if we see any bmap calls here on a modified, data-journaled file, * take extra steps to flush any blocks which might be in the cache. */ static sector_t ext4_bmap(struct address_space *mapping, sector_t block) { … } static int ext4_read_folio(struct file *file, struct folio *folio) { … } static void ext4_readahead(struct readahead_control *rac) { … } static void ext4_invalidate_folio(struct folio *folio, size_t offset, size_t length) { … } static int __ext4_journalled_invalidate_folio(struct folio *folio, size_t offset, size_t length) { … } /* Wrapper for aops... */ static void ext4_journalled_invalidate_folio(struct folio *folio, size_t offset, size_t length) { … } static bool ext4_release_folio(struct folio *folio, gfp_t wait) { … } static bool ext4_inode_datasync_dirty(struct inode *inode) { … } static void ext4_set_iomap(struct inode *inode, struct iomap *iomap, struct ext4_map_blocks *map, loff_t offset, loff_t length, unsigned int flags) { … } static int ext4_iomap_alloc(struct inode *inode, struct ext4_map_blocks *map, unsigned int flags) { … } static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length, unsigned flags, struct iomap *iomap, struct iomap *srcmap) { … } static int ext4_iomap_overwrite_begin(struct inode *inode, loff_t offset, loff_t length, unsigned flags, struct iomap *iomap, struct iomap *srcmap) { … } static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length, ssize_t written, unsigned flags, struct iomap *iomap) { … } const struct iomap_ops ext4_iomap_ops = …; const struct iomap_ops ext4_iomap_overwrite_ops = …; static int ext4_iomap_begin_report(struct inode *inode, loff_t offset, loff_t length, unsigned int flags, struct iomap *iomap, struct iomap *srcmap) { … } const struct iomap_ops ext4_iomap_report_ops = …; /* * For data=journal mode, folio should be marked dirty only when it was * writeably mapped. When that happens, it was already attached to the * transaction and marked as jbddirty (we take care of this in * ext4_page_mkwrite()). On transaction commit, we writeprotect page mappings * so we should have nothing to do here, except for the case when someone * had the page pinned and dirtied the page through this pin (e.g. by doing * direct IO to it). In that case we'd need to attach buffers here to the * transaction but we cannot due to lock ordering. We cannot just dirty the * folio and leave attached buffers clean, because the buffers' dirty state is * "definitive". We cannot just set the buffers dirty or jbddirty because all * the journalling code will explode. So what we do is to mark the folio * "pending dirty" and next time ext4_writepages() is called, attach buffers * to the transaction appropriately. */ static bool ext4_journalled_dirty_folio(struct address_space *mapping, struct folio *folio) { … } static bool ext4_dirty_folio(struct address_space *mapping, struct folio *folio) { … } static int ext4_iomap_swap_activate(struct swap_info_struct *sis, struct file *file, sector_t *span) { … } static const struct address_space_operations ext4_aops = …; static const struct address_space_operations ext4_journalled_aops = …; static const struct address_space_operations ext4_da_aops = …; static const struct address_space_operations ext4_dax_aops = …; void ext4_set_aops(struct inode *inode) { … } /* * Here we can't skip an unwritten buffer even though it usually reads zero * because it might have data in pagecache (eg, if called from ext4_zero_range, * ext4_punch_hole, etc) which needs to be properly zeroed out. Otherwise a * racing writeback can come later and flush the stale pagecache to disk. */ static int __ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) { … } /* * ext4_block_zero_page_range() zeros out a mapping of length 'length' * starting from file offset 'from'. The range to be zero'd must * be contained with in one block. If the specified range exceeds * the end of the block it will be shortened to end of the block * that corresponds to 'from' */ static int ext4_block_zero_page_range(handle_t *handle, struct address_space *mapping, loff_t from, loff_t length) { … } /* * ext4_block_truncate_page() zeroes out a mapping from file offset `from' * up to the end of the block which corresponds to `from'. * This required during truncate. We need to physically zero the tail end * of that block so it doesn't yield old data if the file is later grown. */ static int ext4_block_truncate_page(handle_t *handle, struct address_space *mapping, loff_t from) { … } int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode, loff_t lstart, loff_t length) { … } int ext4_can_truncate(struct inode *inode) { … } /* * We have to make sure i_disksize gets properly updated before we truncate * page cache due to hole punching or zero range. Otherwise i_disksize update * can get lost as it may have been postponed to submission of writeback but * that will never happen after we truncate page cache. */ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset, loff_t len) { … } static void ext4_wait_dax_page(struct inode *inode) { … } int ext4_break_layouts(struct inode *inode) { … } /* * ext4_punch_hole: punches a hole in a file by releasing the blocks * associated with the given offset and length * * @inode: File inode * @offset: The offset where the hole will begin * @len: The length of the hole * * Returns: 0 on success or negative on failure */ int ext4_punch_hole(struct file *file, loff_t offset, loff_t length) { … } int ext4_inode_attach_jinode(struct inode *inode) { … } /* * ext4_truncate() * * We block out ext4_get_block() block instantiations across the entire * transaction, and VFS/VM ensures that ext4_truncate() cannot run * simultaneously on behalf of the same inode. * * As we work through the truncate and commit bits of it to the journal there * is one core, guiding principle: the file's tree must always be consistent on * disk. We must be able to restart the truncate after a crash. * * The file's tree may be transiently inconsistent in memory (although it * probably isn't), but whenever we close off and commit a journal transaction, * the contents of (the filesystem + the journal) must be consistent and * restartable. It's pretty simple, really: bottom up, right to left (although * left-to-right works OK too). * * Note that at recovery time, journal replay occurs *before* the restart of * truncate against the orphan inode list. * * The committed inode has the new, desired i_size (which is the same as * i_disksize in this case). After a crash, ext4_orphan_cleanup() will see * that this inode's truncate did not complete and it will again call * ext4_truncate() to have another go. So there will be instantiated blocks * to the right of the truncation point in a crashed ext4 filesystem. But * that's fine - as long as they are linked from the inode, the post-crash * ext4_truncate() run will find them and release them. */ int ext4_truncate(struct inode *inode) { … } static inline u64 ext4_inode_peek_iversion(const struct inode *inode) { … } static int ext4_inode_blocks_set(struct ext4_inode *raw_inode, struct ext4_inode_info *ei) { … } static int ext4_fill_raw_inode(struct inode *inode, struct ext4_inode *raw_inode) { … } /* * ext4_get_inode_loc returns with an extra refcount against the inode's * underlying buffer_head on success. If we pass 'inode' and it does not * have in-inode xattr, we have all inode data in memory that is needed * to recreate the on-disk version of this inode. */ static int __ext4_get_inode_loc(struct super_block *sb, unsigned long ino, struct inode *inode, struct ext4_iloc *iloc, ext4_fsblk_t *ret_block) { … } static int __ext4_get_inode_loc_noinmem(struct inode *inode, struct ext4_iloc *iloc) { … } int ext4_get_inode_loc(struct inode *inode, struct ext4_iloc *iloc) { … } int ext4_get_fc_inode_loc(struct super_block *sb, unsigned long ino, struct ext4_iloc *iloc) { … } static bool ext4_should_enable_dax(struct inode *inode) { … } void ext4_set_inode_flags(struct inode *inode, bool init) { … } static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode, struct ext4_inode_info *ei) { … } static inline int ext4_iget_extra_inode(struct inode *inode, struct ext4_inode *raw_inode, struct ext4_inode_info *ei) { … } int ext4_get_projid(struct inode *inode, kprojid_t *projid) { … } /* * ext4 has self-managed i_version for ea inodes, it stores the lower 32bit of * refcount in i_version, so use raw values if inode has EXT4_EA_INODE_FL flag * set. */ static inline void ext4_inode_set_iversion_queried(struct inode *inode, u64 val) { … } static const char *check_igot_inode(struct inode *inode, ext4_iget_flags flags) { … } struct inode *__ext4_iget(struct super_block *sb, unsigned long ino, ext4_iget_flags flags, const char *function, unsigned int line) { … } static void __ext4_update_other_inode_time(struct super_block *sb, unsigned long orig_ino, unsigned long ino, struct ext4_inode *raw_inode) { … } /* * Opportunistically update the other time fields for other inodes in * the same inode table block. */ static void ext4_update_other_inodes_time(struct super_block *sb, unsigned long orig_ino, char *buf) { … } /* * Post the struct inode info into an on-disk inode location in the * buffer-cache. This gobbles the caller's reference to the * buffer_head in the inode location struct. * * The caller must have write access to iloc->bh. */ static int ext4_do_update_inode(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { … } /* * ext4_write_inode() * * We are called from a few places: * * - Within generic_file_aio_write() -> generic_write_sync() for O_SYNC files. * Here, there will be no transaction running. We wait for any running * transaction to commit. * * - Within flush work (sys_sync(), kupdate and such). * We wait on commit, if told to. * * - Within iput_final() -> write_inode_now() * We wait on commit, if told to. * * In all cases it is actually safe for us to return without doing anything, * because the inode has been copied into a raw inode buffer in * ext4_mark_inode_dirty(). This is a correctness thing for WB_SYNC_ALL * writeback. * * Note that we are absolutely dependent upon all inode dirtiers doing the * right thing: they *must* call mark_inode_dirty() after dirtying info in * which we are interested. * * It would be a bug for them to not do this. The code: * * mark_inode_dirty(inode) * stuff(); * inode->i_size = expr; * * is in error because write_inode() could occur while `stuff()' is running, * and the new i_size will be lost. Plus the inode will no longer be on the * superblock's dirty inode list. */ int ext4_write_inode(struct inode *inode, struct writeback_control *wbc) { … } /* * In data=journal mode ext4_journalled_invalidate_folio() may fail to invalidate * buffers that are attached to a folio straddling i_size and are undergoing * commit. In that case we have to wait for commit to finish and try again. */ static void ext4_wait_for_tail_page_commit(struct inode *inode) { … } /* * ext4_setattr() * * Called from notify_change. * * We want to trap VFS attempts to truncate the file as soon as * possible. In particular, we want to make sure that when the VFS * shrinks i_size, we put the inode on the orphan list and modify * i_disksize immediately, so that during the subsequent flushing of * dirty pages and freeing of disk blocks, we can guarantee that any * commit will leave the blocks being flushed in an unused state on * disk. (On recovery, the inode will get truncated and the blocks will * be freed, so we have a strong guarantee that no future commit will * leave these blocks visible to the user.) * * Another thing we have to assure is that if we are in ordered mode * and inode is still attached to the committing transaction, we must * we start writeout of all the dirty pages which are being truncated. * This way we are sure that all the data written in the previous * transaction are already on disk (truncate waits for pages under * writeback). * * Called with inode->i_rwsem down. */ int ext4_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { … } u32 ext4_dio_alignment(struct inode *inode) { … } int ext4_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { … } int ext4_file_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags) { … } static int ext4_index_trans_blocks(struct inode *inode, int lblocks, int pextents) { … } /* * Account for index blocks, block groups bitmaps and block group * descriptor blocks if modify datablocks and index blocks * worse case, the indexs blocks spread over different block groups * * If datablocks are discontiguous, they are possible to spread over * different block groups too. If they are contiguous, with flexbg, * they could still across block group boundary. * * Also account for superblock, inode, quota and xattr blocks */ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks, int pextents) { … } /* * Calculate the total number of credits to reserve to fit * the modification of a single pages into a single transaction, * which may include multiple chunks of block allocations. * * This could be called via ext4_write_begin() * * We need to consider the worse case, when * one new block per extent. */ int ext4_writepage_trans_blocks(struct inode *inode) { … } /* * Calculate the journal credits for a chunk of data modification. * * This is called from DIO, fallocate or whoever calling * ext4_map_blocks() to map/allocate a chunk of contiguous disk blocks. * * journal buffers for data blocks are not included here, as DIO * and fallocate do no need to journal data buffers. */ int ext4_chunk_trans_blocks(struct inode *inode, int nrblocks) { … } /* * The caller must have previously called ext4_reserve_inode_write(). * Give this, we know that the caller already has write access to iloc->bh. */ int ext4_mark_iloc_dirty(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { … } /* * On success, We end up with an outstanding reference count against * iloc->bh. This _must_ be cleaned up later. */ int ext4_reserve_inode_write(handle_t *handle, struct inode *inode, struct ext4_iloc *iloc) { … } static int __ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc *iloc, handle_t *handle, int *no_expand) { … } /* * Expand an inode by new_extra_isize bytes. * Returns 0 on success or negative error number on failure. */ static int ext4_try_to_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc iloc, handle_t *handle) { … } int ext4_expand_extra_isize(struct inode *inode, unsigned int new_extra_isize, struct ext4_iloc *iloc) { … } /* * What we do here is to mark the in-core inode as clean with respect to inode * dirtiness (it may still be data-dirty). * This means that the in-core inode may be reaped by prune_icache * without having to perform any I/O. This is a very good thing, * because *any* task may call prune_icache - even ones which * have a transaction open against a different journal. * * Is this cheating? Not really. Sure, we haven't written the * inode out, but prune_icache isn't a user-visible syncing function. * Whenever the user wants stuff synced (sys_sync, sys_msync, sys_fsync) * we start and wait on commits. */ int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode, const char *func, unsigned int line) { … } /* * ext4_dirty_inode() is called from __mark_inode_dirty() * * We're really interested in the case where a file is being extended. * i_size has been changed by generic_commit_write() and we thus need * to include the updated inode in the current transaction. * * Also, dquot_alloc_block() will always dirty the inode when blocks * are allocated to the file. * * If the inode is marked synchronous, we don't honour that here - doing * so would cause a commit on atime updates, which we don't bother doing. * We handle synchronous inodes at the highest possible level. */ void ext4_dirty_inode(struct inode *inode, int flags) { … } int ext4_change_inode_journal_flag(struct inode *inode, int val) { … } static int ext4_bh_unmapped(handle_t *handle, struct inode *inode, struct buffer_head *bh) { … } vm_fault_t ext4_page_mkwrite(struct vm_fault *vmf) { … }
Codebase Browser
linux