// SPDX-License-Identifier: GPL-2.0+ /* * linux/fs/jbd2/journal.c * * Written by Stephen C. Tweedie <[email protected]>, 1998 * * Copyright 1998 Red Hat corp --- All Rights Reserved * * Generic filesystem journal-writing code; part of the ext2fs * journaling system. * * This file manages journals: areas of disk reserved for logging * transactional updates. This includes the kernel journaling thread * which is responsible for scheduling updates to the log. * * We do not actually manage the physical storage of the journal in this * file: that is left to a per-journal policy function, which allows us * to store the journal within a filesystem-specified area for ext2 * journaling (ext2 can use a reserved inode for storing the log). */ #include <linux/module.h> #include <linux/time.h> #include <linux/fs.h> #include <linux/jbd2.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/freezer.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/poison.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/math64.h> #include <linux/hash.h> #include <linux/log2.h> #include <linux/vmalloc.h> #include <linux/backing-dev.h> #include <linux/bitops.h> #include <linux/ratelimit.h> #include <linux/sched/mm.h> #define CREATE_TRACE_POINTS #include <trace/events/jbd2.h> #include <linux/uaccess.h> #include <asm/page.h> #ifdef CONFIG_JBD2_DEBUG static ushort jbd2_journal_enable_debug __read_mostly; module_param_named(jbd2_debug, jbd2_journal_enable_debug, ushort, 0644); MODULE_PARM_DESC(…) …; #endif EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); EXPORT_SYMBOL(…); static int jbd2_journal_create_slab(size_t slab_size); #ifdef CONFIG_JBD2_DEBUG void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...) { … } #endif /* Checksumming functions */ static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) { … } /* * Helper function used to manage commit timeouts */ static void commit_timeout(struct timer_list *t) { … } /* * kjournald2: The main thread function used to manage a logging device * journal. * * This kernel thread is responsible for two things: * * 1) COMMIT: Every so often we need to commit the current state of the * filesystem to disk. The journal thread is responsible for writing * all of the metadata buffers to disk. If a fast commit is ongoing * journal thread waits until it's done and then continues from * there on. * * 2) CHECKPOINT: We cannot reuse a used section of the log file until all * of the data in that part of the log has been rewritten elsewhere on * the disk. Flushing these old buffers to reclaim space in the log is * known as checkpointing, and this thread is responsible for that job. */ static int kjournald2(void *arg) { … } static int jbd2_journal_start_thread(journal_t *journal) { … } static void journal_kill_thread(journal_t *journal) { … } /* * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal. * * Writes a metadata buffer to a given disk block. The actual IO is not * performed but a new buffer_head is constructed which labels the data * to be written with the correct destination disk block. * * Any magic-number escaping which needs to be done will cause a * copy-out here. If the buffer happens to start with the * JBD2_MAGIC_NUMBER, then we can't write it to the log directly: the * magic number is only written to the log for descripter blocks. In * this case, we copy the data and replace the first word with 0, and we * return a result code which indicates that this buffer needs to be * marked as an escaped buffer in the corresponding log descriptor * block. The missing word can then be restored when the block is read * during recovery. * * If the source buffer has already been modified by a new transaction * since we took the last commit snapshot, we use the frozen copy of * that data for IO. If we end up using the existing buffer_head's data * for the write, then we have to make sure nobody modifies it while the * IO is in progress. do_get_write_access() handles this. * * The function returns a pointer to the buffer_head to be used for IO. * * * Return value: * <0: Error * =0: Finished OK without escape * =1: Finished OK with escape */ int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, struct buffer_head **bh_out, sector_t blocknr) { … } /* * Allocation code for the journal file. Manage the space left in the * journal, so that we can begin checkpointing when appropriate. */ /* * Called with j_state_lock locked for writing. * Returns true if a transaction commit was started. */ static int __jbd2_log_start_commit(journal_t *journal, tid_t target) { … } int jbd2_log_start_commit(journal_t *journal, tid_t tid) { … } /* * Force and wait any uncommitted transactions. We can only force the running * transaction if we don't have an active handle, otherwise, we will deadlock. * Returns: <0 in case of error, * 0 if nothing to commit, * 1 if transaction was successfully committed. */ static int __jbd2_journal_force_commit(journal_t *journal) { … } /** * jbd2_journal_force_commit_nested - Force and wait upon a commit if the * calling process is not within transaction. * * @journal: journal to force * Returns true if progress was made. * * This is used for forcing out undo-protected data which contains * bitmaps, when the fs is running out of space. */ int jbd2_journal_force_commit_nested(journal_t *journal) { … } /** * jbd2_journal_force_commit() - force any uncommitted transactions * @journal: journal to force * * Caller want unconditional commit. We can only force the running transaction * if we don't have an active handle, otherwise, we will deadlock. */ int jbd2_journal_force_commit(journal_t *journal) { … } /* * Start a commit of the current running transaction (if any). Returns true * if a transaction is going to be committed (or is currently already * committing), and fills its tid in at *ptid */ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid) { … } /* * Return 1 if a given transaction has not yet sent barrier request * connected with a transaction commit. If 0 is returned, transaction * may or may not have sent the barrier. Used to avoid sending barrier * twice in common cases. */ int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid) { … } EXPORT_SYMBOL(…); /* * Wait for a specified commit to complete. * The caller may not hold the journal lock. */ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) { … } /* * Start a fast commit. If there's an ongoing fast or full commit wait for * it to complete. Returns 0 if a new fast commit was started. Returns -EALREADY * if a fast commit is not needed, either because there's an already a commit * going on or this tid has already been committed. Returns -EINVAL if no jbd2 * commit has yet been performed. */ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid) { … } EXPORT_SYMBOL(…); /* * Stop a fast commit. If fallback is set, this function starts commit of * TID tid before any other fast commit can start. */ static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback) { … } int jbd2_fc_end_commit(journal_t *journal) { … } EXPORT_SYMBOL(…); int jbd2_fc_end_commit_fallback(journal_t *journal) { … } EXPORT_SYMBOL(…); /* Return 1 when transaction with given tid has already committed. */ int jbd2_transaction_committed(journal_t *journal, tid_t tid) { … } EXPORT_SYMBOL(…); /* * When this function returns the transaction corresponding to tid * will be completed. If the transaction has currently running, start * committing that transaction before waiting for it to complete. If * the transaction id is stale, it is by definition already completed, * so just return SUCCESS. */ int jbd2_complete_transaction(journal_t *journal, tid_t tid) { … } EXPORT_SYMBOL(…); /* * Log buffer allocation routines: */ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp) { … } /* Map one fast commit buffer for use by the file system */ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out) { … } EXPORT_SYMBOL(…); /* * Wait on fast commit buffers that were allocated by jbd2_fc_get_buf * for completion. */ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks) { … } EXPORT_SYMBOL(…); int jbd2_fc_release_bufs(journal_t *journal) { … } EXPORT_SYMBOL(…); /* * Conversion of logical to physical block numbers for the journal * * On external journals the journal blocks are identity-mapped, so * this is a no-op. If needed, we can use j_blk_offset - everything is * ready. */ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, unsigned long long *retp) { … } /* * We play buffer_head aliasing tricks to write data/metadata blocks to * the journal without copying their contents, but for journal * descriptor blocks we do need to generate bona fide buffers. * * After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying * the buffer's contents they really should run flush_dcache_page(bh->b_page). * But we don't bother doing that, so there will be coherency problems with * mmaps of blockdevs which hold live JBD-controlled filesystems. */ struct buffer_head * jbd2_journal_get_descriptor_buffer(transaction_t *transaction, int type) { … } void jbd2_descriptor_block_csum_set(journal_t *j, struct buffer_head *bh) { … } /* * Return tid of the oldest transaction in the journal and block in the journal * where the transaction starts. * * If the journal is now empty, return which will be the next transaction ID * we will write and where will that transaction start. * * The return value is 0 if journal tail cannot be pushed any further, 1 if * it can. */ int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block) { … } /* * Update information in journal structure and in on disk journal superblock * about log tail. This function does not check whether information passed in * really pushes log tail further. It's responsibility of the caller to make * sure provided log tail information is valid (e.g. by holding * j_checkpoint_mutex all the time between computing log tail and calling this * function as is the case with jbd2_cleanup_journal_tail()). * * Requires j_checkpoint_mutex */ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) { … } /* * This is a variation of __jbd2_update_log_tail which checks for validity of * provided log tail and locks j_checkpoint_mutex. So it is safe against races * with other threads updating log tail. */ void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) { … } struct jbd2_stats_proc_session { … }; static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos) { … } static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos) { … } static int jbd2_seq_info_show(struct seq_file *seq, void *v) { … } static void jbd2_seq_info_stop(struct seq_file *seq, void *v) { … } static const struct seq_operations jbd2_seq_info_ops = …; static int jbd2_seq_info_open(struct inode *inode, struct file *file) { … } static int jbd2_seq_info_release(struct inode *inode, struct file *file) { … } static const struct proc_ops jbd2_info_proc_ops = …; static struct proc_dir_entry *proc_jbd2_stats; static void jbd2_stats_proc_init(journal_t *journal) { … } static void jbd2_stats_proc_exit(journal_t *journal) { … } /* Minimum size of descriptor tag */ static int jbd2_min_tag_size(void) { … } /** * jbd2_journal_shrink_scan() * @shrink: shrinker to work on * @sc: reclaim request to process * * Scan the checkpointed buffer on the checkpoint list and release the * journal_head. */ static unsigned long jbd2_journal_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) { … } /** * jbd2_journal_shrink_count() * @shrink: shrinker to work on * @sc: reclaim request to process * * Count the number of checkpoint buffers on the checkpoint list. */ static unsigned long jbd2_journal_shrink_count(struct shrinker *shrink, struct shrink_control *sc) { … } /* * If the journal init or create aborts, we need to mark the journal * superblock as being NULL to prevent the journal destroy from writing * back a bogus superblock. */ static void journal_fail_superblock(journal_t *journal) { … } /* * Check the superblock for a given journal, performing initial * validation of the format. */ static int journal_check_superblock(journal_t *journal) { … } static int journal_revoke_records_per_block(journal_t *journal) { … } static int jbd2_journal_get_max_txn_bufs(journal_t *journal) { … } /* * Base amount of descriptor blocks we reserve for each transaction. */ static int jbd2_descriptor_blocks_per_trans(journal_t *journal) { … } /* * Initialize number of blocks each transaction reserves for its bookkeeping * and maximum number of blocks a transaction can use. This needs to be called * after the journal size and the fastcommit area size are initialized. */ static void jbd2_journal_init_transaction_limits(journal_t *journal) { … } /* * Load the on-disk journal superblock and read the key fields into the * journal_t. */ static int journal_load_superblock(journal_t *journal) { … } /* * Management for journal control blocks: functions to create and * destroy journal_t structures, and to initialise and read existing * journal blocks from disk. */ /* First: create and setup a journal_t object in memory. We initialise * very few fields yet: that has to wait until we have created the * journal structures from from scratch, or loaded them from disk. */ static journal_t *journal_init_common(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int blocksize) { … } /* jbd2_journal_init_dev and jbd2_journal_init_inode: * * Create a journal structure assigned some fixed set of disk blocks to * the journal. We don't actually touch those disk blocks yet, but we * need to set up all of the mapping information to tell the journaling * system where the journal blocks are. * */ /** * journal_t * jbd2_journal_init_dev() - creates and initialises a journal structure * @bdev: Block device on which to create the journal * @fs_dev: Device which hold journalled filesystem for this journal. * @start: Block nr Start of journal. * @len: Length of the journal in blocks. * @blocksize: blocksize of journalling device * * Returns: a newly created journal_t * * * jbd2_journal_init_dev creates a journal which maps a fixed contiguous * range of blocks on an arbitrary block device. * */ journal_t *jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int blocksize) { … } /** * journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode. * @inode: An inode to create the journal in * * jbd2_journal_init_inode creates a journal which maps an on-disk inode as * the journal. The inode must exist already, must support bmap() and * must have all data blocks preallocated. */ journal_t *jbd2_journal_init_inode(struct inode *inode) { … } /* * Given a journal_t structure, initialise the various fields for * startup of a new journaling session. We use this both when creating * a journal, and after recovering an old journal to reset it for * subsequent use. */ static int journal_reset(journal_t *journal) { … } /* * This function expects that the caller will have locked the journal * buffer head, and will return with it unlocked */ static int jbd2_write_superblock(journal_t *journal, blk_opf_t write_flags) { … } /** * jbd2_journal_update_sb_log_tail() - Update log tail in journal sb on disk. * @journal: The journal to update. * @tail_tid: TID of the new transaction at the tail of the log * @tail_block: The first block of the transaction at the tail of the log * @write_flags: Flags for the journal sb write operation * * Update a journal's superblock information about log tail and write it to * disk, waiting for the IO to complete. */ int jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, unsigned long tail_block, blk_opf_t write_flags) { … } /** * jbd2_mark_journal_empty() - Mark on disk journal as empty. * @journal: The journal to update. * @write_flags: Flags for the journal sb write operation * * Update a journal's dynamic superblock fields to show that journal is empty. * Write updated superblock to disk waiting for IO to complete. */ static void jbd2_mark_journal_empty(journal_t *journal, blk_opf_t write_flags) { … } /** * __jbd2_journal_erase() - Discard or zeroout journal blocks (excluding superblock) * @journal: The journal to erase. * @flags: A discard/zeroout request is sent for each physically contigous * region of the journal. Either JBD2_JOURNAL_FLUSH_DISCARD or * JBD2_JOURNAL_FLUSH_ZEROOUT must be set to determine which operation * to perform. * * Note: JBD2_JOURNAL_FLUSH_ZEROOUT attempts to use hardware offload. Zeroes * will be explicitly written if no hardware offload is available, see * blkdev_issue_zeroout for more details. */ static int __jbd2_journal_erase(journal_t *journal, unsigned int flags) { … } /** * jbd2_journal_update_sb_errno() - Update error in the journal. * @journal: The journal to update. * * Update a journal's errno. Write updated superblock to disk waiting for IO * to complete. */ void jbd2_journal_update_sb_errno(journal_t *journal) { … } EXPORT_SYMBOL(…); /** * jbd2_journal_load() - Read journal from disk. * @journal: Journal to act on. * * Given a journal_t structure which tells us which disk blocks contain * a journal, read the journal from disk to initialise the in-memory * structures. */ int jbd2_journal_load(journal_t *journal) { … } /** * jbd2_journal_destroy() - Release a journal_t structure. * @journal: Journal to act on. * * Release a journal_t structure once it is no longer in use by the * journaled object. * Return <0 if we couldn't clean up the journal. */ int jbd2_journal_destroy(journal_t *journal) { … } /** * jbd2_journal_check_used_features() - Check if features specified are used. * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Check whether the journal uses all of a given set of * features. Return true (non-zero) if it does. **/ int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { … } /** * jbd2_journal_check_available_features() - Check feature set in journalling layer * @journal: Journal to check. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Check whether the journaling code supports the use of * all of a given set of features on this journal. Return true * (non-zero) if it can. */ int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { … } static int jbd2_journal_initialize_fast_commit(journal_t *journal) { … } /** * jbd2_journal_set_features() - Mark a given journal feature in the superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Mark a given journal feature as present on the * superblock. Returns true if the requested features could be set. * */ int jbd2_journal_set_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { … } /* * jbd2_journal_clear_features() - Clear a given journal feature in the * superblock * @journal: Journal to act on. * @compat: bitmask of compatible features * @ro: bitmask of features that force read-only mount * @incompat: bitmask of incompatible features * * Clear a given journal feature as present on the * superblock. */ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { … } EXPORT_SYMBOL(…); /** * jbd2_journal_flush() - Flush journal * @journal: Journal to act on. * @flags: optional operation on the journal blocks after the flush (see below) * * Flush all data for a given journal to disk and empty the journal. * Filesystems can use this when remounting readonly to ensure that * recovery does not need to happen on remount. Optionally, a discard or zeroout * can be issued on the journal blocks after flushing. * * flags: * JBD2_JOURNAL_FLUSH_DISCARD: issues discards for the journal blocks * JBD2_JOURNAL_FLUSH_ZEROOUT: issues zeroouts for the journal blocks */ int jbd2_journal_flush(journal_t *journal, unsigned int flags) { … } /** * jbd2_journal_wipe() - Wipe journal contents * @journal: Journal to act on. * @write: flag (see below) * * Wipe out all of the contents of a journal, safely. This will produce * a warning if the journal contains any valid recovery information. * Must be called between journal_init_*() and jbd2_journal_load(). * * If 'write' is non-zero, then we wipe out the journal on disk; otherwise * we merely suppress recovery. */ int jbd2_journal_wipe(journal_t *journal, int write) { … } /** * jbd2_journal_abort () - Shutdown the journal immediately. * @journal: the journal to shutdown. * @errno: an error number to record in the journal indicating * the reason for the shutdown. * * Perform a complete, immediate shutdown of the ENTIRE * journal (not of a single transaction). This operation cannot be * undone without closing and reopening the journal. * * The jbd2_journal_abort function is intended to support higher level error * recovery mechanisms such as the ext2/ext3 remount-readonly error * mode. * * Journal abort has very specific semantics. Any existing dirty, * unjournaled buffers in the main filesystem will still be written to * disk by bdflush, but the journaling mechanism will be suspended * immediately and no further transaction commits will be honoured. * * Any dirty, journaled buffers will be written back to disk without * hitting the journal. Atomicity cannot be guaranteed on an aborted * filesystem, but we _do_ attempt to leave as much data as possible * behind for fsck to use for cleanup. * * Any attempt to get a new transaction handle on a journal which is in * ABORT state will just result in an -EROFS error return. A * jbd2_journal_stop on an existing handle will return -EIO if we have * entered abort state during the update. * * Recursive transactions are not disturbed by journal abort until the * final jbd2_journal_stop, which will receive the -EIO error. * * Finally, the jbd2_journal_abort call allows the caller to supply an errno * which will be recorded (if possible) in the journal superblock. This * allows a client to record failure conditions in the middle of a * transaction without having to complete the transaction to record the * failure to disk. ext3_error, for example, now uses this * functionality. * */ void jbd2_journal_abort(journal_t *journal, int errno) { … } /** * jbd2_journal_errno() - returns the journal's error state. * @journal: journal to examine. * * This is the errno number set with jbd2_journal_abort(), the last * time the journal was mounted - if the journal was stopped * without calling abort this will be 0. * * If the journal has been aborted on this mount time -EROFS will * be returned. */ int jbd2_journal_errno(journal_t *journal) { … } /** * jbd2_journal_clear_err() - clears the journal's error state * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly * mode. */ int jbd2_journal_clear_err(journal_t *journal) { … } /** * jbd2_journal_ack_err() - Ack journal err. * @journal: journal to act on. * * An error must be cleared or acked to take a FS out of readonly * mode. */ void jbd2_journal_ack_err(journal_t *journal) { … } int jbd2_journal_blocks_per_page(struct inode *inode) { … } /* * helper functions to deal with 32 or 64bit block numbers. */ size_t journal_tag_bytes(journal_t *journal) { … } /* * JBD memory management * * These functions are used to allocate block-sized chunks of memory * used for making copies of buffer_head data. Very often it will be * page-sized chunks of data, but sometimes it will be in * sub-page-size chunks. (For example, 16k pages on Power systems * with a 4k block file system.) For blocks smaller than a page, we * use a SLAB allocator. There are slab caches for each block size, * which are allocated at mount time, if necessary, and we only free * (all of) the slab caches when/if the jbd2 module is unloaded. For * this reason we don't need to a mutex to protect access to * jbd2_slab[] allocating or releasing memory; only in * jbd2_journal_create_slab(). */ #define JBD2_MAX_SLABS … static struct kmem_cache *jbd2_slab[JBD2_MAX_SLABS]; static const char *jbd2_slab_names[JBD2_MAX_SLABS] = …; static void jbd2_journal_destroy_slabs(void) { … } static int jbd2_journal_create_slab(size_t size) { … } static struct kmem_cache *get_slab(size_t size) { … } void *jbd2_alloc(size_t size, gfp_t flags) { … } void jbd2_free(void *ptr, size_t size) { if (size < PAGE_SIZE) kmem_cache_free(get_slab(size), ptr); else free_pages((unsigned long)ptr, get_order(size)); }; /* * Journal_head storage management */ static struct kmem_cache *jbd2_journal_head_cache; #ifdef CONFIG_JBD2_DEBUG static atomic_t nr_journal_heads = …; #endif static int __init jbd2_journal_init_journal_head_cache(void) { … } static void jbd2_journal_destroy_journal_head_cache(void) { … } /* * journal_head splicing and dicing */ static struct journal_head *journal_alloc_journal_head(void) { … } static void journal_free_journal_head(struct journal_head *jh) { … } /* * A journal_head is attached to a buffer_head whenever JBD has an * interest in the buffer. * * Whenever a buffer has an attached journal_head, its ->b_state:BH_JBD bit * is set. This bit is tested in core kernel code where we need to take * JBD-specific actions. Testing the zeroness of ->b_private is not reliable * there. * * When a buffer has its BH_JBD bit set, its ->b_count is elevated by one. * * When a buffer has its BH_JBD bit set it is immune from being released by * core kernel code, mainly via ->b_count. * * A journal_head is detached from its buffer_head when the journal_head's * b_jcount reaches zero. Running transaction (b_transaction) and checkpoint * transaction (b_cp_transaction) hold their references to b_jcount. * * Various places in the kernel want to attach a journal_head to a buffer_head * _before_ attaching the journal_head to a transaction. To protect the * journal_head in this situation, jbd2_journal_add_journal_head elevates the * journal_head's b_jcount refcount by one. The caller must call * jbd2_journal_put_journal_head() to undo this. * * So the typical usage would be: * * (Attach a journal_head if needed. Increments b_jcount) * struct journal_head *jh = jbd2_journal_add_journal_head(bh); * ... * (Get another reference for transaction) * jbd2_journal_grab_journal_head(bh); * jh->b_transaction = xxx; * (Put original reference) * jbd2_journal_put_journal_head(jh); */ /* * Give a buffer_head a journal_head. * * May sleep. */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh) { … } /* * Grab a ref against this buffer_head's journal_head. If it ended up not * having a journal_head, return NULL */ struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh) { … } EXPORT_SYMBOL(…); static void __journal_remove_journal_head(struct buffer_head *bh) { … } static void journal_release_journal_head(struct journal_head *jh, size_t b_size) { … } /* * Drop a reference on the passed journal_head. If it fell to zero then * release the journal_head from the buffer_head. */ void jbd2_journal_put_journal_head(struct journal_head *jh) { … } EXPORT_SYMBOL(…); /* * Initialize jbd inode head */ void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode) { … } /* * Function to be called before we start removing inode from memory (i.e., * clear_inode() is a fine place to be called from). It removes inode from * transaction's lists. */ void jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode) { … } #ifdef CONFIG_PROC_FS #define JBD2_STATS_PROC_NAME … static void __init jbd2_create_jbd_stats_proc_entry(void) { … } static void __exit jbd2_remove_jbd_stats_proc_entry(void) { … } #else #define jbd2_create_jbd_stats_proc_entry … #define jbd2_remove_jbd_stats_proc_entry … #endif struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache; static int __init jbd2_journal_init_inode_cache(void) { … } static int __init jbd2_journal_init_handle_cache(void) { … } static void jbd2_journal_destroy_inode_cache(void) { … } static void jbd2_journal_destroy_handle_cache(void) { … } /* * Module startup and shutdown */ static int __init journal_init_caches(void) { … } static void jbd2_journal_destroy_caches(void) { … } static int __init journal_init(void) { … } static void __exit journal_exit(void) { … } MODULE_DESCRIPTION(…) …; MODULE_LICENSE(…) …; module_init(…) …; module_exit(journal_exit);
Codebase Browser
linux