This patch is no longer needed for Lustre, since Lustre 2.2. It is kept in the kernel patch series for compatibility with older Lustre releases to simplify the upgrade process so that both the kernel and Lustre do not need to be upgraded at the same time. See Jira issue LU-433. This allows the jbd transaction commit callbacks to be registered. The ext4 jbd2 code has a different commit callback (one per transaction) that could be used to provide equivalent functionality. This would require modifying the existing ext4 commit callback (used by mballoc when freeing data blocks) to be mutiplexed so it will store 2 different callback functions and 2 different lists of callback data. Index: linux+rh+chaos/include/linux/jbd2.h =================================================================== --- linux+rh+chaos.orig/include/linux/jbd2.h +++ linux+rh+chaos/include/linux/jbd2.h @@ -415,6 +415,27 @@ struct jbd2_inode { unsigned int i_flags; }; +#define HAVE_JOURNAL_CALLBACK_STATUS +/** + * struct journal_callback - Base structure for callback information. + * @jcb_list: list information for other callbacks attached to the same handle. + * @jcb_func: Function to call with this callback structure. + * + * This struct is a 'seed' structure for a using with your own callback + * structs. If you are using callbacks you must allocate one of these + * or another struct of your own definition which has this struct + * as it's first element and pass it to journal_callback_set(). + * + * This is used internally by jbd2 to maintain callback information. + * + * See journal_callback_set for more information. + **/ +struct journal_callback { + struct list_head jcb_list; /* t_jcb_lock */ + void (*jcb_func)(struct journal_callback *jcb, int error); + /* user data goes here */ +}; + struct jbd2_revoke_table_s; /** @@ -423,6 +444,7 @@ struct jbd2_revoke_table_s; * @h_transaction: Which compound transaction is this update a part of? * @h_buffer_credits: Number of remaining buffers we are allowed to dirty. * @h_ref: Reference count on this handle + * @h_jcb: List of application registered callbacks for this handle. * @h_err: Field for caller's use to track errors through large fs operations * @h_sync: flag for sync-on-close * @h_jdata: flag to force data journaling @@ -448,6 +470,13 @@ struct handle_s /* operations */ int h_err; + /* + * List of application registered callbacks for this handle. The + * function(s) will be called after the transaction that this handle is + * part of has been committed to disk. [t_jcb_lock] + */ + struct list_head h_jcb; + /* Flags [no locking] */ unsigned int h_sync: 1; /* sync-on-close */ unsigned int h_jdata: 1; /* force data journaling */ @@ -503,6 +532,8 @@ struct transaction_chp_stats_s { * j_state_lock * ->j_list_lock (journal_unmap_buffer) * + * t_handle_lock + * ->t_jcb_lock */ struct transaction_s @@ -659,6 +690,16 @@ struct transaction_s * structures associated with the transaction */ struct list_head t_private_list; + + /* + * Protects the callback list + */ + spinlock_t t_jcb_lock; + /* + * List of registered callback functions for this transaction. + * Called when the transaction is committed. [t_jcb_lock] + */ + struct list_head t_jcb; }; struct transaction_run_stats_s { @@ -1115,6 +1156,9 @@ extern int jbd2_journal_stop(handle_t * extern int jbd2_journal_flush (journal_t *); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); +extern void jbd2_journal_callback_set(handle_t *handle, + void (*fn)(struct journal_callback *,int), + struct journal_callback *jcb); extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, Index: linux+rh+chaos/fs/jbd2/checkpoint.c =================================================================== --- linux+rh+chaos.orig/fs/jbd2/checkpoint.c +++ linux+rh+chaos/fs/jbd2/checkpoint.c @@ -759,6 +759,7 @@ void __jbd2_journal_drop_transaction(jou J_ASSERT(transaction->t_checkpoint_list == NULL); J_ASSERT(transaction->t_checkpoint_io_list == NULL); J_ASSERT(transaction->t_updates == 0); + J_ASSERT(list_empty(&transaction->t_jcb)); J_ASSERT(journal->j_committing_transaction != transaction); J_ASSERT(journal->j_running_transaction != transaction); Index: linux+rh+chaos/fs/jbd2/commit.c =================================================================== --- linux+rh+chaos.orig/fs/jbd2/commit.c +++ linux+rh+chaos/fs/jbd2/commit.c @@ -857,6 +857,30 @@ wait_for_iobuf: transaction can be removed from any checkpoint list it was on before. */ + /* + * Call any callbacks that had been registered for handles in this + * transaction. It is up to the callback to free any allocated + * memory. + * + * The spinlocking (t_jcb_lock) here is surely unnecessary... + */ + spin_lock(&commit_transaction->t_jcb_lock); + if (!list_empty(&commit_transaction->t_jcb)) { + struct list_head *p, *n; + int error = is_journal_aborted(journal); + + list_for_each_safe(p, n, &commit_transaction->t_jcb) { + struct journal_callback *jcb; + + jcb = list_entry(p, struct journal_callback, jcb_list); + list_del(p); + spin_unlock(&commit_transaction->t_jcb_lock); + jcb->jcb_func(jcb, error); + spin_lock(&commit_transaction->t_jcb_lock); + } + } + spin_unlock(&commit_transaction->t_jcb_lock); + jbd_debug(3, "JBD: commit phase 6\n"); J_ASSERT(list_empty(&commit_transaction->t_inode_list)); Index: linux+rh+chaos/fs/jbd2/journal.c =================================================================== --- linux+rh+chaos.orig/fs/jbd2/journal.c +++ linux+rh+chaos/fs/jbd2/journal.c @@ -90,6 +90,8 @@ EXPORT_SYMBOL(jbd2_journal_file_inode); EXPORT_SYMBOL(jbd2_journal_init_jbd_inode); EXPORT_SYMBOL(jbd2_journal_release_jbd_inode); EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate); +EXPORT_SYMBOL(jbd2_journal_callback_set); +EXPORT_SYMBOL(jbd2_journal_bmap); static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *); static void __journal_abort_soft (journal_t *journal, int errno); Index: linux+rh+chaos/fs/jbd2/transaction.c =================================================================== --- linux+rh+chaos.orig/fs/jbd2/transaction.c +++ linux+rh+chaos/fs/jbd2/transaction.c @@ -52,7 +52,9 @@ jbd2_get_transaction(journal_t *journal, transaction->t_start_time = ktime_get(); transaction->t_tid = journal->j_transaction_sequence++; transaction->t_expires = jiffies + journal->j_commit_interval; + INIT_LIST_HEAD(&transaction->t_jcb); spin_lock_init(&transaction->t_handle_lock); + spin_lock_init(&transaction->t_jcb_lock); INIT_LIST_HEAD(&transaction->t_inode_list); INIT_LIST_HEAD(&transaction->t_private_list); @@ -257,6 +259,7 @@ static handle_t *new_handle(int nblocks) memset(handle, 0, sizeof(*handle)); handle->h_buffer_credits = nblocks; handle->h_ref = 1; + INIT_LIST_HEAD(&handle->h_jcb); lockdep_init_map(&handle->h_lockdep_map, "jbd2_handle", &jbd2_handle_key, 0); @@ -1216,6 +1219,36 @@ drop: } /** + * void jbd2_journal_callback_set() - Register a callback function for this handle. + * @handle: handle to attach the callback to. + * @func: function to callback. + * @jcb: structure with additional information required by func() , and + * some space for jbd2 internal information. + * + * The function will be + * called when the transaction that this handle is part of has been + * committed to disk with the original callback data struct and the + * error status of the journal as parameters. There is no guarantee of + * ordering between handles within a single transaction, nor between + * callbacks registered on the same handle. + * + * The caller is responsible for allocating the journal_callback struct. + * This is to allow the caller to add as much extra data to the callback + * as needed, but reduce the overhead of multiple allocations. The caller + * allocated struct must start with a struct journal_callback at offset 0, + * and has the caller-specific data afterwards. + */ +void jbd2_journal_callback_set(handle_t *handle, + void (*func)(struct journal_callback *jcb, int error), + struct journal_callback *jcb) +{ + spin_lock(&handle->h_transaction->t_jcb_lock); + list_add_tail(&jcb->jcb_list, &handle->h_jcb); + spin_unlock(&handle->h_transaction->t_jcb_lock); + jcb->jcb_func = func; +} + +/** * int jbd2_journal_stop() - complete a transaction * @handle: tranaction to complete. * @@ -1321,6 +1354,11 @@ int jbd2_journal_stop(handle_t *handle) wake_up(&journal->j_wait_transaction_locked); } + /* Move callbacks from the handle to the transaction. */ + spin_lock(&transaction->t_jcb_lock); + list_splice(&handle->h_jcb, &transaction->t_jcb); + spin_unlock(&transaction->t_jcb_lock); + /* * If the handle is marked SYNC, we need to set another commit * going! We also want to force a commit if the current