diff options
Diffstat (limited to 'fs/jbd2/journal.c')
| -rw-r--r-- | fs/jbd2/journal.c | 1754 |
1 files changed, 1035 insertions, 719 deletions
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 954cff001df..67b8e303946 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -35,14 +35,29 @@ #include <linux/kthread.h> #include <linux/poison.h> #include <linux/proc_fs.h> -#include <linux/debugfs.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> + +#define CREATE_TRACE_POINTS +#include <trace/events/jbd2.h> #include <asm/uaccess.h> #include <asm/page.h> -EXPORT_SYMBOL(jbd2_journal_start); -EXPORT_SYMBOL(jbd2_journal_restart); +#ifdef CONFIG_JBD2_DEBUG +ushort jbd2_journal_enable_debug __read_mostly; +EXPORT_SYMBOL(jbd2_journal_enable_debug); + +module_param_named(jbd2_debug, jbd2_journal_enable_debug, ushort, 0644); +MODULE_PARM_DESC(jbd2_debug, "Debugging level for jbd2"); +#endif + EXPORT_SYMBOL(jbd2_journal_extend); EXPORT_SYMBOL(jbd2_journal_stop); EXPORT_SYMBOL(jbd2_journal_lock_updates); @@ -50,9 +65,8 @@ EXPORT_SYMBOL(jbd2_journal_unlock_updates); EXPORT_SYMBOL(jbd2_journal_get_write_access); EXPORT_SYMBOL(jbd2_journal_get_create_access); EXPORT_SYMBOL(jbd2_journal_get_undo_access); -EXPORT_SYMBOL(jbd2_journal_dirty_data); +EXPORT_SYMBOL(jbd2_journal_set_triggers); EXPORT_SYMBOL(jbd2_journal_dirty_metadata); -EXPORT_SYMBOL(jbd2_journal_release_buffer); EXPORT_SYMBOL(jbd2_journal_forget); #if 0 EXPORT_SYMBOL(journal_sync_buffer); @@ -62,19 +76,17 @@ EXPORT_SYMBOL(jbd2_journal_revoke); EXPORT_SYMBOL(jbd2_journal_init_dev); EXPORT_SYMBOL(jbd2_journal_init_inode); -EXPORT_SYMBOL(jbd2_journal_update_format); EXPORT_SYMBOL(jbd2_journal_check_used_features); EXPORT_SYMBOL(jbd2_journal_check_available_features); EXPORT_SYMBOL(jbd2_journal_set_features); -EXPORT_SYMBOL(jbd2_journal_create); EXPORT_SYMBOL(jbd2_journal_load); EXPORT_SYMBOL(jbd2_journal_destroy); -EXPORT_SYMBOL(jbd2_journal_update_superblock); EXPORT_SYMBOL(jbd2_journal_abort); EXPORT_SYMBOL(jbd2_journal_errno); EXPORT_SYMBOL(jbd2_journal_ack_err); EXPORT_SYMBOL(jbd2_journal_clear_err); EXPORT_SYMBOL(jbd2_log_wait_commit); +EXPORT_SYMBOL(jbd2_log_start_commit); EXPORT_SYMBOL(jbd2_journal_start_commit); EXPORT_SYMBOL(jbd2_journal_force_commit_nested); EXPORT_SYMBOL(jbd2_journal_wipe); @@ -82,9 +94,70 @@ EXPORT_SYMBOL(jbd2_journal_blocks_per_page); EXPORT_SYMBOL(jbd2_journal_invalidatepage); EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers); EXPORT_SYMBOL(jbd2_journal_force_commit); +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_inode_cache); -static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *); static void __journal_abort_soft (journal_t *journal, int errno); +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, ...) +{ + struct va_format vaf; + va_list args; + + if (level > jbd2_journal_enable_debug) + return; + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + printk(KERN_DEBUG "%s: (%s, %u): %pV\n", file, func, line, &vaf); + va_end(args); +} +EXPORT_SYMBOL(__jbd2_debug); +#endif + +/* Checksumming functions */ +static int jbd2_verify_csum_type(journal_t *j, journal_superblock_t *sb) +{ + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return 1; + + return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; +} + +static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) +{ + __u32 csum; + __be32 old_csum; + + old_csum = sb->s_checksum; + sb->s_checksum = 0; + csum = jbd2_chksum(j, ~0, (char *)sb, sizeof(journal_superblock_t)); + sb->s_checksum = old_csum; + + return cpu_to_be32(csum); +} + +static int jbd2_superblock_csum_verify(journal_t *j, journal_superblock_t *sb) +{ + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return 1; + + return sb->s_checksum == jbd2_superblock_csum(j, sb); +} + +static void jbd2_superblock_csum_set(journal_t *j, journal_superblock_t *sb) +{ + if (!JBD2_HAS_INCOMPAT_FEATURE(j, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + return; + + sb->s_checksum = jbd2_superblock_csum(j, sb); +} /* * Helper function used to manage commit timeouts @@ -125,17 +198,16 @@ static int kjournald2(void *arg) setup_timer(&journal->j_commit_timer, commit_timeout, (unsigned long)current); + set_freezable(); + /* Record that the journal thread is running */ journal->j_task = current; wake_up(&journal->j_wait_done_commit); - printk(KERN_INFO "kjournald2 starting. Commit interval %ld seconds\n", - journal->j_commit_interval / HZ); - /* * And now, wait forever for commit wakeup events. */ - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); loop: if (journal->j_flags & JBD2_UNMOUNT) @@ -146,10 +218,10 @@ loop: if (journal->j_commit_sequence != journal->j_commit_request) { jbd_debug(1, "OK, requests differ\n"); - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); del_timer_sync(&journal->j_commit_timer); jbd2_journal_commit_transaction(journal); - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); goto loop; } @@ -161,9 +233,9 @@ loop: * be already stopped. */ jbd_debug(1, "Now suspending kjournald2\n"); - spin_unlock(&journal->j_state_lock); - refrigerator(); - spin_lock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); + try_to_freeze(); + write_lock(&journal->j_state_lock); } else { /* * We assume on resume that commits are already there, @@ -183,9 +255,9 @@ loop: if (journal->j_flags & JBD2_UNMOUNT) should_sleep = 0; if (should_sleep) { - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); schedule(); - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); } finish_wait(&journal->j_wait_commit, &wait); } @@ -203,7 +275,7 @@ loop: goto loop; end_loop: - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); del_timer_sync(&journal->j_commit_timer); journal->j_task = NULL; wake_up(&journal->j_wait_done_commit); @@ -215,7 +287,8 @@ static int jbd2_journal_start_thread(journal_t *journal) { struct task_struct *t; - t = kthread_run(kjournald2, journal, "kjournald2"); + t = kthread_run(kjournald2, journal, "jbd2/%s", + journal->j_devname); if (IS_ERR(t)) return PTR_ERR(t); @@ -225,16 +298,16 @@ static int jbd2_journal_start_thread(journal_t *journal) static void journal_kill_thread(journal_t *journal) { - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); journal->j_flags |= JBD2_UNMOUNT; while (journal->j_task) { + write_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_commit); - spin_unlock(&journal->j_state_lock); wait_event(journal->j_wait_done_commit, journal->j_task == NULL); - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); } - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); } /* @@ -256,14 +329,12 @@ static void journal_kill_thread(journal_t *journal) * * 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 lock the buffer to prevent anyone - * else from using and possibly modifying it while the IO is in - * progress. - * - * The function returns a pointer to the buffer_heads to be used for IO. + * 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. * - * We assume that the journal has already been locked in this function. + * The function returns a pointer to the buffer_head to be used for IO. + * * * Return value: * <0: Error @@ -276,18 +347,18 @@ static void journal_kill_thread(journal_t *journal) int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct journal_head *jh_in, - struct journal_head **jh_out, - unsigned long long blocknr) + struct buffer_head **bh_out, + sector_t blocknr) { int need_copy_out = 0; int done_copy_out = 0; int do_escape = 0; char *mapped_data; struct buffer_head *new_bh; - struct journal_head *new_jh; struct page *new_page; unsigned int new_offset; struct buffer_head *bh_in = jh2bh(jh_in); + journal_t *journal = transaction->t_journal; /* * The buffer really shouldn't be locked: only the current committing @@ -300,14 +371,26 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction, */ J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in)); - new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL); +retry_alloc: + new_bh = alloc_buffer_head(GFP_NOFS); + if (!new_bh) { + /* + * Failure is not an option, but __GFP_NOFAIL is going + * away; so we retry ourselves here. + */ + congestion_wait(BLK_RW_ASYNC, HZ/50); + goto retry_alloc; + } + /* keep subsequent assertions sane */ + atomic_set(&new_bh->b_count, 1); + + jbd_lock_bh_state(bh_in); +repeat: /* * If a new transaction has already done a buffer copy-out, then * we use that version of the data for the commit. */ - jbd_lock_bh_state(bh_in); -repeat: if (jh_in->b_frozen_data) { done_copy_out = 1; new_page = virt_to_page(jh_in->b_frozen_data); @@ -317,7 +400,17 @@ repeat: new_offset = offset_in_page(jh2bh(jh_in)->b_data); } - mapped_data = kmap_atomic(new_page, KM_USER0); + mapped_data = kmap_atomic(new_page); + /* + * Fire data frozen trigger if data already wasn't frozen. Do this + * before checking for escaping, as the trigger may modify the magic + * offset. If a copy-out happens afterwards, it will have the correct + * data in the buffer. + */ + if (!done_copy_out) + jbd2_buffer_frozen_trigger(jh_in, mapped_data + new_offset, + jh_in->b_triggers); + /* * Check for escaping */ @@ -326,7 +419,7 @@ repeat: need_copy_out = 1; do_escape = 1; } - kunmap_atomic(mapped_data, KM_USER0); + kunmap_atomic(mapped_data); /* * Do we need to do a data copy? @@ -336,6 +429,10 @@ repeat: jbd_unlock_bh_state(bh_in); tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS); + if (!tmp) { + brelse(new_bh); + return -ENOMEM; + } jbd_lock_bh_state(bh_in); if (jh_in->b_frozen_data) { jbd2_free(tmp, bh_in->b_size); @@ -343,13 +440,20 @@ repeat: } jh_in->b_frozen_data = tmp; - mapped_data = kmap_atomic(new_page, KM_USER0); - memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size); - kunmap_atomic(mapped_data, KM_USER0); + mapped_data = kmap_atomic(new_page); + memcpy(tmp, mapped_data + new_offset, bh_in->b_size); + kunmap_atomic(mapped_data); new_page = virt_to_page(tmp); new_offset = offset_in_page(tmp); done_copy_out = 1; + + /* + * This isn't strictly necessary, as we're using frozen + * data for the escaping, but it keeps consistency with + * b_frozen_data usage. + */ + jh_in->b_frozen_triggers = jh_in->b_triggers; } /* @@ -357,28 +461,20 @@ repeat: * copying, we can finally do so. */ if (do_escape) { - mapped_data = kmap_atomic(new_page, KM_USER0); + mapped_data = kmap_atomic(new_page); *((unsigned int *)(mapped_data + new_offset)) = 0; - kunmap_atomic(mapped_data, KM_USER0); + kunmap_atomic(mapped_data); } - /* keep subsequent assertions sane */ - new_bh->b_state = 0; - init_buffer(new_bh, NULL, NULL); - atomic_set(&new_bh->b_count, 1); - jbd_unlock_bh_state(bh_in); - - new_jh = jbd2_journal_add_journal_head(new_bh); /* This sleeps */ - set_bh_page(new_bh, new_page, new_offset); - new_jh->b_transaction = NULL; - new_bh->b_size = jh2bh(jh_in)->b_size; - new_bh->b_bdev = transaction->t_journal->j_dev; + new_bh->b_size = bh_in->b_size; + new_bh->b_bdev = journal->j_dev; new_bh->b_blocknr = blocknr; + new_bh->b_private = bh_in; set_buffer_mapped(new_bh); set_buffer_dirty(new_bh); - *jh_out = new_jh; + *bh_out = new_bh; /* * The to-be-written buffer needs to get moved to the io queue, @@ -386,9 +482,11 @@ repeat: * copying is moved to the transaction's shadow queue. */ JBUFFER_TRACE(jh_in, "file as BJ_Shadow"); - jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow); - JBUFFER_TRACE(new_jh, "file as BJ_IO"); - jbd2_journal_file_buffer(new_jh, transaction, BJ_IO); + spin_lock(&journal->j_list_lock); + __jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow); + spin_unlock(&journal->j_list_lock); + set_buffer_shadow(bh_in); + jbd_unlock_bh_state(bh_in); return do_escape | (done_copy_out << 1); } @@ -399,55 +497,43 @@ repeat: */ /* - * __jbd2_log_space_left: Return the number of free blocks left in the journal. - * - * Called with the journal already locked. - * - * Called under j_state_lock + * Called with j_state_lock locked for writing. + * Returns true if a transaction commit was started. */ - -int __jbd2_log_space_left(journal_t *journal) +int __jbd2_log_start_commit(journal_t *journal, tid_t target) { - int left = journal->j_free; - - assert_spin_locked(&journal->j_state_lock); - - /* - * Be pessimistic here about the number of those free blocks which - * might be required for log descriptor control blocks. - */ - -#define MIN_LOG_RESERVED_BLOCKS 32 /* Allow for rounding errors */ - - left -= MIN_LOG_RESERVED_BLOCKS; - - if (left <= 0) + /* Return if the txn has already requested to be committed */ + if (journal->j_commit_request == target) return 0; - left -= (left >> 3); - return left; -} -/* - * Called under j_state_lock. Returns true if a transaction was started. - */ -int __jbd2_log_start_commit(journal_t *journal, tid_t target) -{ /* - * Are we already doing a recent enough commit? + * The only transaction we can possibly wait upon is the + * currently running transaction (if it exists). Otherwise, + * the target tid must be an old one. */ - if (!tid_geq(journal->j_commit_request, target)) { + if (journal->j_running_transaction && + journal->j_running_transaction->t_tid == target) { /* - * We want a new commit: OK, mark the request and wakup the + * We want a new commit: OK, mark the request and wakeup the * commit thread. We do _not_ do the commit ourselves. */ journal->j_commit_request = target; - jbd_debug(1, "JBD: requesting commit %d/%d\n", + jbd_debug(1, "JBD2: requesting commit %d/%d\n", journal->j_commit_request, journal->j_commit_sequence); + journal->j_running_transaction->t_requested = jiffies; wake_up(&journal->j_wait_commit); return 1; - } + } else if (!tid_geq(journal->j_commit_request, target)) + /* This should never happen, but if it does, preserve + the evidence before kjournald goes into a loop and + increments j_commit_sequence beyond all recognition. */ + WARN_ONCE(1, "JBD2: bad log_start_commit: %u %u %u %u\n", + journal->j_commit_request, + journal->j_commit_sequence, + target, journal->j_running_transaction ? + journal->j_running_transaction->t_tid : 0); return 0; } @@ -455,73 +541,157 @@ int jbd2_log_start_commit(journal_t *journal, tid_t tid) { int ret; - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); ret = __jbd2_log_start_commit(journal, tid); - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); return ret; } /* - * Force and wait upon a commit if the calling process is not within - * transaction. This is used for forcing out undo-protected data which contains - * bitmaps, when the fs is running out of space. - * - * We can only force the running transaction if we don't have an active handle; - * otherwise, we will deadlock. - * - * Returns true if a transaction was started. + * 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. */ -int jbd2_journal_force_commit_nested(journal_t *journal) +static int __jbd2_journal_force_commit(journal_t *journal) { transaction_t *transaction = NULL; tid_t tid; + int need_to_start = 0, ret = 0; - spin_lock(&journal->j_state_lock); + read_lock(&journal->j_state_lock); if (journal->j_running_transaction && !current->journal_info) { transaction = journal->j_running_transaction; - __jbd2_log_start_commit(journal, transaction->t_tid); + if (!tid_geq(journal->j_commit_request, transaction->t_tid)) + need_to_start = 1; } else if (journal->j_committing_transaction) transaction = journal->j_committing_transaction; if (!transaction) { - spin_unlock(&journal->j_state_lock); - return 0; /* Nothing to retry */ + /* Nothing to commit */ + read_unlock(&journal->j_state_lock); + return 0; } - tid = transaction->t_tid; - spin_unlock(&journal->j_state_lock); - jbd2_log_wait_commit(journal, tid); - return 1; + read_unlock(&journal->j_state_lock); + if (need_to_start) + jbd2_log_start_commit(journal, tid); + ret = jbd2_log_wait_commit(journal, tid); + if (!ret) + ret = 1; + + return ret; +} + +/** + * Force and wait upon a commit if the calling process is not within + * transaction. This is used for forcing out undo-protected data which contains + * bitmaps, when the fs is running out of space. + * + * @journal: journal to force + * Returns true if progress was made. + */ +int jbd2_journal_force_commit_nested(journal_t *journal) +{ + int ret; + + ret = __jbd2_journal_force_commit(journal); + return ret > 0; +} + +/** + * int 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) +{ + int ret; + + J_ASSERT(!current->journal_info); + ret = __jbd2_journal_force_commit(journal); + if (ret > 0) + ret = 0; + return ret; } /* * Start a commit of the current running transaction (if any). Returns true - * if a transaction was started, and fills its tid in at *ptid + * 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) { int ret = 0; - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); if (journal->j_running_transaction) { tid_t tid = journal->j_running_transaction->t_tid; - ret = __jbd2_log_start_commit(journal, tid); - if (ret && ptid) + __jbd2_log_start_commit(journal, tid); + /* There's a running transaction and we've just made sure + * it's commit has been scheduled. */ + if (ptid) *ptid = tid; - } else if (journal->j_committing_transaction && ptid) { + ret = 1; + } else if (journal->j_committing_transaction) { /* - * If ext3_write_super() recently started a commit, then we - * have to wait for completion of that transaction + * If commit has been started, then we have to wait for + * completion of that transaction. */ - *ptid = journal->j_committing_transaction->t_tid; + if (ptid) + *ptid = journal->j_committing_transaction->t_tid; ret = 1; } - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); return ret; } /* + * 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) +{ + int ret = 0; + transaction_t *commit_trans; + + if (!(journal->j_flags & JBD2_BARRIER)) + return 0; + read_lock(&journal->j_state_lock); + /* Transaction already committed? */ + if (tid_geq(journal->j_commit_sequence, tid)) + goto out; + commit_trans = journal->j_committing_transaction; + if (!commit_trans || commit_trans->t_tid != tid) { + ret = 1; + goto out; + } + /* + * Transaction is being committed and we already proceeded to + * submitting a flush to fs partition? + */ + if (journal->j_fs_dev != journal->j_dev) { + if (!commit_trans->t_need_data_flush || + commit_trans->t_state >= T_COMMIT_DFLUSH) + goto out; + } else { + if (commit_trans->t_state >= T_COMMIT_JFLUSH) + goto out; + } + ret = 1; +out: + read_unlock(&journal->j_state_lock); + return ret; +} +EXPORT_SYMBOL(jbd2_trans_will_send_data_barrier); + +/* * Wait for a specified commit to complete. * The caller may not hold the journal lock. */ @@ -529,35 +699,62 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) { int err = 0; + read_lock(&journal->j_state_lock); #ifdef CONFIG_JBD2_DEBUG - spin_lock(&journal->j_state_lock); if (!tid_geq(journal->j_commit_request, tid)) { - printk(KERN_EMERG + printk(KERN_ERR "%s: error: j_commit_request=%d, tid=%d\n", - __FUNCTION__, journal->j_commit_request, tid); + __func__, journal->j_commit_request, tid); } - spin_unlock(&journal->j_state_lock); #endif - spin_lock(&journal->j_state_lock); while (tid_gt(tid, journal->j_commit_sequence)) { - jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n", + jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n", tid, journal->j_commit_sequence); + read_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_commit); - spin_unlock(&journal->j_state_lock); wait_event(journal->j_wait_done_commit, !tid_gt(tid, journal->j_commit_sequence)); - spin_lock(&journal->j_state_lock); + read_lock(&journal->j_state_lock); } - spin_unlock(&journal->j_state_lock); + read_unlock(&journal->j_state_lock); - if (unlikely(is_journal_aborted(journal))) { - printk(KERN_EMERG "journal commit I/O error\n"); + if (unlikely(is_journal_aborted(journal))) err = -EIO; - } return err; } /* + * 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) +{ + int need_to_wait = 1; + + read_lock(&journal->j_state_lock); + if (journal->j_running_transaction && + journal->j_running_transaction->t_tid == tid) { + if (journal->j_commit_request != tid) { + /* transaction not yet started, so request it */ + read_unlock(&journal->j_state_lock); + jbd2_log_start_commit(journal, tid); + goto wait_commit; + } + } else if (!(journal->j_committing_transaction && + journal->j_committing_transaction->t_tid == tid)) + need_to_wait = 0; + read_unlock(&journal->j_state_lock); + if (!need_to_wait) + return 0; +wait_commit: + return jbd2_log_wait_commit(journal, tid); +} +EXPORT_SYMBOL(jbd2_complete_transaction); + +/* * Log buffer allocation routines: */ @@ -565,7 +762,7 @@ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp) { unsigned long blocknr; - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); J_ASSERT(journal->j_free > 1); blocknr = journal->j_head; @@ -573,7 +770,7 @@ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp) journal->j_free--; if (journal->j_head == journal->j_last) journal->j_head = journal->j_first; - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); return jbd2_journal_bmap(journal, blocknr, retp); } @@ -595,13 +792,9 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, if (ret) *retp = ret; else { - char b[BDEVNAME_SIZE]; - printk(KERN_ALERT "%s: journal block not found " "at offset %lu on %s\n", - __FUNCTION__, - blocknr, - bdevname(journal->j_dev, b)); + __func__, blocknr, journal->j_devname); err = -EIO; __journal_abort_soft(journal, err); } @@ -621,7 +814,7 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, * But we don't bother doing that, so there will be coherency problems with * mmaps of blockdevs which hold live JBD-controlled filesystems. */ -struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal) +struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal) { struct buffer_head *bh; unsigned long long blocknr; @@ -633,166 +826,113 @@ struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal) return NULL; bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); + if (!bh) + return NULL; lock_buffer(bh); memset(bh->b_data, 0, journal->j_blocksize); set_buffer_uptodate(bh); unlock_buffer(bh); BUFFER_TRACE(bh, "return this buffer"); - return jbd2_journal_add_journal_head(bh); -} - -struct jbd2_stats_proc_session { - journal_t *journal; - struct transaction_stats_s *stats; - int start; - int max; -}; - -static void *jbd2_history_skip_empty(struct jbd2_stats_proc_session *s, - struct transaction_stats_s *ts, - int first) -{ - if (ts == s->stats + s->max) - ts = s->stats; - if (!first && ts == s->stats + s->start) - return NULL; - while (ts->ts_type == 0) { - ts++; - if (ts == s->stats + s->max) - ts = s->stats; - if (ts == s->stats + s->start) - return NULL; - } - return ts; - + return bh; } -static void *jbd2_seq_history_start(struct seq_file *seq, loff_t *pos) +/* + * 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) { - struct jbd2_stats_proc_session *s = seq->private; - struct transaction_stats_s *ts; - int l = *pos; + transaction_t *transaction; + int ret; - if (l == 0) - return SEQ_START_TOKEN; - ts = jbd2_history_skip_empty(s, s->stats + s->start, 1); - if (!ts) - return NULL; - l--; - while (l) { - ts = jbd2_history_skip_empty(s, ++ts, 0); - if (!ts) - break; - l--; + read_lock(&journal->j_state_lock); + spin_lock(&journal->j_list_lock); + transaction = journal->j_checkpoint_transactions; + if (transaction) { + *tid = transaction->t_tid; + *block = transaction->t_log_start; + } else if ((transaction = journal->j_committing_transaction) != NULL) { + *tid = transaction->t_tid; + *block = transaction->t_log_start; + } else if ((transaction = journal->j_running_transaction) != NULL) { + *tid = transaction->t_tid; + *block = journal->j_head; + } else { + *tid = journal->j_transaction_sequence; + *block = journal->j_head; } - return ts; -} - -static void *jbd2_seq_history_next(struct seq_file *seq, void *v, loff_t *pos) -{ - struct jbd2_stats_proc_session *s = seq->private; - struct transaction_stats_s *ts = v; - - ++*pos; - if (v == SEQ_START_TOKEN) - return jbd2_history_skip_empty(s, s->stats + s->start, 1); - else - return jbd2_history_skip_empty(s, ++ts, 0); -} + ret = tid_gt(*tid, journal->j_tail_sequence); + spin_unlock(&journal->j_list_lock); + read_unlock(&journal->j_state_lock); -static int jbd2_seq_history_show(struct seq_file *seq, void *v) -{ - struct transaction_stats_s *ts = v; - if (v == SEQ_START_TOKEN) { - seq_printf(seq, "%-4s %-5s %-5s %-5s %-5s %-5s %-5s %-6s %-5s " - "%-5s %-5s %-5s %-5s %-5s\n", "R/C", "tid", - "wait", "run", "lock", "flush", "log", "hndls", - "block", "inlog", "ctime", "write", "drop", - "close"); - return 0; - } - if (ts->ts_type == JBD2_STATS_RUN) - seq_printf(seq, "%-4s %-5lu %-5u %-5u %-5u %-5u %-5u " - "%-6lu %-5lu %-5lu\n", "R", ts->ts_tid, - jiffies_to_msecs(ts->u.run.rs_wait), - jiffies_to_msecs(ts->u.run.rs_running), - jiffies_to_msecs(ts->u.run.rs_locked), - jiffies_to_msecs(ts->u.run.rs_flushing), - jiffies_to_msecs(ts->u.run.rs_logging), - ts->u.run.rs_handle_count, - ts->u.run.rs_blocks, - ts->u.run.rs_blocks_logged); - else if (ts->ts_type == JBD2_STATS_CHECKPOINT) - seq_printf(seq, "%-4s %-5lu %48s %-5u %-5lu %-5lu %-5lu\n", - "C", ts->ts_tid, " ", - jiffies_to_msecs(ts->u.chp.cs_chp_time), - ts->u.chp.cs_written, ts->u.chp.cs_dropped, - ts->u.chp.cs_forced_to_close); - else - J_ASSERT(0); - return 0; + return ret; } -static void jbd2_seq_history_stop(struct seq_file *seq, void *v) +/* + * 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 + */ +void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) { -} + unsigned long freed; -static struct seq_operations jbd2_seq_history_ops = { - .start = jbd2_seq_history_start, - .next = jbd2_seq_history_next, - .stop = jbd2_seq_history_stop, - .show = jbd2_seq_history_show, -}; + BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); -static int jbd2_seq_history_open(struct inode *inode, struct file *file) -{ - journal_t *journal = PDE(inode)->data; - struct jbd2_stats_proc_session *s; - int rc, size; - - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (s == NULL) - return -ENOMEM; - size = sizeof(struct transaction_stats_s) * journal->j_history_max; - s->stats = kmalloc(size, GFP_KERNEL); - if (s->stats == NULL) { - kfree(s); - return -ENOMEM; - } - spin_lock(&journal->j_history_lock); - memcpy(s->stats, journal->j_history, size); - s->max = journal->j_history_max; - s->start = journal->j_history_cur % s->max; - spin_unlock(&journal->j_history_lock); + /* + * We cannot afford for write to remain in drive's caches since as + * soon as we update j_tail, next transaction can start reusing journal + * space and if we lose sb update during power failure we'd replay + * old transaction with possibly newly overwritten data. + */ + jbd2_journal_update_sb_log_tail(journal, tid, block, WRITE_FUA); + write_lock(&journal->j_state_lock); + freed = block - journal->j_tail; + if (block < journal->j_tail) + freed += journal->j_last - journal->j_first; - rc = seq_open(file, &jbd2_seq_history_ops); - if (rc == 0) { - struct seq_file *m = file->private_data; - m->private = s; - } else { - kfree(s->stats); - kfree(s); - } - return rc; + trace_jbd2_update_log_tail(journal, tid, block, freed); + jbd_debug(1, + "Cleaning journal tail from %d to %d (offset %lu), " + "freeing %lu\n", + journal->j_tail_sequence, tid, block, freed); + journal->j_free += freed; + journal->j_tail_sequence = tid; + journal->j_tail = block; + write_unlock(&journal->j_state_lock); } -static int jbd2_seq_history_release(struct inode *inode, struct file *file) +/* + * This is a variaon 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 seq_file *seq = file->private_data; - struct jbd2_stats_proc_session *s = seq->private; - - kfree(s->stats); - kfree(s); - return seq_release(inode, file); + mutex_lock(&journal->j_checkpoint_mutex); + if (tid_gt(tid, journal->j_tail_sequence)) + __jbd2_update_log_tail(journal, tid, block); + mutex_unlock(&journal->j_checkpoint_mutex); } -static struct file_operations jbd2_seq_history_fops = { - .owner = THIS_MODULE, - .open = jbd2_seq_history_open, - .read = seq_read, - .llseek = seq_lseek, - .release = jbd2_seq_history_release, +struct jbd2_stats_proc_session { + journal_t *journal; + struct transaction_stats_s *stats; + int start; + int max; }; static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos) @@ -811,27 +951,34 @@ static int jbd2_seq_info_show(struct seq_file *seq, void *v) if (v != SEQ_START_TOKEN) return 0; - seq_printf(seq, "%lu transaction, each upto %u blocks\n", - s->stats->ts_tid, - s->journal->j_max_transaction_buffers); + seq_printf(seq, "%lu transactions (%lu requested), " + "each up to %u blocks\n", + s->stats->ts_tid, s->stats->ts_requested, + s->journal->j_max_transaction_buffers); if (s->stats->ts_tid == 0) return 0; seq_printf(seq, "average: \n %ums waiting for transaction\n", - jiffies_to_msecs(s->stats->u.run.rs_wait / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_wait / s->stats->ts_tid)); + seq_printf(seq, " %ums request delay\n", + (s->stats->ts_requested == 0) ? 0 : + jiffies_to_msecs(s->stats->run.rs_request_delay / + s->stats->ts_requested)); seq_printf(seq, " %ums running transaction\n", - jiffies_to_msecs(s->stats->u.run.rs_running / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_running / s->stats->ts_tid)); seq_printf(seq, " %ums transaction was being locked\n", - jiffies_to_msecs(s->stats->u.run.rs_locked / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_locked / s->stats->ts_tid)); seq_printf(seq, " %ums flushing data (in ordered mode)\n", - jiffies_to_msecs(s->stats->u.run.rs_flushing / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_flushing / s->stats->ts_tid)); seq_printf(seq, " %ums logging transaction\n", - jiffies_to_msecs(s->stats->u.run.rs_logging / s->stats->ts_tid)); + jiffies_to_msecs(s->stats->run.rs_logging / s->stats->ts_tid)); + seq_printf(seq, " %lluus average transaction commit time\n", + div_u64(s->journal->j_average_commit_time, 1000)); seq_printf(seq, " %lu handles per transaction\n", - s->stats->u.run.rs_handle_count / s->stats->ts_tid); + s->stats->run.rs_handle_count / s->stats->ts_tid); seq_printf(seq, " %lu blocks per transaction\n", - s->stats->u.run.rs_blocks / s->stats->ts_tid); + s->stats->run.rs_blocks / s->stats->ts_tid); seq_printf(seq, " %lu logged blocks per transaction\n", - s->stats->u.run.rs_blocks_logged / s->stats->ts_tid); + s->stats->run.rs_blocks_logged / s->stats->ts_tid); return 0; } @@ -839,7 +986,7 @@ static void jbd2_seq_info_stop(struct seq_file *seq, void *v) { } -static struct seq_operations jbd2_seq_info_ops = { +static const struct seq_operations jbd2_seq_info_ops = { .start = jbd2_seq_info_start, .next = jbd2_seq_info_next, .stop = jbd2_seq_info_stop, @@ -848,7 +995,7 @@ static struct seq_operations jbd2_seq_info_ops = { static int jbd2_seq_info_open(struct inode *inode, struct file *file) { - journal_t *journal = PDE(inode)->data; + journal_t *journal = PDE_DATA(inode); struct jbd2_stats_proc_session *s; int rc, size; @@ -887,7 +1034,7 @@ static int jbd2_seq_info_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -static struct file_operations jbd2_seq_info_fops = { +static const struct file_operations jbd2_seq_info_fops = { .owner = THIS_MODULE, .open = jbd2_seq_info_open, .read = seq_read, @@ -899,52 +1046,17 @@ static struct proc_dir_entry *proc_jbd2_stats; static void jbd2_stats_proc_init(journal_t *journal) { - char name[BDEVNAME_SIZE]; - - snprintf(name, sizeof(name) - 1, "%s", bdevname(journal->j_dev, name)); - journal->j_proc_entry = proc_mkdir(name, proc_jbd2_stats); + journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats); if (journal->j_proc_entry) { - struct proc_dir_entry *p; - p = create_proc_entry("history", S_IRUGO, - journal->j_proc_entry); - if (p) { - p->proc_fops = &jbd2_seq_history_fops; - p->data = journal; - p = create_proc_entry("info", S_IRUGO, - journal->j_proc_entry); - if (p) { - p->proc_fops = &jbd2_seq_info_fops; - p->data = journal; - } - } + proc_create_data("info", S_IRUGO, journal->j_proc_entry, + &jbd2_seq_info_fops, journal); } } static void jbd2_stats_proc_exit(journal_t *journal) { - char name[BDEVNAME_SIZE]; - - snprintf(name, sizeof(name) - 1, "%s", bdevname(journal->j_dev, name)); remove_proc_entry("info", journal->j_proc_entry); - remove_proc_entry("history", journal->j_proc_entry); - remove_proc_entry(name, proc_jbd2_stats); -} - -static void journal_init_stats(journal_t *journal) -{ - int size; - - if (!proc_jbd2_stats) - return; - - journal->j_history_max = 100; - size = sizeof(struct transaction_stats_s) * journal->j_history_max; - journal->j_history = kzalloc(size, GFP_KERNEL); - if (!journal->j_history) { - journal->j_history_max = 0; - return; - } - spin_lock_init(&journal->j_history_lock); + remove_proc_entry(journal->j_devname, proc_jbd2_stats); } /* @@ -961,23 +1073,25 @@ static journal_t * journal_init_common (void) journal_t *journal; int err; - journal = kzalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL); + journal = kzalloc(sizeof(*journal), GFP_KERNEL); if (!journal) - goto fail; + return NULL; init_waitqueue_head(&journal->j_wait_transaction_locked); - init_waitqueue_head(&journal->j_wait_logspace); init_waitqueue_head(&journal->j_wait_done_commit); - init_waitqueue_head(&journal->j_wait_checkpoint); init_waitqueue_head(&journal->j_wait_commit); init_waitqueue_head(&journal->j_wait_updates); + init_waitqueue_head(&journal->j_wait_reserved); mutex_init(&journal->j_barrier); mutex_init(&journal->j_checkpoint_mutex); spin_lock_init(&journal->j_revoke_lock); spin_lock_init(&journal->j_list_lock); - spin_lock_init(&journal->j_state_lock); + rwlock_init(&journal->j_state_lock); journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE); + journal->j_min_batch_time = 0; + journal->j_max_batch_time = 15000; /* 15ms */ + atomic_set(&journal->j_reserved_credits, 0); /* The journal is marked for error until we succeed with recovery! */ journal->j_flags = JBD2_ABORT; @@ -986,14 +1100,12 @@ static journal_t * journal_init_common (void) err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH); if (err) { kfree(journal); - goto fail; + return NULL; } - journal_init_stats(journal); + spin_lock_init(&journal->j_history_lock); return journal; -fail: - return NULL; } /* jbd2_journal_init_dev and jbd2_journal_init_inode: @@ -1006,13 +1118,14 @@ fail: */ /** - * journal_t * jbd2_journal_init_dev() - creates an initialises a journal structure + * 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 * + * + * 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. @@ -1024,6 +1137,7 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev, { journal_t *journal = journal_init_common(); struct buffer_head *bh; + char *p; int n; if (!journal) @@ -1031,28 +1145,40 @@ journal_t * jbd2_journal_init_dev(struct block_device *bdev, /* journal descriptor can store up to n blocks -bzzz */ journal->j_blocksize = blocksize; - n = journal->j_blocksize / sizeof(journal_block_tag_t); - journal->j_wbufsize = n; - journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL); - if (!journal->j_wbuf) { - printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n", - __FUNCTION__); - kfree(journal); - journal = NULL; - goto out; - } journal->j_dev = bdev; journal->j_fs_dev = fs_dev; journal->j_blk_offset = start; journal->j_maxlen = len; + bdevname(journal->j_dev, journal->j_devname); + p = journal->j_devname; + while ((p = strchr(p, '/'))) + *p = '!'; jbd2_stats_proc_init(journal); + n = journal->j_blocksize / sizeof(journal_block_tag_t); + journal->j_wbufsize = n; + journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL); + if (!journal->j_wbuf) { + printk(KERN_ERR "%s: Can't allocate bhs for commit thread\n", + __func__); + goto out_err; + } bh = __getblk(journal->j_dev, start, journal->j_blocksize); - J_ASSERT(bh != NULL); + if (!bh) { + printk(KERN_ERR + "%s: Cannot get buffer for journal superblock\n", + __func__); + goto out_err; + } journal->j_sb_buffer = bh; journal->j_superblock = (journal_superblock_t *)bh->b_data; -out: + return journal; +out_err: + kfree(journal->j_wbuf); + jbd2_stats_proc_exit(journal); + kfree(journal); + return NULL; } /** @@ -1067,6 +1193,7 @@ journal_t * jbd2_journal_init_inode (struct inode *inode) { struct buffer_head *bh; journal_t *journal = journal_init_common(); + char *p; int err; int n; unsigned long long blocknr; @@ -1076,6 +1203,12 @@ journal_t * jbd2_journal_init_inode (struct inode *inode) journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev; journal->j_inode = inode; + bdevname(journal->j_dev, journal->j_devname); + p = journal->j_devname; + while ((p = strchr(p, '/'))) + *p = '!'; + p = journal->j_devname + strlen(journal->j_devname); + sprintf(p, "-%lu", journal->j_inode->i_ino); jbd_debug(1, "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n", journal, inode->i_sb->s_id, inode->i_ino, @@ -1091,27 +1224,35 @@ journal_t * jbd2_journal_init_inode (struct inode *inode) journal->j_wbufsize = n; journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL); if (!journal->j_wbuf) { - printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n", - __FUNCTION__); - kfree(journal); - return NULL; + printk(KERN_ERR "%s: Can't allocate bhs for commit thread\n", + __func__); + goto out_err; } err = jbd2_journal_bmap(journal, 0, &blocknr); /* If that failed, give up */ if (err) { - printk(KERN_ERR "%s: Cannnot locate journal superblock\n", - __FUNCTION__); - kfree(journal); - return NULL; + printk(KERN_ERR "%s: Cannot locate journal superblock\n", + __func__); + goto out_err; } bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); - J_ASSERT(bh != NULL); + if (!bh) { + printk(KERN_ERR + "%s: Cannot get buffer for journal superblock\n", + __func__); + goto out_err; + } journal->j_sb_buffer = bh; journal->j_superblock = (journal_superblock_t *)bh->b_data; return journal; +out_err: + kfree(journal->j_wbuf); + jbd2_stats_proc_exit(journal); + kfree(journal); + return NULL; } /* @@ -1140,6 +1281,12 @@ static int journal_reset(journal_t *journal) first = be32_to_cpu(sb->s_first); last = be32_to_cpu(sb->s_maxlen); + if (first + JBD2_MIN_JOURNAL_BLOCKS > last + 1) { + printk(KERN_ERR "JBD2: Journal too short (blocks %llu-%llu).\n", + first, last); + journal_fail_superblock(journal); + return -EINVAL; + } journal->j_first = first; journal->j_last = last; @@ -1154,145 +1301,168 @@ static int journal_reset(journal_t *journal) journal->j_max_transaction_buffers = journal->j_maxlen / 4; - /* Add the dynamic fields and write it to disk. */ - jbd2_journal_update_superblock(journal, 1); + /* + * As a special case, if the on-disk copy is already marked as needing + * no recovery (s_start == 0), then we can safely defer the superblock + * update until the next commit by setting JBD2_FLUSHED. This avoids + * attempting a write to a potential-readonly device. + */ + if (sb->s_start == 0) { + jbd_debug(1, "JBD2: Skipping superblock update on recovered sb " + "(start %ld, seq %d, errno %d)\n", + journal->j_tail, journal->j_tail_sequence, + journal->j_errno); + journal->j_flags |= JBD2_FLUSHED; + } else { + /* Lock here to make assertions happy... */ + mutex_lock(&journal->j_checkpoint_mutex); + /* + * Update log tail information. We use WRITE_FUA since new + * transaction will start reusing journal space and so we + * must make sure information about current log tail is on + * disk before that. + */ + jbd2_journal_update_sb_log_tail(journal, + journal->j_tail_sequence, + journal->j_tail, + WRITE_FUA); + mutex_unlock(&journal->j_checkpoint_mutex); + } return jbd2_journal_start_thread(journal); } -/** - * int jbd2_journal_create() - Initialise the new journal file - * @journal: Journal to create. This structure must have been initialised - * - * Given a journal_t structure which tells us which disk blocks we can - * use, create a new journal superblock and initialise all of the - * journal fields from scratch. - **/ -int jbd2_journal_create(journal_t *journal) +static void jbd2_write_superblock(journal_t *journal, int write_op) { - unsigned long long blocknr; - struct buffer_head *bh; - journal_superblock_t *sb; - int i, err; - - if (journal->j_maxlen < JBD2_MIN_JOURNAL_BLOCKS) { - printk (KERN_ERR "Journal length (%d blocks) too short.\n", - journal->j_maxlen); - journal_fail_superblock(journal); - return -EINVAL; - } + struct buffer_head *bh = journal->j_sb_buffer; + journal_superblock_t *sb = journal->j_superblock; + int ret; - if (journal->j_inode == NULL) { + trace_jbd2_write_superblock(journal, write_op); + if (!(journal->j_flags & JBD2_BARRIER)) + write_op &= ~(REQ_FUA | REQ_FLUSH); + lock_buffer(bh); + if (buffer_write_io_error(bh)) { /* - * We don't know what block to start at! + * Oh, dear. A previous attempt to write the journal + * superblock failed. This could happen because the + * USB device was yanked out. Or it could happen to + * be a transient write error and maybe the block will + * be remapped. Nothing we can do but to retry the + * write and hope for the best. */ - printk(KERN_EMERG - "%s: creation of journal on external device!\n", - __FUNCTION__); - BUG(); - } - - /* Zero out the entire journal on disk. We cannot afford to - have any blocks on disk beginning with JBD2_MAGIC_NUMBER. */ - jbd_debug(1, "JBD: Zeroing out journal blocks...\n"); - for (i = 0; i < journal->j_maxlen; i++) { - err = jbd2_journal_bmap(journal, i, &blocknr); - if (err) - return err; - bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); - lock_buffer(bh); - memset (bh->b_data, 0, journal->j_blocksize); - BUFFER_TRACE(bh, "marking dirty"); - mark_buffer_dirty(bh); - BUFFER_TRACE(bh, "marking uptodate"); + printk(KERN_ERR "JBD2: previous I/O error detected " + "for journal superblock update for %s.\n", + journal->j_devname); + clear_buffer_write_io_error(bh); set_buffer_uptodate(bh); - unlock_buffer(bh); - __brelse(bh); } + jbd2_superblock_csum_set(journal, sb); + get_bh(bh); + bh->b_end_io = end_buffer_write_sync; + ret = submit_bh(write_op, bh); + wait_on_buffer(bh); + if (buffer_write_io_error(bh)) { + clear_buffer_write_io_error(bh); + set_buffer_uptodate(bh); + ret = -EIO; + } + if (ret) { + printk(KERN_ERR "JBD2: Error %d detected when updating " + "journal superblock for %s.\n", ret, + journal->j_devname); + } +} - sync_blockdev(journal->j_dev); - jbd_debug(1, "JBD: journal cleared.\n"); - - /* OK, fill in the initial static fields in the new superblock */ - sb = journal->j_superblock; - - sb->s_header.h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); - sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2); +/** + * 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_op: With which operation should we write the journal sb + * + * Update a journal's superblock information about log tail and write it to + * disk, waiting for the IO to complete. + */ +void jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid, + unsigned long tail_block, int write_op) +{ + journal_superblock_t *sb = journal->j_superblock; - sb->s_blocksize = cpu_to_be32(journal->j_blocksize); - sb->s_maxlen = cpu_to_be32(journal->j_maxlen); - sb->s_first = cpu_to_be32(1); + BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); + jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", + tail_block, tail_tid); - journal->j_transaction_sequence = 1; + sb->s_sequence = cpu_to_be32(tail_tid); + sb->s_start = cpu_to_be32(tail_block); - journal->j_flags &= ~JBD2_ABORT; - journal->j_format_version = 2; + jbd2_write_superblock(journal, write_op); - return journal_reset(journal); + /* Log is no longer empty */ + write_lock(&journal->j_state_lock); + WARN_ON(!sb->s_sequence); + journal->j_flags &= ~JBD2_FLUSHED; + write_unlock(&journal->j_state_lock); } /** - * void jbd2_journal_update_superblock() - Update journal sb on disk. + * jbd2_mark_journal_empty() - Mark on disk journal as empty. * @journal: The journal to update. - * @wait: Set to '0' if you don't want to wait for IO completion. * - * Update a journal's dynamic superblock fields and write it to disk, - * optionally waiting for the IO to complete. + * Update a journal's dynamic superblock fields to show that journal is empty. + * Write updated superblock to disk waiting for IO to complete. */ -void jbd2_journal_update_superblock(journal_t *journal, int wait) +static void jbd2_mark_journal_empty(journal_t *journal) { journal_superblock_t *sb = journal->j_superblock; - struct buffer_head *bh = journal->j_sb_buffer; - /* - * As a special case, if the on-disk copy is already marked as needing - * no recovery (s_start == 0) and there are no outstanding transactions - * in the filesystem, then we can safely defer the superblock update - * until the next commit by setting JBD2_FLUSHED. This avoids - * attempting a write to a potential-readonly device. - */ - if (sb->s_start == 0 && journal->j_tail_sequence == - journal->j_transaction_sequence) { - jbd_debug(1,"JBD: Skipping superblock update on recovered sb " - "(start %ld, seq %d, errno %d)\n", - journal->j_tail, journal->j_tail_sequence, - journal->j_errno); - goto out; + BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); + read_lock(&journal->j_state_lock); + /* Is it already empty? */ + if (sb->s_start == 0) { + read_unlock(&journal->j_state_lock); + return; } - - spin_lock(&journal->j_state_lock); - jbd_debug(1,"JBD: updating superblock (start %ld, seq %d, errno %d)\n", - journal->j_tail, journal->j_tail_sequence, journal->j_errno); + jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n", + journal->j_tail_sequence); sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); - sb->s_start = cpu_to_be32(journal->j_tail); - sb->s_errno = cpu_to_be32(journal->j_errno); - spin_unlock(&journal->j_state_lock); + sb->s_start = cpu_to_be32(0); + read_unlock(&journal->j_state_lock); - BUFFER_TRACE(bh, "marking dirty"); - mark_buffer_dirty(bh); - if (wait) - sync_dirty_buffer(bh); - else - ll_rw_block(SWRITE, 1, &bh); + jbd2_write_superblock(journal, WRITE_FUA); -out: - /* If we have just flushed the log (by marking s_start==0), then - * any future commit will have to be careful to update the - * superblock again to re-record the true start of the log. */ + /* Log is no longer empty */ + write_lock(&journal->j_state_lock); + journal->j_flags |= JBD2_FLUSHED; + write_unlock(&journal->j_state_lock); +} - spin_lock(&journal->j_state_lock); - if (sb->s_start) - journal->j_flags &= ~JBD2_FLUSHED; - else - journal->j_flags |= JBD2_FLUSHED; - spin_unlock(&journal->j_state_lock); + +/** + * 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) +{ + journal_superblock_t *sb = journal->j_superblock; + + read_lock(&journal->j_state_lock); + jbd_debug(1, "JBD2: updating superblock error (errno %d)\n", + journal->j_errno); + sb->s_errno = cpu_to_be32(journal->j_errno); + read_unlock(&journal->j_state_lock); + + jbd2_write_superblock(journal, WRITE_SYNC); } +EXPORT_SYMBOL(jbd2_journal_update_sb_errno); /* * Read the superblock for a given journal, performing initial * validation of the format. */ - static int journal_get_superblock(journal_t *journal) { struct buffer_head *bh; @@ -1306,19 +1476,22 @@ static int journal_get_superblock(journal_t *journal) ll_rw_block(READ, 1, &bh); wait_on_buffer(bh); if (!buffer_uptodate(bh)) { - printk (KERN_ERR - "JBD: IO error reading journal superblock\n"); + printk(KERN_ERR + "JBD2: IO error reading journal superblock\n"); goto out; } } + if (buffer_verified(bh)) + return 0; + sb = journal->j_superblock; err = -EINVAL; if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) || sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) { - printk(KERN_WARNING "JBD: no valid journal superblock found\n"); + printk(KERN_WARNING "JBD2: no valid journal superblock found\n"); goto out; } @@ -1330,17 +1503,62 @@ static int journal_get_superblock(journal_t *journal) journal->j_format_version = 2; break; default: - printk(KERN_WARNING "JBD: unrecognised superblock format ID\n"); + printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n"); goto out; } if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen) journal->j_maxlen = be32_to_cpu(sb->s_maxlen); else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) { - printk (KERN_WARNING "JBD: journal file too short\n"); + printk(KERN_WARNING "JBD2: journal file too short\n"); + goto out; + } + + if (be32_to_cpu(sb->s_first) == 0 || + be32_to_cpu(sb->s_first) >= journal->j_maxlen) { + printk(KERN_WARNING + "JBD2: Invalid start block of journal: %u\n", + be32_to_cpu(sb->s_first)); + goto out; + } + + if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) && + JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + /* Can't have checksum v1 and v2 on at the same time! */ + printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 " + "at the same time!\n"); + goto out; + } + + if (!jbd2_verify_csum_type(journal, sb)) { + printk(KERN_ERR "JBD2: Unknown checksum type\n"); + goto out; + } + + /* Load the checksum driver */ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); + if (IS_ERR(journal->j_chksum_driver)) { + printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); + err = PTR_ERR(journal->j_chksum_driver); + journal->j_chksum_driver = NULL; + goto out; + } + } + + /* Check superblock checksum */ + if (!jbd2_superblock_csum_verify(journal, sb)) { + printk(KERN_ERR "JBD2: journal checksum error\n"); goto out; } + /* Precompute checksum seed for all metadata */ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, + sizeof(sb->s_uuid)); + + set_buffer_verified(bh); + return 0; out: @@ -1400,17 +1618,31 @@ int jbd2_journal_load(journal_t *journal) ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) || (sb->s_feature_incompat & ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) { - printk (KERN_WARNING - "JBD: Unrecognised features on journal\n"); + printk(KERN_WARNING + "JBD2: Unrecognised features on journal\n"); return -EINVAL; } } + /* + * Create a slab for this blocksize + */ + err = jbd2_journal_create_slab(be32_to_cpu(sb->s_blocksize)); + if (err) + return err; + /* Let the recovery code check whether it needs to recover any * data from the journal. */ if (jbd2_journal_recover(journal)) goto recovery_error; + if (journal->j_failed_commit) { + printk(KERN_ERR "JBD2: journal transaction %u on %s " + "is corrupt.\n", journal->j_failed_commit, + journal->j_devname); + return -EIO; + } + /* OK, we've finished with the dynamic journal bits: * reinitialise the dynamic contents of the superblock in memory * and reset them on disk. */ @@ -1422,7 +1654,7 @@ int jbd2_journal_load(journal_t *journal) return 0; recovery_error: - printk (KERN_WARNING "JBD: recovery failed\n"); + printk(KERN_WARNING "JBD2: recovery failed\n"); return -EIO; } @@ -1432,9 +1664,12 @@ recovery_error: * * 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. */ -void jbd2_journal_destroy(journal_t *journal) +int jbd2_journal_destroy(journal_t *journal) { + int err = 0; + /* Wait for the commit thread to wake up and die. */ journal_kill_thread(journal); @@ -1448,7 +1683,9 @@ void jbd2_journal_destroy(journal_t *journal) spin_lock(&journal->j_list_lock); while (journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); + mutex_lock(&journal->j_checkpoint_mutex); jbd2_log_do_checkpoint(journal); + mutex_unlock(&journal->j_checkpoint_mutex); spin_lock(&journal->j_list_lock); } @@ -1457,11 +1694,13 @@ void jbd2_journal_destroy(journal_t *journal) J_ASSERT(journal->j_checkpoint_transactions == NULL); spin_unlock(&journal->j_list_lock); - /* We can now mark the journal as empty. */ - journal->j_tail = 0; - journal->j_tail_sequence = ++journal->j_transaction_sequence; if (journal->j_sb_buffer) { - jbd2_journal_update_superblock(journal, 1); + if (!is_journal_aborted(journal)) { + mutex_lock(&journal->j_checkpoint_mutex); + jbd2_mark_journal_empty(journal); + mutex_unlock(&journal->j_checkpoint_mutex); + } else + err = -EIO; brelse(journal->j_sb_buffer); } @@ -1471,8 +1710,12 @@ void jbd2_journal_destroy(journal_t *journal) iput(journal->j_inode); if (journal->j_revoke) jbd2_journal_destroy_revoke(journal); + if (journal->j_chksum_driver) + crypto_free_shash(journal->j_chksum_driver); kfree(journal->j_wbuf); kfree(journal); + + return err; } @@ -1494,6 +1737,10 @@ int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, if (!compat && !ro && !incompat) return 1; + /* Load journal superblock if it is not loaded yet. */ + if (journal->j_format_version == 0 && + journal_get_superblock(journal) != 0) + return 0; if (journal->j_format_version == 1) return 0; @@ -1521,13 +1768,9 @@ int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { - journal_superblock_t *sb; - if (!compat && !ro && !incompat) return 1; - sb = journal->j_superblock; - /* We can support any known requested features iff the * superblock is in version 2. Otherwise we fail to support any * extended sb features. */ @@ -1558,6 +1801,10 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com int jbd2_journal_set_features (journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { +#define INCOMPAT_FEATURE_ON(f) \ + ((incompat & (f)) && !(sb->s_feature_incompat & cpu_to_be32(f))) +#define COMPAT_FEATURE_ON(f) \ + ((compat & (f)) && !(sb->s_feature_compat & cpu_to_be32(f))) journal_superblock_t *sb; if (jbd2_journal_check_used_features(journal, compat, ro, incompat)) @@ -1566,16 +1813,54 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, if (!jbd2_journal_check_available_features(journal, compat, ro, incompat)) return 0; + /* Asking for checksumming v2 and v1? Only give them v2. */ + if (incompat & JBD2_FEATURE_INCOMPAT_CSUM_V2 && + compat & JBD2_FEATURE_COMPAT_CHECKSUM) + compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM; + jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n", compat, ro, incompat); sb = journal->j_superblock; + /* If enabling v2 checksums, update superblock */ + if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V2)) { + sb->s_checksum_type = JBD2_CRC32C_CHKSUM; + sb->s_feature_compat &= + ~cpu_to_be32(JBD2_FEATURE_COMPAT_CHECKSUM); + + /* Load the checksum driver */ + if (journal->j_chksum_driver == NULL) { + journal->j_chksum_driver = crypto_alloc_shash("crc32c", + 0, 0); + if (IS_ERR(journal->j_chksum_driver)) { + printk(KERN_ERR "JBD2: Cannot load crc32c " + "driver.\n"); + journal->j_chksum_driver = NULL; + return 0; + } + } + + /* Precompute checksum seed for all metadata */ + if (JBD2_HAS_INCOMPAT_FEATURE(journal, + JBD2_FEATURE_INCOMPAT_CSUM_V2)) + journal->j_csum_seed = jbd2_chksum(journal, ~0, + sb->s_uuid, + sizeof(sb->s_uuid)); + } + + /* If enabling v1 checksums, downgrade superblock */ + if (COMPAT_FEATURE_ON(JBD2_FEATURE_COMPAT_CHECKSUM)) + sb->s_feature_incompat &= + ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_CSUM_V2); + sb->s_feature_compat |= cpu_to_be32(compat); sb->s_feature_ro_compat |= cpu_to_be32(ro); sb->s_feature_incompat |= cpu_to_be32(incompat); return 1; +#undef COMPAT_FEATURE_ON +#undef INCOMPAT_FEATURE_ON } /* @@ -1606,61 +1891,6 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, EXPORT_SYMBOL(jbd2_journal_clear_features); /** - * int jbd2_journal_update_format () - Update on-disk journal structure. - * @journal: Journal to act on. - * - * Given an initialised but unloaded journal struct, poke about in the - * on-disk structure to update it to the most recent supported version. - */ -int jbd2_journal_update_format (journal_t *journal) -{ - journal_superblock_t *sb; - int err; - - err = journal_get_superblock(journal); - if (err) - return err; - - sb = journal->j_superblock; - - switch (be32_to_cpu(sb->s_header.h_blocktype)) { - case JBD2_SUPERBLOCK_V2: - return 0; - case JBD2_SUPERBLOCK_V1: - return journal_convert_superblock_v1(journal, sb); - default: - break; - } - return -EINVAL; -} - -static int journal_convert_superblock_v1(journal_t *journal, - journal_superblock_t *sb) -{ - int offset, blocksize; - struct buffer_head *bh; - - printk(KERN_WARNING - "JBD: Converting superblock from version 1 to 2.\n"); - - /* Pre-initialise new fields to zero */ - offset = ((char *) &(sb->s_feature_compat)) - ((char *) sb); - blocksize = be32_to_cpu(sb->s_blocksize); - memset(&sb->s_feature_compat, 0, blocksize-offset); - - sb->s_nr_users = cpu_to_be32(1); - sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2); - journal->j_format_version = 2; - - bh = journal->j_sb_buffer; - BUFFER_TRACE(bh, "marking dirty"); - mark_buffer_dirty(bh); - sync_dirty_buffer(bh); - return 0; -} - - -/** * int jbd2_journal_flush () - Flush journal * @journal: Journal to act on. * @@ -1673,9 +1903,8 @@ int jbd2_journal_flush(journal_t *journal) { int err = 0; transaction_t *transaction = NULL; - unsigned long old_tail; - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); /* Force everything buffered to the log... */ if (journal->j_running_transaction) { @@ -1688,20 +1917,27 @@ int jbd2_journal_flush(journal_t *journal) if (transaction) { tid_t tid = transaction->t_tid; - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); jbd2_log_wait_commit(journal, tid); } else { - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); } /* ...and flush everything in the log out to disk. */ spin_lock(&journal->j_list_lock); while (!err && journal->j_checkpoint_transactions != NULL) { spin_unlock(&journal->j_list_lock); + mutex_lock(&journal->j_checkpoint_mutex); err = jbd2_log_do_checkpoint(journal); + mutex_unlock(&journal->j_checkpoint_mutex); spin_lock(&journal->j_list_lock); } spin_unlock(&journal->j_list_lock); + + if (is_journal_aborted(journal)) + return -EIO; + + mutex_lock(&journal->j_checkpoint_mutex); jbd2_cleanup_journal_tail(journal); /* Finally, mark the journal as really needing no recovery. @@ -1709,21 +1945,16 @@ int jbd2_journal_flush(journal_t *journal) * the magic code for a fully-recovered superblock. Any future * commits of data to the journal will restore the current * s_start value. */ - spin_lock(&journal->j_state_lock); - old_tail = journal->j_tail; - journal->j_tail = 0; - spin_unlock(&journal->j_state_lock); - jbd2_journal_update_superblock(journal, 1); - spin_lock(&journal->j_state_lock); - journal->j_tail = old_tail; - + jbd2_mark_journal_empty(journal); + mutex_unlock(&journal->j_checkpoint_mutex); + write_lock(&journal->j_state_lock); J_ASSERT(!journal->j_running_transaction); J_ASSERT(!journal->j_committing_transaction); J_ASSERT(!journal->j_checkpoint_transactions); J_ASSERT(journal->j_head == journal->j_tail); J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence); - spin_unlock(&journal->j_state_lock); - return err; + write_unlock(&journal->j_state_lock); + return 0; } /** @@ -1741,7 +1972,6 @@ int jbd2_journal_flush(journal_t *journal) int jbd2_journal_wipe(journal_t *journal, int write) { - journal_superblock_t *sb; int err = 0; J_ASSERT (!(journal->j_flags & JBD2_LOADED)); @@ -1750,44 +1980,29 @@ int jbd2_journal_wipe(journal_t *journal, int write) if (err) return err; - sb = journal->j_superblock; - if (!journal->j_tail) goto no_recovery; - printk (KERN_WARNING "JBD: %s recovery information on journal\n", + printk(KERN_WARNING "JBD2: %s recovery information on journal\n", write ? "Clearing" : "Ignoring"); err = jbd2_journal_skip_recovery(journal); - if (write) - jbd2_journal_update_superblock(journal, 1); + if (write) { + /* Lock to make assertions happy... */ + mutex_lock(&journal->j_checkpoint_mutex); + jbd2_mark_journal_empty(journal); + mutex_unlock(&journal->j_checkpoint_mutex); + } no_recovery: return err; } /* - * journal_dev_name: format a character string to describe on what - * device this journal is present. - */ - -static const char *journal_dev_name(journal_t *journal, char *buffer) -{ - struct block_device *bdev; - - if (journal->j_inode) - bdev = journal->j_inode->i_sb->s_bdev; - else - bdev = journal->j_dev; - - return bdevname(bdev, buffer); -} - -/* * Journal abort has very specific semantics, which we describe * for journal abort. * - * Two internal function, which provide abort to te jbd layer + * Two internal functions, which provide abort to the jbd layer * itself are here. */ @@ -1799,20 +2014,19 @@ static const char *journal_dev_name(journal_t *journal, char *buffer) void __jbd2_journal_abort_hard(journal_t *journal) { transaction_t *transaction; - char b[BDEVNAME_SIZE]; if (journal->j_flags & JBD2_ABORT) return; printk(KERN_ERR "Aborting journal on device %s.\n", - journal_dev_name(journal, b)); + journal->j_devname); - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); journal->j_flags |= JBD2_ABORT; transaction = journal->j_running_transaction; if (transaction) __jbd2_log_start_commit(journal, transaction->t_tid); - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); } /* Soft abort: record the abort error status in the journal superblock, @@ -1828,7 +2042,7 @@ static void __journal_abort_soft (journal_t *journal, int errno) __jbd2_journal_abort_hard(journal); if (errno) - jbd2_journal_update_superblock(journal, 1); + jbd2_journal_update_sb_errno(journal); } /** @@ -1886,7 +2100,7 @@ void jbd2_journal_abort(journal_t *journal, int errno) * int jbd2_journal_errno () - returns the journal's error state. * @journal: journal to examine. * - * This is the errno numbet set with jbd2_journal_abort(), the last + * 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. * @@ -1897,12 +2111,12 @@ int jbd2_journal_errno(journal_t *journal) { int err; - spin_lock(&journal->j_state_lock); + read_lock(&journal->j_state_lock); if (journal->j_flags & JBD2_ABORT) err = -EROFS; else err = journal->j_errno; - spin_unlock(&journal->j_state_lock); + read_unlock(&journal->j_state_lock); return err; } @@ -1910,19 +2124,19 @@ int jbd2_journal_errno(journal_t *journal) * int 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 + * An error must be cleared or acked to take a FS out of readonly * mode. */ int jbd2_journal_clear_err(journal_t *journal) { int err = 0; - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); if (journal->j_flags & JBD2_ABORT) err = -EROFS; else journal->j_errno = 0; - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); return err; } @@ -1930,15 +2144,15 @@ int jbd2_journal_clear_err(journal_t *journal) * void 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 + * An error must be cleared or acked to take a FS out of readonly * mode. */ void jbd2_journal_ack_err(journal_t *journal) { - spin_lock(&journal->j_state_lock); + write_lock(&journal->j_state_lock); if (journal->j_errno) journal->j_flags |= JBD2_ACK_ERR; - spin_unlock(&journal->j_state_lock); + write_unlock(&journal->j_state_lock); } int jbd2_journal_blocks_per_page(struct inode *inode) @@ -1951,12 +2165,139 @@ int jbd2_journal_blocks_per_page(struct inode *inode) */ size_t journal_tag_bytes(journal_t *journal) { + journal_block_tag_t tag; + size_t x = 0; + + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) + x += sizeof(tag.t_checksum); + if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT)) - return JBD2_TAG_SIZE64; + return x + JBD2_TAG_SIZE64; else - return JBD2_TAG_SIZE32; + return x + JBD2_TAG_SIZE32; +} + +/* + * 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 8 +static struct kmem_cache *jbd2_slab[JBD2_MAX_SLABS]; + +static const char *jbd2_slab_names[JBD2_MAX_SLABS] = { + "jbd2_1k", "jbd2_2k", "jbd2_4k", "jbd2_8k", + "jbd2_16k", "jbd2_32k", "jbd2_64k", "jbd2_128k" +}; + + +static void jbd2_journal_destroy_slabs(void) +{ + int i; + + for (i = 0; i < JBD2_MAX_SLABS; i++) { + if (jbd2_slab[i]) + kmem_cache_destroy(jbd2_slab[i]); + jbd2_slab[i] = NULL; + } +} + +static int jbd2_journal_create_slab(size_t size) +{ + static DEFINE_MUTEX(jbd2_slab_create_mutex); + int i = order_base_2(size) - 10; + size_t slab_size; + + if (size == PAGE_SIZE) + return 0; + + if (i >= JBD2_MAX_SLABS) + return -EINVAL; + + if (unlikely(i < 0)) + i = 0; + mutex_lock(&jbd2_slab_create_mutex); + if (jbd2_slab[i]) { + mutex_unlock(&jbd2_slab_create_mutex); + return 0; /* Already created */ + } + + slab_size = 1 << (i+10); + jbd2_slab[i] = kmem_cache_create(jbd2_slab_names[i], slab_size, + slab_size, 0, NULL); + mutex_unlock(&jbd2_slab_create_mutex); + if (!jbd2_slab[i]) { + printk(KERN_EMERG "JBD2: no memory for jbd2_slab cache\n"); + return -ENOMEM; + } + return 0; +} + +static struct kmem_cache *get_slab(size_t size) +{ + int i = order_base_2(size) - 10; + + BUG_ON(i >= JBD2_MAX_SLABS); + if (unlikely(i < 0)) + i = 0; + BUG_ON(jbd2_slab[i] == NULL); + return jbd2_slab[i]; } +void *jbd2_alloc(size_t size, gfp_t flags) +{ + void *ptr; + + BUG_ON(size & (size-1)); /* Must be a power of 2 */ + + flags |= __GFP_REPEAT; + if (size == PAGE_SIZE) + ptr = (void *)__get_free_pages(flags, 0); + else if (size > PAGE_SIZE) { + int order = get_order(size); + + if (order < 3) + ptr = (void *)__get_free_pages(flags, order); + else + ptr = vmalloc(size); + } else + ptr = kmem_cache_alloc(get_slab(size), flags); + + /* Check alignment; SLUB has gotten this wrong in the past, + * and this can lead to user data corruption! */ + BUG_ON(((unsigned long) ptr) & (size-1)); + + return ptr; +} + +void jbd2_free(void *ptr, size_t size) +{ + if (size == PAGE_SIZE) { + free_pages((unsigned long)ptr, 0); + return; + } + if (size > PAGE_SIZE) { + int order = get_order(size); + + if (order < 3) + free_pages((unsigned long)ptr, order); + else + vfree(ptr); + return; + } + kmem_cache_free(get_slab(size), ptr); +}; + /* * Journal_head storage management */ @@ -1965,7 +2306,7 @@ static struct kmem_cache *jbd2_journal_head_cache; static atomic_t nr_journal_heads = ATOMIC_INIT(0); #endif -static int journal_init_jbd2_journal_head_cache(void) +static int jbd2_journal_init_journal_head_cache(void) { int retval; @@ -1978,16 +2319,17 @@ static int journal_init_jbd2_journal_head_cache(void) retval = 0; if (!jbd2_journal_head_cache) { retval = -ENOMEM; - printk(KERN_EMERG "JBD: no memory for journal_head cache\n"); + printk(KERN_EMERG "JBD2: no memory for journal_head cache\n"); } return retval; } -static void jbd2_journal_destroy_jbd2_journal_head_cache(void) +static void jbd2_journal_destroy_journal_head_cache(void) { - J_ASSERT(jbd2_journal_head_cache != NULL); - kmem_cache_destroy(jbd2_journal_head_cache); - jbd2_journal_head_cache = NULL; + if (jbd2_journal_head_cache) { + kmem_cache_destroy(jbd2_journal_head_cache); + jbd2_journal_head_cache = NULL; + } } /* @@ -1996,22 +2338,17 @@ static void jbd2_journal_destroy_jbd2_journal_head_cache(void) static struct journal_head *journal_alloc_journal_head(void) { struct journal_head *ret; - static unsigned long last_warning; #ifdef CONFIG_JBD2_DEBUG atomic_inc(&nr_journal_heads); #endif - ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS); + ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS); if (!ret) { jbd_debug(1, "out of memory for journal_head\n"); - if (time_after(jiffies, last_warning + 5*HZ)) { - printk(KERN_NOTICE "ENOMEM in %s, retrying.\n", - __FUNCTION__); - last_warning = jiffies; - } + pr_notice_ratelimited("ENOMEM in %s, retrying.\n", __func__); while (!ret) { yield(); - ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS); + ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS); } } return ret; @@ -2040,10 +2377,9 @@ static void journal_free_journal_head(struct journal_head *jh) * 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 may be detached from its buffer_head when the journal_head's - * b_transaction, b_cp_transaction and b_next_transaction pointers are NULL. - * Various places in JBD call jbd2_journal_remove_journal_head() to indicate that the - * journal_head can be dropped if needed. + * 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 @@ -2056,17 +2392,16 @@ static void journal_free_journal_head(struct journal_head *jh) * (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); - * - * Now, the journal_head's b_jcount is zero, but it is safe from being released - * because it has a non-zero b_transaction. */ /* * Give a buffer_head a journal_head. * - * Doesn't need the journal lock. * May sleep. */ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh) @@ -2075,10 +2410,8 @@ struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh) struct journal_head *new_jh = NULL; repeat: - if (!buffer_jbd(bh)) { + if (!buffer_jbd(bh)) new_jh = journal_alloc_journal_head(); - memset(new_jh, 0, sizeof(*new_jh)); - } jbd_lock_bh_journal_head(bh); if (buffer_jbd(bh)) { @@ -2130,61 +2463,29 @@ static void __journal_remove_journal_head(struct buffer_head *bh) struct journal_head *jh = bh2jh(bh); J_ASSERT_JH(jh, jh->b_jcount >= 0); - - get_bh(bh); - if (jh->b_jcount == 0) { - if (jh->b_transaction == NULL && - jh->b_next_transaction == NULL && - jh->b_cp_transaction == NULL) { - J_ASSERT_JH(jh, jh->b_jlist == BJ_None); - J_ASSERT_BH(bh, buffer_jbd(bh)); - J_ASSERT_BH(bh, jh2bh(jh) == bh); - BUFFER_TRACE(bh, "remove journal_head"); - if (jh->b_frozen_data) { - printk(KERN_WARNING "%s: freeing " - "b_frozen_data\n", - __FUNCTION__); - jbd2_free(jh->b_frozen_data, bh->b_size); - } - if (jh->b_committed_data) { - printk(KERN_WARNING "%s: freeing " - "b_committed_data\n", - __FUNCTION__); - jbd2_free(jh->b_committed_data, bh->b_size); - } - bh->b_private = NULL; - jh->b_bh = NULL; /* debug, really */ - clear_buffer_jbd(bh); - __brelse(bh); - journal_free_journal_head(jh); - } else { - BUFFER_TRACE(bh, "journal_head was locked"); - } + J_ASSERT_JH(jh, jh->b_transaction == NULL); + J_ASSERT_JH(jh, jh->b_next_transaction == NULL); + J_ASSERT_JH(jh, jh->b_cp_transaction == NULL); + J_ASSERT_JH(jh, jh->b_jlist == BJ_None); + J_ASSERT_BH(bh, buffer_jbd(bh)); + J_ASSERT_BH(bh, jh2bh(jh) == bh); + BUFFER_TRACE(bh, "remove journal_head"); + if (jh->b_frozen_data) { + printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__); + jbd2_free(jh->b_frozen_data, bh->b_size); } + if (jh->b_committed_data) { + printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__); + jbd2_free(jh->b_committed_data, bh->b_size); + } + bh->b_private = NULL; + jh->b_bh = NULL; /* debug, really */ + clear_buffer_jbd(bh); + journal_free_journal_head(jh); } /* - * jbd2_journal_remove_journal_head(): if the buffer isn't attached to a transaction - * and has a zero b_jcount then remove and release its journal_head. If we did - * see that the buffer is not used by any transaction we also "logically" - * decrement ->b_count. - * - * We in fact take an additional increment on ->b_count as a convenience, - * because the caller usually wants to do additional things with the bh - * after calling here. - * The caller of jbd2_journal_remove_journal_head() *must* run __brelse(bh) at some - * time. Once the caller has run __brelse(), the buffer is eligible for - * reaping by try_to_free_buffers(). - */ -void jbd2_journal_remove_journal_head(struct buffer_head *bh) -{ - jbd_lock_bh_journal_head(bh); - __journal_remove_journal_head(bh); - jbd_unlock_bh_journal_head(bh); -} - -/* - * Drop a reference on the passed journal_head. If it fell to zero then try to + * 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) @@ -2194,51 +2495,57 @@ void jbd2_journal_put_journal_head(struct journal_head *jh) jbd_lock_bh_journal_head(bh); J_ASSERT_JH(jh, jh->b_jcount > 0); --jh->b_jcount; - if (!jh->b_jcount && !jh->b_transaction) { + if (!jh->b_jcount) { __journal_remove_journal_head(bh); + jbd_unlock_bh_journal_head(bh); __brelse(bh); - } - jbd_unlock_bh_journal_head(bh); + } else + jbd_unlock_bh_journal_head(bh); } /* - * debugfs tunables + * Initialize jbd inode head */ -#ifdef CONFIG_JBD2_DEBUG -u8 jbd2_journal_enable_debug __read_mostly; -EXPORT_SYMBOL(jbd2_journal_enable_debug); - -#define JBD2_DEBUG_NAME "jbd2-debug" - -static struct dentry *jbd2_debugfs_dir; -static struct dentry *jbd2_debug; - -static void __init jbd2_create_debugfs_entry(void) -{ - jbd2_debugfs_dir = debugfs_create_dir("jbd2", NULL); - if (jbd2_debugfs_dir) - jbd2_debug = debugfs_create_u8(JBD2_DEBUG_NAME, S_IRUGO, - jbd2_debugfs_dir, - &jbd2_journal_enable_debug); -} - -static void __exit jbd2_remove_debugfs_entry(void) +void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode) { - debugfs_remove(jbd2_debug); - debugfs_remove(jbd2_debugfs_dir); + jinode->i_transaction = NULL; + jinode->i_next_transaction = NULL; + jinode->i_vfs_inode = inode; + jinode->i_flags = 0; + INIT_LIST_HEAD(&jinode->i_list); } -#else - -static void __init jbd2_create_debugfs_entry(void) +/* + * 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) { -} + if (!journal) + return; +restart: + spin_lock(&journal->j_list_lock); + /* Is commit writing out inode - we have to wait */ + if (test_bit(__JI_COMMIT_RUNNING, &jinode->i_flags)) { + wait_queue_head_t *wq; + DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING); + wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING); + prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&journal->j_list_lock); + schedule(); + finish_wait(wq, &wait.wait); + goto restart; + } -static void __exit jbd2_remove_debugfs_entry(void) -{ + if (jinode->i_transaction) { + list_del(&jinode->i_list); + jinode->i_transaction = NULL; + } + spin_unlock(&journal->j_list_lock); } -#endif #ifdef CONFIG_PROC_FS @@ -2262,17 +2569,19 @@ static void __exit jbd2_remove_jbd_stats_proc_entry(void) #endif -struct kmem_cache *jbd2_handle_cache; +struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache; -static int __init journal_init_handle_cache(void) +static int __init jbd2_journal_init_handle_cache(void) { - jbd2_handle_cache = kmem_cache_create("jbd2_journal_handle", - sizeof(handle_t), - 0, /* offset */ - SLAB_TEMPORARY, /* flags */ - NULL); /* ctor */ + jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY); if (jbd2_handle_cache == NULL) { - printk(KERN_EMERG "JBD: failed to create handle cache\n"); + printk(KERN_EMERG "JBD2: failed to create handle cache\n"); + return -ENOMEM; + } + jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0); + if (jbd2_inode_cache == NULL) { + printk(KERN_EMERG "JBD2: failed to create inode cache\n"); + kmem_cache_destroy(jbd2_handle_cache); return -ENOMEM; } return 0; @@ -2282,6 +2591,9 @@ static void jbd2_journal_destroy_handle_cache(void) { if (jbd2_handle_cache) kmem_cache_destroy(jbd2_handle_cache); + if (jbd2_inode_cache) + kmem_cache_destroy(jbd2_inode_cache); + } /* @@ -2294,17 +2606,21 @@ static int __init journal_init_caches(void) ret = jbd2_journal_init_revoke_caches(); if (ret == 0) - ret = journal_init_jbd2_journal_head_cache(); + ret = jbd2_journal_init_journal_head_cache(); + if (ret == 0) + ret = jbd2_journal_init_handle_cache(); if (ret == 0) - ret = journal_init_handle_cache(); + ret = jbd2_journal_init_transaction_cache(); return ret; } static void jbd2_journal_destroy_caches(void) { jbd2_journal_destroy_revoke_caches(); - jbd2_journal_destroy_jbd2_journal_head_cache(); + jbd2_journal_destroy_journal_head_cache(); jbd2_journal_destroy_handle_cache(); + jbd2_journal_destroy_transaction_cache(); + jbd2_journal_destroy_slabs(); } static int __init journal_init(void) @@ -2314,10 +2630,11 @@ static int __init journal_init(void) BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024); ret = journal_init_caches(); - if (ret != 0) + if (ret == 0) { + jbd2_create_jbd_stats_proc_entry(); + } else { jbd2_journal_destroy_caches(); - jbd2_create_debugfs_entry(); - jbd2_create_jbd_stats_proc_entry(); + } return ret; } @@ -2326,9 +2643,8 @@ static void __exit journal_exit(void) #ifdef CONFIG_JBD2_DEBUG int n = atomic_read(&nr_journal_heads); if (n) - printk(KERN_EMERG "JBD: leaked %d journal_heads!\n", n); + printk(KERN_ERR "JBD2: leaked %d journal_heads!\n", n); #endif - jbd2_remove_debugfs_entry(); jbd2_remove_jbd_stats_proc_entry(); jbd2_journal_destroy_caches(); } |