diff options
Diffstat (limited to 'fs/jbd2/journal.c')
| -rw-r--r-- | fs/jbd2/journal.c | 1626 |
1 files changed, 1040 insertions, 586 deletions
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 8ef6b6daaa7a..c973162d5b31 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -49,8 +49,7 @@ #include <asm/page.h> #ifdef CONFIG_JBD2_DEBUG -ushort jbd2_journal_enable_debug __read_mostly; -EXPORT_SYMBOL(jbd2_journal_enable_debug); +static ushort jbd2_journal_enable_debug __read_mostly; module_param_named(jbd2_debug, jbd2_journal_enable_debug, ushort, 0644); MODULE_PARM_DESC(jbd2_debug, "Debugging level for jbd2"); @@ -66,9 +65,6 @@ EXPORT_SYMBOL(jbd2_journal_get_undo_access); EXPORT_SYMBOL(jbd2_journal_set_triggers); EXPORT_SYMBOL(jbd2_journal_dirty_metadata); EXPORT_SYMBOL(jbd2_journal_forget); -#if 0 -EXPORT_SYMBOL(journal_sync_buffer); -#endif EXPORT_SYMBOL(jbd2_journal_flush); EXPORT_SYMBOL(jbd2_journal_revoke); @@ -84,22 +80,21 @@ 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); -EXPORT_SYMBOL(jbd2_journal_blocks_per_page); -EXPORT_SYMBOL(jbd2_journal_invalidatepage); +EXPORT_SYMBOL(jbd2_journal_blocks_per_folio); +EXPORT_SYMBOL(jbd2_journal_invalidate_folio); EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers); EXPORT_SYMBOL(jbd2_journal_force_commit); -EXPORT_SYMBOL(jbd2_journal_inode_add_write); -EXPORT_SYMBOL(jbd2_journal_inode_add_wait); +EXPORT_SYMBOL(jbd2_journal_inode_ranged_write); +EXPORT_SYMBOL(jbd2_journal_inode_ranged_wait); +EXPORT_SYMBOL(jbd2_journal_finish_inode_data_buffers); 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 void __journal_abort_soft (journal_t *journal, int errno); static int jbd2_journal_create_slab(size_t slab_size); #ifdef CONFIG_JBD2_DEBUG @@ -117,54 +112,29 @@ void __jbd2_debug(int level, const char *file, const char *func, printk(KERN_DEBUG "%s: (%s, %u): %pV", 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_journal_has_csum_v2or3_feature(j)) - return 1; - - return sb->s_checksum_type == JBD2_CRC32C_CHKSUM; -} - -static __be32 jbd2_superblock_csum(journal_t *j, journal_superblock_t *sb) +static __be32 jbd2_superblock_csum(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)); + csum = jbd2_chksum(~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_journal_has_csum_v2or3(j)) - 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_journal_has_csum_v2or3(j)) - return; - - sb->s_checksum = jbd2_superblock_csum(j, sb); -} - /* * Helper function used to manage commit timeouts */ static void commit_timeout(struct timer_list *t) { - journal_t *journal = from_timer(journal, t, j_commit_timer); + journal_t *journal = timer_container_of(journal, t, j_commit_timer); wake_up_process(journal->j_task); } @@ -177,7 +147,9 @@ static void commit_timeout(struct timer_list *t) * * 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. + * 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 @@ -219,13 +191,13 @@ loop: if (journal->j_flags & JBD2_UNMOUNT) goto end_loop; - jbd_debug(1, "commit_sequence=%d, commit_request=%d\n", + jbd2_debug(1, "commit_sequence=%u, commit_request=%u\n", journal->j_commit_sequence, journal->j_commit_request); if (journal->j_commit_sequence != journal->j_commit_request) { - jbd_debug(1, "OK, requests differ\n"); + jbd2_debug(1, "OK, requests differ\n"); write_unlock(&journal->j_state_lock); - del_timer_sync(&journal->j_commit_timer); + timer_delete_sync(&journal->j_commit_timer); jbd2_journal_commit_transaction(journal); write_lock(&journal->j_state_lock); goto loop; @@ -238,7 +210,7 @@ loop: * good idea, because that depends on threads that may * be already stopped. */ - jbd_debug(1, "Now suspending kjournald2\n"); + jbd2_debug(1, "Now suspending kjournald2\n"); write_unlock(&journal->j_state_lock); try_to_freeze(); write_lock(&journal->j_state_lock); @@ -248,19 +220,12 @@ loop: * so we don't sleep */ DEFINE_WAIT(wait); - int should_sleep = 1; prepare_to_wait(&journal->j_wait_commit, &wait, TASK_INTERRUPTIBLE); - if (journal->j_commit_sequence != journal->j_commit_request) - should_sleep = 0; transaction = journal->j_running_transaction; - if (transaction && time_after_eq(jiffies, - transaction->t_expires)) - should_sleep = 0; - if (journal->j_flags & JBD2_UNMOUNT) - should_sleep = 0; - if (should_sleep) { + if (transaction == NULL || + time_before(jiffies, transaction->t_expires)) { write_unlock(&journal->j_state_lock); schedule(); write_lock(&journal->j_state_lock); @@ -268,7 +233,7 @@ loop: finish_wait(&journal->j_wait_commit, &wait); } - jbd_debug(1, "kjournald2 wakes\n"); + jbd2_debug(1, "kjournald2 wakes\n"); /* * Were we woken up by a commit wakeup event? @@ -276,15 +241,15 @@ loop: transaction = journal->j_running_transaction; if (transaction && time_after_eq(jiffies, transaction->t_expires)) { journal->j_commit_request = transaction->t_tid; - jbd_debug(1, "woke because of timeout\n"); + jbd2_debug(1, "woke because of timeout\n"); } goto loop; end_loop: - del_timer_sync(&journal->j_commit_timer); + timer_delete_sync(&journal->j_commit_timer); journal->j_task = NULL; wake_up(&journal->j_wait_done_commit); - jbd_debug(1, "Journal thread exiting.\n"); + jbd2_debug(1, "Journal thread exiting.\n"); write_unlock(&journal->j_state_lock); return 0; } @@ -316,6 +281,16 @@ static void journal_kill_thread(journal_t *journal) write_unlock(&journal->j_state_lock); } +static inline bool jbd2_data_needs_escaping(char *data) +{ + return *((__be32 *)data) == cpu_to_be32(JBD2_MAGIC_NUMBER); +} + +static inline void jbd2_data_do_escape(char *data) +{ + *((unsigned int *)data) = 0; +} + /* * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal. * @@ -340,15 +315,11 @@ static void journal_kill_thread(journal_t *journal) * 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 * - * On success: - * Bit 0 set == escape performed on the data - * Bit 1 set == buffer copy-out performed (kfree the data after IO) + * Return value: + * =0: Finished OK without escape + * =1: Finished OK with escape */ int jbd2_journal_write_metadata_buffer(transaction_t *transaction, @@ -356,12 +327,9 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction, 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 page *new_page; + struct folio *new_folio; unsigned int new_offset; struct buffer_head *bh_in = jh2bh(jh_in); journal_t *journal = transaction->t_journal; @@ -382,88 +350,65 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction, /* keep subsequent assertions sane */ atomic_set(&new_bh->b_count, 1); - jbd_lock_bh_state(bh_in); -repeat: + spin_lock(&jh_in->b_state_lock); /* * If a new transaction has already done a buffer copy-out, then * we use that version of the data for the commit. */ if (jh_in->b_frozen_data) { - done_copy_out = 1; - new_page = virt_to_page(jh_in->b_frozen_data); - new_offset = offset_in_page(jh_in->b_frozen_data); + new_folio = virt_to_folio(jh_in->b_frozen_data); + new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data); + do_escape = jbd2_data_needs_escaping(jh_in->b_frozen_data); + if (do_escape) + jbd2_data_do_escape(jh_in->b_frozen_data); } else { - new_page = jh2bh(jh_in)->b_page; - new_offset = offset_in_page(jh2bh(jh_in)->b_data); - } + char *tmp; + char *mapped_data; - 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, + new_folio = bh_in->b_folio; + new_offset = offset_in_folio(new_folio, bh_in->b_data); + mapped_data = kmap_local_folio(new_folio, new_offset); + /* + * 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. + */ + jbd2_buffer_frozen_trigger(jh_in, mapped_data, jh_in->b_triggers); + do_escape = jbd2_data_needs_escaping(mapped_data); + kunmap_local(mapped_data); + /* + * Do we need to do a data copy? + */ + if (!do_escape) + goto escape_done; - /* - * Check for escaping - */ - if (*((__be32 *)(mapped_data + new_offset)) == - cpu_to_be32(JBD2_MAGIC_NUMBER)) { - need_copy_out = 1; - do_escape = 1; - } - kunmap_atomic(mapped_data); - - /* - * Do we need to do a data copy? - */ - if (need_copy_out && !done_copy_out) { - char *tmp; - - 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); + spin_unlock(&jh_in->b_state_lock); + tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS | __GFP_NOFAIL); + spin_lock(&jh_in->b_state_lock); if (jh_in->b_frozen_data) { jbd2_free(tmp, bh_in->b_size); - goto repeat; + goto copy_done; } jh_in->b_frozen_data = tmp; - 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; - + memcpy_from_folio(tmp, new_folio, new_offset, bh_in->b_size); /* * 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; - } - /* - * Did we need to do an escaping? Now we've done all the - * copying, we can finally do so. - */ - if (do_escape) { - mapped_data = kmap_atomic(new_page); - *((unsigned int *)(mapped_data + new_offset)) = 0; - kunmap_atomic(mapped_data); +copy_done: + new_folio = virt_to_folio(jh_in->b_frozen_data); + new_offset = offset_in_folio(new_folio, jh_in->b_frozen_data); + jbd2_data_do_escape(jh_in->b_frozen_data); } - set_bh_page(new_bh, new_page, new_offset); +escape_done: + folio_set_bh(new_bh, new_folio, new_offset); new_bh->b_size = bh_in->b_size; new_bh->b_bdev = journal->j_dev; new_bh->b_blocknr = blocknr; @@ -483,9 +428,9 @@ repeat: __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); + spin_unlock(&jh_in->b_state_lock); - return do_escape | (done_copy_out << 1); + return do_escape; } /* @@ -497,7 +442,7 @@ repeat: * Called with j_state_lock locked for writing. * Returns true if a transaction commit was started. */ -int __jbd2_log_start_commit(journal_t *journal, tid_t target) +static int __jbd2_log_start_commit(journal_t *journal, tid_t target) { /* Return if the txn has already requested to be committed */ if (journal->j_commit_request == target) @@ -516,7 +461,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target) */ journal->j_commit_request = target; - jbd_debug(1, "JBD2: requesting commit %d/%d\n", + jbd2_debug(1, "JBD2: requesting commit %u/%u\n", journal->j_commit_request, journal->j_commit_sequence); journal->j_running_transaction->t_requested = jiffies; @@ -529,7 +474,7 @@ int __jbd2_log_start_commit(journal_t *journal, tid_t target) 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 ? + target, journal->j_running_transaction ? journal->j_running_transaction->t_tid : 0); return 0; } @@ -582,12 +527,14 @@ static int __jbd2_journal_force_commit(journal_t *journal) } /** - * 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. + * 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) { @@ -598,7 +545,7 @@ int jbd2_journal_force_commit_nested(journal_t *journal) } /** - * int journal_force_commit() - force any uncommitted transactions + * jbd2_journal_force_commit() - force any uncommitted transactions * @journal: journal to force * * Caller want unconditional commit. We can only force the running transaction @@ -656,7 +603,7 @@ int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid) int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid) { int ret = 0; - transaction_t *commit_trans; + transaction_t *commit_trans, *running_trans; if (!(journal->j_flags & JBD2_BARRIER)) return 0; @@ -666,6 +613,16 @@ int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid) goto out; commit_trans = journal->j_committing_transaction; if (!commit_trans || commit_trans->t_tid != tid) { + running_trans = journal->j_running_transaction; + /* + * The query transaction hasn't started committing, + * it must still be running. + */ + if (WARN_ON_ONCE(!running_trans || + running_trans->t_tid != tid)) + goto out; + + running_trans->t_need_data_flush = 1; ret = 1; goto out; } @@ -714,12 +671,12 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) #ifdef CONFIG_JBD2_DEBUG if (!tid_geq(journal->j_commit_request, tid)) { printk(KERN_ERR - "%s: error: j_commit_request=%d, tid=%d\n", + "%s: error: j_commit_request=%u, tid=%u\n", __func__, journal->j_commit_request, tid); } #endif while (tid_gt(tid, journal->j_commit_sequence)) { - jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n", + jbd2_debug(1, "JBD2: want %u, j_commit_sequence=%u\n", tid, journal->j_commit_sequence); read_unlock(&journal->j_state_lock); wake_up(&journal->j_wait_commit); @@ -734,20 +691,89 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) return err; } -/* Return 1 when transaction with given tid has already committed. */ -int jbd2_transaction_committed(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) { - int ret = 1; + if (unlikely(is_journal_aborted(journal))) + return -EIO; + /* + * Fast commits only allowed if at least one full commit has + * been processed. + */ + if (!journal->j_stats.ts_tid) + return -EINVAL; + + write_lock(&journal->j_state_lock); + if (tid_geq(journal->j_commit_sequence, tid)) { + write_unlock(&journal->j_state_lock); + return -EALREADY; + } + + if (journal->j_flags & JBD2_FULL_COMMIT_ONGOING || + (journal->j_flags & JBD2_FAST_COMMIT_ONGOING)) { + DEFINE_WAIT(wait); + + prepare_to_wait(&journal->j_fc_wait, &wait, + TASK_UNINTERRUPTIBLE); + write_unlock(&journal->j_state_lock); + schedule(); + finish_wait(&journal->j_fc_wait, &wait); + return -EALREADY; + } + journal->j_flags |= JBD2_FAST_COMMIT_ONGOING; + write_unlock(&journal->j_state_lock); + + return 0; +} +EXPORT_SYMBOL(jbd2_fc_begin_commit); + +/* + * 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) +{ + if (journal->j_fc_cleanup_callback) + journal->j_fc_cleanup_callback(journal, 0, tid); + write_lock(&journal->j_state_lock); + journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING; + if (fallback) + journal->j_flags |= JBD2_FULL_COMMIT_ONGOING; + write_unlock(&journal->j_state_lock); + wake_up(&journal->j_fc_wait); + if (fallback) + return jbd2_complete_transaction(journal, tid); + return 0; +} + +int jbd2_fc_end_commit(journal_t *journal) +{ + return __jbd2_fc_end_commit(journal, 0, false); +} +EXPORT_SYMBOL(jbd2_fc_end_commit); + +int jbd2_fc_end_commit_fallback(journal_t *journal) +{ + tid_t tid; read_lock(&journal->j_state_lock); - if (journal->j_running_transaction && - journal->j_running_transaction->t_tid == tid) - ret = 0; - if (journal->j_committing_transaction && - journal->j_committing_transaction->t_tid == tid) - ret = 0; + tid = journal->j_running_transaction ? + journal->j_running_transaction->t_tid : 0; read_unlock(&journal->j_state_lock); - return ret; + return __jbd2_fc_end_commit(journal, tid, true); +} +EXPORT_SYMBOL(jbd2_fc_end_commit_fallback); + +/* Return 1 when transaction with given tid has already committed. */ +int jbd2_transaction_committed(journal_t *journal, tid_t tid) +{ + return tid_geq(READ_ONCE(journal->j_commit_sequence), tid); } EXPORT_SYMBOL(jbd2_transaction_committed); @@ -802,6 +828,90 @@ int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp) return jbd2_journal_bmap(journal, blocknr, 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) +{ + unsigned long long pblock; + unsigned long blocknr; + int ret = 0; + struct buffer_head *bh; + int fc_off; + + *bh_out = NULL; + + if (journal->j_fc_off + journal->j_fc_first >= journal->j_fc_last) + return -EINVAL; + + fc_off = journal->j_fc_off; + blocknr = journal->j_fc_first + fc_off; + journal->j_fc_off++; + ret = jbd2_journal_bmap(journal, blocknr, &pblock); + if (ret) + return ret; + + bh = __getblk(journal->j_dev, pblock, journal->j_blocksize); + if (!bh) + return -ENOMEM; + + journal->j_fc_wbuf[fc_off] = bh; + + *bh_out = bh; + + return 0; +} +EXPORT_SYMBOL(jbd2_fc_get_buf); + +/* + * 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) +{ + struct buffer_head *bh; + int i, j_fc_off; + + j_fc_off = journal->j_fc_off; + + /* + * Wait in reverse order to minimize chances of us being woken up before + * all IOs have completed + */ + for (i = j_fc_off - 1; i >= j_fc_off - num_blks; i--) { + bh = journal->j_fc_wbuf[i]; + wait_on_buffer(bh); + /* + * Update j_fc_off so jbd2_fc_release_bufs can release remain + * buffer head. + */ + if (unlikely(!buffer_uptodate(bh))) { + journal->j_fc_off = i + 1; + return -EIO; + } + put_bh(bh); + journal->j_fc_wbuf[i] = NULL; + } + + return 0; +} +EXPORT_SYMBOL(jbd2_fc_wait_bufs); + +void jbd2_fc_release_bufs(journal_t *journal) +{ + struct buffer_head *bh; + int i, j_fc_off; + + j_fc_off = journal->j_fc_off; + + for (i = j_fc_off - 1; i >= 0; i--) { + bh = journal->j_fc_wbuf[i]; + if (!bh) + break; + put_bh(bh); + journal->j_fc_wbuf[i] = NULL; + } +} +EXPORT_SYMBOL(jbd2_fc_release_bufs); + /* * Conversion of logical to physical block numbers for the journal * @@ -814,18 +924,25 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, { int err = 0; unsigned long long ret; + sector_t block = blocknr; - if (journal->j_inode) { - ret = bmap(journal->j_inode, blocknr); - if (ret) - *retp = ret; - else { + if (journal->j_bmap) { + err = journal->j_bmap(journal, &block); + if (err == 0) + *retp = block; + } else if (journal->j_inode) { + ret = bmap(journal->j_inode, &block); + + if (ret || !block) { printk(KERN_ALERT "%s: journal block not found " "at offset %lu on %s\n", __func__, blocknr, journal->j_devname); + jbd2_journal_abort(journal, ret ? ret : -EFSCORRUPTED); err = -EIO; - __journal_abort_soft(journal, err); + } else { + *retp = block; } + } else { *retp = blocknr; /* +journal->j_blk_offset */ } @@ -838,7 +955,7 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, * 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). + * the buffer's contents they really should run flush_dcache_folio(bh->b_folio). * But we don't bother doing that, so there will be coherency problems with * mmaps of blockdevs which hold live JBD-controlled filesystems. */ @@ -859,6 +976,7 @@ jbd2_journal_get_descriptor_buffer(transaction_t *transaction, int type) bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize); if (!bh) return NULL; + atomic_dec(&transaction->t_outstanding_credits); lock_buffer(bh); memset(bh->b_data, 0, journal->j_blocksize); header = (journal_header_t *)bh->b_data; @@ -882,7 +1000,7 @@ void jbd2_descriptor_block_csum_set(journal_t *j, struct buffer_head *bh) tail = (struct jbd2_journal_block_tail *)(bh->b_data + j->j_blocksize - sizeof(struct jbd2_journal_block_tail)); tail->t_checksum = 0; - csum = jbd2_chksum(j, j->j_csum_seed, bh->b_data, j->j_blocksize); + csum = jbd2_chksum(j->j_csum_seed, bh->b_data, j->j_blocksize); tail->t_checksum = cpu_to_be32(csum); } @@ -948,8 +1066,7 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) * space and if we lose sb update during power failure we'd replay * old transaction with possibly newly overwritten data. */ - ret = jbd2_journal_update_sb_log_tail(journal, tid, block, - REQ_SYNC | REQ_FUA); + ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_FUA); if (ret) goto out; @@ -959,8 +1076,8 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block) freed += journal->j_last - journal->j_first; trace_jbd2_update_log_tail(journal, tid, block, freed); - jbd_debug(1, - "Cleaning journal tail from %d to %d (offset %lu), " + jbd2_debug(1, + "Cleaning journal tail from %u to %u (offset %lu), " "freeing %lu\n", journal->j_tail_sequence, tid, block, freed); @@ -1000,6 +1117,7 @@ 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) { + (*pos)++; return NULL; } @@ -1053,7 +1171,7 @@ static const struct seq_operations jbd2_seq_info_ops = { static int jbd2_seq_info_open(struct inode *inode, struct file *file) { - journal_t *journal = PDE_DATA(inode); + journal_t *journal = pde_data(inode); struct jbd2_stats_proc_session *s; int rc, size; @@ -1092,12 +1210,11 @@ static int jbd2_seq_info_release(struct inode *inode, struct file *file) return seq_release(inode, file); } -static const struct file_operations jbd2_seq_info_fops = { - .owner = THIS_MODULE, - .open = jbd2_seq_info_open, - .read = seq_read, - .llseek = seq_lseek, - .release = jbd2_seq_info_release, +static const struct proc_ops jbd2_info_proc_ops = { + .proc_open = jbd2_seq_info_open, + .proc_read = seq_read, + .proc_lseek = seq_lseek, + .proc_release = jbd2_seq_info_release, }; static struct proc_dir_entry *proc_jbd2_stats; @@ -1107,7 +1224,7 @@ static void jbd2_stats_proc_init(journal_t *journal) journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats); if (journal->j_proc_entry) { proc_create_data("info", S_IRUGO, journal->j_proc_entry, - &jbd2_seq_info_fops, journal); + &jbd2_info_proc_ops, journal); } } @@ -1117,44 +1234,333 @@ static void jbd2_stats_proc_exit(journal_t *journal) remove_proc_entry(journal->j_devname, proc_jbd2_stats); } +/* Minimum size of descriptor tag */ +static int jbd2_min_tag_size(void) +{ + /* + * Tag with 32-bit block numbers does not use last four bytes of the + * structure + */ + return sizeof(journal_block_tag_t) - 4; +} + +/** + * 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) +{ + journal_t *journal = shrink->private_data; + unsigned long nr_to_scan = sc->nr_to_scan; + unsigned long nr_shrunk; + unsigned long count; + + count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count); + trace_jbd2_shrink_scan_enter(journal, sc->nr_to_scan, count); + + nr_shrunk = jbd2_journal_shrink_checkpoint_list(journal, &nr_to_scan); + + count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count); + trace_jbd2_shrink_scan_exit(journal, nr_to_scan, nr_shrunk, count); + + return nr_shrunk; +} + +/** + * 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) +{ + journal_t *journal = shrink->private_data; + unsigned long count; + + count = percpu_counter_read_positive(&journal->j_checkpoint_jh_count); + trace_jbd2_shrink_count(journal, sc->nr_to_scan, count); + + return count; +} + +/* + * 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) +{ + struct buffer_head *bh = journal->j_sb_buffer; + brelse(bh); + journal->j_sb_buffer = NULL; +} + +/* + * Check the superblock for a given journal, performing initial + * validation of the format. + */ +static int journal_check_superblock(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + int num_fc_blks; + int 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 "JBD2: no valid journal superblock found\n"); + return err; + } + + if (be32_to_cpu(sb->s_header.h_blocktype) != JBD2_SUPERBLOCK_V1 && + be32_to_cpu(sb->s_header.h_blocktype) != JBD2_SUPERBLOCK_V2) { + printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n"); + return err; + } + + if (be32_to_cpu(sb->s_maxlen) > journal->j_total_len) { + printk(KERN_WARNING "JBD2: journal file too short\n"); + return err; + } + + if (be32_to_cpu(sb->s_first) == 0 || + be32_to_cpu(sb->s_first) >= journal->j_total_len) { + printk(KERN_WARNING + "JBD2: Invalid start block of journal: %u\n", + be32_to_cpu(sb->s_first)); + return err; + } + + /* + * If this is a V2 superblock, then we have to check the + * features flags on it. + */ + if (!jbd2_format_support_feature(journal)) + return 0; + + if ((sb->s_feature_ro_compat & + ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) || + (sb->s_feature_incompat & + ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) { + printk(KERN_WARNING "JBD2: Unrecognised features on journal\n"); + return err; + } + + num_fc_blks = jbd2_has_feature_fast_commit(journal) ? + jbd2_journal_get_num_fc_blks(sb) : 0; + if (be32_to_cpu(sb->s_maxlen) < JBD2_MIN_JOURNAL_BLOCKS || + be32_to_cpu(sb->s_maxlen) - JBD2_MIN_JOURNAL_BLOCKS < num_fc_blks) { + printk(KERN_ERR "JBD2: journal file too short %u,%d\n", + be32_to_cpu(sb->s_maxlen), num_fc_blks); + return err; + } + + if (jbd2_has_feature_csum2(journal) && + jbd2_has_feature_csum3(journal)) { + /* Can't have checksum v2 and v3 at the same time! */ + printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 " + "at the same time!\n"); + return err; + } + + if (jbd2_journal_has_csum_v2or3(journal) && + jbd2_has_feature_checksum(journal)) { + /* Can't have checksum v1 and v2 on at the same time! */ + printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2/3 " + "at the same time!\n"); + return err; + } + + if (jbd2_journal_has_csum_v2or3(journal)) { + if (sb->s_checksum_type != JBD2_CRC32C_CHKSUM) { + printk(KERN_ERR "JBD2: Unknown checksum type\n"); + return err; + } + + /* Check superblock checksum */ + if (sb->s_checksum != jbd2_superblock_csum(sb)) { + printk(KERN_ERR "JBD2: journal checksum error\n"); + err = -EFSBADCRC; + return err; + } + } + + return 0; +} + +static int journal_revoke_records_per_block(journal_t *journal) +{ + int record_size; + int space = journal->j_blocksize - sizeof(jbd2_journal_revoke_header_t); + + if (jbd2_has_feature_64bit(journal)) + record_size = 8; + else + record_size = 4; + + if (jbd2_journal_has_csum_v2or3(journal)) + space -= sizeof(struct jbd2_journal_block_tail); + return space / record_size; +} + +static int jbd2_journal_get_max_txn_bufs(journal_t *journal) +{ + return (journal->j_total_len - journal->j_fc_wbufsize) / 3; +} + +/* + * Base amount of descriptor blocks we reserve for each transaction. + */ +static int jbd2_descriptor_blocks_per_trans(journal_t *journal) +{ + int tag_space = journal->j_blocksize - sizeof(journal_header_t); + int tags_per_block; + + /* Subtract UUID */ + tag_space -= 16; + if (jbd2_journal_has_csum_v2or3(journal)) + tag_space -= sizeof(struct jbd2_journal_block_tail); + /* Commit code leaves a slack space of 16 bytes at the end of block */ + tags_per_block = (tag_space - 16) / journal_tag_bytes(journal); + /* + * Revoke descriptors are accounted separately so we need to reserve + * space for commit block and normal transaction descriptor blocks. + */ + return 1 + DIV_ROUND_UP(jbd2_journal_get_max_txn_bufs(journal), + tags_per_block); +} + +/* + * 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) +{ + journal->j_revoke_records_per_block = + journal_revoke_records_per_block(journal); + journal->j_transaction_overhead_buffers = + jbd2_descriptor_blocks_per_trans(journal); + journal->j_max_transaction_buffers = + jbd2_journal_get_max_txn_bufs(journal); +} + +/* + * Load the on-disk journal superblock and read the key fields into the + * journal_t. + */ +static int journal_load_superblock(journal_t *journal) +{ + int err; + struct buffer_head *bh; + journal_superblock_t *sb; + + bh = getblk_unmovable(journal->j_dev, journal->j_blk_offset, + journal->j_blocksize); + if (bh) + err = bh_read(bh, 0); + if (!bh || err < 0) { + pr_err("%s: Cannot read journal superblock\n", __func__); + brelse(bh); + return -EIO; + } + + journal->j_sb_buffer = bh; + sb = (journal_superblock_t *)bh->b_data; + journal->j_superblock = sb; + err = journal_check_superblock(journal); + if (err) { + journal_fail_superblock(journal); + return err; + } + + journal->j_tail_sequence = be32_to_cpu(sb->s_sequence); + journal->j_tail = be32_to_cpu(sb->s_start); + journal->j_first = be32_to_cpu(sb->s_first); + journal->j_errno = be32_to_cpu(sb->s_errno); + journal->j_last = be32_to_cpu(sb->s_maxlen); + + if (be32_to_cpu(sb->s_maxlen) < journal->j_total_len) + journal->j_total_len = be32_to_cpu(sb->s_maxlen); + /* Precompute checksum seed for all metadata */ + if (jbd2_journal_has_csum_v2or3(journal)) + journal->j_csum_seed = jbd2_chksum(~0, sb->s_uuid, + sizeof(sb->s_uuid)); + /* After journal features are set, we can compute transaction limits */ + jbd2_journal_init_transaction_limits(journal); + + if (jbd2_has_feature_fast_commit(journal)) { + journal->j_fc_last = be32_to_cpu(sb->s_maxlen); + journal->j_last = journal->j_fc_last - + jbd2_journal_get_num_fc_blks(sb); + journal->j_fc_first = journal->j_last + 1; + journal->j_fc_off = 0; + } + + return 0; +} + + /* * 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. */ +/* The journal_init_common() function creates and fills a journal_t object + * in memory. It calls journal_load_superblock() to load the on-disk journal + * superblock and initialize the journal_t object. + */ static journal_t *journal_init_common(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int blocksize) { - static struct lock_class_key jbd2_trans_commit_key; journal_t *journal; int err; - struct buffer_head *bh; int n; journal = kzalloc(sizeof(*journal), GFP_KERNEL); if (!journal) - return NULL; + return ERR_PTR(-ENOMEM); + + lockdep_register_key(&journal->jbd2_trans_commit_key); + journal->j_blocksize = blocksize; + journal->j_dev = bdev; + journal->j_fs_dev = fs_dev; + journal->j_blk_offset = start; + journal->j_total_len = len; + jbd2_init_fs_dev_write_error(journal); + + err = journal_load_superblock(journal); + if (err) + goto err_cleanup; init_waitqueue_head(&journal->j_wait_transaction_locked); init_waitqueue_head(&journal->j_wait_done_commit); init_waitqueue_head(&journal->j_wait_commit); init_waitqueue_head(&journal->j_wait_updates); init_waitqueue_head(&journal->j_wait_reserved); + init_waitqueue_head(&journal->j_fc_wait); + mutex_init(&journal->j_abort_mutex); 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_history_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); + lockdep_init_map(&journal->j_trans_commit_map, "jbd2_handle", + &journal->jbd2_trans_commit_key, 0); /* The journal is marked for error until we succeed with recovery! */ journal->j_flags = JBD2_ABORT; @@ -1164,40 +1570,50 @@ static journal_t *journal_init_common(struct block_device *bdev, if (err) goto err_cleanup; - spin_lock_init(&journal->j_history_lock); - - lockdep_init_map(&journal->j_trans_commit_map, "jbd2_handle", - &jbd2_trans_commit_key, 0); - - /* journal descriptor can store up to n blocks -bzzz */ - journal->j_blocksize = blocksize; - journal->j_dev = bdev; - journal->j_fs_dev = fs_dev; - journal->j_blk_offset = start; - journal->j_maxlen = len; - n = journal->j_blocksize / sizeof(journal_block_tag_t); + /* + * journal descriptor can store up to n blocks, we need enough + * buffers to write out full descriptor block. + */ + err = -ENOMEM; + n = journal->j_blocksize / jbd2_min_tag_size(); journal->j_wbufsize = n; + journal->j_fc_wbuf = NULL; journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *), GFP_KERNEL); if (!journal->j_wbuf) goto err_cleanup; - bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize); - if (!bh) { - pr_err("%s: Cannot get buffer for journal superblock\n", - __func__); + err = percpu_counter_init(&journal->j_checkpoint_jh_count, 0, + GFP_KERNEL); + if (err) + goto err_cleanup; + + journal->j_shrink_transaction = NULL; + + journal->j_shrinker = shrinker_alloc(0, "jbd2-journal:(%u:%u)", + MAJOR(bdev->bd_dev), + MINOR(bdev->bd_dev)); + if (!journal->j_shrinker) { + err = -ENOMEM; goto err_cleanup; } - journal->j_sb_buffer = bh; - journal->j_superblock = (journal_superblock_t *)bh->b_data; + + journal->j_shrinker->scan_objects = jbd2_journal_shrink_scan; + journal->j_shrinker->count_objects = jbd2_journal_shrink_count; + journal->j_shrinker->private_data = journal; + + shrinker_register(journal->j_shrinker); return journal; err_cleanup: + percpu_counter_destroy(&journal->j_checkpoint_jh_count); kfree(journal->j_wbuf); jbd2_journal_destroy_revoke(journal); + journal_fail_superblock(journal); + lockdep_unregister_key(&journal->jbd2_trans_commit_key); kfree(journal); - return NULL; + return ERR_PTR(err); } /* jbd2_journal_init_dev and jbd2_journal_init_inode: @@ -1230,10 +1646,11 @@ journal_t *jbd2_journal_init_dev(struct block_device *bdev, journal_t *journal; journal = journal_init_common(bdev, fs_dev, start, len, blocksize); - if (!journal) - return NULL; + if (IS_ERR(journal)) + return ERR_CAST(journal); - bdevname(journal->j_dev, journal->j_devname); + snprintf(journal->j_devname, sizeof(journal->j_devname), + "%pg", journal->j_dev); strreplace(journal->j_devname, '/', '!'); jbd2_stats_proc_init(journal); @@ -1251,48 +1668,36 @@ journal_t *jbd2_journal_init_dev(struct block_device *bdev, journal_t *jbd2_journal_init_inode(struct inode *inode) { journal_t *journal; - char *p; - unsigned long long blocknr; + sector_t blocknr; + int err = 0; - blocknr = bmap(inode, 0); - if (!blocknr) { - pr_err("%s: Cannot locate journal superblock\n", - __func__); - return NULL; + blocknr = 0; + err = bmap(inode, &blocknr); + if (err || !blocknr) { + pr_err("%s: Cannot locate journal superblock\n", __func__); + return err ? ERR_PTR(err) : ERR_PTR(-EINVAL); } - jbd_debug(1, "JBD2: inode %s/%ld, size %lld, bits %d, blksize %ld\n", + jbd2_debug(1, "JBD2: inode %s/%ld, size %lld, bits %d, blksize %ld\n", inode->i_sb->s_id, inode->i_ino, (long long) inode->i_size, inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize); journal = journal_init_common(inode->i_sb->s_bdev, inode->i_sb->s_bdev, blocknr, inode->i_size >> inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize); - if (!journal) - return NULL; + if (IS_ERR(journal)) + return ERR_CAST(journal); journal->j_inode = inode; - bdevname(journal->j_dev, journal->j_devname); - p = strreplace(journal->j_devname, '/', '!'); - sprintf(p, "-%lu", journal->j_inode->i_ino); + snprintf(journal->j_devname, sizeof(journal->j_devname), + "%pg-%lu", journal->j_dev, journal->j_inode->i_ino); + strreplace(journal->j_devname, '/', '!'); jbd2_stats_proc_init(journal); return journal; } /* - * 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) -{ - struct buffer_head *bh = journal->j_sb_buffer; - brelse(bh); - journal->j_sb_buffer = NULL; -} - -/* * 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 @@ -1316,15 +1721,33 @@ static int journal_reset(journal_t *journal) journal->j_first = first; journal->j_last = last; - journal->j_head = first; - journal->j_tail = first; - journal->j_free = last - first; + if (journal->j_head != 0 && journal->j_flags & JBD2_CYCLE_RECORD) { + /* + * Disable the cycled recording mode if the journal head block + * number is not correct. + */ + if (journal->j_head < first || journal->j_head >= last) { + printk(KERN_WARNING "JBD2: Incorrect Journal head block %lu, " + "disable journal_cycle_record\n", + journal->j_head); + journal->j_head = journal->j_first; + } + } else { + journal->j_head = journal->j_first; + } + journal->j_tail = journal->j_head; + journal->j_free = journal->j_last - journal->j_first; journal->j_tail_sequence = journal->j_transaction_sequence; journal->j_commit_sequence = journal->j_transaction_sequence - 1; journal->j_commit_request = journal->j_commit_sequence; - journal->j_max_transaction_buffers = journal->j_maxlen / 4; + /* + * Now that journal recovery is done, turn fast commits off here. This + * way, if fast commit was enabled before the crash but if now FS has + * disabled it, we don't enable fast commits. + */ + jbd2_clear_feature_fast_commit(journal); /* * As a special case, if the on-disk copy is already marked as needing @@ -1333,8 +1756,8 @@ static int journal_reset(journal_t *journal) * 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", + jbd2_debug(1, "JBD2: Skipping superblock update on recovered sb " + "(start %ld, seq %u, errno %d)\n", journal->j_tail, journal->j_tail_sequence, journal->j_errno); journal->j_flags |= JBD2_FLUSHED; @@ -1349,23 +1772,38 @@ static int journal_reset(journal_t *journal) */ jbd2_journal_update_sb_log_tail(journal, journal->j_tail_sequence, - journal->j_tail, - REQ_SYNC | REQ_FUA); + journal->j_tail, REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } return jbd2_journal_start_thread(journal); } -static int jbd2_write_superblock(journal_t *journal, int write_flags) +/* + * 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) { struct buffer_head *bh = journal->j_sb_buffer; journal_superblock_t *sb = journal->j_superblock; - int ret; + int ret = 0; - trace_jbd2_write_superblock(journal, write_flags); + /* Buffer got discarded which means block device got invalidated */ + if (!buffer_mapped(bh)) { + unlock_buffer(bh); + return -EIO; + } + + /* + * Always set high priority flags to exempt from block layer's + * QOS policies, e.g. writeback throttle. + */ + write_flags |= JBD2_JOURNAL_REQ_FLAGS; if (!(journal->j_flags & JBD2_BARRIER)) write_flags &= ~(REQ_FUA | REQ_PREFLUSH); - lock_buffer(bh); + + trace_jbd2_write_superblock(journal, write_flags); + if (buffer_write_io_error(bh)) { /* * Oh, dear. A previous attempt to write the journal @@ -1381,10 +1819,11 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) clear_buffer_write_io_error(bh); set_buffer_uptodate(bh); } - jbd2_superblock_csum_set(journal, sb); + if (jbd2_journal_has_csum_v2or3(journal)) + sb->s_checksum = jbd2_superblock_csum(sb); get_bh(bh); bh->b_end_io = end_buffer_write_sync; - ret = submit_bh(REQ_OP_WRITE, write_flags, bh); + submit_bh(REQ_OP_WRITE | write_flags, bh); wait_on_buffer(bh); if (buffer_write_io_error(bh)) { clear_buffer_write_io_error(bh); @@ -1392,10 +1831,10 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) ret = -EIO; } if (ret) { - printk(KERN_ERR "JBD2: Error %d detected when updating " - "journal superblock for %s.\n", ret, - journal->j_devname); - jbd2_journal_abort(journal, ret); + printk(KERN_ERR "JBD2: I/O error when updating journal superblock for %s.\n", + journal->j_devname); + if (!is_journal_aborted(journal)) + jbd2_journal_abort(journal, ret); } return ret; @@ -1406,34 +1845,40 @@ static int jbd2_write_superblock(journal_t *journal, int write_flags) * @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 + * @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, int write_op) + unsigned long tail_block, + blk_opf_t write_flags) { journal_superblock_t *sb = journal->j_superblock; int ret; if (is_journal_aborted(journal)) return -EIO; + ret = jbd2_check_fs_dev_write_error(journal); + if (ret) { + jbd2_journal_abort(journal, ret); + return -EIO; + } BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex)); - jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", + jbd2_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n", tail_block, tail_tid); + lock_buffer(journal->j_sb_buffer); sb->s_sequence = cpu_to_be32(tail_tid); sb->s_start = cpu_to_be32(tail_block); - ret = jbd2_write_superblock(journal, write_op); + ret = jbd2_write_superblock(journal, write_flags); if (ret) goto out; /* 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); @@ -1444,206 +1889,173 @@ out: /** * jbd2_mark_journal_empty() - Mark on disk journal as empty. * @journal: The journal to update. - * @write_op: With which operation should we write the journal sb + * @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, int write_op) +static void jbd2_mark_journal_empty(journal_t *journal, blk_opf_t write_flags) { journal_superblock_t *sb = journal->j_superblock; + bool had_fast_commit = false; 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); + lock_buffer(journal->j_sb_buffer); + if (sb->s_start == 0) { /* Is it already empty? */ + unlock_buffer(journal->j_sb_buffer); return; } - jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n", + + jbd2_debug(1, "JBD2: Marking journal as empty (seq %u)\n", journal->j_tail_sequence); sb->s_sequence = cpu_to_be32(journal->j_tail_sequence); sb->s_start = cpu_to_be32(0); - read_unlock(&journal->j_state_lock); + sb->s_head = cpu_to_be32(journal->j_head); + if (jbd2_has_feature_fast_commit(journal)) { + /* + * When journal is clean, no need to commit fast commit flag and + * make file system incompatible with older kernels. + */ + jbd2_clear_feature_fast_commit(journal); + had_fast_commit = true; + } - jbd2_write_superblock(journal, write_op); + jbd2_write_superblock(journal, write_flags); - /* Log is no longer empty */ + if (had_fast_commit) + jbd2_set_feature_fast_commit(journal); + + /* Log is empty */ write_lock(&journal->j_state_lock); journal->j_flags |= JBD2_FLUSHED; write_unlock(&journal->j_state_lock); } - /** - * jbd2_journal_update_sb_errno() - Update error in the journal. - * @journal: The journal to update. + * __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. * - * 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; - int errcode; - - read_lock(&journal->j_state_lock); - errcode = journal->j_errno; - read_unlock(&journal->j_state_lock); - if (errcode == -ESHUTDOWN) - errcode = 0; - jbd_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode); - sb->s_errno = cpu_to_be32(errcode); - - jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA); -} -EXPORT_SYMBOL(jbd2_journal_update_sb_errno); - -/* - * Read the superblock for a given journal, performing initial - * validation of the format. + * 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 journal_get_superblock(journal_t *journal) +static int __jbd2_journal_erase(journal_t *journal, unsigned int flags) { - struct buffer_head *bh; - journal_superblock_t *sb; - int err = -EIO; + int err = 0; + unsigned long block, log_offset; /* logical */ + unsigned long long phys_block, block_start, block_stop; /* physical */ + loff_t byte_start, byte_stop, byte_count; + + /* flags must be set to either discard or zeroout */ + if ((flags & ~JBD2_JOURNAL_FLUSH_VALID) || !flags || + ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && + (flags & JBD2_JOURNAL_FLUSH_ZEROOUT))) + return -EINVAL; - bh = journal->j_sb_buffer; + if ((flags & JBD2_JOURNAL_FLUSH_DISCARD) && + !bdev_max_discard_sectors(journal->j_dev)) + return -EOPNOTSUPP; - J_ASSERT(bh != NULL); - if (!buffer_uptodate(bh)) { - ll_rw_block(REQ_OP_READ, 0, 1, &bh); - wait_on_buffer(bh); - if (!buffer_uptodate(bh)) { - printk(KERN_ERR - "JBD2: IO error reading journal superblock\n"); - goto out; + /* + * lookup block mapping and issue discard/zeroout for each + * contiguous region + */ + log_offset = be32_to_cpu(journal->j_superblock->s_first); + block_start = ~0ULL; + for (block = log_offset; block < journal->j_total_len; block++) { + err = jbd2_journal_bmap(journal, block, &phys_block); + if (err) { + pr_err("JBD2: bad block at offset %lu", block); + return err; } - } - - 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 "JBD2: no valid journal superblock found\n"); - goto out; - } - - switch(be32_to_cpu(sb->s_header.h_blocktype)) { - case JBD2_SUPERBLOCK_V1: - journal->j_format_version = 1; - break; - case JBD2_SUPERBLOCK_V2: - journal->j_format_version = 2; - break; - default: - 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 "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_feature_csum2(journal) && - jbd2_has_feature_csum3(journal)) { - /* Can't have checksum v2 and v3 at the same time! */ - printk(KERN_ERR "JBD2: Can't enable checksumming v2 and v3 " - "at the same time!\n"); - goto out; - } + if (block_start == ~0ULL) + block_stop = block_start = phys_block; - if (jbd2_journal_has_csum_v2or3_feature(journal) && - jbd2_has_feature_checksum(journal)) { - /* Can't have checksum v1 and v2 on at the same time! */ - printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2/3 " - "at the same time!\n"); - goto out; - } + /* + * last block not contiguous with current block, + * process last contiguous region and return to this block on + * next loop + */ + if (phys_block != block_stop) { + block--; + } else { + block_stop++; + /* + * if this isn't the last block of journal, + * no need to process now because next block may also + * be part of this contiguous region + */ + if (block != journal->j_total_len - 1) + continue; + } - if (!jbd2_verify_csum_type(journal, sb)) { - printk(KERN_ERR "JBD2: Unknown checksum type\n"); - goto out; - } + /* + * end of contiguous region or this is last block of journal, + * take care of the region + */ + byte_start = block_start * journal->j_blocksize; + byte_stop = block_stop * journal->j_blocksize; + byte_count = (block_stop - block_start) * journal->j_blocksize; + + truncate_inode_pages_range(journal->j_dev->bd_mapping, + byte_start, byte_stop - 1); + + if (flags & JBD2_JOURNAL_FLUSH_DISCARD) { + err = blkdev_issue_discard(journal->j_dev, + byte_start >> SECTOR_SHIFT, + byte_count >> SECTOR_SHIFT, + GFP_NOFS); + } else if (flags & JBD2_JOURNAL_FLUSH_ZEROOUT) { + err = blkdev_issue_zeroout(journal->j_dev, + byte_start >> SECTOR_SHIFT, + byte_count >> SECTOR_SHIFT, + GFP_NOFS, 0); + } - /* Load the checksum driver */ - if (jbd2_journal_has_csum_v2or3_feature(journal)) { - 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; + if (unlikely(err != 0)) { + pr_err("JBD2: (error %d) unable to wipe journal at physical blocks [%llu, %llu)", + err, block_start, block_stop); + return err; } - } - /* Check superblock checksum */ - if (!jbd2_superblock_csum_verify(journal, sb)) { - printk(KERN_ERR "JBD2: journal checksum error\n"); - err = -EFSBADCRC; - goto out; + /* reset start and stop after processing a region */ + block_start = ~0ULL; } - /* Precompute checksum seed for all metadata */ - if (jbd2_journal_has_csum_v2or3(journal)) - journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid, - sizeof(sb->s_uuid)); - - set_buffer_verified(bh); - - return 0; - -out: - journal_fail_superblock(journal); - return err; + return blkdev_issue_flush(journal->j_dev); } -/* - * Load the on-disk journal superblock and read the key fields into the - * journal_t. +/** + * 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. */ - -static int load_superblock(journal_t *journal) +void jbd2_journal_update_sb_errno(journal_t *journal) { - int err; - journal_superblock_t *sb; - - err = journal_get_superblock(journal); - if (err) - return err; - - sb = journal->j_superblock; + journal_superblock_t *sb = journal->j_superblock; + int errcode; - journal->j_tail_sequence = be32_to_cpu(sb->s_sequence); - journal->j_tail = be32_to_cpu(sb->s_start); - journal->j_first = be32_to_cpu(sb->s_first); - journal->j_last = be32_to_cpu(sb->s_maxlen); - journal->j_errno = be32_to_cpu(sb->s_errno); + lock_buffer(journal->j_sb_buffer); + errcode = journal->j_errno; + if (errcode == -ESHUTDOWN) + errcode = 0; + jbd2_debug(1, "JBD2: updating superblock error (errno %d)\n", errcode); + sb->s_errno = cpu_to_be32(errcode); - return 0; + jbd2_write_superblock(journal, REQ_FUA); } - +EXPORT_SYMBOL(jbd2_journal_update_sb_errno); /** - * int jbd2_journal_load() - Read journal from disk. + * jbd2_journal_load() - Read journal from disk. * @journal: Journal to act on. * * Given a journal_t structure which tells us which disk blocks contain @@ -1653,26 +2065,7 @@ static int load_superblock(journal_t *journal) int jbd2_journal_load(journal_t *journal) { int err; - journal_superblock_t *sb; - - err = load_superblock(journal); - if (err) - return err; - - sb = journal->j_superblock; - /* If this is a V2 superblock, then we have to check the - * features flags on it. */ - - if (journal->j_format_version >= 2) { - if ((sb->s_feature_ro_compat & - ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) || - (sb->s_feature_incompat & - ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) { - printk(KERN_WARNING - "JBD2: Unrecognised features on journal\n"); - return -EINVAL; - } - } + journal_superblock_t *sb = journal->j_superblock; /* * Create a slab for this blocksize @@ -1683,8 +2076,11 @@ int jbd2_journal_load(journal_t *journal) /* Let the recovery code check whether it needs to recover any * data from the journal. */ - if (jbd2_journal_recover(journal)) - goto recovery_error; + err = jbd2_journal_recover(journal); + if (err) { + pr_warn("JBD2: journal recovery failed\n"); + return err; + } if (journal->j_failed_commit) { printk(KERN_ERR "JBD2: journal transaction %u on %s " @@ -1692,24 +2088,27 @@ int jbd2_journal_load(journal_t *journal) journal->j_devname); return -EFSCORRUPTED; } + /* + * clear JBD2_ABORT flag initialized in journal_init_common + * here to update log tail information with the newest seq. + */ + journal->j_flags &= ~JBD2_ABORT; /* OK, we've finished with the dynamic journal bits: * reinitialise the dynamic contents of the superblock in memory * and reset them on disk. */ - if (journal_reset(journal)) - goto recovery_error; + err = journal_reset(journal); + if (err) { + pr_warn("JBD2: journal reset failed\n"); + return err; + } - journal->j_flags &= ~JBD2_ABORT; journal->j_flags |= JBD2_LOADED; return 0; - -recovery_error: - printk(KERN_WARNING "JBD2: recovery failed\n"); - return -EIO; } /** - * void jbd2_journal_destroy() - Release a journal_t structure. + * 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 @@ -1753,6 +2152,18 @@ int jbd2_journal_destroy(journal_t *journal) J_ASSERT(journal->j_checkpoint_transactions == NULL); spin_unlock(&journal->j_list_lock); + /* + * OK, all checkpoint transactions have been checked, now check the + * writeback errseq of fs dev and abort the journal if some buffer + * failed to write back to the original location, otherwise the + * filesystem may become inconsistent. + */ + if (!is_journal_aborted(journal)) { + int ret = jbd2_check_fs_dev_write_error(journal); + if (ret) + jbd2_journal_abort(journal, ret); + } + if (journal->j_sb_buffer) { if (!is_journal_aborted(journal)) { mutex_lock_io(&journal->j_checkpoint_mutex); @@ -1762,22 +2173,25 @@ int jbd2_journal_destroy(journal_t *journal) ++journal->j_transaction_sequence; write_unlock(&journal->j_state_lock); - jbd2_mark_journal_empty(journal, - REQ_SYNC | REQ_PREFLUSH | REQ_FUA); + jbd2_mark_journal_empty(journal, REQ_PREFLUSH | REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } else err = -EIO; brelse(journal->j_sb_buffer); } + if (journal->j_shrinker) { + percpu_counter_destroy(&journal->j_checkpoint_jh_count); + shrinker_free(journal->j_shrinker); + } if (journal->j_proc_entry) jbd2_stats_proc_exit(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_fc_wbuf); kfree(journal->j_wbuf); + lockdep_unregister_key(&journal->jbd2_trans_commit_key); kfree(journal); return err; @@ -1785,7 +2199,7 @@ int jbd2_journal_destroy(journal_t *journal) /** - *int jbd2_journal_check_used_features () - Check if features specified are used. + * 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 @@ -1795,18 +2209,14 @@ int jbd2_journal_destroy(journal_t *journal) * features. Return true (non-zero) if it does. **/ -int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, +int jbd2_journal_check_used_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { journal_superblock_t *sb; 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) + if (!jbd2_format_support_feature(journal)) return 0; sb = journal->j_superblock; @@ -1820,7 +2230,7 @@ int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, } /** - * int jbd2_journal_check_available_features() - Check feature set in journalling layer + * 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 @@ -1830,17 +2240,13 @@ int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat, * 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, +int jbd2_journal_check_available_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { if (!compat && !ro && !incompat) return 1; - /* We can support any known requested features iff the - * superblock is in version 2. Otherwise we fail to support any - * extended sb features. */ - - if (journal->j_format_version != 2) + if (!jbd2_format_support_feature(journal)) return 0; if ((compat & JBD2_KNOWN_COMPAT_FEATURES) == compat && @@ -1851,8 +2257,35 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com return 0; } +static int +jbd2_journal_initialize_fast_commit(journal_t *journal) +{ + journal_superblock_t *sb = journal->j_superblock; + unsigned long long num_fc_blks; + + num_fc_blks = jbd2_journal_get_num_fc_blks(sb); + if (journal->j_last - num_fc_blks < JBD2_MIN_JOURNAL_BLOCKS) + return -ENOSPC; + + /* Are we called twice? */ + WARN_ON(journal->j_fc_wbuf != NULL); + journal->j_fc_wbuf = kmalloc_array(num_fc_blks, + sizeof(struct buffer_head *), GFP_KERNEL); + if (!journal->j_fc_wbuf) + return -ENOMEM; + + journal->j_fc_wbufsize = num_fc_blks; + journal->j_fc_last = journal->j_last; + journal->j_last = journal->j_fc_last - num_fc_blks; + journal->j_fc_first = journal->j_last + 1; + journal->j_fc_off = 0; + journal->j_free = journal->j_last - journal->j_first; + + return 0; +} + /** - * int jbd2_journal_set_features () - Mark a given journal feature in the superblock + * 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 @@ -1863,7 +2296,7 @@ int jbd2_journal_check_available_features (journal_t *journal, unsigned long com * */ -int jbd2_journal_set_features (journal_t *journal, unsigned long compat, +int jbd2_journal_set_features(journal_t *journal, unsigned long compat, unsigned long ro, unsigned long incompat) { #define INCOMPAT_FEATURE_ON(f) \ @@ -1889,33 +2322,27 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, compat & JBD2_FEATURE_COMPAT_CHECKSUM) compat &= ~JBD2_FEATURE_COMPAT_CHECKSUM; - jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n", + jbd2_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n", compat, ro, incompat); sb = journal->j_superblock; - /* If enabling v3 checksums, update superblock */ + if (incompat & JBD2_FEATURE_INCOMPAT_FAST_COMMIT) { + if (jbd2_journal_initialize_fast_commit(journal)) { + pr_err("JBD2: Cannot enable fast commits.\n"); + return 0; + } + } + + lock_buffer(journal->j_sb_buffer); + + /* If enabling v3 checksums, update superblock and precompute seed */ if (INCOMPAT_FEATURE_ON(JBD2_FEATURE_INCOMPAT_CSUM_V3)) { 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 */ - journal->j_csum_seed = jbd2_chksum(journal, ~0, - sb->s_uuid, - sizeof(sb->s_uuid)); - } + journal->j_csum_seed = jbd2_chksum(~0, sb->s_uuid, + sizeof(sb->s_uuid)); } /* If enabling v1 checksums, downgrade superblock */ @@ -1927,6 +2354,14 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, 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); + /* + * Update the checksum now so that it is valid even for read-only + * filesystems where jbd2_write_superblock() doesn't get called. + */ + if (jbd2_journal_has_csum_v2or3(journal)) + sb->s_checksum = jbd2_superblock_csum(sb); + unlock_buffer(journal->j_sb_buffer); + jbd2_journal_init_transaction_limits(journal); return 1; #undef COMPAT_FEATURE_ON @@ -1934,7 +2369,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, } /* - * jbd2_journal_clear_features () - Clear a given journal feature in the + * jbd2_journal_clear_features() - Clear a given journal feature in the * superblock * @journal: Journal to act on. * @compat: bitmask of compatible features @@ -1949,27 +2384,41 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat, { journal_superblock_t *sb; - jbd_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n", + jbd2_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n", compat, ro, incompat); sb = journal->j_superblock; + lock_buffer(journal->j_sb_buffer); 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); + /* + * Update the checksum now so that it is valid even for read-only + * filesystems where jbd2_write_superblock() doesn't get called. + */ + if (jbd2_journal_has_csum_v2or3(journal)) + sb->s_checksum = jbd2_superblock_csum(sb); + unlock_buffer(journal->j_sb_buffer); + jbd2_journal_init_transaction_limits(journal); } EXPORT_SYMBOL(jbd2_journal_clear_features); /** - * int jbd2_journal_flush () - Flush journal + * 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. + * 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) +int jbd2_journal_flush(journal_t *journal, unsigned int flags) { int err = 0; transaction_t *transaction = NULL; @@ -2022,7 +2471,11 @@ 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. */ - jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); + jbd2_mark_journal_empty(journal, REQ_FUA); + + if (flags) + err = __jbd2_journal_erase(journal, flags); + mutex_unlock(&journal->j_checkpoint_mutex); write_lock(&journal->j_state_lock); J_ASSERT(!journal->j_running_transaction); @@ -2036,7 +2489,7 @@ out: } /** - * int jbd2_journal_wipe() - Wipe journal contents + * jbd2_journal_wipe() - Wipe journal contents * @journal: Journal to act on. * @write: flag (see below) * @@ -2050,16 +2503,12 @@ out: int jbd2_journal_wipe(journal_t *journal, int write) { - int err = 0; + int err; J_ASSERT (!(journal->j_flags & JBD2_LOADED)); - err = load_superblock(journal); - if (err) - return err; - if (!journal->j_tail) - goto no_recovery; + return 0; printk(KERN_WARNING "JBD2: %s recovery information on journal\n", write ? "Clearing" : "Ignoring"); @@ -2067,78 +2516,16 @@ int jbd2_journal_wipe(journal_t *journal, int write) err = jbd2_journal_skip_recovery(journal); if (write) { /* Lock to make assertions happy... */ - mutex_lock(&journal->j_checkpoint_mutex); - jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA); + mutex_lock_io(&journal->j_checkpoint_mutex); + jbd2_mark_journal_empty(journal, REQ_FUA); mutex_unlock(&journal->j_checkpoint_mutex); } - no_recovery: return err; } -/* - * Journal abort has very specific semantics, which we describe - * for journal abort. - * - * Two internal functions, which provide abort to the jbd layer - * itself are here. - */ - -/* - * Quick version for internal journal use (doesn't lock the journal). - * Aborts hard --- we mark the abort as occurred, but do _nothing_ else, - * and don't attempt to make any other journal updates. - */ -void __jbd2_journal_abort_hard(journal_t *journal) -{ - transaction_t *transaction; - - if (journal->j_flags & JBD2_ABORT) - return; - - printk(KERN_ERR "Aborting journal on device %s.\n", - journal->j_devname); - - 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); - write_unlock(&journal->j_state_lock); -} - -/* Soft abort: record the abort error status in the journal superblock, - * but don't do any other IO. */ -static void __journal_abort_soft (journal_t *journal, int errno) -{ - int old_errno; - - write_lock(&journal->j_state_lock); - old_errno = journal->j_errno; - if (!journal->j_errno || errno == -ESHUTDOWN) - journal->j_errno = errno; - - if (journal->j_flags & JBD2_ABORT) { - write_unlock(&journal->j_state_lock); - if (!old_errno && old_errno != -ESHUTDOWN && - errno == -ESHUTDOWN) - jbd2_journal_update_sb_errno(journal); - return; - } - write_unlock(&journal->j_state_lock); - - __jbd2_journal_abort_hard(journal); - - if (errno) { - jbd2_journal_update_sb_errno(journal); - write_lock(&journal->j_state_lock); - journal->j_flags |= JBD2_REC_ERR; - write_unlock(&journal->j_state_lock); - } -} - /** - * void jbd2_journal_abort () - Shutdown the journal immediately. + * 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. @@ -2176,20 +2563,60 @@ static void __journal_abort_soft (journal_t *journal, int errno) * failure to disk. ext3_error, for example, now uses this * functionality. * - * Errors which originate from within the journaling layer will NOT - * supply an errno; a null errno implies that absolutely no further - * writes are done to the journal (unless there are any already in - * progress). - * */ void jbd2_journal_abort(journal_t *journal, int errno) { - __journal_abort_soft(journal, errno); + transaction_t *transaction; + + /* + * Lock the aborting procedure until everything is done, this avoid + * races between filesystem's error handling flow (e.g. ext4_abort()), + * ensure panic after the error info is written into journal's + * superblock. + */ + mutex_lock(&journal->j_abort_mutex); + /* + * ESHUTDOWN always takes precedence because a file system check + * caused by any other journal abort error is not required after + * a shutdown triggered. + */ + write_lock(&journal->j_state_lock); + if (journal->j_flags & JBD2_ABORT) { + int old_errno = journal->j_errno; + + write_unlock(&journal->j_state_lock); + if (old_errno != -ESHUTDOWN && errno == -ESHUTDOWN) { + journal->j_errno = errno; + jbd2_journal_update_sb_errno(journal); + } + mutex_unlock(&journal->j_abort_mutex); + return; + } + + /* + * Mark the abort as occurred and start current running transaction + * to release all journaled buffer. + */ + pr_err("Aborting journal on device %s.\n", journal->j_devname); + + journal->j_flags |= JBD2_ABORT; + journal->j_errno = errno; + transaction = journal->j_running_transaction; + if (transaction) + __jbd2_log_start_commit(journal, transaction->t_tid); + write_unlock(&journal->j_state_lock); + + /* + * Record errno to the journal super block, so that fsck and jbd2 + * layer could realise that a filesystem check is needed. + */ + jbd2_journal_update_sb_errno(journal); + mutex_unlock(&journal->j_abort_mutex); } /** - * int jbd2_journal_errno () - returns the journal's error state. + * 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 @@ -2213,7 +2640,7 @@ int jbd2_journal_errno(journal_t *journal) } /** - * int jbd2_journal_clear_err () - clears the journal's error state + * 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 @@ -2233,7 +2660,7 @@ int jbd2_journal_clear_err(journal_t *journal) } /** - * void jbd2_journal_ack_err() - Ack journal err. + * 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 @@ -2247,9 +2674,10 @@ void jbd2_journal_ack_err(journal_t *journal) write_unlock(&journal->j_state_lock); } -int jbd2_journal_blocks_per_page(struct inode *inode) +int jbd2_journal_blocks_per_folio(struct inode *inode) { - return 1 << (PAGE_SHIFT - inode->i_sb->s_blocksize_bits); + return 1 << (PAGE_SHIFT + mapping_max_folio_order(inode->i_mapping) - + inode->i_sb->s_blocksize_bits); } /* @@ -2383,22 +2811,19 @@ static struct kmem_cache *jbd2_journal_head_cache; static atomic_t nr_journal_heads = ATOMIC_INIT(0); #endif -static int jbd2_journal_init_journal_head_cache(void) +static int __init jbd2_journal_init_journal_head_cache(void) { - int retval; - - J_ASSERT(jbd2_journal_head_cache == NULL); + J_ASSERT(!jbd2_journal_head_cache); jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head", sizeof(struct journal_head), 0, /* offset */ SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU, NULL); /* ctor */ - retval = 0; if (!jbd2_journal_head_cache) { - retval = -ENOMEM; printk(KERN_EMERG "JBD2: no memory for journal_head cache\n"); + return -ENOMEM; } - return retval; + return 0; } static void jbd2_journal_destroy_journal_head_cache(void) @@ -2419,11 +2844,12 @@ static struct journal_head *journal_alloc_journal_head(void) #endif ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS); if (!ret) { - jbd_debug(1, "out of memory for journal_head\n"); + jbd2_debug(1, "out of memory for journal_head\n"); pr_notice_ratelimited("ENOMEM in %s, retrying.\n", __func__); ret = kmem_cache_zalloc(jbd2_journal_head_cache, GFP_NOFS | __GFP_NOFAIL); } + spin_lock_init(&ret->b_state_lock); return ret; } @@ -2492,7 +2918,7 @@ repeat: } else { J_ASSERT_BH(bh, (atomic_read(&bh->b_count) > 0) || - (bh->b_page && bh->b_page->mapping)); + (bh->b_folio && bh->b_folio->mapping)); if (!new_jh) { jbd_unlock_bh_journal_head(bh); @@ -2530,12 +2956,12 @@ struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh) jbd_unlock_bh_journal_head(bh); return jh; } +EXPORT_SYMBOL(jbd2_journal_grab_journal_head); static void __journal_remove_journal_head(struct buffer_head *bh) { struct journal_head *jh = bh2jh(bh); - J_ASSERT_JH(jh, jh->b_jcount >= 0); 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); @@ -2543,17 +2969,23 @@ static void __journal_remove_journal_head(struct buffer_head *bh) J_ASSERT_BH(bh, buffer_jbd(bh)); J_ASSERT_BH(bh, jh2bh(jh) == bh); BUFFER_TRACE(bh, "remove journal_head"); + + /* Unlink before dropping the lock */ + bh->b_private = NULL; + jh->b_bh = NULL; /* debug, really */ + clear_buffer_jbd(bh); +} + +static void journal_release_journal_head(struct journal_head *jh, size_t b_size) +{ if (jh->b_frozen_data) { printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__); - jbd2_free(jh->b_frozen_data, bh->b_size); + jbd2_free(jh->b_frozen_data, 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); + jbd2_free(jh->b_committed_data, b_size); } - bh->b_private = NULL; - jh->b_bh = NULL; /* debug, really */ - clear_buffer_jbd(bh); journal_free_journal_head(jh); } @@ -2571,10 +3003,13 @@ void jbd2_journal_put_journal_head(struct journal_head *jh) if (!jh->b_jcount) { __journal_remove_journal_head(bh); jbd_unlock_bh_journal_head(bh); + journal_release_journal_head(jh, bh->b_size); __brelse(bh); - } else + } else { jbd_unlock_bh_journal_head(bh); + } } +EXPORT_SYMBOL(jbd2_journal_put_journal_head); /* * Initialize jbd inode head @@ -2585,6 +3020,8 @@ void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode) jinode->i_next_transaction = NULL; jinode->i_vfs_inode = inode; jinode->i_flags = 0; + jinode->i_dirty_start = 0; + jinode->i_dirty_end = 0; INIT_LIST_HEAD(&jinode->i_list); } @@ -2644,28 +3081,38 @@ static void __exit jbd2_remove_jbd_stats_proc_entry(void) struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache; +static int __init jbd2_journal_init_inode_cache(void) +{ + J_ASSERT(!jbd2_inode_cache); + jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0); + if (!jbd2_inode_cache) { + pr_emerg("JBD2: failed to create inode cache\n"); + return -ENOMEM; + } + return 0; +} + static int __init jbd2_journal_init_handle_cache(void) { + J_ASSERT(!jbd2_handle_cache); jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY); - if (jbd2_handle_cache == NULL) { + if (!jbd2_handle_cache) { 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; } +static void jbd2_journal_destroy_inode_cache(void) +{ + kmem_cache_destroy(jbd2_inode_cache); + jbd2_inode_cache = NULL; +} + static void jbd2_journal_destroy_handle_cache(void) { kmem_cache_destroy(jbd2_handle_cache); jbd2_handle_cache = NULL; - kmem_cache_destroy(jbd2_inode_cache); - jbd2_inode_cache = NULL; } /* @@ -2676,21 +3123,27 @@ static int __init journal_init_caches(void) { int ret; - ret = jbd2_journal_init_revoke_caches(); + ret = jbd2_journal_init_revoke_record_cache(); + if (ret == 0) + ret = jbd2_journal_init_revoke_table_cache(); if (ret == 0) ret = jbd2_journal_init_journal_head_cache(); if (ret == 0) ret = jbd2_journal_init_handle_cache(); if (ret == 0) + ret = jbd2_journal_init_inode_cache(); + if (ret == 0) ret = jbd2_journal_init_transaction_cache(); return ret; } static void jbd2_journal_destroy_caches(void) { - jbd2_journal_destroy_revoke_caches(); + jbd2_journal_destroy_revoke_record_cache(); + jbd2_journal_destroy_revoke_table_cache(); jbd2_journal_destroy_journal_head_cache(); jbd2_journal_destroy_handle_cache(); + jbd2_journal_destroy_inode_cache(); jbd2_journal_destroy_transaction_cache(); jbd2_journal_destroy_slabs(); } @@ -2721,6 +3174,7 @@ static void __exit journal_exit(void) jbd2_journal_destroy_caches(); } +MODULE_DESCRIPTION("Generic filesystem journal-writing module"); MODULE_LICENSE("GPL"); module_init(journal_init); module_exit(journal_exit); |