/* * linux/fs/jbd2/commit.c * * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 * * Copyright 1998 Red Hat corp --- All Rights Reserved * * This file is part of the Linux kernel and is made available under * the terms of the GNU General Public License, version 2, or at your * option, any later version, incorporated herein by reference. * * Journal commit routines for the generic filesystem journaling code; * part of the ext2fs journaling system. */ #include <linux/time.h>#include <linux/fs.h>#include <linux/jbd2.h>#include <linux/errno.h>#include <linux/slab.h>#include <linux/mm.h>#include <linux/pagemap.h>#include <linux/jiffies.h>#include <linux/crc32.h>#include <linux/writeback.h>#include <linux/backing-dev.h>#include <linux/bio.h>#include <linux/blkdev.h>#include <linux/bitops.h>#include <trace/events/jbd2.h>#include <asm/system.h> /* * Default IO end handler for temporary BJ_IO buffer_heads. */static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate){ BUFFER_TRACE(bh, ""); if (uptodate) set_buffer_uptodate(bh); else clear_buffer_uptodate(bh); unlock_buffer(bh);} /* * When an ext4 file is truncated, it is possible that some pages are not * successfully freed, because they are attached to a committing transaction. * After the transaction commits, these pages are left on the LRU, with no * ->mapping, and with attached buffers. These pages are trivially reclaimable * by the VM, but their apparent absence upsets the VM accounting, and it makes * the numbers in /proc/meminfo look odd. * * So here, we have a buffer which has just come off the forget list. Look to * see if we can strip all buffers from the backing page. * * Called under lock_journal(), and possibly under journal_datalist_lock. The * caller provided us with a ref against the buffer, and we drop that here. */static void release_buffer_page(struct buffer_head *bh){ struct page *page; if (buffer_dirty(bh)) goto nope; if (atomic_read(&bh->b_count) != 1) goto nope; page = bh->b_page; if (!page) goto nope; if (page->mapping) goto nope; /* OK, it's a truncated page */ if (!trylock_page(page)) goto nope; page_cache_get(page); __brelse(bh); try_to_free_buffers(page); unlock_page(page); page_cache_release(page); return; nope: __brelse(bh);} /* * Done it all: now submit the commit record. We should have * cleaned up our previous buffers by now, so if we are in abort * mode we can now just skip the rest of the journal write * entirely. * * Returns 1 if the journal needs to be aborted or 0 on success */static int journal_submit_commit_record(journal_t *journal, transaction_t *commit_transaction, struct buffer_head **cbh, __u32 crc32_sum){ struct journal_head *descriptor; struct commit_header *tmp; struct buffer_head *bh; int ret; struct timespec now = current_kernel_time(); *cbh = NULL; if (is_journal_aborted(journal)) return 0; descriptor = jbd2_journal_get_descriptor_buffer(journal); if (!descriptor) return 1; bh = jh2bh(descriptor); tmp = (struct commit_header *)bh->b_data; tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK); tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid); tmp->h_commit_sec = cpu_to_be64(now.tv_sec); tmp->h_commit_nsec = cpu_to_be32(now.tv_nsec); if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) { tmp->h_chksum_type = JBD2_CRC32_CHKSUM; tmp->h_chksum_size = JBD2_CRC32_CHKSUM_SIZE; tmp->h_chksum[0] = cpu_to_be32(crc32_sum); } JBUFFER_TRACE(descriptor, "submit commit block"); lock_buffer(bh); clear_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = journal_end_buffer_io_sync; if (journal->j_flags & JBD2_BARRIER && !JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) ret = submit_bh(WRITE_SYNC | WRITE_FLUSH_FUA, bh); else ret = submit_bh(WRITE_SYNC, bh); *cbh = bh; return ret;} /* * This function along with journal_submit_commit_record * allows to write the commit record asynchronously. */static int journal_wait_on_commit_record(journal_t *journal, struct buffer_head *bh){ int ret = 0; clear_buffer_dirty(bh); wait_on_buffer(bh); if (unlikely(!buffer_uptodate(bh))) ret = -EIO; put_bh(bh); /* One for getblk() */ jbd2_journal_put_journal_head(bh2jh(bh)); return ret;} /* * write the filemap data using writepage() address_space_operations. * We don't do block allocation here even for delalloc. We don't * use writepages() because with dealyed allocation we may be doing * block allocation in writepages(). */static int journal_submit_inode_data_buffers(struct address_space *mapping){ int ret; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = mapping->nrpages * 2, .range_start = 0, .range_end = i_size_read(mapping->host), }; ret = generic_writepages(mapping, &wbc); return ret;} /* * Submit all the data buffers of inode associated with the transaction to * disk. * * We are in a committing transaction. Therefore no new inode can be added to * our inode list. We use JI_COMMIT_RUNNING flag to protect inode we currently * operate on from being released while we write out pages. */static int journal_submit_data_buffers(journal_t *journal, transaction_t *commit_transaction){ struct jbd2_inode *jinode; int err, ret = 0; struct address_space *mapping; spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { mapping = jinode->i_vfs_inode->i_mapping; set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); spin_unlock(&journal->j_list_lock); /* * submit the inode data buffers. We use writepage * instead of writepages. Because writepages can do * block allocation with delalloc. We need to write * only allocated blocks here. */ trace_jbd2_submit_inode_data(jinode->i_vfs_inode); err = journal_submit_inode_data_buffers(mapping); if (!ret) ret = err; spin_lock(&journal->j_list_lock); J_ASSERT(jinode->i_transaction == commit_transaction); clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); smp_mb__after_clear_bit(); wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); } spin_unlock(&journal->j_list_lock); return ret;} /* * Wait for data submitted for writeout, refile inodes to proper * transaction if needed. * */static int journal_finish_inode_data_buffers(journal_t *journal, transaction_t *commit_transaction){ struct jbd2_inode *jinode, *next_i; int err, ret = 0; /* For locking, see the comment in journal_submit_data_buffers() */ spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); spin_unlock(&journal->j_list_lock); err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping); if (err) { /* * Because AS_EIO is cleared by * filemap_fdatawait_range(), set it again so * that user process can get -EIO from fsync(). */ set_bit(AS_EIO, &jinode->i_vfs_inode->i_mapping->flags); if (!ret) ret = err; } spin_lock(&journal->j_list_lock); clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); smp_mb__after_clear_bit(); wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); } /* Now refile inode to proper lists */ list_for_each_entry_safe(jinode, next_i, &commit_transaction->t_inode_list, i_list) { list_del(&jinode->i_list); if (jinode->i_next_transaction) { jinode->i_transaction = jinode->i_next_transaction; jinode->i_next_transaction = NULL; list_add(&jinode->i_list, &jinode->i_transaction->t_inode_list); } else { jinode->i_transaction = NULL; } } spin_unlock(&journal->j_list_lock); return ret;} static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh){ struct page *page = bh->b_page; char *addr; __u32 checksum; addr = kmap_atomic(page, KM_USER0); checksum = crc32_be(crc32_sum, (void *)(addr + offset_in_page(bh->b_data)), bh->b_size); kunmap_atomic(addr, KM_USER0); return checksum;} static void write_tag_block(int tag_bytes, journal_block_tag_t *tag, unsigned long long block){ tag->t_blocknr = cpu_to_be32(block & (u32)~0); if (tag_bytes > JBD2_TAG_SIZE32) tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1);} /* * jbd2_journal_commit_transaction * * The primary function for committing a transaction to the log. This * function is called by the journal thread to begin a complete commit. */void jbd2_journal_commit_transaction(journal_t *journal){ struct transaction_stats_s stats; transaction_t *commit_transaction; struct journal_head *jh, *new_jh, *descriptor; struct buffer_head **wbuf = journal->j_wbuf; int bufs; int flags; int err; unsigned long long blocknr; ktime_t start_time; u64 commit_time; char *tagp = NULL; journal_header_t *header; journal_block_tag_t *tag = NULL; int space_left = 0; int first_tag = 0; int tag_flag; int i, to_free = 0; int tag_bytes = journal_tag_bytes(journal); struct buffer_head *cbh = NULL; /* For transactional checksums */ __u32 crc32_sum = ~0; struct blk_plug plug; /* * First job: lock down the current transaction and wait for * all outstanding updates to complete. */ /* Do we need to erase the effects of a prior jbd2_journal_flush? */ if (journal->j_flags & JBD2_FLUSHED) { jbd_debug(3, "super block updated\n"); jbd2_journal_update_superblock(journal, 1); } else { jbd_debug(3, "superblock not updated\n"); } J_ASSERT(journal->j_running_transaction != NULL); J_ASSERT(journal->j_committing_transaction == NULL); commit_transaction = journal->j_running_transaction; J_ASSERT(commit_transaction->t_state == T_RUNNING); trace_jbd2_start_commit(journal, commit_transaction); jbd_debug(1, "JBD2: starting commit of transaction %d\n", commit_transaction->t_tid); write_lock(&journal->j_state_lock); commit_transaction->t_state = T_LOCKED; trace_jbd2_commit_locking(journal, commit_transaction); stats.run.rs_wait = commit_transaction->t_max_wait; stats.run.rs_locked = jiffies; stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start, stats.run.rs_locked); spin_lock(&commit_transaction->t_handle_lock); while (atomic_read(&commit_transaction->t_updates)) { DEFINE_WAIT(wait); prepare_to_wait(&journal->j_wait_updates, &wait, TASK_UNINTERRUPTIBLE); if (atomic_read(&commit_transaction->t_updates)) { spin_unlock(&commit_transaction->t_handle_lock); write_unlock(&journal->j_state_lock); schedule(); write_lock(&journal->j_state_lock); spin_lock(&commit_transaction->t_handle_lock); } finish_wait(&journal->j_wait_updates, &wait); } spin_unlock(&commit_transaction->t_handle_lock); J_ASSERT (atomic_read(&commit_transaction->t_outstanding_credits) <= journal->j_max_transaction_buffers); /* * First thing we are allowed to do is to discard any remaining * BJ_Reserved buffers. Note, it is _not_ permissible to assume * that there are no such buffers: if a large filesystem * operation like a truncate needs to split itself over multiple * transactions, then it may try to do a jbd2_journal_restart() while * there are still BJ_Reserved buffers outstanding. These must * be released cleanly from the current transaction. * * In this case, the filesystem must still reserve write access * again before modifying the buffer in the new transaction, but * we do not require it to remember exactly which old buffers it * has reserved. This is consistent with the existing behaviour * that multiple jbd2_journal_get_write_access() calls to the same * buffer are perfectly permissible. */ while (commit_transaction->t_reserved_list) { jh = commit_transaction->t_reserved_list; JBUFFER_TRACE(jh, "reserved, unused: refile"); /* * A jbd2_journal_get_undo_access()+jbd2_journal_release_buffer() may * leave undo-committed data. */ if (jh->b_committed_data) { struct buffer_head *bh = jh2bh(jh); jbd_lock_bh_state(bh); jbd2_free(jh->b_committed_data, bh->b_size); jh->b_committed_data = NULL; jbd_unlock_bh_state(bh); } jbd2_journal_refile_buffer(journal, jh); } /* * Now try to drop any written-back buffers from the journal's * checkpoint lists. We do this *before* commit because it potentially * frees some memory */ spin_lock(&journal->j_list_lock); __jbd2_journal_clean_checkpoint_list(journal); spin_unlock(&journal->j_list_lock); jbd_debug(3, "JBD2: commit phase 1\n"); /* * Switch to a new revoke table. */ jbd2_journal_switch_revoke_table(journal); trace_jbd2_commit_flushing(journal, commit_transaction); stats.run.rs_flushing = jiffies; stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked, stats.run.rs_flushing); commit_transaction->t_state = T_FLUSH; journal->j_committing_transaction = commit_transaction; journal->j_running_transaction = NULL; start_time = ktime_get(); commit_transaction->t_log_start = journal->j_head; wake_up(&journal->j_wait_transaction_locked); write_unlock(&journal->j_state_lock); jbd_debug(3, "JBD2: commit phase 2\n"); /* * Now start flushing things to disk, in the order they appear * on the transaction lists. Data blocks go first. */ err = journal_submit_data_buffers(journal, commit_transaction); if (err) jbd2_journal_abort(journal, err); blk_start_plug(&plug); jbd2_journal_write_revoke_records(journal, commit_transaction, WRITE_SYNC); blk_finish_plug(&plug); jbd_debug(3, "JBD2: commit phase 2\n"); /* * Way to go: we have now written out all of the data for a * transaction! Now comes the tricky part: we need to write out * metadata. Loop over the transaction's entire buffer list: */ write_lock(&journal->j_state_lock); commit_transaction->t_state = T_COMMIT; write_unlock(&journal->j_state_lock); trace_jbd2_commit_logging(journal, commit_transaction); stats.run.rs_logging = jiffies; stats.run.rs_flushing = jbd2_time_diff(stats.run.rs_flushing, stats.run.rs_logging); stats.run.rs_blocks = atomic_read(&commit_transaction->t_outstanding_credits); stats.run.rs_blocks_logged = 0; J_ASSERT(commit_transaction->t_nr_buffers <= atomic_read(&commit_transaction->t_outstanding_credits)); err = 0; descriptor = NULL; bufs = 0; blk_start_plug(&plug); while (commit_transaction->t_buffers) { /* Find the next buffer to be journaled... */ jh = commit_transaction->t_buffers; /* If we're in abort mode, we just un-journal the buffer and release it. */ if (is_journal_aborted(journal)) {Lines 1–500 of 1048. Load more
/* * linux/fs/jbd2/commit.c * * Written by Stephen C. Tweedie <sct@redhat.com>, 1998 * * Copyright 1998 Red Hat corp --- All Rights Reserved * * This file is part of the Linux kernel and is made available under * the terms of the GNU General Public License, version 2, or at your * option, any later version, incorporated herein by reference. * * Journal commit routines for the generic filesystem journaling code; * part of the ext2fs journaling system. */ #include <linux/time.h> #include <linux/fs.h> #include <linux/jbd2.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/jiffies.h> #include <linux/crc32.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/bio.h> #include <linux/blkdev.h> #include <linux/bitops.h> #include <trace/events/jbd2.h> #include <asm/system.h> /* * Default IO end handler for temporary BJ_IO buffer_heads. */ static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate) { BUFFER_TRACE(bh, ""); if (uptodate) set_buffer_uptodate(bh); else clear_buffer_uptodate(bh); unlock_buffer(bh); } /* * When an ext4 file is truncated, it is possible that some pages are not * successfully freed, because they are attached to a committing transaction. * After the transaction commits, these pages are left on the LRU, with no * ->mapping, and with attached buffers. These pages are trivially reclaimable * by the VM, but their apparent absence upsets the VM accounting, and it makes * the numbers in /proc/meminfo look odd. * * So here, we have a buffer which has just come off the forget list. Look to * see if we can strip all buffers from the backing page. * * Called under lock_journal(), and possibly under journal_datalist_lock. The * caller provided us with a ref against the buffer, and we drop that here. */ static void release_buffer_page(struct buffer_head *bh) { struct page *page; if (buffer_dirty(bh)) goto nope; if (atomic_read(&bh->b_count) != 1) goto nope; page = bh->b_page; if (!page) goto nope; if (page->mapping) goto nope; /* OK, it's a truncated page */ if (!trylock_page(page)) goto nope; page_cache_get(page); __brelse(bh); try_to_free_buffers(page); unlock_page(page); page_cache_release(page); return; nope: __brelse(bh); } /* * Done it all: now submit the commit record. We should have * cleaned up our previous buffers by now, so if we are in abort * mode we can now just skip the rest of the journal write * entirely. * * Returns 1 if the journal needs to be aborted or 0 on success */ static int journal_submit_commit_record(journal_t *journal, transaction_t *commit_transaction, struct buffer_head **cbh, __u32 crc32_sum) { struct journal_head *descriptor; struct commit_header *tmp; struct buffer_head *bh; int ret; struct timespec now = current_kernel_time(); *cbh = NULL; if (is_journal_aborted(journal)) return 0; descriptor = jbd2_journal_get_descriptor_buffer(journal); if (!descriptor) return 1; bh = jh2bh(descriptor); tmp = (struct commit_header *)bh->b_data; tmp->h_magic = cpu_to_be32(JBD2_MAGIC_NUMBER); tmp->h_blocktype = cpu_to_be32(JBD2_COMMIT_BLOCK); tmp->h_sequence = cpu_to_be32(commit_transaction->t_tid); tmp->h_commit_sec = cpu_to_be64(now.tv_sec); tmp->h_commit_nsec = cpu_to_be32(now.tv_nsec); if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM)) { tmp->h_chksum_type = JBD2_CRC32_CHKSUM; tmp->h_chksum_size = JBD2_CRC32_CHKSUM_SIZE; tmp->h_chksum[0] = cpu_to_be32(crc32_sum); } JBUFFER_TRACE(descriptor, "submit commit block"); lock_buffer(bh); clear_buffer_dirty(bh); set_buffer_uptodate(bh); bh->b_end_io = journal_end_buffer_io_sync; if (journal->j_flags & JBD2_BARRIER && !JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT)) ret = submit_bh(WRITE_SYNC | WRITE_FLUSH_FUA, bh); else ret = submit_bh(WRITE_SYNC, bh); *cbh = bh; return ret; } /* * This function along with journal_submit_commit_record * allows to write the commit record asynchronously. */ static int journal_wait_on_commit_record(journal_t *journal, struct buffer_head *bh) { int ret = 0; clear_buffer_dirty(bh); wait_on_buffer(bh); if (unlikely(!buffer_uptodate(bh))) ret = -EIO; put_bh(bh); /* One for getblk() */ jbd2_journal_put_journal_head(bh2jh(bh)); return ret; } /* * write the filemap data using writepage() address_space_operations. * We don't do block allocation here even for delalloc. We don't * use writepages() because with dealyed allocation we may be doing * block allocation in writepages(). */ static int journal_submit_inode_data_buffers(struct address_space *mapping) { int ret; struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = mapping->nrpages * 2, .range_start = 0, .range_end = i_size_read(mapping->host), }; ret = generic_writepages(mapping, &wbc); return ret; } /* * Submit all the data buffers of inode associated with the transaction to * disk. * * We are in a committing transaction. Therefore no new inode can be added to * our inode list. We use JI_COMMIT_RUNNING flag to protect inode we currently * operate on from being released while we write out pages. */ static int journal_submit_data_buffers(journal_t *journal, transaction_t *commit_transaction) { struct jbd2_inode *jinode; int err, ret = 0; struct address_space *mapping; spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { mapping = jinode->i_vfs_inode->i_mapping; set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); spin_unlock(&journal->j_list_lock); /* * submit the inode data buffers. We use writepage * instead of writepages. Because writepages can do * block allocation with delalloc. We need to write * only allocated blocks here. */ trace_jbd2_submit_inode_data(jinode->i_vfs_inode); err = journal_submit_inode_data_buffers(mapping); if (!ret) ret = err; spin_lock(&journal->j_list_lock); J_ASSERT(jinode->i_transaction == commit_transaction); clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); smp_mb__after_clear_bit(); wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); } spin_unlock(&journal->j_list_lock); return ret; } /* * Wait for data submitted for writeout, refile inodes to proper * transaction if needed. * */ static int journal_finish_inode_data_buffers(journal_t *journal, transaction_t *commit_transaction) { struct jbd2_inode *jinode, *next_i; int err, ret = 0; /* For locking, see the comment in journal_submit_data_buffers() */ spin_lock(&journal->j_list_lock); list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) { set_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); spin_unlock(&journal->j_list_lock); err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping); if (err) { /* * Because AS_EIO is cleared by * filemap_fdatawait_range(), set it again so * that user process can get -EIO from fsync(). */ set_bit(AS_EIO, &jinode->i_vfs_inode->i_mapping->flags); if (!ret) ret = err; } spin_lock(&journal->j_list_lock); clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags); smp_mb__after_clear_bit(); wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING); } /* Now refile inode to proper lists */ list_for_each_entry_safe(jinode, next_i, &commit_transaction->t_inode_list, i_list) { list_del(&jinode->i_list); if (jinode->i_next_transaction) { jinode->i_transaction = jinode->i_next_transaction; jinode->i_next_transaction = NULL; list_add(&jinode->i_list, &jinode->i_transaction->t_inode_list); } else { jinode->i_transaction = NULL; } } spin_unlock(&journal->j_list_lock); return ret; } static __u32 jbd2_checksum_data(__u32 crc32_sum, struct buffer_head *bh) { struct page *page = bh->b_page; char *addr; __u32 checksum; addr = kmap_atomic(page, KM_USER0); checksum = crc32_be(crc32_sum, (void *)(addr + offset_in_page(bh->b_data)), bh->b_size); kunmap_atomic(addr, KM_USER0); return checksum; } static void write_tag_block(int tag_bytes, journal_block_tag_t *tag, unsigned long long block) { tag->t_blocknr = cpu_to_be32(block & (u32)~0); if (tag_bytes > JBD2_TAG_SIZE32) tag->t_blocknr_high = cpu_to_be32((block >> 31) >> 1); } /* * jbd2_journal_commit_transaction * * The primary function for committing a transaction to the log. This * function is called by the journal thread to begin a complete commit. */ void jbd2_journal_commit_transaction(journal_t *journal) { struct transaction_stats_s stats; transaction_t *commit_transaction; struct journal_head *jh, *new_jh, *descriptor; struct buffer_head **wbuf = journal->j_wbuf; int bufs; int flags; int err; unsigned long long blocknr; ktime_t start_time; u64 commit_time; char *tagp = NULL; journal_header_t *header; journal_block_tag_t *tag = NULL; int space_left = 0; int first_tag = 0; int tag_flag; int i, to_free = 0; int tag_bytes = journal_tag_bytes(journal); struct buffer_head *cbh = NULL; /* For transactional checksums */ __u32 crc32_sum = ~0; struct blk_plug plug; /* * First job: lock down the current transaction and wait for * all outstanding updates to complete. */ /* Do we need to erase the effects of a prior jbd2_journal_flush? */ if (journal->j_flags & JBD2_FLUSHED) { jbd_debug(3, "super block updated\n"); jbd2_journal_update_superblock(journal, 1); } else { jbd_debug(3, "superblock not updated\n"); } J_ASSERT(journal->j_running_transaction != NULL); J_ASSERT(journal->j_committing_transaction == NULL); commit_transaction = journal->j_running_transaction; J_ASSERT(commit_transaction->t_state == T_RUNNING); trace_jbd2_start_commit(journal, commit_transaction); jbd_debug(1, "JBD2: starting commit of transaction %d\n", commit_transaction->t_tid); write_lock(&journal->j_state_lock); commit_transaction->t_state = T_LOCKED; trace_jbd2_commit_locking(journal, commit_transaction); stats.run.rs_wait = commit_transaction->t_max_wait; stats.run.rs_locked = jiffies; stats.run.rs_running = jbd2_time_diff(commit_transaction->t_start, stats.run.rs_locked); spin_lock(&commit_transaction->t_handle_lock); while (atomic_read(&commit_transaction->t_updates)) { DEFINE_WAIT(wait); prepare_to_wait(&journal->j_wait_updates, &wait, TASK_UNINTERRUPTIBLE); if (atomic_read(&commit_transaction->t_updates)) { spin_unlock(&commit_transaction->t_handle_lock); write_unlock(&journal->j_state_lock); schedule(); write_lock(&journal->j_state_lock); spin_lock(&commit_transaction->t_handle_lock); } finish_wait(&journal->j_wait_updates, &wait); } spin_unlock(&commit_transaction->t_handle_lock); J_ASSERT (atomic_read(&commit_transaction->t_outstanding_credits) <= journal->j_max_transaction_buffers); /* * First thing we are allowed to do is to discard any remaining * BJ_Reserved buffers. Note, it is _not_ permissible to assume * that there are no such buffers: if a large filesystem * operation like a truncate needs to split itself over multiple * transactions, then it may try to do a jbd2_journal_restart() while * there are still BJ_Reserved buffers outstanding. These must * be released cleanly from the current transaction. * * In this case, the filesystem must still reserve write access * again before modifying the buffer in the new transaction, but * we do not require it to remember exactly which old buffers it * has reserved. This is consistent with the existing behaviour * that multiple jbd2_journal_get_write_access() calls to the same * buffer are perfectly permissible. */ while (commit_transaction->t_reserved_list) { jh = commit_transaction->t_reserved_list; JBUFFER_TRACE(jh, "reserved, unused: refile"); /* * A jbd2_journal_get_undo_access()+jbd2_journal_release_buffer() may * leave undo-committed data. */ if (jh->b_committed_data) { struct buffer_head *bh = jh2bh(jh); jbd_lock_bh_state(bh); jbd2_free(jh->b_committed_data, bh->b_size); jh->b_committed_data = NULL; jbd_unlock_bh_state(bh); } jbd2_journal_refile_buffer(journal, jh); } /* * Now try to drop any written-back buffers from the journal's * checkpoint lists. We do this *before* commit because it potentially * frees some memory */ spin_lock(&journal->j_list_lock); __jbd2_journal_clean_checkpoint_list(journal); spin_unlock(&journal->j_list_lock); jbd_debug(3, "JBD2: commit phase 1\n"); /* * Switch to a new revoke table. */ jbd2_journal_switch_revoke_table(journal); trace_jbd2_commit_flushing(journal, commit_transaction); stats.run.rs_flushing = jiffies; stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked, stats.run.rs_flushing); commit_transaction->t_state = T_FLUSH; journal->j_committing_transaction = commit_transaction; journal->j_running_transaction = NULL; start_time = ktime_get(); commit_transaction->t_log_start = journal->j_head; wake_up(&journal->j_wait_transaction_locked); write_unlock(&journal->j_state_lock); jbd_debug(3, "JBD2: commit phase 2\n"); /* * Now start flushing things to disk, in the order they appear * on the transaction lists. Data blocks go first. */ err = journal_submit_data_buffers(journal, commit_transaction); if (err) jbd2_journal_abort(journal, err); blk_start_plug(&plug); jbd2_journal_write_revoke_records(journal, commit_transaction, WRITE_SYNC); blk_finish_plug(&plug); jbd_debug(3, "JBD2: commit phase 2\n"); /* * Way to go: we have now written out all of the data for a * transaction! Now comes the tricky part: we need to write out * metadata. Loop over the transaction's entire buffer list: */ write_lock(&journal->j_state_lock); commit_transaction->t_state = T_COMMIT; write_unlock(&journal->j_state_lock); trace_jbd2_commit_logging(journal, commit_transaction); stats.run.rs_logging = jiffies; stats.run.rs_flushing = jbd2_time_diff(stats.run.rs_flushing, stats.run.rs_logging); stats.run.rs_blocks = atomic_read(&commit_transaction->t_outstanding_credits); stats.run.rs_blocks_logged = 0; J_ASSERT(commit_transaction->t_nr_buffers <= atomic_read(&commit_transaction->t_outstanding_credits)); err = 0; descriptor = NULL; bufs = 0; blk_start_plug(&plug); while (commit_transaction->t_buffers) { /* Find the next buffer to be journaled... */ jh = commit_transaction->t_buffers; /* If we're in abort mode, we just un-journal the buffer and release it. */ if (is_journal_aborted(journal)) {