Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "The siginificant new ext4 feature this time around is Harshad's new
  fast_commit mode.

  In addition, thanks to Mauricio for fixing a race where mmap'ed pages
  that are being changed in parallel with a data=journal transaction
  commit could result in bad checksums in the failure that could cause
  journal replays to fail.

  Also notable is Ritesh's buffered write optimization which can result
  in significant improvements on parallel write workloads. (The kernel
  test robot reported a 330.6% improvement on fio.write_iops on a 96
  core system using DAX)

  Besides that, we have the usual miscellaneous cleanups and bug fixes"

Link: https://lore.kernel.org/r/20200925071217.GO28663@shao2-debian

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (46 commits)
  ext4: fix invalid inode checksum
  ext4: add fast commit stats in procfs
  ext4: add a mount opt to forcefully turn fast commits on
  ext4: fast commit recovery path
  jbd2: fast commit recovery path
  ext4: main fast-commit commit path
  jbd2: add fast commit machinery
  ext4 / jbd2: add fast commit initialization
  ext4: add fast_commit feature and handling for extended mount options
  doc: update ext4 and journalling docs to include fast commit feature
  ext4: Detect already used quota file early
  jbd2: avoid transaction reuse after reformatting
  ext4: use the normal helper to get the actual inode
  ext4: fix bs < ps issue reported with dioread_nolock mount opt
  ext4: data=journal: write-protect pages on j_submit_inode_data_buffers()
  ext4: data=journal: fixes for ext4_page_mkwrite()
  jbd2, ext4, ocfs2: introduce/use journal callbacks j_submit|finish_inode_data_buffers()
  jbd2: introduce/export functions jbd2_journal_submit|finish_inode_data_buffers()
  ext4: introduce ext4_sb_bread_unmovable() to replace sb_bread_unmovable()
  ext4: use ext4_sb_bread() instead of sb_bread()
  ...

1 files changed, 76 insertions, 30 deletions

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 6d2da8ad0e6f..fa688e163a80 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -187,20 +187,48 @@ static int journal_wait_on_commit_record(journal_t *journal,
  * use writepages() because with delayed allocation we may be doing
  * block allocation in writepages().
  */
-static int journal_submit_inode_data_buffers(struct address_space *mapping,
-		loff_t dirty_start, loff_t dirty_end)
+int jbd2_journal_submit_inode_data_buffers(struct jbd2_inode *jinode)
 {
-	int ret;
+	struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
 	struct writeback_control wbc = {
 		.sync_mode =  WB_SYNC_ALL,
 		.nr_to_write = mapping->nrpages * 2,
-		.range_start = dirty_start,
-		.range_end = dirty_end,
+		.range_start = jinode->i_dirty_start,
+		.range_end = jinode->i_dirty_end,
 	};
 
-	ret = generic_writepages(mapping, &wbc);
-	return ret;
+	/*
+	 * 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.
+	 */
+	return generic_writepages(mapping, &wbc);
+}
+
+/* Send all the data buffers related to an inode */
+int jbd2_submit_inode_data(struct jbd2_inode *jinode)
+{
+
+	if (!jinode || !(jinode->i_flags & JI_WRITE_DATA))
+		return 0;
+
+	trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
+	return jbd2_journal_submit_inode_data_buffers(jinode);
+
+}
+EXPORT_SYMBOL(jbd2_submit_inode_data);
+
+int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode)
+{
+	if (!jinode || !(jinode->i_flags & JI_WAIT_DATA) ||
+		!jinode->i_vfs_inode || !jinode->i_vfs_inode->i_mapping)
+		return 0;
+	return filemap_fdatawait_range_keep_errors(
+		jinode->i_vfs_inode->i_mapping, jinode->i_dirty_start,
+		jinode->i_dirty_end);
 }
+EXPORT_SYMBOL(jbd2_wait_inode_data);
 
 /*
  * Submit all the data buffers of inode associated with the transaction to
@@ -215,29 +243,20 @@ static int journal_submit_data_buffers(journal_t *journal,
 {
 	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) {
-		loff_t dirty_start = jinode->i_dirty_start;
-		loff_t dirty_end = jinode->i_dirty_end;
-
 		if (!(jinode->i_flags & JI_WRITE_DATA))
 			continue;
-		mapping = jinode->i_vfs_inode->i_mapping;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		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.
-		 */
+		/* submit the inode data buffers. */
 		trace_jbd2_submit_inode_data(jinode->i_vfs_inode);
-		err = journal_submit_inode_data_buffers(mapping, dirty_start,
-				dirty_end);
-		if (!ret)
-			ret = err;
+		if (journal->j_submit_inode_data_buffers) {
+			err = journal->j_submit_inode_data_buffers(jinode);
+			if (!ret)
+				ret = err;
+		}
 		spin_lock(&journal->j_list_lock);
 		J_ASSERT(jinode->i_transaction == commit_transaction);
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
@@ -248,6 +267,15 @@ static int journal_submit_data_buffers(journal_t *journal,
 	return ret;
 }
 
+int jbd2_journal_finish_inode_data_buffers(struct jbd2_inode *jinode)
+{
+	struct address_space *mapping = jinode->i_vfs_inode->i_mapping;
+
+	return filemap_fdatawait_range_keep_errors(mapping,
+						   jinode->i_dirty_start,
+						   jinode->i_dirty_end);
+}
+
 /*
  * Wait for data submitted for writeout, refile inodes to proper
  * transaction if needed.
@@ -262,18 +290,16 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 	/* 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) {
-		loff_t dirty_start = jinode->i_dirty_start;
-		loff_t dirty_end = jinode->i_dirty_end;
-
 		if (!(jinode->i_flags & JI_WAIT_DATA))
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		err = filemap_fdatawait_range_keep_errors(
-				jinode->i_vfs_inode->i_mapping, dirty_start,
-				dirty_end);
-		if (!ret)
-			ret = err;
+		/* wait for the inode data buffers writeout. */
+		if (journal->j_finish_inode_data_buffers) {
+			err = journal->j_finish_inode_data_buffers(jinode);
+			if (!ret)
+				ret = err;
+		}
 		spin_lock(&journal->j_list_lock);
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
 		smp_mb();
@@ -413,6 +439,20 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	J_ASSERT(journal->j_running_transaction != NULL);
 	J_ASSERT(journal->j_committing_transaction == NULL);
 
+	write_lock(&journal->j_state_lock);
+	journal->j_flags |= JBD2_FULL_COMMIT_ONGOING;
+	while (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();
+		write_lock(&journal->j_state_lock);
+		finish_wait(&journal->j_fc_wait, &wait);
+	}
+	write_unlock(&journal->j_state_lock);
+
 	commit_transaction = journal->j_running_transaction;
 
 	trace_jbd2_start_commit(journal, commit_transaction);
@@ -420,6 +460,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 			commit_transaction->t_tid);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_fc_off = 0;
 	J_ASSERT(commit_transaction->t_state == T_RUNNING);
 	commit_transaction->t_state = T_LOCKED;
 
@@ -1119,12 +1160,16 @@ restart_loop:
 
 	if (journal->j_commit_callback)
 		journal->j_commit_callback(journal, commit_transaction);
+	if (journal->j_fc_cleanup_callback)
+		journal->j_fc_cleanup_callback(journal, 1);
 
 	trace_jbd2_end_commit(journal, commit_transaction);
 	jbd_debug(1, "JBD2: commit %d complete, head %d\n",
 		  journal->j_commit_sequence, journal->j_tail_sequence);
 
 	write_lock(&journal->j_state_lock);
+	journal->j_flags &= ~JBD2_FULL_COMMIT_ONGOING;
+	journal->j_flags &= ~JBD2_FAST_COMMIT_ONGOING;
 	spin_lock(&journal->j_list_lock);
 	commit_transaction->t_state = T_FINISHED;
 	/* Check if the transaction can be dropped now that we are finished */
@@ -1136,6 +1181,7 @@ restart_loop:
 	spin_unlock(&journal->j_list_lock);
 	write_unlock(&journal->j_state_lock);
 	wake_up(&journal->j_wait_done_commit);
+	wake_up(&journal->j_fc_wait);
 
 	/*
 	 * Calculate overall stats